DOWNHOLE ESTIMATION OF MULTIPHASE FLOWS IN PRODUCTION SYSTEMS

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims priority to U.S. Provisional Application No. 63/555,653, filed Feb. 20, 2024, which is incorporated by reference herein in its entirety.

FIELD OF THE INVENTION

This disclosure relates generally to hydrocarbon production and, more particularly, to methods and apparatuses to perform downhole flow metering in multiphase flows.

BACKGROUND INFORMATION

Wellbores may be drilled into subsurface rocks to create wells to access subterranean fluids, such as hydrocarbons, stored in subterranean formations. When these subterranean fluids are produced from the wells, it may be desirable to obtain certain characteristics of the produced fluids to facilitate efficient and economic exploration and production. For example, it may be desirable to obtain flow rates and/or other characteristics of the produced fluids. These produced fluids are often multiphase fluids (e.g., having some combination of water, oil, and gas) in multiple reservoir zones that have respective flowmeters. However, in some embodiments, the presence of multiple phases and zones may provide an interpretation problem where there are more unknowns than are solvable using conventional mechanisms.

SUMMARY

A summary of certain embodiments described herein is set forth below. It should be understood that these aspects are presented merely to provide the reader with a brief summary of these certain embodiments and that these aspects are not intended to limit the scope of this disclosure.

In one embodiment, a system includes multiple sensors located in different zones of a hydrocarbon production system. The multiple sensors are configured to capture parameters about flow through multiple zones of a wellbore. The system also includes a processor that is configured to obtain data about a multiphase flow through the plurality of zones of the wellbore of the hydrocarbon production system from the multiple sensors and to solve an interpretation problem for a first unknown in a bottommost zone. The processor is configured to use a value for the first unknown in the bottommost zone to solve for a second unknown in an upper zone that is above the bottommost zone in the wellbore of the hydrocarbon production system. The processor is configured to change control parameters of the hydrocarbon production system based at least in part on the first unknown and the second unknown.

In another embodiment, a method includes receiving measurements at a processor from a plurality of sensors in a plurality of zones of a wellbore of a hydrocarbon production system. The method also includes solving, via the processor, an interpretation problem for a first unknown in a bottommost zone of the plurality of zones. Moreover, the method includes using a first value for the first unknown in the bottommost zone to solve for a second unknown using the processor. The second unknown pertains to a parameter in an upper zone of the plurality of zones that is above the bottommost zone in the wellbore of the hydrocarbon production system. Furthermore, the method includes causing, by the processor, a change in an aperture of a programmable flow control valve of the hydrocarbon production system based at least in part on the first unknown and the second unknown.

In a further embodiment, a system includes a plurality of pressure sensors configured to measure pressure in a plurality of zones in a wellbore in a hydrocarbon production system. The system also includes a plurality of field control valves in the plurality of zones configured to control flow from an annulus into tubing of the wellbore based at least in part on respective aperture sizes of the plurality of field control valves. Moreover, the system includes a plurality of temperature sensors configured to measure temperature in the plurality of zones. The system further includes one or more processors configured to receive the temperature measurements for the plurality of zones and to receive the pressure measurements for the plurality of zones. The one or more processors are further configured to estimate no upstream flow in a most upstream zone of the plurality of zones. The most upstream zone is the furthest zone from a wellhead of the wellbore. The one or more processors also are configured to determine flow properties in the most upstream zone and to use the determined flow properties in the most upstream zone, respective temperature measurements, and respective pressure measurements to determine flow properties of each zone of the plurality of zones in a sequence of most upstream to most downstream. Furthermore, the one or more processors are configured to, based at least in part on flow properties of at least one of the plurality of zones, cause at least one aperture of the plurality of field control valves to change.

BRIEF DESCRIPTION OF THE DRAWINGS

Various aspects of this disclosure may be better understood upon reading the following detailed description and upon reference to the drawings, in which:

FIG. 1 illustrates a diagram of a data capturing system used to capture data in and/or around an oilfield, such as in a wellbore, in accordance with embodiments of the present disclosure;

FIG. 2 illustrates a computing system used to process data from the data capturing system of FIG. 1, in accordance with embodiments of the present disclosure;

FIG. 3 illustrates a machine learning (ML) based workflow using the computing system of FIG. 2, in accordance with embodiments of the present disclosure;

FIG. 4 illustrates a diagram of a well that may be located in the wellbore of FIG. 1, in accordance with embodiments of the present disclosure;

FIG. 5 illustrates a process for using a machine learning engine to combine historical measurements, real-time measurements, and simulation results to provide output multiphase flow estimations, in accordance with embodiments of the present disclosure;

FIG. 6 illustrates a cross-section of a zone of the well of FIG. 4, in accordance with embodiments of the present disclosure;

FIG. 7 illustrates a cross-section of a bottommost zone of the well of FIG. 4, in accordance with embodiments of the present disclosure;

FIG. 8 illustrates a graph interpreting unknowns of the zones of FIG. 6 or 7, in accordance with embodiments of the present disclosure; and

FIG. 9 illustrates a flow diagram of a process that may be performed using one or more computing devices of FIG. 2 to characterize flow properties in a multizonal and multiphase flow, in accordance with embodiments of the present disclosure.

DETAILED DESCRIPTION

In the following, reference is made to embodiments of the disclosure. It should be understood, however, that the disclosure is not limited to specific described embodiments. Instead, any combination of the following features and elements, whether related to different embodiments or not, is contemplated to implement and practice the disclosure. Furthermore, although embodiments of the disclosure may achieve advantages over other possible solutions and/or over the prior art, whether or not a particular advantage is achieved by a given embodiment is not limiting of the disclosure. Thus, the following aspects, features, embodiments, and advantages are merely illustrative and are not considered elements or limitations of the claims except where explicitly recited in a claim. Likewise, reference to “the disclosure” shall not be construed as a generalization of inventive subject matter disclosed herein and should not be considered to be an element or limitation of the claims except where explicitly recited in a claim.

Although the terms first, second, third, etc., may be used herein to describe various elements, components, regions, layers and/or sections, these elements, components, regions, layers and/or sections should not be limited by these terms. These terms may be only used to distinguish one element, component, region, layer or section from another region, layer, or section. Terms such as “first,” “second” and other numerical terms, when used herein, do not imply a sequence or order unless clearly indicated by the context. Thus, a first element, component, region, layer, or section discussed herein could be termed a second element, component, region, layer, or section without departing from the teachings of the example embodiments.

When introducing elements of various embodiments of the present disclosure, the articles “a,” “an,” and “the” are intended to mean that there are one or more of the elements. The terms “comprising,” “including,” and “having” are intended to be inclusive and mean that there may be additional elements other than the listed elements. Additionally, it should be understood that references to “one embodiment” or “an embodiment” of the present disclosure are not intended to be interpreted as excluding the existence of additional embodiments that also incorporate the recited features. Furthermore, when reciting “or,” this disclosure intends such language to be an inclusive or where “A or B” is intended as “A or B or a combination of A and B” unless explicitly indicating that a specific recitation of “or” is intended to be interpreted as an exclusive or.

As used herein, the terms “connect”, “connection”, “connected”, “in connection with”, and “connecting” are used to mean “in direct connection with” or “in connection with via one or more elements”; and the term “set” is used to mean “one element” or “more than one element”. Further, the terms “couple”, “coupling”, “coupled”, “coupled together”, and “coupled with” are used to mean “directly coupled together” or “coupled together via one or more elements”. As used herein, the terms “up” and “down”; “upper” and “lower”; “top” and “bottom”; and other like terms indicating relative positions to a given point or element are utilized to more clearly describe some elements. Commonly, these terms relate to a reference point at the surface from which drilling operations are initiated as being the top point and the total depth being the lowest point, wherein the well (e.g., wellbore, borehole) is vertical, horizontal or slanted relative to the surface.

Language of degree used herein, such as the terms “approximately,” “about,” “generally,” and “substantially” as used herein represent a value, amount, or characteristic close to the stated value, amount, or characteristic that still performs a desired function or achieves a desired result. For example, the terms “approximately,” “about,” “generally,” and “substantially” may refer to an amount that is within less than 10% of, within less than 5% of, within less than 1% of, within less than 0.1% of, and/or within less than 0.01% of the stated amount. As another example, in certain embodiments, the terms “generally parallel” and “substantially parallel” or “generally perpendicular” and “substantially perpendicular” refer to a value, amount, or characteristic that departs from exactly parallel or perpendicular, respectively, by less than or equal to 15 degrees, 10 degrees, 5 degrees, 3 degrees, 1 degree, or 0.1 degree.

Some embodiments will now be described with reference to the figures. Like elements in the various figures will be referenced with like numbers for consistency. In the following description, numerous details are set forth to provide an understanding of various embodiments and/or features. It will be understood, however, by those skilled in the art, that some embodiments may be practiced without many of these details, and that numerous variations or modifications from the described embodiments are possible. As used herein, the terms “above” and “below,” “up” and “down,” “upper” and “lower,” “upwardly” and “downwardly,” and other like terms indicating relative positions above or below a given point are used in this description to more clearly describe certain embodiments. Furthermore, “optimize” as used herein is intended to cover scenarios where certain objectives/parameters are enhanced or improved even if there may be further improvement available. In other words, an operation may be optimized without being the most optimized possible solution.

This disclosure relates to a methodology for continuously obtaining multiphase (e.g., two or more phases) downhole full bore flow rates, by combining both downhole and surface data. The method includes actual flow metering data in the full bore, completed by other type of data which shows some sensitivity to the downhole flow rates (e.g., downhole flow control valves, surface choke, and surface flow metering). The composite dataset is consumed using both physical-based and data-driven models. Traditional methodology for estimating flowrates rely on vertical flux modelling. However, this disclosure relates to using dedicated full bore downhole flow metering data to extend phase flow estimations to the flows along the tubing for multiple phases.

Additionally or alternatively, this disclosure relates to a methodology for obtaining multiphase (e.g., 2 phases) downhole full bore flow rates in multiple reservoir zones using data from a downhole flowmeter installed in each zone. The downhole flowmeter is made of a set of pressure and temperature sensors. For a given zone, the interpretation problem is stated as the determination of three unknowns. However, the flowmeter may provide only two independent data points. To circumvent this issue, the proposed methodology starts at the most bottom zone of the well, where one of the unknowns to be determined (upstream tubing flow) is known to be zero. Resolution in this bottommost zone yields the downstream tubing flow at the bottommost zone. This downstream tubing flow at the bottommost zone is equal to the upstream tubing flow for the next zone directly above the bottommost zone. With this additional knowledge, this next zone interpretation problem can then be solved (e.g., two unknowns with two data points). The procedure then continues sequentially, one zone after another until the interpretation problem is solved for all of the zones along the borehole.

With the foregoing in mind, FIG. 1 illustrates a system 10 to capture and produce data output 12 in an oilfield that is captured as part of a clean-out operation, wireline operation, pumping operation, drilling operation, extraction operation, or any other operation being performed. In the illustrated embodiment, the data capture is being at least partially performed by a tool 14 suspended by a rig 15 and into a wellbore 16 during such operations. During production, data may be acquired using some tools (e.g., surface measurements). The tool 14 is adapted for deployment into wellbore 16 for generating well logs, performing downhole tests, collecting samples, and/or collecting any other data. For instance, the tool 14 may assist in performing a logging while drilling (LWD) operation. Additionally or alternatively, the tool 14 may, for example, have an explosive, radioactive, electrical, or acoustic energy source 18 that sends and/or receives electrical signals to surrounding subterranean formations 20 and/or fluids therein. Return signals may be detected using the tool 14 and/or other tools located at other locations at/near the oilfield. Additionally or alternatively, the tool 14 may include downhole chokes, sensors (e.g., flowmeters), and/or other devices for measuring and/or controlling flows through the wellbore 16.

Computer facilities may be positioned at various locations about the oilfield (e.g., the surface unit 22) and/or at remote locations. The surface unit 22 may be used to communicate with the tool 14 and/or offsite operations, as well as with other surface or downhole sensors. The surface unit 22 is capable of communicating with the tool 14, sensors, pumps, one or more chokes 23 (surface and/or subsurface chokes), and/or other equipment. For instance, the choke 23 may be an adjustable choke that controls fluid flow out of the wellbore. The surface unit 22 may also collect data generated during the drilling operation, clean-out operation, production operation, and/or logging and produces data output 12, which may then be stored or transmitted. In other words, the surface unit 22 may collect data generated during any corresponding operation and may produce data output 12 that may be stored or transmitted.

The surface unit 22 may include one or more various sensors and/or gauges that may additionally or alternatively be located at other locations in the oilfield. These sensors and/or gauges may be positioned about the oilfield (e.g., in/at the rig 15) to collect data relating to various field operations. As shown, at least one downhole sensor 24 is positioned in the tool 14 to measure downhole parameters which relate to, for example flow rates, porosity, permeability, fluid composition and/or other parameters of the field operation. During drilling, different or more parameters, such as weight on bit, torque on bit, pressures, temperatures, flow rates, compositions, rotary speed, and/or other parameters of the field operation, may be measured.

The surface unit 22 may include a transceiver 33 to enable communications between the surface unit 22 and various portions of the oilfield or other locations. The surface unit 22 may also be provided with or functionally connected to one or more controllers for actuating mechanisms at the oilfield. The surface unit 22 may then send command signals to the oilfield in response to data received. The surface unit 22 may receive commands via the transceiver 33 and/or may itself execute commands to the controller. A computing system including a processor may be included to analyze the data (locally or remotely), make decisions, control operations, and/or actuate the controller. In this manner, the oilfield may be selectively adjusted based on the data collected. This technique may be used to enhance portions of the field operation, such as controlling drilling, weight on bit, pump rates, and/or other parameters. These adjustments may be made automatically based on an executing application with or without user input.

A mud pit 26 is used to draw drilling mud into the drilling tools via flow line 28 for circulating drilling mud down through the drilling tools, then up wellbore 16 and back to the surface. The drilling mud may be filtered and returned to the mud pit 26. A circulating system may be used for storing, controlling, or filtering the flowing drilling muds. The drilling tools are advanced into subterranean formations 20 to reach a reservoir 30 from which petrochemicals are extracted. Each well may target one or more reservoirs using one or more locations along the wellbore 16.

Generally, the wellbore 16 is drilled according to a drilling plan that is established prior to drilling. The drilling plan sets forth equipment, pressures, trajectories and/or other parameters that define the drilling process for the wellsite. The drilling operation may then be performed according to the drilling plan. For instance, the wellbore 16 may have various different geometries, such as vertical (as shown), deviated, and/or horizontal.

After the drilling operation is completed, at least some drilling mud and/or other materials other than the desired subterranean fluid may remain in the wellbore. To remove these unwanted materials, a clean-up operation may be performed. As effluent travel upwards through the wellbore 16, it travels through the choke 23. As previously noted, this effluent may be multiphase consisting of multiple fluids (e.g., oil, gas, and water). This multiphase fluid traverses the choke 23 and enters into a separation and analysis system 32. The separation and analysis system 32 may be at least partially included in the surface unit 22. The separation and analysis system 32 may include a horizontal separator, a vertical separator, and/or any other mechanisms that may facilitate separation of the incoming effluent. For instance, the separator may include a 3-phase gravity separator that separates the effluent into its separate gas, oil, and water sub-elements. The analysis portion of the separation and analysis system 32 may evaluate how successful the separation of the sub-elements has been.

The data gathered by sensors 24 may be collected by the surface unit 22 and/or other data collection sources for analysis or other processing. The data collected by the sensors 24 may be used alone and/or in combination with other data. The data may be collected in one or more databases and/or transmitted to another location on-site or offsite. The data may be historical data, real time data, or combinations thereof. The real time data may be used in real time or stored for later use. The data may also be combined with historical data and/or other inputs for further analysis. The data may be stored in separate databases and/or combined into a single database.

FIG. 2 is a block diagram of a system 250 that may be used for analyzing/utilizing the data output 12 from the system 10, as described in FIG. 1. The data output 12, as described in FIG. 1, is received as input data 252 at a computing device 254. The computing device 254 may be implemented in the surface unit 22 and/or may be implemented at other locations within the oilfield or remotely from the oilfield where the remote locations are able to receive the data via the transceiver 33. The various functional blocks shown in FIG. 2 may include hardware elements (including circuitry), software elements (including computer code stored on a tangible, non-transitory computer-readable medium), or a combination of both hardware and software elements. It should be noted that FIG. 2 is merely one example of a particular implementation and is intended to illustrate the types of components that may be present in the computing device 254.

As illustrated, the computing device 254 includes one or more processor(s) 256, a memory 258, a display 260, input devices 262, one or more neural networks(s) 264, and one or more interface(s) 266. In the computing device 254, the processor(s) 256 may be operably coupled with the memory 258 to facilitate the use of the processors(s) 256 to implement various stored programs. Such programs or instructions executed by the processor(s) 256 may be stored in any suitable article of manufacture that includes one or more tangible, computer-readable media at least collectively storing the instructions or routines, such as the memory 258. The memory 258 may include any suitable articles of manufacture for storing data and executable instructions, such as random-access memory, read-only memory, rewritable flash memory, hard drives, and optical discs. In addition, programs (e.g., an operating system) encoded on such a computer program product may also include instructions that may be executed by the processor(s) 256 to enable the computing device 254 to provide various functionalities.

The input devices 262 of the computing device 254 may enable a user to interact with the computing device 254 (e.g., pressing a button to increase or decrease a volume level). The interface(s) 266 may enable the computing device 254 to interface with various other electronic devices. The interface(s) 266 may include, for example, one or more network interfaces for a personal area network (PAN), such as a Bluetooth network, for a local area network (LAN) or wireless local area network (WLAN), such as an IEEE 802.11x Wi-Fi network or an IEEE 802.15.4 wireless network, and/or for a wide area network (WAN), such as a cellular network. The interface(s) 266 may additionally or alternatively include one or more interfaces for, for example, broadband fixed wireless access networks (WiMAX), mobile broadband Wireless networks (mobile WiMAX), and so forth.

In certain embodiments, to enable the computing device 254 to communicate over the aforementioned wireless networks (e.g., Wi-Fi, WiMAX, mobile WiMAX, 4G, LTE, and so forth), the computing device 254 may include a transceiver (Tx/Rx) 267. The transceiver 267 may include any circuitry that may be useful in both wirelessly receiving and wirelessly transmitting signals (e.g., data signals). The transceiver 267 may include a transmitter and a receiver combined into a single unit.

The input devices 262, in combination with the display 260, may allow a user to control the computing device 254. For example, the input devices 262 may be used to control/initiate operation of the neural network(s) 264. Some input devices 262 may include a keyboard and/or mouse, a microphone that may obtain a user's voice for various voice-related features, and/or a speaker that may enable audio playback. The input devices 262 may also include a headphone input that may provide a connection to external speakers and/or headphones.

The neural network(s) 264 may include hardware and/or software logic that may be arranged in one or more network layers. In some embodiments, the neural network(s) 264 may be used to implement machine learning and may include one or more suitable neural network types. For instance, the neural network(s) 264 may include a perceptron, a feed-forward neural network, a multi-layer perceptron, a convolutional neural network, a long short-term memory (LSTM) network, a sequence-to-sequence model, and/or a modular neural network. In some embodiments, the neural network(s) 264 may include at least one deep learning neural network. Furthermore, the neural network(s) 264 may be at least partially implemented using the one or more processor(s) 256. For instance, the neural network(s) 264 may be implemented using the one or more processor(s) 256. For example, the neural network(s) 264 may be implemented using a central processing unit (CPU), a graphics processing unit (GPU), a programmable logic device (e.g., a field-programmable gate array (FPGA), an application-specific integrated circuit (ASIC)), other suitable circuitry, or a combination thereof.

The output of the neural network(s) 264 may be based on the input data 252, such as flow rates or other data captured during drilling, clean-out, extraction/production, and/or other operations. This output may be used by the computing device 254. Additionally or alternatively, the output from the neural network(s) 264 may be transmitted using a communication path 268 from the computing device 254 to a gateway 270. The communication path 268 may use any of the communication techniques previously discussed as available via the interface(s) 266. For instance, the interface(s) 266 may connect to the gateway 270 using wired (e.g., Ethernet) and/or wireless (e.g., IEEE 802.11) connections. The gateway 270 couples the computing device 254 to a wide-area network (WAN) connection 272, such as the Internet. The WAN connection 272 may couple the computing device 254 to a cloud network 274. The cloud network 274 may include one or more computing devices 254 grouped into one or more locations (e.g., data centers). The cloud network 274 includes one or more databases 276 that may be used to store the output of the neural network(s) 264 and/or other data. In some embodiments, the cloud network 274 may perform additional transformations on the data using its own processor(s) 256 and/or neural network(s) 264.

The computing device 254 may be used to implement a machine learning (ML)-based methodology (e.g., using the neural network(s) 264). As discussed below, the ML-based methodology may combine a hybrid model combining physical measurements with synthetic data and combining surface data with downhole data including monitoring data in the full wellbore 16. FIG. 3 is a flow diagram of a ML-based process 300. The process 300 uses an offline model 302 that is developed using module A 304 and module B 306.

Module A 304 includes physical test measurement data from downhole tool tests (e.g., the tool 14) including validation and verification tests for downhole systems, validation and verification tests for monitoring sensors, manufacturing for downhole systems, system integration test and so on. The measured and system control parameters can include and/or be measured using, but are not limited to the following: temperature and pressure sensors, flow rate and related sensors (e.g., Venturi sensors), thermal anemometry sensors, passive acoustic/pressure array of sensors, active acoustic measurements (Doppler, time-of-flight, etc.), induction sensors, electrical measurements (resistive, capacitive, dielectric, etc.), photoacoustic measurements, nuclear magnetic resonance (NMR) measurements, nuclear spectroscopy, data from downhole flow control valves (FCV) including choke aperture and pressure differential across the valves and the like, data from wellhead valves including choke aperture and pressure differential across the valves and the like, data from surface flow metering such as a Vx Spectra flowmeter available from SLB, and/or any other suitable physical test measurements that may impact multiphase flow through the wellbore 16.

Module B 306 includes synthetic data that may be obtained from simulations using a simulator implemented using one or more computing devices 254. The simulation data may represent downhole and/or surface systems based on a physical model or “digital avatar” for the system 10. The digital avatar may model the physics of the valves in the system including downhole FCVs and/or surface chokes, flow sensors dedicated to downhole flow metering, and/or other portions of the system that may impact multiphase flow through the wellbore 16. Moreover, the fluid flow along the whole well production system from bottom of the hole to surface may be determined using a devoted simulator, such as a steady-state multiphase flow simulator (e.g., PIPESIM), a dynamic multiphase flow simulator (e.g., OLGA), TMIX, and/or other simulators. Moreover, the simulators may also consider the temperature behavior.

The physical measurements from Module A 304 and the synthetic data from Module B 306 are calibrated in the offline model 302 using field data from Module C 308 for each well before production including the tool test data, commissioning data from all the tools considered in the interpretation, well characterizations, production tests, well geometry, cleanout results, and/or any other data from the field that may be used to calibrate the offline model 302 to the specific wellbore 16.

The offline model 302 also receives field data in real-time as Module D 310. For instance, the real-time field data may be and/or may include the input data 252. The real-time field data may include data from sensors in the field during real-time operation that may include surface data, downhole data from multiple zones, or a combination thereof. The surface data may be continuous data (e.g., pressure differential and/or choke aperture) from a flow meter (e.g., a Vx Spectra flow meter). The downhole data may include choke aperture, pressure differential across the choke, temperature, wellhead pressure, and/or other suitable data from multiple zones and possibly from nearby wells.

The offline model 302 uses an ML engine, Module E 312, that uses one or more computing devices 254 to implement machine learning. The ML engine may perform data reconciliation to decrease errors in the system. Specifically, the ML engine analyzes the relationship between input data of Module D 310 and output estimates 314 with given inputs in given conditions. The data reconciliation step applied after forming the offline model 302 using Module A 304 and Module B 306 reduces errors such as random errors from the physical measurements, systematic errors from the physical measurements, systematic errors from the simulation engine, and/or other errors in the calculations. The output of the ML engine is the output estimates 314 that estimates flow rates for multiple phases (e.g., 2, 3, or more phases). The estimates may be for various zones along the wellbore 16, such as along the entire wellbore 16 where subsurface sensors are along with their associated uncertainties.

FIG. 4 is a diagram of a well 340 that may be in the borehole 16. Although the well is illustrated with a particular geometry, the well 340 may have any suitable geometry, such as vertical, horizontal, deviated, and/or any other possible geometry. As illustrated, the well 340 includes a casing 342 for the well 340 and tubing 344. The casing 342 has multiple reservoir access portions 346 where the well 340 may access one or more reservoirs from various locations. As illustrated, the reservoir access portions 346 are within respective zones of the well 340. In the illustrated embodiment of the well 340, the well 340 includes a first zone 354, a second zone 356, and a third zone 358. However, embodiments of the well 340 compliant with the teachings herein may include any suitable number of zones, such as two, three, four, or more zones. The well 340 includes a wellhead choke 352 as a surface choke. In compartmentalized reservoirs, the first zone 354, the second zone 356, and the third zone 358 may be separated using packers 360.

The well 340 also includes two or more subsurface chokes/flow control valves (FCVs). As illustrated, each zone may include a respective FCV. For instance, the first zone 354 includes an FCV 362, the second zone 356 includes a FCV 364, and the third zone 358 includes an FCV 366. The FCVs 362, 364, and 366 may be independently controlled due to various factors in the well 340. For instance, the apertures of the FCVs 362, 364, and 366 may be set at least in part on flows of various phases in the respective zones. Additionally or alternatively, the FCVs 362, 364, and 366 may be controlled to cause specific flow parameters, such as to shape slugs or perform cleanout of the wellbore 16. Along with the FCVs 362, 364, and 366, the first zone 354, the second zone 356, and the third zone 358 includes sensors 368, 370, and 372 that may include flow meters that measure flow rates, pressure, temperatures, and/or other parameters at, near, and/or across the FCVs 362, 364, and 364. The teachings herein may include any suitable number of sensors, such as two, three, four, or more sensors.

Using the embodiment of the well 340, Module B 306 would include inputs and outputs of a set of simulators run with a dedicated well flow simulator (e.g., PIPESIM) using the exact well geometry for a high number of cases. The main simulation inputs may include (for each of the three zones): the FCV choke aperture, the total flow through the choke, and the phase fractions (oil, water, gas, etc.) of the flow though each choke. The outputs are the simulated measurements of the flow meters in each zone, and possibly choke/flow data from the wellhead choke 352. The Module E 312 is a trained ML model using the simulations from Module B 306 along with additional test measurements from Module A 304 and calibration from Module C 308.

Module D 310 is the real-time acquired field data from the wellhead choke 352, the FCVs 362, 364, and 366 and related sensors 368, 370, and 372. Module E 312 uses this data to predict a multiphase (e.g., 3 phase) flow rate in real-time for each zone including the total flow through the respective chokes and the phase fractions of flows through the respective chokes. FIG. 5 illustrates this process 400 with the digital avatar 402 used to generate simulated well data 404 and simulated well flow rates 406. The digital avatar 402 includes choke and flow sensor data (FloX and Vx) and simulated data while the simulated well data 404 and the simulated well flow rates 406 include choke apertures/openings, pressure differentials across the chokes, flow rates downhole and out of the well head, and/or other suitable parameters. A ML-based model 408/ML engine may be used to refine the simulated well flow rates 406 using the simulated well data 404, historical well data 410, and real-time well data 412. The historical well data 410 may include historical choke apertures/openings, historical pressure differentials across the chokes, historical flow rates downhole and out of the well head, and/or other suitable historical parameters while the real-time well data 412 includes real-time choke apertures/openings, real-time pressure differentials across the chokes, real-time flow rates downhole and out of the well head, and/or other suitable real-time parameters. The ML-based model 408 may also generate/refine historical well flow rates 414 and real-time estimated flow rates 416 based on the historical well data 410 and/or the real-time well data 412. The historical well flow rates 414 and real-time estimated flow rates 416 may include respective flow rates for each zone and their respective phase fractions to determine flow of each phase.

FIG. 6 is a cross-section of a zone 420 (e.g., second zone 356 or third zone 358) of the well 340. As illustrated, the zone 420 includes a portion of the tubing 344 running through the zone 420. The zone 420 also includes an annulus 421 that is outside of the tubing 344 but inside the casing 342. The annulus 421 and the inside of the tubing 344 are separated by an aperture 422. The aperture 422 may be part of an FCV, such as the FCV 364 or 366. There is a flow 424 through the aperture 422. This flow may be a mixture that has a temperature that is at least partially based on the Joule-Thomson effect that effects a temperature change of gas or liquid when it is forced through a pressure difference of the aperture 422. However, this temperature (TJT) may be difficult or impossible to capture at the aperture 422. Instead, other measurements may be made by the sensors 368, 370, and/or 372. For instance, the sensors 368, 370, and/or 372 may be used to capture an annulus pressure (Pann) 428, an annulus temperature (Tann) 430, a tubing upstream temperature (Ttub_up) 434 upstream of the aperture 422 (i.e., away from the wellhead), a tubing downstream pressure (Ptub_dn) 438 downstream of the aperture 422 (i.e., towards the wellhead), a tubing downstream temperature (Ttub_dn) 440, and/or other parameters may be measured directly. Other parameters in the zone 420 may be difficult and/or impossible to measure directly similar to the TJT. For instance, the illustrated zone 420 shows a total flow in the annulus (Qann) 426 that includes a mix of two phases (e.g., oil and water) in a phase fraction indicated by the following equation:

α w + α o = 1 , ( Equation ⁢ 1 )

where the Qann 426 is a two-phase flow of two phases (e.g., oil and water, oil and gas, water and gas, or the like). Although the following discusses oil and water phases, the following discussion may be applied consistently with any other phase mixture of multiphase flows. α_w is a phase fraction that indicates a percentage of the Qann 426 that is water while α_o is a phase fraction that indicates a percentage of the Qann 426 that is oil. As noted in Equation 1, the percentages added together form 100% of the Qann 426.

The illustrated embodiment of the zone 420 also shows a total flow in the tubing upstream of the aperture 422 (Qtub_up) 432 flowing toward the aperture 422 and a total flow in the tubing downstream of the aperture 422 (Qtub_dn) 436. The relationship of Qann 426, Qtub_up 432, and the Qtub_dn 436 are reflected in the following equation:

Q t ⁢ ub ⁢ _ ⁢ dn = Q tub ⁢ _ ⁢ up + Q a ⁢ n ⁢ n . ( Equation ⁢ 2 )

The Qann 426 through the aperture 422 may be determined using the following equation:

Q a ⁢ n ⁢ n = C d ⁢ A ⁢ 2 ⁢ ( P a ⁢ n ⁢ n - P tub ⁢ _ ⁢ dn ) ρ ⁡ ( α w , α o ) ( Equation ⁢ 3 )

where Cd are choke parameters related to the geometry of the choke aperture 422, A is the area of the aperture 422, and ρ(α_w, α_o) is a density of the mixture of the two phases in the Qann 426 characterized by the phase fractions and their respective densities. Deriving the total flow and the phase fractions enable determining the flows of the individual phases where multiplying the Qann 426 times the phase fraction of a phase (e.g., water, oil, or gas) provides the flow of the corresponding phase through the annulus 421.

As previously noted, the Tur may not be practically measured directly and may be determined indirectly. For instance, T_JT may be found using the following equation:

T a ⁢ n ⁢ n - T JT = [ μ ⁡ ( α W , α o ) ] ⁢ ( P a ⁢ n ⁢ n - P tub ⁢ _ ⁢ db ) , ( Equation ⁢ 4 )

where ρ(α_w, α_o) is the Joule-Thomson coefficient of the mixed fluid characterized by the phase fractions and their respective Joule-Thomson coefficients.

Furthermore, the temperature mixing of the fluids may be expressed using the following equation:

T tub ⁢ _ ⁢ dn ⁢ Q tub ⁢ _ ⁢ dn = T tub ⁢ _ ⁢ up ⁢ Q tub ⁢ _ ⁢ up + T JT ⁢ Q a ⁢ n ⁢ n . ( Equation ⁢ 5 )

Equations 3-5 provide 2 independent equations (Equation 3 and Equations 4 and 5) with 3 independent unknowns: Q_{tub_up}, Q_ann, and α_w. These equations may be combined to form a new equation:

T tub ⁢ _ ⁢ dn ( Q tub ⁢ _ ⁢ up + Q a ⁢ n ⁢ n ) = T tub ⁢ _ ⁢ up ⁢ Q tub ⁢ _ ⁢ up + [ T a ⁢ n ⁢ n - [ μ ⁡ ( α w , α o ) ] ⁢ ( P a ⁢ n ⁢ n - P tub ⁢ _ ⁢ dn ) ] ⁢ Q a ⁢ n ⁢ n . ( Equation ⁢ 6 )

In some embodiments, this equation may be replaced by a more elaborated model from computational fluid dynamics (CFD) simulations of the flow through respective chokes. Even with the combined equation of two independent equations, the problem is under-determined due to more unknowns than independent equations. However, as illustrated in zone 450 of FIG. 7 in the bottommost zone of the well 340 (e.g., the first zone 354), there is no flow coming from upstream of the tubing 344 to the corresponding FCV 362. In other words, the zone 450 is like the zone 420 except that since the zone 450 is the bottommost zone, the Qtub_up 432 is 0 in this zone as opposed to some unknown value in the zone 420. In the zone 450, one unknown is eliminated thereby causing the problem to utilize two independent equations to solve two unknowns. For instance, the remaining unknowns Q_ann, and α_w may be interpreted using a graphical approach, such as using graph 500 of FIG. 8. Additionally or alternatively, the problem equations (Equation 3 and Equations 3 plus 5) may be solved numerically by solving the problem in a non-linear system of two equations using a numerical solver (e.g., MATLAB).

As previously noted, FIG. 8 shows a graph 500 that may be used to solve the problem of the bottommost zone, such as zone 450. The graph 500 has a vertical axis 502 that corresponds to annulus total flow (Q_ann) and a horizontal axis 504 that corresponds to a phase fraction (e.g., water fraction). The graph 500 also includes a line 506 that corresponds to a plot of an equation on the graph that corresponds to a pressure interpretation. For very low flow through the choke, the downstream pressure is close to the reservoir or pressure annulus (e.g., 8.5 kpsi). The higher the flow through the choke, the higher the pressure differential thereby causing a lower Ptub_dn. The graph 500 may also take into account some uncertainties in the pressure and plot a region 508 between lines that include some amount of uncertainty (e.g., ±1 psi). Furthermore, the graph 500 includes a line 510 that corresponds to a temperature interpretation. For very low flow through the choke, the downstream temperature is close to the reservoir or annulus temperature (e.g., 130° C.). The higher the flow through the choke, the higher temperature differential (e.g., due to JT effect). Tdub_dn is higher than the Tann due to the negative JT coefficients of both oil and water. Like the region 508, the graph 500 may include an uncertainty region 514 that accommodates some amount of uncertainty (e.g., ±0.01° C.).

For the sake of an example, a solution 512 may exist for Q_ann=6 kbpd and α_w=10% where the lines 506 and 510 intersect. For instance, the intersection may correspond to a value (e.g., Ptub_db=8 kpsi) with a corresponding pressure differential (e.g., 500 psi) through the aperture 422. Once these values are obtained, zonal phasic flows may be derived for both phases (e.g., oil and water). For instance, if aw is known and the water flow Qw,ann or total flow Qann may be derivable from another value. Likewise, the oil flow may be found by subtracting the water flow Qann,w from the total flow Qann.

Once a problem is solved/interpreted for the bottommost region, the values found for the Qtub_dn 436 (total and/or for any individual phases) for this zone may be used as Qtub_up 432 for an adjacent zone that is downstream of the bottommost zone. In embodiments where there is a significant pressure or temperature difference between zones, an adjustment may be made to the downstream flow of one zone to the upstream flow of the next zone. For example, this adjustment may be applied according to a well flow simulation model, such as PIPESIM. Using this known value for Qtub_up 432 for the adjacent upper zone, there are now two unknowns and two independent equations enabling solving of the unknowns for the adjacent upper zone. The solving of these unknowns may be performed similar to how the bottommost zone is resolved, such as using a numerical solver and/or solved using graphical intersections and also used to find phasic zonal flows. Once this zone (e.g., the second zone 356) is resolved, it's Qtub_dn 436 may be used as Qtub_up 432 for the next zone (e.g., the third zone 358). This use of flows from one zone to the next zone may be resolved in order until the complete well and all of its zones have been resolved.

FIG. 9 is a flow diagram of a process 520 that may be performed using one or more computing devices 254. In some embodiments, at least a portion of the process 520 may be performed by well equipment located in the field (surface or sub-surface) and/or using cloud computing. The process 520 includes the one or more computing devices 254 obtaining data about multiphase flow through a wellbore with multiple zones (block 522). For instance, one or more processors of the one or more computing devices 254 may receive temperature, pressure, flow rates, phase fractions, and/or other parameters from historical measurements in Module A 304, synthetic data from simulators in Module B 306, real-time surface data from sensors as Module D 310, manual input, and/or a combination thereof. The one or more processors solves an interpretation (e.g., an interpretation problem) for a bottommost zone of the multiple zones (block 524). For instance, the processor determines that the Qtub_up 432 of the bottommost zone is zero and solves for Qann 426 and Qtub_dn 436 using a numerical solver and/or using a graphical solver. Solving the interpretation for the bottommost zone includes solving for total flow, solving for a flow of a first phase (e.g., water) of the total flow, and/or solving for a flow of a second phase (e.g., oil) of the total flow through the annulus 421 and the tubing 344.

The one or more processors then uses the solved interpretation (e.g., Qtub_dn 436) of a bottommost zone to solve an interpretation of a next higher zone (block 526). For instance, the one or more processors may solve for unknowns (e.g., Qtub_dn 436 and Qann 426) in the next higher zone using values (e.g., Qtub_dn 436) and values (e.g., Qtub_up 432) from the bottommost zone. The one or more processors determines whether all zones have been interpreted (block 528). If more zones are to be interpreted, the one or more processors moves the next zone and interprets it similar to how a previous zone has been interpreted. Once all zones have been interpreted, the one or more processors applies one or more commands to control production operations in the wellbore 16 (block 530). For instance, the one or more processors may change aperture sizes of the programmable chokes/FCVs downhole based on the determined values. For instance, if water flow exceeds a threshold for a zone/the entire well, the one or more processors may at least partially close at least one of the chokes FCVs based on the flow rates.

Although a few embodiments of the disclosure have been described in detail above, those of ordinary skill in the art will readily appreciate that many modifications are possible without materially departing from the teachings of this disclosure. Accordingly, such modifications are intended to be included within the scope of this disclosure as defined in the claims. It is also contemplated that various combinations or sub-combinations of the specific features and aspects of the embodiments described may be made and still fall within the scope of the disclosure. It should be understood that various features and aspects of the disclosed embodiments can be combined with, or substituted for, one another in order to form varying modes of the embodiments of the disclosure. Thus, it is intended that the scope of the disclosure herein should not be limited by the particular embodiments described above.

The techniques presented and claimed herein are referenced and applied to material objects and concrete examples of a practical nature that demonstrably improve the present technical field and, as such, are not abstract, intangible, or purely theoretical. Moreover, although various actions are discussed as part of processes in a specific order, at least some of the actions may be performed in different orders. Additionally, at least some of the actions may be performed by one or more processors 256 of suitable computing devices. Further, if any claims appended to the end of this specification contain one or more elements designated as “means for [perform]ing [a function] . . . ” or “step for [perform]ing [a function] . . . ,” it is intended that such elements are to be interpreted under 35 U.S.C. § 112 (f). However, for any claims containing elements designated in any other manner, it is intended that such elements are not to be interpreted under 35 U.S.C. § 112 (f).29