FIELD OPERATIONS FRAMEWORK

Description

BACKGROUND

A reservoir can be a subsurface formation that can be characterized at least in part by its porosity and fluid permeability. As an example, a reservoir may be part of a basin such as a sedimentary basin. A basin can be a depression (e.g., caused by plate tectonic activity, subsidence, etc.) in which sediments accumulate. As an example, where hydrocarbon source rocks occur in combination with appropriate depth and duration of burial, a petroleum system may develop within a basin, which may form a reservoir that includes hydrocarbon fluids (e.g., oil, gas, etc.). Various operations may be performed in the field to access such hydrocarbon fluids and/or produce such hydrocarbon fluids. While hydrocarbon fluid reservoirs are mentioned as an example, a reservoir that includes water and brine may be assessed, for example, for one or more purposes such as, for example, carbon storage (e.g., sequestration), water production or storage, geothermal production or storage, metallic extraction from brine, etc.

SUMMARY

A method can include generating a pill blend recommendation based at least in part on formation characteristics to mitigate formation loss of drilling fluid during drilling of a borehole, where the pill blend recommendation specifies a particle size distribution determined by a framework that relates historical pill blends and mitigation success; and, responsive to an indication of formation loss of drilling fluid during the drilling of the borehole, issuing an instruction to pump a pill blend formulated according to the pill blend recommendation. A system can include one or more processors; memory accessible to at least one of the one or more processors; processor-executable instructions stored in the memory and executable to instruct the system to: generate a pill blend recommendation based at least in part on formation characteristics to mitigate formation loss of drilling fluid during drilling of a borehole, where the pill blend recommendation specifies a particle size distribution determined by a framework that relates historical pill blends and mitigation success; and, responsive to an indication of formation loss of drilling fluid during the drilling of the borehole, issue an instruction to pump a pill blend formulated according to the pill blend recommendation. One or more computer-readable storage media can include processor-executable instructions to instruct a computing system to: generate a pill blend recommendation based at least in part on formation characteristics to mitigate formation loss of drilling fluid during drilling of a borehole, where the pill blend recommendation specifies a particle size distribution determined by a framework that relates historical pill blends and mitigation success; and, responsive to an indication of formation loss of drilling fluid during the drilling of the borehole, issue an instruction to pump a pill blend formulated according to the pill blend recommendation. Various other apparatuses, systems, methods, etc., are also disclosed.

This summary is provided to introduce a selection of concepts that are further described below in the detailed description. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used as an aid in limiting the scope of the claimed subject matter.

BRIEF DESCRIPTION OF THE DRAWINGS

Features and advantages of the described implementations can be more readily understood by reference to the following description taken in conjunction with the accompanying drawings.

FIG. 1 illustrates an example system that includes various framework components associated with one or more geologic environments;

FIG. 2 illustrates an example of a system;

FIG. 3 illustrates an example of a drilling equipment and examples of borehole shapes;

FIG. 4 illustrates an example of a system;

FIG. 5 illustrates an example of graphic of various examples of formation fluid losses;

FIG. 6 illustrates an example of a method;

FIG. 7 illustrates an example of a data structure;

FIG. 8 illustrates examples of plots;

FIG. 9 illustrates an example of a workflow;

FIG. 10 illustrates an example of a framework;

FIG. 11 illustrates an example of a method and an example of a system; and

FIG. 12 illustrates examples of computer and network equipment.

DETAILED DESCRIPTION

This description is not to be taken in a limiting sense, but rather is made merely for the purpose of describing the general principles of the implementations. The scope of the described implementations should be ascertained with reference to the issued claims.

FIG. 1 shows an example of a system 100 that includes a workspace framework 110 that can provide for instantiation of, rendering of, interactions with, etc., a graphical user interface (GUI) 120. In the example of FIG. 1, the GUI 120 can include graphical controls for computational frameworks (e.g., applications) 121, projects 122, visualization 123, one or more other features 124, data access 125, and data storage 126.

In the example of FIG. 1, the workspace framework 110 may be tailored to a particular geologic environment such as an example geologic environment 150. For example, the geologic environment 150 may include layers (e.g., stratification) that include a reservoir 151 and that may be intersected by a fault 153. A geologic environment 150 may be outfitted with a variety of sensors, detectors, actuators, etc. In such an environment, various types of equipment such as, for example, equipment 152 may include communication circuitry to receive and to transmit information, optionally with respect to one or more networks 155. Such information may include information associated with downhole equipment 154, which may be equipment to acquire information, to assist with resource recovery, etc. Other equipment 156 may be located remote from a wellsite and include sensing, detecting, emitting, or other circuitry. Such equipment may include storage and communication circuitry to store and to communicate data, instructions, etc. One or more satellites may be provided for purposes of communications, data acquisition, etc. For example, FIG. 1 shows a satellite 170 in communication with the network 155 that may be configured for communications, noting that the satellite may additionally or alternatively include circuitry for imagery (e.g., spatial, spectral, temporal, radiometric, etc.).

FIG. 1 also shows the geologic environment 150 as optionally including equipment 157 and 158 associated with a well that includes a substantially horizontal portion that may intersect with one or more fractures 159. For example, consider a well in a formation that may include natural fractures, artificial fractures (e.g., hydraulic fractures) or a combination of natural and artificial fractures. As an example, a well may be drilled for a reservoir that is laterally extensive. In such an example, lateral variations in properties, stresses, etc., may exist where an assessment of such variations may assist with planning, operations, etc., to develop a laterally extensive reservoir (e.g., via fracturing, injecting, extracting, etc.). As an example, the equipment 157 and/or 158 may include components, a system, systems, etc. for fracturing, seismic sensing, analysis of seismic data, assessment of one or more fractures, etc.

In the example of FIG. 1, the GUI 120 shows some examples of computational frameworks, including the DRILLPLAN, PETREL, TECHLOG, PETROMOD, ECLIPSE, and INTERSECT frameworks (SLB, Houston, Texas).

The DRILLPLAN framework provides for digital well construction planning and includes features for automation of repetitive tasks and validation workflows, enabling improved quality drilling programs (e.g., digital drilling plans, etc.) to be produced quickly with assured coherency.

The DRILLOPS framework (SLB, Houston, Texas), which may be included in the system 100 of FIG. 1, may execute a digital drilling plan and help to ensure plan adherence, while delivering goal-based automation. The DRILLOPS framework may generate activity plans automatically for individual operations, whether they are monitored and/or controlled on the rig or in town. Automation may utilize data analysis and learning systems to assist and optimize tasks, such as, for example, setting ROP to drilling a stand. A preset menu of automatable drilling tasks may be rendered, and, using data analysis and models, a plan may be executed in a manner to achieve a specified goal, where, for example, measurements may be utilized for calibration and/or one or more other purposes. The DRILLOPS framework provides flexibility to modify and replan activities dynamically, for example, based on a live appraisal of various factors (e.g., equipment, personnel, and supplies). Well construction activities (e.g., tripping, drilling, cementing, etc.) may be continually monitored and dynamically updated using feedback from operational activities. The DRILLOPS framework may provide for various levels of automation based on planning and/or re-planning (e.g., via the DRILLPLAN framework), feedback, etc.

The PETREL framework can be part of the DELFI cognitive exploration and production (E&P) environment (SLB, Houston, Texas, referred to as the DELFI environment) for utilization in geosciences and geoengineering, for example, to analyze subsurface data from exploration to production of fluid from a reservoir.

One or more types of frameworks may be implemented within or in a manner operatively coupled to the DELFI environment, which is a secure, cognitive, cloud-based collaborative environment that integrates data and workflows with digital technologies, such as artificial intelligence (AI) and machine learning (ML). Such an environment can provide for operations that involve one or more frameworks. The DELFI environment may be referred to as the DELFI framework, which may be a framework of frameworks. The DELFI environment can include various other frameworks, which may operate using one or more types of models (e.g., simulation models, etc.).

The TECHLOG framework can handle and process field and laboratory data for a variety of geologic environments (e.g., deepwater exploration, shale, etc.). The TECHLOG framework can structure wellbore data for analyses, planning, etc.

The PIPESIM simulator includes solvers that may provide simulation results such as, for example, multiphase flow results (e.g., from a reservoir to a wellhead and beyond, etc.), flowline and surface facility performance, etc. The PIPESIM simulator may be integrated, for example, with the AVOCET production operations framework (SLB, Houston Texas). The PIPESIM simulator may be an optimizer that can optimize one or more operational scenarios at least in part via simulation of physical phenomena.

The ECLIPSE framework provides a reservoir simulator with numerical solvers for prediction of dynamic behavior for various types of reservoirs and development schemes.

The INTERSECT framework provides a high-resolution reservoir simulator for simulation of geological features and quantification of uncertainties, for example, by creating production scenarios and, with the integration of precise models of the surface facilities and field operations, the INTERSECT framework can produce results, which may be continuously updated by real-time data exchanges (e.g., from one or more types of data acquisition equipment in the field that can acquire data during one or more types of field operations, etc.). The INTERSECT framework can provide completion configurations for complex wells where such configurations can be built in the field, can provide detailed chemical-enhanced-oil-recovery (EOR) formulations where such formulations can be implemented in the field, can analyze application of steam injection and other thermal EOR techniques for implementation in the field, advanced production controls in terms of reservoir coupling and flexible field management, and flexibility to script customized solutions for improved modeling and field management control. The INTERSECT framework, as with the other example frameworks, may be utilized as part of the DELFI environment, for example, for rapid simulation of multiple concurrent cases.

The aforementioned DELFI environment provides various features for workflows as to subsurface analysis, planning, construction and production, for example, as illustrated in the workspace framework 110. As shown in FIG. 1, outputs from the workspace framework 110 can be utilized for directing, controlling, etc., one or more processes in the geologic environment 150, and feedback 160 can be received via one or more interfaces in one or more forms (e.g., acquired data as to operational conditions, equipment conditions, environment conditions, etc.).

In the example of FIG. 1, the visualization features 123 may be implemented via the workspace framework 110, for example, to perform tasks as associated with one or more of subsurface regions, planning operations, constructing wells and/or surface fluid networks, and producing from a reservoir.

Visualization features may provide for visualization of various earth models, properties, etc., in one or more dimensions. As an example, visualization features may include one or more control features for control of equipment, which can include, for example, field equipment that can perform one or more field operations. A workflow may utilize one or more frameworks to generate information that can be utilized to control one or more types of field equipment (e.g., drilling equipment, wireline equipment, fracturing equipment, etc.).

As to a reservoir model that may be suitable for utilization by a simulator, consider acquisition of seismic data as acquired via reflection seismology, which finds use in geophysics, for example, to estimate properties of subsurface formations. Seismic data may be processed and interpreted, for example, to understand better composition, fluid content, extent and geometry of subsurface rocks. Such interpretation results can be utilized to plan, simulate, perform, etc., one or more operations for production of fluid from a reservoir (e.g., reservoir rock, etc.). Field acquisition equipment may be utilized to acquire seismic data, which may be in the form of traces where a trace can include values organized with respect to time and/or depth (e.g., consider 1D, 2D, 3D or 4D seismic data).

A model may be a simulated version of a geologic environment where a simulator may include features for simulating physical phenomena in a geologic environment based at least in part on a model or models. A simulator, such as a reservoir simulator, can simulate fluid flow in a geologic environment based at least in part on a model that can be generated via a framework that receives seismic data. A simulator can be a computerized system (e.g., a computing system) that can execute instructions using one or more processors to solve a system of equations that describe physical phenomena subject to various constraints. While several simulators are illustrated in the example of FIG. 1, one or more other simulators may be utilized, additionally or alternatively.

FIG. 2 shows an example of a system 200 that can be operatively coupled to one or more databases, data streams, etc. For example, one or more pieces of field equipment, laboratory equipment, computing equipment (e.g., local and/or remote), etc., can provide and/or generate data that may be utilized in the system 200.

As shown, the system 200 can include a geological/geophysical data block 210, a surface models block 220 (e.g., for one or more structural models), a volume modules block 230, an applications block 240, a numerical processing block 250 and an operational decision block 260. As shown in the example of FIG. 2, the geological/geophysical data block 210 can include data from well tops or drill holes 212, data from seismic interpretation 214, data from outcrop interpretation and optionally data from geological knowledge. As an example, the geological/geophysical data block 210 can include data from digital images, which can include digital images of cores, cuttings, cavings, outcrops, etc. As to the surface models block 220, it may provide for creation, editing, etc. of one or more surface models based on, for example, one or more of fault surfaces 222, horizon surfaces 224 and optionally topological relationships 226. As to the volume models block 230, it may provide for creation, editing, etc. of one or more volume models based on, for example, one or more of boundary representations 232 (e.g., to form a watertight model), structured grids 234 and unstructured meshes 236.

As shown in the example of FIG. 2, the system 200 may allow for implementing one or more workflows, for example, where data of the data block 210 are used to create, edit, etc. one or more surface models of the surface models block 220, which may be used to create, edit, etc. one or more volume models of the volume models block 230. As indicated in the example of FIG. 2, the surface models block 220 may provide one or more structural models, which may be input to the applications block 240. For example, such a structural model may be provided to one or more applications, optionally without performing one or more processes of the volume models block 230 (e.g., for purposes of numerical processing by the numerical processing block 250). Accordingly, the system 200 may be suitable for one or more workflows for structural modeling (e.g., optionally without performing numerical processing per the numerical processing block 250).

As to the applications block 240, it may include applications such as a well prognosis application 242, a reserve calculation application 244 and a well stability assessment application 246. As to the numerical processing block 250, it may include a process for seismic velocity modeling 251 followed by seismic processing 252, a process for facies and petrophysical property interpolation 253 followed by flow simulation 254, and a process for geomechanical simulation 255 followed by geochemical simulation 256. As indicated, as an example, a workflow may proceed from the volume models block 230 to the numerical processing block 250 and then to the applications block 240 and/or to the operational decision block 260. As another example, a workflow may proceed from the surface models block 220 to the applications block 240 and then to the operational decisions block 260 (e.g., consider an application that operates using a structural model).

In the example of FIG. 2, the operational decisions block 260 may include a seismic survey design process 261, a well rate adjustment process 252, a well trajectory planning process 263, a well completion planning process 264 and a process for one or more prospects, for example, to decide whether to explore, develop, abandon, etc. a prospect.

Referring again to the data block 210, the well tops or drill hole data 212 may include spatial localization, and optionally surface dip, of an interface between two geological formations or of a subsurface discontinuity such as a geological fault; the seismic interpretation data 214 may include a set of points, lines or surface patches interpreted from seismic reflection data, and representing interfaces between media (e.g., geological formations in which seismic wave velocity differs) or subsurface discontinuities; the outcrop interpretation data 216 may include a set of lines or points, optionally associated with measured dip, representing boundaries between geological formations or geological faults, as interpreted on the earth surface; and the geological knowledge data 218 may include, for example knowledge of the paleo-tectonic and sedimentary evolution of a region.

As to the facies and petrophysical property interpolation 253, it may include an assessment of type of rocks and of their petrophysical properties (e.g., porosity, permeability), for example, optionally in areas not sampled by well logs or coring. As an example, such an interpolation may be constrained by interpretations from log and core data, and by prior geological knowledge.

As to the various applications of the applications block 240, the well prognosis application 242 may include predicting type and characteristics of geological formations that may be encountered by a drill bit, and location where such rocks may be encountered (e.g., before a well is drilled); the reserve calculations application 244 may include assessing total amount of hydrocarbons or ore material present in a subsurface environment (e.g., and estimates of which proportion can be recovered, given a set of economic and technical constraints); and the well stability assessment application 246 may include estimating risk that a well, already drilled or to-be-drilled, will collapse or be damaged due underground stress.

As to the operational decision block 260, the seismic survey design process 261 may include deciding where to place seismic sources and receivers to optimize the coverage and quality of the collected seismic information while minimizing cost of acquisition; the well rate adjustment process 262 may include controlling injection and production well schedules and rates (e.g., to maximize recovery and production); the well trajectory planning process 263 may include designing a well trajectory to maximize potential recovery and production while minimizing drilling risks and costs; the well trajectory planning process 264 may include selecting proper well tubing, casing and completion (e.g., to meet expected production or injection targets in specified reservoir formations); and the prospect process 265 may include decision making, in an exploration context, to continue exploring, start producing or abandon prospects (e.g., based on an integrated assessment of technical and financial risks against expected benefits).

The system 200 can include and/or can be operatively coupled to a system such as the system 100 of FIG. 1. For example, the workspace framework 110 may provide for instantiation of, rendering of, interactions with, etc., the graphical user interface (GUI) 120 to perform one or more actions as to the system 200. In such an example, access may be provided to one or more frameworks (e.g., DRILLPLAN, DRILLOPS, PETREL, TECHLOG, PIPESIM, ECLIPSE, INTERSECT, etc.). One or more frameworks may provide for geo data acquisition as in block 210, for structural modeling as in block 220, for volume modeling as in block 230, for running an application as in block 240, for numerical processing as in block 250, for operational decision making as in block 260, etc.

As an example, the system 200 may provide for monitoring data, which can include geo data per the geo data block 210. In various examples, geo data may be acquired during one or more operations. For example, consider acquiring geo data during drilling operations via downhole equipment and/or surface equipment. As an example, the operational decision block 260 can include capabilities for monitoring, analyzing, etc., such data for purposes of making one or more operational decisions, which may include controlling equipment, revising operations, revising a plan, etc. In such an example, data may be fed into the system 200 at one or more points where the quality of the data may be of particular interest. For example, data quality may be characterized by one or more metrics where data quality may provide indications as to trust, probabilities, etc., which may be germane to operational decision making and/or other decision making.

FIG. 3 shows an example of a wellsite system 300 (e.g., at a wellsite that may be onshore or offshore). As shown, the wellsite system 300 can include a mud tank 301 for holding mud and other material (e.g., where mud can be a drilling fluid), a suction line 303 that serves as an inlet to a mud pump 304 for pumping mud from the mud tank 301 such that mud flows to a vibrating hose 306, a drawworks 307 for winching drill line or drill lines 312, a standpipe 308 that receives mud from the vibrating hose 306, a kelly hose 309 that receives mud from the standpipe 308, a gooseneck or goosenecks 310, a traveling block 311, a crown block 313 for carrying the traveling block 311 via the drill line or drill lines 312, a derrick 314, a kelly 318 or a top drive 340, a kelly drive bushing 319, a rotary table 320, a drill floor 321, a bell nipple 322, one or more blowout preventors (BOPs) 323, a drillstring 325, a drill bit 326, a casing head 327 and a flow pipe 328 that carries mud and other material to, for example, the mud tank 301.

In the example system of FIG. 3, a borehole 332 is formed in subsurface formations 330 by rotary drilling; noting that various example embodiments may also use one or more directional drilling techniques, equipment, etc.

As shown in the example of FIG. 3, the drillstring 325 is suspended within the borehole 332 and has a drillstring assembly 350 that includes the drill bit 326 at its lower end. As an example, the drillstring assembly 350 may be a bottom hole assembly (BHA).

The wellsite system 300 can provide for operation of the drillstring 325 and other operations. As shown, the wellsite system 300 includes the traveling block 311 and the derrick 314 positioned over the borehole 332. As mentioned, the wellsite system 300 can include the rotary table 320 where the drillstring 325 pass through an opening in the rotary table 320.

As shown in the example of FIG. 3, the wellsite system 300 can include the kelly 318 and associated components, etc., or the top drive 340 and associated components. As to a kelly example, the kelly 318 may be a square or hexagonal metal/alloy bar with a hole drilled therein that serves as a mud flow path. The kelly 318 can be used to transmit rotary motion from the rotary table 320 via the kelly drive bushing 319 to the drillstring 325, while allowing the drillstring 325 to be lowered or raised during rotation. The kelly 318 can pass through the kelly drive bushing 319, which can be driven by the rotary table 320. As an example, the rotary table 320 can include a master bushing that operatively couples to the kelly drive bushing 319 such that rotation of the rotary table 320 can turn the kelly drive bushing 319 and hence the kelly 318. The kelly drive bushing 319 can include an inside profile matching an outside profile (e.g., square, hexagonal, etc.) of the kelly 318; however, with slightly larger dimensions so that the kelly 318 can freely move up and down inside the kelly drive bushing 319.

As to a top drive example, the top drive 340 can provide functions performed by a kelly and a rotary table. The top drive 340 can turn the drillstring 325. As an example, the top drive 340 can include one or more motors (e.g., electric and/or hydraulic) connected with appropriate gearing to a short section of pipe called a quill, that in turn may be screwed into a saver sub or the drillstring 325 itself. The top drive 340 can be suspended from the traveling block 311, so the rotary mechanism is free to travel up and down the derrick 314. As an example, a top drive 340 may allow for drilling to be performed with more joint stands than a kelly/rotary table approach.

In the example of FIG. 3, the mud tank 301 can hold mud, which can be one or more types of drilling fluids. As an example, a wellbore may be drilled to produce fluid, inject fluid or both (e.g., hydrocarbons, minerals, water, etc.).

In the example of FIG. 3, the drillstring 325 (e.g., including one or more downhole tools) may be composed of a series of pipes threadably connected together to form a long tube with the drill bit 326 at the lower end thereof. As the drillstring 325 is advanced into a wellbore for drilling, at some point in time prior to or coincident with drilling, the mud may be pumped by the pump 304 from the mud tank 301 (e.g., or other source) via the lines 306, 308 and 309 to a port of the kelly 318 or, for example, to a port of the top drive 340. The mud can then flow via a passage (e.g., or passages) in the drillstring 325 and out of ports located on the drill bit 326 (see, e.g., a directional arrow). As the mud exits the drillstring 325 via ports in the drill bit 326, it can then circulate upwardly through an annular region between an outer surface(s) of the drillstring 325 and surrounding wall(s) (e.g., open borehole, casing, etc.), as indicated by directional arrows. In such a manner, the mud lubricates the drill bit 326 and carries heat energy (e.g., frictional or other energy) and formation cuttings to the surface where the mud may be returned to the mud tank 301, for example, for recirculation with processing to remove cuttings and other material.

In the example of FIG. 3, processed mud pumped by the pump 304 into the drillstring 325 may, after exiting the drillstring 325, form a mudcake that lines the wellbore which, among other functions, may reduce friction between the drillstring 325 and surrounding wall(s) (e.g., borehole, casing, etc.). A reduction in friction may facilitate advancing or retracting the drillstring 325. During a drilling operation, the entire drillstring 325 may be pulled from a wellbore and optionally replaced, for example, with a new or sharpened drill bit, a smaller diameter drillstring, etc. As mentioned, the act of pulling a drillstring out of a hole or replacing it in a hole is referred to as tripping. A trip may be referred to as an upward trip or an outward trip (e.g., pulling out of hole (POOH)) or as a downward trip or an inward trip (e.g., running in hole (RIH)) depending on trip direction.

As an example, consider a downward trip where upon arrival of the drill bit 326 of the drillstring 325 at a bottom of a wellbore, pumping of the mud commences to lubricate the drill bit 326 for purposes of drilling to enlarge the wellbore. As mentioned, the mud can be pumped by the pump 304 into a passage of the drillstring 325 and, upon filling of the passage, the mud may be used as a transmission medium to transmit energy, for example, energy that may encode information as in mud-pulse telemetry. Characteristics of the mud can be utilized to determine how pulses are transmitted (e.g., pulse shape, energy loss, transmission time, etc.).

As an example, mud-pulse telemetry equipment may include a downhole device configured to effect changes in pressure in the mud to create an acoustic wave or waves upon which information may modulated. In such an example, information from downhole equipment (e.g., one or more modules of the drillstring 325) may be transmitted uphole to an uphole device, which may relay such information to other equipment for processing, control, etc.

As an example, telemetry equipment may operate via transmission of energy via the drillstring 325 itself. For example, consider a signal generator that imparts coded energy signals to the drillstring 325 and repeaters that may receive such energy and repeat it to further transmit the coded energy signals (e.g., information, etc.).

As an example, the drillstring 325 may be fitted with telemetry equipment 352 that includes a rotatable drive shaft, a turbine impeller mechanically coupled to the drive shaft such that the mud can cause the turbine impeller to rotate, a modulator rotor mechanically coupled to the drive shaft such that rotation of the turbine impeller causes said modulator rotor to rotate, a modulator stator mounted adjacent to or proximate to the modulator rotor such that rotation of the modulator rotor relative to the modulator stator creates pressure pulses in the mud, and a controllable brake for selectively braking rotation of the modulator rotor to modulate pressure pulses. In such example, an alternator may be coupled to the aforementioned drive shaft where the alternator includes at least one stator winding electrically coupled to a control circuit to selectively short the at least one stator winding to electromagnetically brake the alternator and thereby selectively brake rotation of the modulator rotor to modulate the pressure pulses in the mud.

In the example of FIG. 3, an uphole control and/or data acquisition system 362 may include circuitry to sense pressure pulses generated by telemetry equipment 352 and, for example, communicate sensed pressure pulses or information derived therefrom for process, control, etc.

The assembly 350 of the illustrated example includes a logging-while-drilling (LWD) module 354, a measurement-while-drilling (MWD) module 356, an optional module 358, a rotary-steerable system (RSS) and/or motor 360, and the drill bit 326. Such components or modules may be referred to as tools where a drillstring can include a plurality of tools.

As to an RSS, it involves technology utilized for directional drilling. Directional drilling involves drilling into the Earth to form a deviated bore such that the trajectory of the bore is not vertical; rather, the trajectory deviates from vertical along one or more portions of the bore. As an example, consider a target that is located at a lateral distance from a surface location where a rig may be stationed. In such an example, drilling can commence with a vertical portion and then deviate from vertical such that the bore is aimed at the target and, eventually, reaches the target. Directional drilling may be implemented where a target may be inaccessible from a vertical location at the surface of the Earth, where material exists in the Earth that may impede drilling or otherwise be detrimental (e.g., consider a salt dome, etc.), where a formation is laterally extensive (e.g., consider a relatively thin yet laterally extensive reservoir), where multiple bores are to be drilled from a single surface bore, where a relief well is desired, etc.

One approach to directional drilling involves a mud motor; however, a mud motor can present some challenges depending on factors such as rate of penetration (ROP), transferring weight to a bit (e.g., weight on bit, WOB) due to friction, etc. A mud motor can be a positive displacement motor (PDM) that operates to drive a bit (e.g., during directional drilling, etc.). A PDM operates as drilling fluid is pumped through it where the PDM converts hydraulic power of the drilling fluid into mechanical power to cause the bit to rotate.

As an example, a PDM may operate in a combined rotating mode where surface equipment is utilized to rotate a bit of a drillstring (e.g., a rotary table, a top drive, etc.) by rotating the entire drillstring and where drilling fluid is utilized to rotate the bit of the drillstring. In such an example, a surface RPM (SRPM) may be determined by use of the surface equipment and a downhole RPM of the mud motor may be determined using various factors related to flow of drilling fluid, mud motor type, etc. As an example, in the combined rotating mode, bit RPM can be determined or estimated as a sum of the SRPM and the mud motor RPM, assuming the SRPM and the mud motor RPM are in the same direction.

The LWD module 354 may be housed in a suitable type of drill collar and can contain one or a plurality of selected types of logging tools. It will also be understood that more than one LWD and/or MWD module can be employed. Where the position of an LWD module is mentioned, as an example, it may refer to a module at the position of the LWD module 354, the MWD module 356, etc. An LWD module can include capabilities for measuring, processing, and storing information, as well as for communicating with the surface equipment. In the illustrated example, the LWD module 354 may include a seismic measuring device.

The MWD module 356 may be housed in a suitable type of drill collar and can contain one or more devices for measuring characteristics of the drillstring 325 and the drill bit 326. As an example, the MWD module 356 may include equipment for generating electrical power, for example, to power various components of the drillstring 325. As an example, the MWD module 356 may include the telemetry equipment 352, for example, where the turbine impeller can generate power by flow of the mud; it being understood that other power and/or battery systems may be employed for purposes of powering various components. As an example, the MWD module 356 may include one or more of the following types of measuring devices: a weight-on-bit measuring device, a torque measuring device, a vibration measuring device, a shock measuring device, a stick slip measuring device, a direction measuring device, and an inclination measuring device.

FIG. 3 also shows some examples of types of holes that may be drilled. For example, consider a slant hole 372, an S-shaped hole 374, a deep inclined hole 376 and a horizontal hole 378.

A drilling operation can include directional drilling where, for example, at least a portion of a well includes a curved axis. For example, consider a radius that defines curvature where an inclination with regard to the vertical may vary until reaching an angle between approximately 30 degrees and approximately 60 degrees or, for example, an angle to approximately 90 degrees or possibly greater than approximately 90 degrees.

A directional well can include several shapes where each of the shapes may aim to meet particular operational demands. As an example, a drilling process may be performed on the basis of information as and when it is relayed to a drilling engineer. As an example, inclination and/or direction may be modified based on information received during a drilling process.

As explained, a system may be a steerable system and may include equipment to perform a method such as geosteering. A steerable system can include equipment on a lower part of a drillstring which, just above a drill bit, a bent sub may be mounted. Above directional drilling equipment, a drillstring can include MWD equipment that provides real time or near real time data of interest (e.g., inclination, direction, pressure, temperature, real weight on the drill bit, torque stress, etc.) and/or LWD equipment. As to the latter, LWD equipment can make it possible to send to the surface various types of data of interest, including for example, geological data (e.g., gamma ray log, resistivity, density and sonic logs, etc.).

The coupling of sensors providing information on the course of a well trajectory, in real time or near real time, with, for example, one or more logs characterizing the formations from a geological viewpoint, can allow for implementing a geosteering method. Such a method can include navigating a subsurface environment to follow a desired route to reach a desired target or targets.

A drillstring may include an azimuthal density neutron (ADN) tool for measuring density and porosity; an MWD tool for measuring inclination, azimuth and shocks; a compensated dual resistivity (CDR) tool for measuring resistivity and gamma ray related phenomena; one or more variable gauge stabilizers; one or more bend joints; and a geosteering tool, which may include a motor and optionally equipment for measuring and/or responding to one or more of inclination, resistivity and gamma ray related phenomena.

Geosteering can include intentional directional control of a wellbore based on results of downhole geological logging measurements in a manner that aims to keep a directional wellbore within a desired region, zone (e.g., a pay zone), etc. Geosteering may include directing a wellbore to keep the wellbore in a particular section of a reservoir, for example, to minimize gas and/or water breakthrough and, for example, to maximize economic production from a well that includes the wellbore.

Referring again to FIG. 3, the wellsite system 300 can include one or more sensors 364 that are operatively coupled to the control and/or data acquisition system 362. As an example, a sensor or sensors may be at surface locations. As an example, a sensor or sensors may be at downhole locations. As an example, a sensor or sensors may be at one or more remote locations that are not within a distance of the order of approximately one hundred meters from the wellsite system 300.

The system 300 can include one or more sensors 366 that can sense and/or transmit signals to a fluid conduit such as a drilling fluid conduit (e.g., a drilling mud conduit). For example, in the system 300, the one or more sensors 366 can be operatively coupled to portions of the standpipe 308 through which mud flows. As an example, a downhole tool can generate pulses that can travel through the mud and be sensed by one or more of the one or more sensors 366. In such an example, the downhole tool can include associated circuitry such as, for example, encoding circuitry that can encode signals, for example, to reduce demands as to transmission. Circuitry at the surface may include decoding circuitry to decode encoded information transmitted at least in part via mud-pulse telemetry. Circuitry at the surface may include encoder circuitry and/or decoder circuitry and circuitry downhole may include encoder circuitry and/or decoder circuitry. As an example, the system 300 can include a transmitter that can generate signals that can be transmitted downhole via mud (e.g., drilling fluid) as a transmission medium.

FIG. 4 shows an example of a drilling fluid system 400 that may aim to provide for various operations, which may include one or more of removing cuttings from a well, controlling formation pressures, suspending and releasing cuttings, sealing permeable formations, maintaining wellbore stability, minimizing formation damage, cooling, lubricating and supporting a bit and drilling assembly, transmitting hydraulic energy to one or more downhole tools and/or a bit, ensuring adequate formation evaluation, controlling corrosion, facilitating cementing and completion, preventing gas hydrate formation, and minimizing impact on the environment.

As shown in the example of FIG. 4, the system 400 can include a return line 410 and a discharge line 490 (see also, e.g., the lines, pipes, hoses, etc., 306, 308, 309, 310, and 328 of FIG. 3). In the example of FIG. 4, the system 400 may include a shaker 422, a desander 424, a desilter 426, and a degasser 428 associated with various mud pits 420 (e.g., mud tanks) that can receive drilling fluid via the return line 410 and output processed drilling fluid to an active pit 432 that may be in fluid communication with a suction pit 434 and a reserve pit 436 where the suction pit 434 may be in fluid communication with a pump 450 that can pump drilling fluid to the discharge line 490. As an example, one or more mixing units 442 may be included, for example, for addition of one or more materials to the drilling fluid before it is pumped to the discharge line 490.

As an example, the system 400 may be utilized for one or more types of operations, which may include drilling, wireline, completions, blow out control, etc. As to completions, as an example, a cementing operation may include pumping and/or receiving of drilling fluid where cement may be positioned between casing and a borehole wall.

FIG. 5 shows an example graphic 500 of a portion of a subsurface environment that includes a borehole and various features about a wall of the borehole where drillpipe is disposed in the borehole to form a supply path for flow of drilling fluid and to form an annulus between the drillpipe and the wall of the borehole, which may be an expected return path for the drilling fluid.

As shown in the graphic 500, drilling fluid may be lost to the environment via one or more mechanisms, which may alter characteristics of drilling fluid, a borehole and/or a formation. For example, during drilling, a filter cake may form on the wall of a borehole. A filter cake may be residue deposited on a permeable medium when a slurry, such as drilling fluid, is forced against the medium under a pressure. As an example, fluid leakoff from drilling fluid may occur as filtrate, which can be fluid that passes through a wall of a borehole, leaving residue as a filter cake on the wall of the borehole. In such a process, the bulk properties of the circulating drilling fluid may change in a manner that may be dependent on time. For example, consider fluid leakoff occurring until a filter cake becomes relatively impermeable to further filtrate.

Drilling fluids (e.g., muds) may be characterized to determine filtration rate and filter-cake properties. Filter cake properties such as thickness, toughness, slickness and permeability may be determined as filter cake that forms on permeable zones in a borehole may increase risks as to stuck pipe or one or more other types of drilling problems. Additionally, reduced oil and/or gas production may result from reservoir damage when a poor filter cake allows deep filtrate invasion. Often, a certain degree of filter cake buildup may be desirable, for example, to isolate one or more formations from drilling fluid. As an example, in various openhole completions in high-angle or horizontal boreholes, formation of an external filter cake may be desirable to a type of filter cake that forms partly inside the formation, as the latter may pose a higher potential for formation damage.

The graphic 500 also shows examples of drilling fines migration and plugged pores, which may arise due to particulates in supplied drilling fluid and/or particulates carried by supplied drilling fluid.

As to fractures, a borehole may intersect one or more existing fractures and/or drilling of a borehole may cause one or more fractures. As shown in the graphic 500, fractures may provide for loss of drilling fluid.

As explained, drilling fluid may be lost via one or more mechanisms, which may be associated with formation types and/or features that may exist in a subsurface environment. For example, formations types such as gravel, high-permeability sand, vugular, cavernous, etc., may be associated with various types of fluid loss mechanisms. While fractures have been mentioned, features such as faults may also provide for fluid loss. For example, consider fluid loss to an unsealed fault that is intersected by a borehole. In various instances, loss due to one or more fractures, one or more faults, etc., may be substantial and considered abnormal, unexpected and/or undesirable.

As to volume of drilling fluid that may be lost, consider losses of a couple of barrels per hour to hundreds of barrels in a matter of minutes. Given the functions of drilling fluid, substantial losses may increase risk of kicks. A kick can be a flow of formation fluid into a borehole during drilling operations. A kick may be physically caused by the pressure in a borehole being less than that of formation fluid, thus causing pressure-driven flow. An undesirably low borehole pressure may occur when mud weight is too low such that hydrostatic pressure exerted on the formation by the fluid column may be insufficient to hold the formation fluid in the formation. Such a phenomenon may occur if the mud density is suddenly lightened or is not to specification to begin with, or if a drilled formation has a higher pressure than expected, which may be referred to as an underbalanced kick. In various instances, rapid loss of drilling fluid to a formation at one depth may cause a pressure imbalance at another depth, which may then result in a kick. A kick may also occur if dynamic and transient fluid pressure effects (e.g., due to motion of a drillstring or casing) effectively lower the pressure in the borehole below that of the formation, which may be referred to as an induced kick.

In various instances where a kick occurs, characteristics of drilling fluid may be altered. For example, consider dilution of drilling fluid by formation fluid, which may include one or more phases (e.g., solid, liquid and gas). As to gas, it may impact mud weight due to buoyancy as it travels upwardly in an annulus. As to solids, they may alter density, either by being stable and/or by settling in a manner that may generate a density gradient. As to liquid, it may effectively dilute drilling fluid. For example, consider a water-based mud that is diluted by a water kick.

As explained, drilling fluid may be lost via one or more mechanisms. To address loss of drilling fluid, one or more actions may be taken. For example, consider addition of a pill to circulating drilling fluid. A pill may be a relatively small volume of a slurry used for a specific purpose in a drilling operation. Various types of pills may be deployed from time to time at a rig site in an effort to stop circulation loss, free stuck drillpipe, etc.

A pill may include so-called lost circulation material (LCM), which can be a collective term for substances added to drilling fluid when drilling fluid is being lost to one or more formations downhole. Lost circulation materials may include materials that may be fibrous (e.g., cedar bark, shredded cane stalks, mineral fiber and hair), flaky (e.g., mica flakes and pieces of plastic or cellophane sheeting) and/or granular (e.g., ground and sized limestone or marble, wood, nut hulls, FORMICA material, corncobs and cotton hulls). As an example, LCM may be provided in the form of bags or sacks (e.g., consider 50 lb bags, etc.).

Various types of LCM may be utilized, which may include one or more reactive types of LCM. For example, consider a reactive pill that may induce one or more types of reactions (e.g., chemical reactions, etc.) that may change one or more properties thereof upon occurrence of such one or more reactions, for example, to provide for blocking one or more fractures. As an example, a pill may include a reactive material that may be shear activated. For example, consider a material that is liquid under certain conditions and then sets rapidly once sheared through openings of a drill bit. As another example, consider a material that may set harder than cement when subjected to temperatures above a threshold temperature (e.g., consider a temperature equal to or greater than approximately 120 degC).

As an example, a pill may include an agent that may be supplied as a liquid or in another form. For example, consider an agent that may include one or more material of the FORM-A-JEL agent (SLB, Houston, Texas), which may be mixed with one or more other materials to form a pill, which may be a reactive type of pill. As an example, mixing may be performed in a mixing pit (e.g., a mixing tank) with a low-shear paddle mixer or cement batch mixer. As an example, a pill may include oil and water with an emulsifier, lime, and a blend of viscosifiers that crosslink after shear activation. As an example, such a pill may be formulated with either diesel or mineral oil depending on availability, local regulations, and exposure to aquifers.

As an example, an agent may include one or more materials of the FORM-A-BLOK agent (SLB, Houston, Texas), which may be mixed with one or more other materials to form a pill. The FORM-A-BLOK agent may provide for forming a lost circulation pill as a single-sack proprietary blend, for example, for wellbore strengthening applications, a variety of lost circulation scenarios (e.g., including fractures and matrix permeability), etc. As an example, such an agent may be applied in the form of a squeeze pill which, depending on the application, de-waters or de-oils rapidly to form a high-shear-strength plug. While the FORM-A-BLOK agent may be mixed with oil- or synthetic-based fluids, mixing as a water-based pill may provide increased strength. As an example, a pill may be weighted with one or more materials (e.g., barite, calcium carbonate, heavy brine, etc.).

As an example, a pill may be referred to as a pill blend. For example, a pill may include LCM blended with one or more fluids, which may include, for example, solids or no solids. As an example, a pill may be a pill blend of LCM and drilling fluid where a particle size distribution (PSD) of the pill blend may be determined based on particle sizes of the LCM and particle sizes of the drilling fluid where an ultimate PSD may be characterized on a volume basis (e.g., D90, D50, D10, etc.).

As an example, a reactive material that is shear-activated may be mixed with a compressive de-watering or de-oiling agent (e.g., FORM-A-BLOK) to form a pill. PSD may be relevant to such a pill. As an example, a pill may be formed using a reactive material where PSD may be relevant directly or, for example, indirectly. For example, a reactive material pill may have an indirect relationship to PSD in that such material may be specified according to particular fracture size ranges that they may be designed to cure. Hence, PSD may be related to downhole features germane to lost circulation such that PSD may be utilized in selecting a reactive material for a pill even though a reactive pill itself may not be characterized by PSD, unless, for example, it includes one or more of LCM, a de-watering agent, a de-oiling agent, etc. Thus, PSD may be directly and/or indirectly relevant to pill design via one or more types of downhole features such that PSD may be a factor in selection of various types of pill materials. As an example, pill selection may be based on and/or otherwise associated with downhole information and/or contextual information, whether a pill is a particulate type of pill or not.

Various types of materials may be referred to as bridging materials. For example, consider one or more types of solids that may be added to a drilling fluid to bridge across a pore throat or one or more fractures of an exposed rock thereby building a filter cake to help reduce loss of whole mud or excessive filtrate. Bridging materials find common use in drilling fluids and in lost circulation treatments. For reservoir applications, a bridging material may be removable material such as, for example, calcium carbonate (acid-soluble), suspended salt (water-soluble) or oil-soluble resins. For lost-circulation treatments, suitably sized products may be used, as explained, as lost-circulation material (LCM).

As explained, lost circulation may refer to reduced or total absence of fluid flow up an annulus when fluid is pumped through a drillstring disposed in a borehole. Though definitions of may vary (e.g., from operator-to-operator, etc.), a reduction of flow may generally be classified as seepage (e.g., less than 20 bbl/hr or 3 m³/hr), partial lost returns (e.g., greater than 20 bbl/hr or 3 m³/hr, but still some returns), and total lost returns where no fluid comes out of the annulus. In this severe latter case, the borehole may not remain full of fluid even if the pumps are turned off. If the borehole does not remain full of fluid, the vertical height of the fluid column may be reduced such that the pressure exerted on one or more open formations is reduced. This in turn can result in another zone flowing into the borehole, while the loss zone is taking mud (drilling fluid), or even a catastrophic loss of well control. Even in the two less severe forms, the loss of fluid to the formation represents an economic loss of a resource (e.g., drilling fluid) that is to be dealt with, and the impact of which may be directly tied to per barrel cost of drilling fluid and loss rate over time (e.g., consider non-productive time (NPT), etc.).

As explained, lost circulation involves a loss of some amount of drilling fluid returning to surface after being pumped into a borehole. As explained, lost circulation may occur for one or more reasons, such as, for example, when a drill bit encounters natural fissures, fractures or caverns, and drilling fluid flows into newly available space. Lost circulation may also be caused by applying more mud pressure (e.g., drilling overbalanced) on a formation than the formation is strong enough to withstand, thereby opening up a fracture into which drilling fluid flows.

As explained, one or more types of material may be utilized to form a pill or pills. A pill may be pumped downhole where it is intended to have a particular effect, after which it may disappear (e.g., be taken up by a fracture in a formation, etc.). Such types of material may include one or more types LCM, which may be defined by various characteristics. Decision making as to addressing lost circulation may be complicated by lack of knowledge, lack of material at a rig site, etc.

As an example, consider decision making responsive to severe lost circulation while drilling at 15,000 feet using an 18 ppg oil-based drilling fluid where a limestone formation has broken down during a gas kick. In such an example, an operator may make a decision to prepare and pump down one or more materials, which may or may not be successful. For example, consider preparing and pumping down a number of LCM pills, which, if unsuccessful, may be followed by preparing and pumping down cement (e.g., a cement squeeze), which, if unsuccessful, may be followed by an LCM squeeze. For example, consider preparing a 100 barrel slurry of a particular LCM mixed with diesel in a turbine blender and weighted to 18 ppg and then pumping down the slurry (e.g., using a cement pump truck or other pump equipment) where a 10 bbl diesel spacer may be pumped ahead and behind the slurry to reduce cross-contamination and to facilitate partial recovery of the slurry. In such an example, consider pumping 50 barrels of the slurry to squeeze the slurry into the formation to thereby diminish loss paths. In this example, resources and time are wasted in figuring out a successful approach. Had the operator known more particularly the nature of the limestone formation break down, it may have been possible to immediately resort to preparing and pumping the particular LCM mixed with diesel, which would have conserved resources, reduced non-productive time (NPT), and expedited the drilling job.

As explained, a series of decisions may be made and actions performed to address lost circulation. Such decisions and actions may be documented, for example, in the form of a drilling report. Such a drilling report may include one or more sections that are specific to hydraulics and specify drilling fluid characteristics, pump rates, lost circulation events, etc. For example, in the foregoing example, such a report may detail decisions and actions that were unsuccessful and decisions and actions that were successful. However, such a report may be merely stored in a file associated with that particular well and remembered by one or more of the operators in the form of experience, which, if recalled responsive to some future scenario at another well, may be beneficial.

As an example, a framework may provide for capturing knowledge in reports as to lost circulation events in a number of wells. Such a framework may utilize one or more techniques, which may include one or more of natural language processing, machine learning, etc. For example, consider a framework that may provide for determining effectiveness of LCM treatments in total and partial loss circulation events through combining data analytics (e.g., natural language processing, etc.) from offset wells and drilling fluids domain knowledge. As explained, currently, knowledge of lost circulation events may merely reside in a file for a well and in the memory of one or more individuals that addressed one or more of the events. As an example, a framework may provide for assessing actual effectiveness of an LCM treatment after being used at a specific loss circulation event and provide for decision making for future loss circulation events.

As explained, selecting an LCM treatment to deal with a fluid loss event tends to be complex and may demand knowledge of one or more of product behavior from laboratory testing, physical properties, particle size distributions, geological conditions to which a product may be pumped, drilling parameters, flow rates, pop-off valve pressures, surface pit capacity, etc. Such knowledge may be utilized in decision making, for example, by one or more domain experts. As an example, a framework may provide for improved decision making, which may include automated and/or semi-automated decision making. For example, consider a framework that may provide for decision making in a repeatable, automated way with access to data and/or one or more data-driven models. In such an example, historical data may be utilized in a contextual sense to inform future decision making, which may be provided via one or more types of machine learning techniques (e.g., supervised learning, semi-supervised learning, unsupervised learning, self-learning, etc.).

In various instances, in a manual selection approach, LCM selection may be initially defined in the lab and depend on experimental data based on the particle size distribution and volume and the predicted and/or measured fracture geometry. Nevertheless, the actual LCM treatment used in the field might vary from the proposed formulation due to one or more factors, such as, for example, one or more local procedures, access to products, trial and error, etc. Once the treatment has been used in the field, in general, there is no connection between the treatment as designed by the lab and its reported effectiveness.

As explained, a framework may bridge product knowledge from the lab and from the field. For example, consider a framework that may implement one or more model-based artificial intelligence (AI) techniques that use historical data to extract relevant information regarding loss characteristics, treatments and procedures reported in daily operations reports (e.g., consider the WELLTRAK database, SLB, Houston, Texas) and a drilling fluids database (e.g., consider the ONETRAX database, SLB, Houston, Texas). As an example, a framework may provide for evaluation of effectiveness of LCM based on one or more success criteria that may be pre-defined and/or defined by one or more users (e.g., operators, etc.).

As an example, a framework may be operatively coupled with an LCM selection tool (e.g., based on lab-based recommendations), such as, for example, the LC Safeguard tool (SLB, Houston, Texas) to provide a science and/or data-based LCM treatment advisor. As an example, such a framework may provide for generation of recommendations as to previously formulated pill blends and/or as to customized pill blends. As an example, a framework may operate in a generative manner where the framework may output a pill blend that may be different than a previously known pill blend. In such an example, the pill blend may be optimized for a particular scenario such that it may be expected to perform in that particular scenario better than a previously known pill blend.

FIG. 6 shows an example of a method 600 that may be implemented by a framework to generate output that can guide field operations at a rig site responsive to an indication of a lost circulation event. As shown, the method 600 may include a reception block 610 for receiving a report (e.g., a daily operations report, etc.), an identification block 620 for identifying a lost circulation event in the report, an identification block 630 for identifying an LCM treatment and concentration (e.g., from a drilling fluids section of the report), a compute block 640 for computing discrete pill particle size distribution (PSD) that was utilized to treat the lost circulation event, a determination block 650 for determining whether the LCM treatment was successful using one or more criteria (e.g., analyzing one or more subsequent operations in the report, for example, using NLP), and an output block 660 for outputting one or more LCM pill recommendations based on past success rate(s) and formation properties of a current borehole. While the method 600 refers to a single report, the method 600 may include receiving a number of reports (e.g., hundreds, thousands, etc.) from one or more databases to provide for generating expertise across a broad range of lost circulation events for one or more types of wells, formations, etc.

As an example, a method may include computing PSD of an entire fluid, which may help to inform PSD of a pill. For example, in various instances, if a fluid already has a particular PSD, then there may be little to no benefit to add more material (e.g., to add a pill). As an example, a method may include computing PSD as a desirable PSD to address an issue and comparing that PSD to a PSD of fluid in circulation, where, for example, if the fluid in circulation is already at/near the desirable PSD (e.g., optimum or practical optimum given material at hand, etc.), there may be little to no benefit of adding a pill, unless, for example, there may be some type of reactive mechanism that is desired. As an example, a method may include determining whether a pill such as a reactive pill may alter fluid PSD and, for example, based on such a determination, deciding to add one or more materials such that fluid PSD is maintained at a desired PSD.

As an example, PSD may be related to one or more characteristics of a downhole feature or features and/or one or more types of loss mechanisms. As an example, a PSD may be utilized to infer one or more characteristics. As an example, a PSD may be utilized as a proxy for one or more characteristics (e.g., fracture type, fracture size, etc.). As an example, a computed PSD may be utilized to select a treatment that may or may not be directly characterized by PSD. As explained, a PSD may be utilized in an indirect manner to select a treatment (e.g., a pill type or blend) that may not be directly characterized by PSD (e.g., consider a reactive pill type, etc.).

As explained, NLP may be utilized to extract knowledge from reports. For example, daily operations reports from a database may include information regarding the breakdown of the drilling operations. In such an example, part of the data recorded by a wellsite supervisor, responsible for writing the report, may include structured data like type of operations (e.g., type of activity and sub-activities), classification of time (e.g., productive time, non-productive time), depth and time. There may also be unstructured data, for example, in the form of open text. As an example, a section for comments may include other details of operations, including drilling parameters, description of fluid losses, treatments used and procedures.

As an example, NLP may be implemented using one or more types of libraries, platforms, etc. For example, consider the Apache OpenNPL platform of the Apache Software Foundation (Forest Hill, Maryland). As an example, one or more machine learning models may be utilized for purposes of extracting information from text (e.g., text in digital character form, image form, etc.). As an example, one or more generative transformers may be utilized that may generate output based on text input.

As an example, NLP may be used to extract data such as time/depth of a lost circulation event and whether LCM has been used to treat the loss. As an example, NLP may utilize a dictionary (e.g., a corpus) of keywords, which may include terms such as, for example, “total loss”, “loss circulation”, “no return”. In such an example, the terms may be used to identify presence of total loss and/or one or more other forms of loss. As an example, NLP may be applied in a manner that can handle grammar, misspellings, alternative language, etc. For example, consider common misspelling and variations such as “total lost” and “total losses”, which may be included in a list of keywords. As an example, different set of keywords may be used to identify blind drill and use of LCM and/or one or more other materials.

As an example, one or more ends of total loss events may be identified by phrases indicative of drilling under normal conditions, typically when the bit depths are increasing without any presence of any “total loss” or “blind drill” keywords.

As an example, for partial loss events, a method may utilize one or more “loss” keywords and/or variations thereof to extract loss rate through regular expressions with variations as to units (e.g., consider BPH (barrels per hour), which may be present as BBL/HR, BBL/H in report text).

FIG. 7 shows an example of a data structure 700 for a particular well that may be utilized for identifying one or more total losses periods and LCM utilization, as indicated in the last two columns. As shown, total losses stopped after LCM utilization and normal drilling resumed. In such an example, the LCM may be determined to be successful. As indicated by an analysis of the text, subsequent use of LCM was to reduce the partial loss rates.

In the example of FIG. 7, the data structure 700 may provide for generating indexes for LCM utilization and losses, which, as explained, may be related (e.g., associated). As shown, the data structure 700 can include indications as to depth (e.g., measured depth and/or total vertical depth) for drilling, which may be associated with time (e.g., time stamped). As an example, a sequence of “1 0 1” over a period of time for a depth segment may indicate that total losses were not successfully treated by a corresponding LCM treatment or treatments, which may be indicated in the LCM column. Hence, the sequence “1 0 1” may be considered to be a single total loss event even though a “0” appears in the sequence. As an example, a framework may provide for implementation of one or more types of rules that may provide for associating indexes and/or determining a depth span and/or a time span of a total loss event. As explained, oftentimes a first attempt at stemming a total loss may fail, however, a framework may utilize the failure (lack of success) as an indication that the particular attempt is not suitable for use when a total loss occurs at a particular depth in a particular formation being drilled using particular drilling fluid, etc.

As explained, a method may include identifying an LCM treatment and concentration used from a report (e.g., a drilling fluids report section, etc.). For example, the daily fluid reports from the ONETRAX database include information on fluid systems, LCM treatments, product names, concentrations and volume, fluid and treatment preparation, and daily summary.

In the ONETRAX database, a table exists that captures the products that are transferred to an active pit daily. Based on the date of LCM used for treating total loss extracted in previous actions of a method, the method may extract the compositions of LCM pills used. As an example, each transaction may have a unique identifier with detailed concentration and volume of the product, which may allow for the total number of pills per day to also be tracked. As an example, a method may include data cleaning, for example, to group the same products reported under different names together through a dictionary.

As to computing the discrete pill particle size distribution (PSD) used to treat lost circulation, a method may access data for individual LCM products where, for example, each LCM product may have its own particle size distribution (PSD) measured by one or more labs, which may allow for estimating the particle size distribution (PSD) of each LCM pill given corresponding concentrations. As an example, a method may employ a volume-based distribution based on D10, D25, D50, D75 and D90 values, i.e., 90 percent of the particle volume (not number) is below that size. As an example, a method may include computing the volume concentration of an LCM pill transferred to an active pit.

As explained, a method may include utilizing one or more success criteria for an LCM treatment to determine whether or not the LCM treatment was successful. As an example, one or more success criteria may depend on the type of losses: total losses versus partial losses.

As to identifying total loss events and related treatment, a method may apply NLP and/or one or more machine learning techniques to report comments. In such an approach, the method may extract a loss event as a total loss event and understand the procedure used to treat the total loss. Additionally, a method may include identifying one or more success criteria based on a response or responses to a loss event. As an example, an LCM treatment may be deemed successful if normal drilling without total losses resumes after the LCM treatment. However, if blind drilling or sidetracks are still required after pumping the LCM, the LCM treatment may be determined to be a failure with respect to its ability to stop total losses. In general, a total loss event will disrupt drilling operations, which may be reflected in one or more activity codes. On the other hand, partial losses may “hide” within drilling operations. As an example, depending on a partial loss rate, drilling operations may continue with “partial” fluid losses. Additionally, LCM causing total losses to drop to a measurable partial loss could be considered in some cases as a successful application of an LCM pill.

As mentioned, identifying partial losses may be more complex than identifying total losses, which may be due in part to the manner in which partial loss events may be reported. As an example, a method may understand if a treatment used in a partial loss was successful by quantifying the partial loss rate prior and after the treatment is pumped. As an example, success may be determined by studying a trend of losses, which may be obtained via real-time data streaming. However, as explained, a method may attempt to extract partial loss data from daily reports. As an example, once an event has been identified and the rate is known or estimated, a method may determine the success rate of the treatment based on the following rate.

As to total losses, consider one or more of the following success criteria: (1) Success: drilling operations are resumed shortly after the use of LCM; (2) Aided success: drilling operations are resumed within 6 hrs after the last use of LCM pills (e.g., noting that such a time may be adjustable, as appropriate); (3) Ineffective: Drilling is resumed after more than 6 hours from the last use of LCM pills (e.g., noting that such a time may be adjustable, as appropriate); and (4) Failure: the loss event is not cured, and the following operations are drilling blind or sidetrack.

As to partial losses, consider one or more of the following success criteria: (1) Success: loss rate decreases after use of LCM; (2) Likely success: No loss rate recorded after use of LCM, but partial losses stop from NLP analysis; (3) Likely failure/undetermined: no loss rate recorded after use of LCM and partial losses continue; (4) Failure: loss rate increases after use of LCM; (5) Failure total loss: total loss happens after LCM is used for treating partial loss; and (6) Failure static loss: mention of the static loss after LCM use.

As explained, a framework may provide for recommending one or more LCM pills based on past success rates and formation properties. As explained, based on past performance of LCM pills in treating total losses in a particular formation, a framework may implement one or more models that can output one or more recommendations as to one or more appropriate LCM pills, which may be accompanied by estimated success probability. In various instances, a framework may generate output that recommends not using an LCM pill, which may be an appropriate course of action, for example, if the success rate is too long (e.g., consider introduction of excessive NPT, etc.).

As explained, a framework may be integrated into and/or operatively coupled to a tool, such as, for example, the LC Safeguard tool, which may allow WCF selection of the best fluid loss treatment by formation type and, for example, fracture characteristics, by combining expertise of drilling fluids experts and knowledge obtained from reports of past wells. As an example, a framework may provide for recommending when to move beyond use of one or more traditional drilling fluids LCM treatments, for example, consider a framework that may provide for recommendation of gunk and/or cement, with or without modeling performance of such products.

As an example, a framework may provide for understanding why some LCM pills are more successful than others. For example, consider a framework that may implement one or more machine learning (ML) models. As an example, consider application of principal component analysis (PCA) that may provide for deducing components and corresponding concentrations for the best LCM pill response to a loss event. Such an approach may be particularly useful for treating losses in a formation with a large amount of previous historical data. As an example, a framework may also provide for applying such a model to a new formation or new field, for example, given domain knowledge to match the closest formation geologically in one or more databases.

FIG. 8 shows example plots 810 and 820 that may be generated by a framework (e.g., as part of a graphical user interface, etc.). In particular, the plot 810 shows probability of total loss within the next 50 meters for drilling a borehole in a first type of formation and the plot 820 shows probability of total loss within the next 50 meters for drilling a borehole in a second type of formation. The plots 810 and 820 may utilize one or more types of windows (e.g., next 10 meters, 20 meters, 30 meters, etc.) and may provide for depths over a desired range, which may be relative or non-relative.

In the plot 810, the formation may be considered to be a low-risk formation and, averaged across its depth, it is shown to be a low-risk formation (e.g., probability is less than 0.025). However, a framework may identify clearly that a risk is far from even with a near-zero risk early in the formation, rising to a medium-level risk towards the end of the formation (e.g., in terms of total vertical depth, TVD). In the plot 820, the formation is a medium-risk formation and has a considerably higher risk overall but with an observed rapid drop-off in risk throughout the formation (e.g., probability decreasing from a peak of approximately 0.12 to less than approximately 0.03). With the characteristics in the plots 810 and 820, a framework may provide for coordinating one or more LCM strategies and/or optimizing one or more drilling parameters in an effort to quickly handle a loss and/or to reduce risk of loss.

As an example, one or more ML models may provide for generation of one or more risk profiles for a borehole that is being drilled in a field. For example, consider a field where offset wells may number in the hundreds such that the number of daily reports available may be in excess of one million. Such a large number of reports may provide for an amount of data sufficient to train one or more ML models, which may include, for example, one or more deep learning ML models. As an example, training of one or more ML models may include one or more of supervised, semi-supervised and unsupervised learning.

As an example, a trained ML model may provide for predicting probabilities of one or more loss types occurring within a given range of drilling of a borehole in a field. For example, consider predicting the likelihood of a risk of a total loss occurring within the next 50 meters of drilling of a borehole in a field (e.g., noting that such a distance may be adjustable, as appropriate). Such an approach may provide for generation of a machine learning-based risk profile for drilling of a borehole. As an example, a framework may provide for tailoring one or more pill recommendations based on position or positions within a risk profile (e.g., as to drilling position or bottom hole position in terms of measured depth or true vertical depth).

As an example, a rig site may be provisioned with one or more materials based at least in part on a generated risk profile. In such an approach, where a lost circulation event occurs, LCM suitable for treating the lost circulation event may be readily available for use at the rig site. Further, if a risk of a type of lost circulation event is not expected to increase until after a few days of drilling, then delivery of suitable LCM to address that type of risk may be scheduled for delivery accordingly. In such an approach, if a risk profile may change due to occurrence of one or more events, changes in circumstances, etc., a decision may be made to cancel delivery of that LCM where it is no longer deemed suitable for treating a particular risk or where the particular risk is now sufficiently low.

As an example, a framework may provide for re-recommending one or more treatments based on available materials, for example, where waiting for ideal material to arrive may be a factor that weighs against waiting (e.g., due to time, cost, resources, potential detrimental effects to a borehole and/or formation, etc.). As an example, where a framework may determine that an ideal solution would be blend X1, with a success rating of 97 percent, and that an acceptable solution would be blend X2 of available materials with a success rating of 87 percent, depending on one or more factors associated with procurement of ideal material, a framework and/or an operator may select blend X2 for implementation rather than blend X1, noting that material may be procured for blend X1 if an underlying issue is likely to re-occur (e.g., at a neighboring site to be drilled, at a deeper depth, etc.). In such an example, data may be stored as to the two different blends where effects thereof may be compared and/or otherwise utilized to improve performance of the framework (e.g., via additional machine learning, etc.).

As an example, a framework may provide for improved pit management (e.g., drilling fluid tank management). For example, where a risk zone is expected to be reached in two days of drilling, pit space may be reserved for mixing a pill blend that is recommended to address the type of loss or losses that may occur in the risk zone. As an example, a framework may provide for generating recommendations as to pill blends on a section-by-section basis of a borehole. As an example, where a pill blend differs from one section to another (e.g., due to drilling through different types of formations, etc.), a framework may recommend a time to prepare a pit for mixing a pill blend, which may include modifying an existing pill blend or disposing of an existing pill blend to free pit space for the new pill blend. As an example, a framework may provide for generating logistics such as planning logistics as to pit space, pit equipment, etc.

As explained, particle size distribution (PSD) may be a parameter of a pill (e.g., a pill blend) that may be related to success or lack thereof in treating lost circulation. For example, an optimal PSD may provide for reducing pill volume to treat a lost circulation event; whereas, a non-optimal PSD may eventually provide for treating a lost circulation event but with a much greater pill volume. As explained, pill volume and pump rate may be factors in determining a treatment time such that a smaller volume may correspond to a lesser treatment time, which may, in turn, result in lesser NPT. For example, consider a scenario where one cubic meter of a pill blend may be sufficient if the PSD of the pill blend is optimal; whereas, if the PSD of the pill blend is non-optimal, 100 cubic meters may be required. In such an approach, there may be a particular particle size or relatively small range of particle sizes that effectively address the cause of the lost circulation event. Given two identical normal PSDs (e.g., Gaussian) with merely different means, one being optimal and the other shifted by 10 percent from optimal, both will include particles of the optimal size; however, the one shifted by 10 percent will includes fewer particles of the optimal size on a volume basis and hence demand a greater volume to treat a lost circulation event where a greater amount of non-optimally sized material may be wasted.

As an example, a framework may account for a length of coverage and annular cross-sectional area. For example, for a smaller section of a borehole, annular cross-sectional area may be less than that for a larger section of a borehole. In such an example, if a length of coverage is specified to be 50 meters, then the larger section of the borehole will demand more pill volume than the smaller section of the borehole to achieve 50 meters of coverage. Hence, a framework may provide for recommending pill volumes based on factors such as length of coverage and annular cross-sectional area, which may be utilized for provisioning material and/or pit space. As an example, in terms of drilling fluid volume, an LCM pill volume may be approximately 2.5 percent of the drilling fluid volume (e.g., generally less than 10 percent of the drilling fluid volume, which may depend on depth of a borehole, generally a lesser percentage as a borehole is deepened). As an example, a framework may provide for recommending a pill along with a pill volume and, for example, pumping rate (e.g., flow rate).

As an example, a framework may aim to provide for usage of lesser product with a higher success rate. As an example, a mixing time of a pill may be of the order of one hour or more, which may be related to pill volume where a larger pill volume demands more time and energy. As explained, various benefits may flow from use of a framework that can recommend an optimal PSD pill at an optimal volume, which may stem to provisioning, energy, space, disposal, etc. As an example, a framework may provide for reductions in emissions, which may include one or more types of greenhouse gas (GHG) emissions. For example, emissions may be reduced in material usage, material transport, material mixing, material pumping, material disposal, etc.

As explained, a framework may provide for selection of one or more treatments, which may be in the form of a pill or pills. In various instances, a framework may assess a scenario and make a recommendation to not implement a treatment. For example, a framework may provide a best treatment option, however, chances of success may be low such that one or more other factors may override that selected treatment option.

FIG. 9 shows an example of a workflow 900 that may be implemented by a framework or frameworks. The workflow 900 provides for addressing the interdependence of stuck pipe events and lost circulation. As explained, utilization of LCM may reduce lost circulation but may increase the probability of stuck pipe through one or more different mechanisms. In the example of FIG. 9, the thicknesses of the arrows, colors, etc., may provide an indication as to how likely one action may lead to another condition or event, noting that such probabilities may also vary from well to well. As explained, in some instances, utilization of LCM may be too costly from a resource and/or time perspective and/or may give rise to an increased and possibly unacceptable risk of sticking (e.g., stuck pipe). Further, as explained, formation damage may occur from use of one or more types of LCMs that may have an impact directly or indirectly on production of fluid from a formation (e.g., oil and/or gas production).

In the example of FIG. 9, the workflow 900 may be organized in terms of causes, preventive measures, undesired events, mitigation, and consequences. For example, causes may include fracture formation, bad filter cake, solids accumulation, mobile formation, etc.; preventive measures may include control fluid properties, increase circulation, ream section, etc.; undesired events may include lost circulation, stuck pipe due to differential sticking, stuck pipe due to pack off, stuck pipe due to mechanical sticking, etc.; mitigation may include using a pill, which may include LCM and/or one or more other types of materials; and consequences may include no fluid returned at surface (e.g., or other degree of excessive fluid loss).

As shown in the example of FIG. 9, bad filter cake may result in stuck pipe, whether manifested due to differential sticking and/or mechanical sticking where, for example, preventive measures may include control of fluid properties and/or reaming of a section. As shown, solids accumulation may result in stuck pipe manifested due to packing off (e.g., pack off) where, for example, preventive measures may include increasing circulation.

As an example, the workflow 900 may include using a pill, as may be selected through use of a framework, to address one or more causes, which may be associated with one or more undesired events. As shown, pill use may be implemented in combination with one or more other actions, which may include one or more of the preventive measures (e.g., control fluid properties, increase circulation, ream section, etc.), noting that pill use and one or more types of preventive measures may be related (e.g., consider controlling fluid properties through pill use). As shown in the workflow 900, a consequence may be, without mitigation or without effective mitigation, a lack of fluid return at surface. As explained, lost circulation may be to such an extent that fluid is lost to a formation such that little to no fluid returns to surface. As explained, loss of fluid may vary from a gradual lowering of mud level in one or more pits (e.g., tanks) to a complete loss of returns.

As explained, lost circulation may be compared with one or more normal and/or expected phenomena, which may include a relatively continuous reduction in mud volume with respect to time and/or depth as may be caused by the loss of a mud fluid phase as filtrate and/or a mud solid phase as filter cake during a filtration process that may occur on relatively permeable formation surfaces. As an example, a framework may account for one or more mechanisms of loss, which may include abnormal or unexpected or undesirable types of loss (e.g., lost circulation types of loss) and/or normal or expected or desirable types of loss (e.g., filtrate, filter cake, etc.). As an example, a framework may provide for characterizing one or more types of fluids, pills, etc., with respect to PSD, for example, with respect to one or more types of loss mechanisms, which may, for example, be related to one or more types of characteristics of a downhole environment (e.g., formation fractures, faults, filter cake, etc.).

FIG. 10 shows an example of a framework 1000 that may include a number of components. For example, consider a data access component 1010 that provides for accessing one or more databases of reports; a natural language processing (NLP) component 1020 that provides for analyzing reports; a machine learning (ML) component 1030 that provides for performing one or more machine learning techniques to generate one or more trained machine learning models that may provide for prediction, classification, etc.; a visualization and/or graphical user interface (GUI) component 1040 that provides for generating one or more visualizations, GUIs, etc., which may provide for user interaction that may include generation of one or more commands for control of field operations; and a field operations control component 1050 that provides for controlling one or more field operations, which may, for example, occur responsive to user interaction and/or automatically. As explained, a framework may provide for generative output to generate one or more recommended pill blends that may not exist in historical pill blends. In such an approach, a recommended pill blend may be optimized or tailored for a particular scenario with a higher probability of success than that of a historical pill blend.

As an example, a framework may implement one or more equations for decision making. For example, consider equations (1) and (2) below:

EV ⁡ ( LCM ) = P ⁡ ( LCM ⁢ success ) × NPT ⁢ cost ⁢ of ⁢ total ⁢ loss ⁢ event - 
 P ⁡ ( LCM ⁢ trigger ⁢ stuck ⁢ pipe ) × NPT ⁢ cost ⁢ of ⁢ stuck ⁢ pipe - cost ⁢ of ⁢ 
 applying ⁢ LCM ( 1 ) EV ⁡ ( LCM ) = P ⁡ ( mud ⁢ loss | no ⁢ LCM ) × S ⁡ ( mud ⁢ loss | no ⁢ LCM ) - 
 P ⁡ ( mud ⁢ loss | LCM ) × S ⁡ ( mud ⁢ loss | LCM ) + P ⁡ ( stuck ⁢ pipe | no ⁢ LCM ) × 
 S ⁢ ( stuck ⁢ pipe | no ⁢ LCM ) - P ⁡ ( stuck ⁢ pipe | LCM ) - S ⁡ ( stuck ⁢ pipe | LCM ) - 
 cost ⁢ of ⁢ applying ⁢ LCM ( 2 )

As explained, drilling fluid and/or LCM may be delivered through a bore of drillpipe. As explained, PSD of LCM may be characterized as D90, D50 and D10, on a volume-basis. As an example, a pill may be characterized similarly where characterization of a pill may consider the pill as a mixture of components, which include one or more LCMs. In various instances, delivery of a pill may occur via ports of a drill bit. Depending on configuration of drillpipe, a bottom hole assembly (BHA), etc., an option may exist for delivery of a pill via a port that may be above a drill bit or, for example, via an open end of drillpipe that does not include a BHA coupled thereto. In various instances, a drillstring may be tripped out, a BHA removed, and drillpipe tripped in for delivery of a pill via an open end of the drillpipe. In such instances, NPT may be substantial as additional time is required to trip out to remove the BHA, to trip in the drillpipe, to then trip out the drillpipe, followed by reattachment of the BHA (e.g., or a different BHA) to form a drillstring, and tripping in of the drillstring. Hence, in decision making as to a lost circulation event, one or more characteristics of a drillstring may be germane to characteristics of a pill. For example, if LCM of a pill is too large to pass through openings in a drill bit or posses to great of a risk of clogging such openings, then a drillpipe based pill delivery option may be considered or use of a pill with different LCM.

As explained, a pill may include one or more LCMs and one or more types of fluids. As an example, a framework may provide for determining a size distribution of a well-mixed pill where LCM is suspended within fluid, for example, due to viscosity of the fluid. As an example, a framework may provide for recommendation of one pill formulation blend over another pill formulation blend. As explained, such a recommendation may be based on success rate and/or lack thereof of a number of pill formulation blends as utilized for prior use to stem losses at one or more wellsites.

As explained with respect to the system 400 of FIG. 4, one or more components may provide for removal of material from drilling fluid. For example, consider one or more components that may provide for removal of at least some amount of LCM. As an example, LCM may be sacrificial LCM that is to remain downhole (e.g., within a formation), etc., such that removal at surface may be lessened. As an example, a framework may consider one or more types of removal mechanisms, which may be downhole mechanisms and/or surface mechanisms. As an example, a framework may provide for recommending a drilling fluid formulation following a lost circulation event that may have been treated by a recommended pill formulation. As an example, a framework may provide for generation of one or more recommendations as to one or more treatments as to a formation or formations, which may depend on prior utilization of one or more pills. For example, a particular type of pre-production treatment for a reservoir may be tailored in view of pill material that may be in contact with the reservoir. In such an example, a pre-production treatment may aim to dissolve LCM in a reservoir as resulting from application of one or more pills to treat lost circulation during drilling.

As an example, a framework may utilize one or more of empirical models, physics-based models, deterministic rules, machine learning models, etc. As to feature engineering for machine learning, as an example, consider one or more of formation type, depth, pipe diameter, drill bit, port(s), BHA, open pipe, fracture density/pore density (e.g., per sq meter), fracture size (e.g., diameter of opening), fracture orientation, length of coverage, pore throat size (e.g., pore diameter), pore connectivity, bridging, temperature, chemical resistance, etc. As an example, features may be available via reports and extractable via NLP of reports.

As an example, a framework may provide for physics-based determinations as to PSD of materials, may provide for case-based reasoning for recommending pill blends, and/or may provide for generation of machine learning-based risk and/or chance of success.

FIG. 11 shows an example of a method 1100 and an example of a system 1190. As shown, the method 1100 can include a generation block 1110 for generating a pill blend recommendation based at least in part on formation characteristics to mitigate formation loss of drilling fluid during drilling of a borehole, where the pill blend recommendation specifies a particle size distribution determined by a framework that relates historical pill blends and mitigation success; and an issuance block 1120 for, responsive to an indication of formation loss of drilling fluid during the drilling of the borehole, issuing an instruction to pump a pill blend formulated according to the pill blend recommendation.

The method 1100 is shown in FIG. 11 in association with various computer-readable media (CRM) blocks 1111 and 1121. Such blocks generally include instructions suitable for execution by one or more processors (or processor cores) to instruct a computing device or system to perform one or more actions. While various blocks are shown, a single medium may be configured with instructions to allow for, at least in part, performance of various actions of the method 1100. As an example, a computer-readable medium (CRM) may be a computer-readable storage medium that is non-transitory and that is not a carrier wave. As an example, one or more of the blocks 1111 and 1121 may be in the form processor-executable instructions.

In the example of FIG. 11, the system 1190 includes one or more information storage devices 1191, one or more computers 1192, one or more networks 1195 and instructions 1196. As to the one or more computers 1192, each computer may include one or more processors (e.g., or processing cores) 1193 and memory 1194 for storing the instructions 1196, for example, executable by at least one of the one or more processors 1193 (see, e.g., the blocks 1111 and 1121). As an example, a computer may include one or more network interfaces (e.g., wired or wireless), one or more graphics cards, a display interface (e.g., wired or wireless), etc.

As to types of machine learning (ML) models that may be implemented for one or more purposes, which may include event detection, consider one or more of a support vector machine (SVM) model, a k-nearest neighbors (KNN) model, an ensemble classifier model, a neural network (NN) model, etc. As an example, a machine learning model can be a deep learning model (e.g., deep Boltzmann machine, deep belief network, convolutional neural network, stacked auto-encoder, etc.), an ensemble model (e.g., random forest, gradient boosting machine, bootstrapped aggregation, AdaBoost, stacked generalization, gradient boosted regression tree, etc.), a neural network model (e.g., radial basis function network, perceptron, back-propagation, Hopfield network, etc.), a regularization model (e.g., ridge regression, least absolute shrinkage and selection operator, elastic net, least angle regression), a rule system model (e.g., cubist, one rule, zero rule, repeated incremental pruning to produce error reduction), a regression model (e.g., linear regression, ordinary least squares regression, stepwise regression, multivariate adaptive regression splines, locally estimated scatterplot smoothing, logistic regression, etc.), a Bayesian model (e.g., naïve Bayes, average on-dependence estimators, Bayesian belief network, Gaussian naïve Bayes, multinomial naïve Bayes, Bayesian network), a decision tree model (e.g., classification and regression tree, iterative dichotomiser 3, C4.5, C5.0, chi-squared automatic interaction detection, decision stump, conditional decision tree, M5), a dimensionality reduction model (e.g., principal component analysis, partial least squares regression, Sammon mapping, multidimensional scaling, projection pursuit, principal component regression, partial least squares discriminant analysis, mixture discriminant analysis, quadratic discriminant analysis, regularized discriminant analysis, flexible discriminant analysis, linear discriminant analysis, etc.), an instance model (e.g., k-nearest neighbor, learning vector quantization, self-organizing map, locally weighted learning, etc.), a clustering model (e.g., k-means, k-medians, expectation maximization, hierarchical clustering, etc.), etc.

As an example, a machine model may be built using a computational framework with a library, a toolbox, etc., such as, for example, those of the MATLAB framework (MathWorks, Inc., Natick, Massachusetts). The MATLAB framework includes a toolbox that provides supervised and unsupervised machine learning algorithms, including support vector machines (SVMs), boosted and bagged decision trees, k-nearest neighbor (KNN), k-means, k-medoids, hierarchical clustering, Gaussian mixture models, and hidden Markov models. Another MATLAB framework toolbox is the Deep Learning Toolbox (DLT), which provides a framework for designing and implementing deep neural networks with algorithms, pretrained models, and apps. The DLT provides convolutional neural networks (ConvNets, CNNs) and long short-term memory (LSTM) networks to perform classification and regression on image, time-series, and text data. The DLT includes features to build network architectures such as generative adversarial networks (GANs) and Siamese networks using custom training loops, shared weights, and automatic differentiation. The DLT provides for model exchange various other frameworks.

As an example, the TENSORFLOW framework (Google LLC, Mountain View, CA) may be implemented, which is an open-source software library for dataflow programming that includes a symbolic math library, which can be implemented for machine learning applications that can include neural networks. As an example, the CAFFE framework may be implemented, which is a DL framework developed by Berkeley AI Research (BAIR) (University of California, Berkeley, California). As another example, consider the SCIKIT platform (e.g., scikit-learn), which utilizes the PYTHON programming language. As an example, a framework such as the APOLLO AI framework may be utilized (APOLLO.AI GmbH, Germany). As an example, a framework such as the PYTORCH framework may be utilized (Facebook AI Research Lab (FAIR), Facebook, Inc., Menlo Park, California).

As an example, a training method can include various actions that can operate on a dataset to train a ML model. As an example, a dataset can be split into training data and test data where test data can provide for evaluation. A method can include cross-validation of parameters and best parameters, which can be provided for model training.

The TENSORFLOW framework can run on multiple CPUs and GPUs (with optional CUDA (NVIDIA Corp., Santa Clara, California) and SYCL (The Khronos Group Inc., Beaverton, Oregon) extensions for general-purpose computing on graphics processing units (GPUs)). TENSORFLOW is available on 64-bit LINUX, MACOS (Apple Inc., Cupertino, California), WINDOWS (Microsoft Corp., Redmond, Washington), and mobile computing platforms including ANDROID (Google LLC, Mountain View, California) and IOS (Apple Inc.) operating system-based platforms.

TENSORFLOW computations can be expressed as stateful dataflow graphs; noting that the name TENSORFLOW derives from the operations that such neural networks perform on multidimensional data arrays. Such arrays can be referred to as “tensors”.

As an example, a device may utilize TENSORFLOW LITE (TFL) or another type of lightweight framework. TFL is a set of tools that enables on-device machine learning where models may run on mobile, embedded, and loT devices. TFL is optimized for on-device machine learning, by addressing latency (no round-trip to a server), privacy (no personal data leaves the device), connectivity (Internet connectivity is demanded), size (reduced model and binary size) and power consumption (e.g., efficient inference and a lack of network connections). TFL includes multiple platform support, covering ANDROID and iOS devices, embedded LINUX, and microcontrollers and diverse language support, which includes JAVA, SWIFT, Objective-C, C++, and PYTHON. TFL provides for high performance, with hardware acceleration and model optimization.

As an example, a method may include generating a pill blend recommendation based at least in part on formation characteristics to mitigate formation loss of drilling fluid during drilling of a borehole, where the pill blend recommendation specifies a particle size distribution determined by a framework that relates historical pill blends and mitigation success; and, responsive to an indication of formation loss of drilling fluid during the drilling of the borehole, issuing an instruction to pump a pill blend formulated according to the pill blend recommendation. In such an example, the particle size distribution may relate to one or more structural features in a subsurface environment (e.g., formation features, etc.). For example, consider one or more types of fractures, borehole wall features, etc.).

As an example, a method may include generating a framework by accessing reports for a number of wellsites, extracting data of the historical pill blends, extracting indicia of mitigation success, determining instances of mitigation success based at least in part on the indicia, and relating the extracted data of the historical pills to the instances of mitigation success. In such an example, extracting indicia of mitigation success may include utilizing one or more success criteria. For example, one or more success criteria may include resuming drilling after pumping of one of the pill blends.

As an example, a method may include generating a risk profile for one or more types of formation losses of drilling fluid, where the risk profile characterizes risk with respect to length of a trajectory of a borehole. In such an example, the trajectory of the borehole may be or include at least a planned trajectory portion. As an example, a method may include issuing one or more instructions for managing a drilling fluid system based at least in part on a risk profile.

As an example, a pill blend may include lost circulation material. For example, consider a particle size distribution that depends at least in part on concentration of the lost circulation material in the pill blend.

As an example, a particle size distribution may depend on one or more formation loss of drilling fluid mechanisms. For example, consider one or more formation loss of drilling fluid mechanisms that may include one or more of filtrate loss, fracture loss, and fault loss.

As an example, a framework may include a trained machine learning model. In such an example, the trained machine learning model may operate responsive to input of features to generate output, where the pill blend recommendation is based at least in part on the output. In such an example, the features may include equipment-based features and formation-based features. In such an example, the equipment-based features may include at least one bottom hole assembly-based feature. As an example, features may include one or more operational features, for example, as may be for performing one or more drilling operations.

As an example, a pill blend recommendation may have an acceptably low risk of clogging one or more openings of a drillstring utilized for drilling a borehole. For example, consider an opening that may be an opening of a drill bit that provides for passage of drilling fluid.

As an example, a particle size distribution may be computed and/or utilized that aims to reduce volume demand for a pill blend. In such an example, the particle size distribution may be based at least in part on volume-based D90, D50, and D10 values. As an example, one or more other values may be utilized alternatively or additionally.

As an example, a system can include one or more processors; memory accessible to at least one of the one or more processors; processor-executable instructions stored in the memory and executable to instruct the system to: generate a pill blend recommendation based at least in part on formation characteristics to mitigate formation loss of drilling fluid during drilling of a borehole, where the pill blend recommendation specifies a particle size distribution determined by a framework that relates historical pill blends and mitigation success; and, responsive to an indication of formation loss of drilling fluid during the drilling of the borehole, issue an instruction to pump a pill blend formulated according to the pill blend recommendation.

As an example, one or more computer-readable storage media can include processor-executable instructions to instruct a computing system to: generate a pill blend recommendation based at least in part on formation characteristics to mitigate formation loss of drilling fluid during drilling of a borehole, where the pill blend recommendation specifies a particle size distribution determined by a framework that relates historical pill blends and mitigation success; and, responsive to an indication of formation loss of drilling fluid during the drilling of the borehole, issue an instruction to pump a pill blend formulated according to the pill blend recommendation.

As an example, a computer program product can include one or more computer-readable storage media that can include processor-executable instructions to instruct a computing system to perform one or more methods and/or one or more portions of a method.

In some embodiments, a method or methods may be executed by a computing system. FIG. 12 shows an example of a system 1200 that can include one or more computing systems 1201-1, 1201-2, 1201-3 and 1201-4, which may be operatively coupled via one or more networks 1209, which may include wired and/or wireless networks.

As an example, a system can include an individual computer system or an arrangement of distributed computer systems. In the example of FIG. 12, the computer system 1201-1 can include one or more modules 1202, which may be or include processor-executable instructions, for example, executable to perform various tasks (e.g., receiving information, requesting information, processing information, simulation, outputting information, etc.).

As an example, a module may be executed independently, or in coordination with, one or more processors 1204, which is (or are) operatively coupled to one or more storage media 1206 (e.g., via wire, wirelessly, etc.). As an example, one or more of the one or more processors 1204 can be operatively coupled to at least one of one or more network interfaces 1207; noting that one or more other components 1208 may also be included. In such an example, the computer system 1201-1 can transmit and/or receive information, for example, via the one or more networks 1209 (e.g., consider one or more of the Internet, a private network, a cellular network, a satellite network, etc.).

As an example, the computer system 1201-1 may receive from and/or transmit information to one or more other devices, which may be or include, for example, one or more of the computer systems 1201-2, etc. A device may be located in a physical location that differs from that of the computer system 1201-1. As an example, a location may be, for example, a processing facility location, a data center location (e.g., server farm, etc.), a rig location, a wellsite location, a downhole location, etc.

As an example, a processor may be or include a microprocessor, microcontroller, processor module or subsystem, programmable integrated circuit, programmable gate array, or another control or computing device.

As an example, the storage media 1206 may be implemented as one or more computer-readable or machine-readable storage media. As an example, storage may be distributed within and/or across multiple internal and/or external enclosures of a computing system and/or additional computing systems.

As an example, a storage medium or storage media may include one or more different forms of memory including semiconductor memory devices such as dynamic or static random access memories (DRAMs or SRAMs), erasable and programmable read-only memories (EPROMs), electrically erasable and programmable read-only memories (EEPROMs) and flash memories, magnetic disks such as fixed, floppy and removable disks, other magnetic media including tape, optical media such as compact disks (CDs) or digital video disks (DVDs), BLUERAY disks, or other types of optical storage, or other types of storage devices.

As an example, a storage medium or media may be located in a machine running machine-readable instructions, or located at a remote site from which machine-readable instructions may be downloaded over a network for execution. As an example, various components of a system such as, for example, a computer system, may be implemented in hardware, software, or a combination of both hardware and software (e.g., including firmware), including one or more signal processing and/or application specific integrated circuits.

As an example, a system may include a processing apparatus that may be or include a general-purpose processors or application specific chips (e.g., or chipsets), such as ASICs, FPGAs, PLDs, or other appropriate devices.

As an example, a device may be a mobile device that includes one or more network interfaces for communication of information. For example, a mobile device may include a wireless network interface (e.g., operable via IEEE 802.11, ETSI GSM, BLUETOOTH, satellite, etc.). As an example, a mobile device may include components such as a main processor, memory, a display, display graphics circuitry (e.g., optionally including touch and gesture circuitry), a SIM slot, audio/video circuitry, motion processing circuitry (e.g., accelerometer, gyroscope), wireless LAN circuitry, smart card circuitry, transmitter circuitry, GPS circuitry, and a battery. As an example, a mobile device may be configured as a cell phone, a tablet, etc. As an example, a method may be implemented (e.g., wholly or in part) using a mobile device. As an example, a system may include one or more mobile devices.

As an example, a system may be a distributed environment, for example, a so-called “cloud” environment where various devices, components, etc. interact for purposes of data storage, communications, computing, etc. As an example, a device or a system may include one or more components for communication of information via one or more of the Internet (e.g., where communication occurs via one or more Internet protocols), a cellular network, a satellite network, etc. As an example, a method may be implemented in a distributed environment (e.g., wholly or in part as a cloud-based service).

As an example, information may be input from a display (e.g., consider a touchscreen), output to a display or both. As an example, information may be output to a projector, a laser device, a printer, etc. such that the information may be viewed. As an example, information may be output stereographically or holographically. As to a printer, consider a 2D or a 3D printer. As an example, a 3D printer may include one or more substances that can be output to construct a 3D object. For example, data may be provided to a 3D printer to construct a 3D representation of a subterranean formation. As an example, layers may be constructed in 3D (e.g., horizons, etc.), geobodies constructed in 3D, etc. As an example, holes, fractures, etc., may be constructed in 3D (e.g., as positive structures, as negative structures, etc.).

Although only a few example embodiments have been described in detail above, those skilled in the art will readily appreciate that many modifications are possible in the example embodiments. Accordingly, all such modifications are intended to be included within the scope of this disclosure as defined in the following claims. In the claims, means-plus-function clauses are intended to cover the structures described herein as performing the recited function and not only structural equivalents, but also equivalent structures. Thus, although a nail and a screw may not be structural equivalents in that a nail employs a cylindrical surface to secure wooden parts together, whereas a screw employs a helical surface, in the environment of fastening wooden parts, a nail and a screw may be equivalent structures.