SYSTEM AND METHODS FOR IMPROVED DRILL PATH ACCURACY

Description

BACKGROUND

The present disclosure relates generally to drilling of wells for oil and gas production and, more particularly (although not necessarily exclusively), to systems and methods for improving drill path accuracy, for example but not limited to systems and methods for improving toolface selection during drilling of wellbores.

SUMMARY

The present invention, as disclosed and described herein, in an aspect thereof includes a drilling system. The drilling system may comprise a processor and a non-transitory memory coupled to the processor. The memory may comprise instructions executable by the processor to receive, during drilling of a wellbore, drilling plan information for the wellbore and information from a bottom hole assembly (BHA) located in the wellbore; and determine a target toolface for drilling a planned path according to the drilling plan information. The memory may further comprise instructions executable by the processor to model one or more forces on the BHA based at least in part on the information from the BHA and the drilling plan information; determine, based at least in part on the modeled one or more forces, a predicted delivered toolface when drilling the planned path according to the drilling plan information using the target toolface; and, responsive to a difference between the predicted delivered toolface and the target toolface, determine an adjusted (or optimum) target toolface accounting for the one or more forces on the BHA. Moreover, the memory may further comprise instructions executable by the processor to send one or more control signals to orient the BHA to the adjusted target toolface to drill the planned path and drill according to the adjusted target toolface.

In various embodiments, the modeled one or more forces comprise at least one of a wellbore friction force and a force associated with a weight of the BHA.

In various embodiments, the memory further comprise instructions executable by the processor to train a machine learning model to model the one or more forces on the BHA and determine the adjusted target toolface for drilling the planned path according to the drilling plan information; and update the machine learning model responsive to drilling the planned path using the adjusted target toolface.

In various embodiments, drilling the wellbore with the predicted delivered toolface results in a drill path that deviates from the planned path.

In various embodiments, the modeled one or more forces on the BHA is further based on historical data received from drilling one or more previous wellbores.

In various embodiments, the wellbore comprises a plurality of portions; and the modeled one or more forces on the BHA is further based on data received from drilling one or more previous segments of the plurality of segments.

In various embodiments, the adjusted target toolface accounting for the one or more forces on the BHA is determined responsive to the difference between the predicted delivered toolface and the target toolface exceeding a threshold value.

In various embodiments, the BHA comprises at least a drill bit at one end thereof. Moreover, the information from the BHA comprises at least one or more of geological formation information, weight on bit (WOB), rate of penetration (ROP), torque, mud pressure, mud flow rate, or differential pressure, toolface, time, equipment information, drilling information associated with the drill bit, and historical information.

Additional aspects includes a method for drilling that may comprise receiving, by a drilling system and during drilling of a wellbore, drilling plan information for the wellbore and information from a BHA located in the wellbore; and determining, by the drilling system, a target toolface for drilling a planned path according to the drilling plan information. The method may further comprise modeling, by the drilling system, one or more forces on the BHA based at least in part on the information from the BHA and the drilling plan information; determining, by the drilling system and based at least in part on the modeled one or more forces, a predicted delivered toolface when drilling the planned path according to the drilling plan information using the target toolface; and, responsive to a difference between the predicted delivered toolface and the target toolface, determining, by the drilling system, an adjusted target toolface accounting for the one or more forces on the BHA. Moreover, the method may further comprise sending, by the drilling system, one or more control signals to orient the BHA to the adjusted target toolface to drill the planned path and drill according to the adjusted target toolface.

Another aspect includes a non-transitory computer readable storage medium storing instructions that, upon execution by one or more processors, may cause the one or more processors to perform operations comprising receiving, during drilling of a wellbore, drilling plan information for the wellbore and information from a BHA located in the wellbore and determining a target toolface for drilling a planned path according to the drilling plan information. The operations may further comprise modeling one or more forces on the BHA based at least in part on the information from the BHA and the drilling plan information; determining, based at least in part on the modeled one or more forces, a predicted delivered toolface when drilling the planned path according to the drilling plan information using the target toolface; and, responsive to a difference between the predicted delivered toolface and the target toolface, determining an adjusted target toolface accounting for the one or more forces on the BHA. Moreover, the operations may further comprise sending one or more control signals to orient the BHA to the adjusted target toolface to drill the planned path and drill according to the adjusted target toolface.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1A is a depiction of a drilling system including a derrick on a drilling rig, in accordance with various embodiments of the present disclosure;

FIG. 1B is a depiction of a computer system, in accordance with various embodiments of the present disclosure;

FIG. 2 is a depiction of a schematic representation of a Bottom Hole Assembly (BHA) in a downhole environment as well as indicators of the forces on the BHA in the downhole environment, in accordance with various embodiments of the present disclosure;

FIG. 3A is a depiction of the BHA from a top view in which the drill bit and kick pad are visible, in accordance with various embodiments of the present disclosure;

FIG. 3B is a depiction of the BHA from a side view in which the drill bit and kick pad are visible, in accordance with various embodiments of the present disclosure;

FIG. 4 is a flow chart illustrating a method to determine or calculate an adjusted target toolface for a BHA to drill a target drill path, in accordance with various embodiments of the present disclosure;

FIG. 5 is a flow chart illustrating another method for optimizing toolface orientation, in accordance with various embodiments of the present disclosure; and

FIG. 6 is a flow chart illustrating a method for training and/or updating a machine learning model implemented to optimize toolface orientation for a BHA, in accordance with various embodiments of the present disclosure.

DETAILED DESCRIPTION

Referring now to the drawings, wherein like reference numbers are used herein to designate like elements throughout, the various views and embodiments of a system and method for determining an adjusted target toolface for drilling a planned path are illustrated and described, and other possible embodiments are described. The figures are not necessarily drawn to scale, and in some instances the drawings have been exaggerated and/or simplified in places for illustrative purposes only. One of ordinary skill in the art will appreciate the many possible applications and variations based on the following examples of possible embodiments.

Drilling a borehole (e.g., wellbore) for the extraction of minerals has become an increasingly complicated operation due to the increased depth and complexity of many boreholes, including the complexity added by directional drilling. Drilling a well typically involves a substantial amount of human decision-making during the drilling process. For example, geologists and drilling engineers use their knowledge, experience, and the available information to make decisions on how to plan the drilling operation, how to accomplish the drilling plan, and how to handle issues that arise during drilling. However, even the best geologists and drilling engineers perform some guesswork due to the unique nature of each borehole. Furthermore, a directional human driller performing the drilling may have drilled other boreholes in the same region and so may have some similar experience. However, during drilling operations, a multitude of input information and other factors may affect a drilling decision being made by a human operator or specialist, such that the amount of information may overwhelm the cognitive ability of the human to properly consider and factor into the drilling decision, including for example an adjusted target toolface for drilling along a desired drill path. Further, human decision-making for drilling decisions can result in expensive mistakes because drilling errors can add significant cost to drilling operations. In some cases, drilling errors may permanently lower the output of a well for years into the future.

In particular, many wellbores are drilled as directional or horizontal wells, and so require some curvature. Such wells often have curved trajectories. Slide drilling is needed to drill curved wells, and so accuracy and precision in orienting the toolface, and then maintaining the desired toolface during drilling, can be very important. Typically, a human operator (such as a directional driller) and/or the drilling system, calculates a target toolface using simple geometric algorithms to determine the plane in which the curvature is desired, and the wellbore is subsequently drilled using the target toolface that in essence “matches” the plane in which the curvature is desired. However, often, it is later determined, that the resulting wellbore was off the target drill path. The target toolface may result in a wellbore that is off the target drill path because the target toolface failed to adequately and/or accurately consider the various forces on the BHA during drilling and thereby fails to account for how those forces affect the BHA which can alter the resulting drill path. The delivered toolface is always in the plane of the resultant contact force and not simply in the plane of the BHA bend angle. To the extent a directional driller may have experience in directional drilling, they may be aware that the target drill path may not directly correspond to the target toolface provided by the system, and may modify the target toolface by some amount in an effort to deliver the desired curvature in the right plane (e.g., the desired drill path). That alteration by the directional driller is usually based on a general reaction to past experience as opposed to a physical model and is often inaccurate. Moreover, the changes in operators during drilling of a well can also result in inaccurate slide drilling based on the knowledge of the particular driller when such changes are made purely based on prior experiences. Experience teaches that different operators will often make different decisions including with respect to toolface and how to best achieve a desired toolface.

According to embodiments of the present disclosure, a computing device may model the various forces on the BHA in the downhole environment and may thereby calculate an adjusted target toolface for the desired curvature in the desired plane (e.g., the desired drill path), resulting in more accurate drilling of the drill path, and thereby reducing costs associated with drilling a wellbore. In other words, according to embodiments of the present disclosure, modelling the forces on the BHA during drilling accurately and more precisely can better predict the delivered toolface and an adjusted target toolface may be calculated and implemented right from the start of a slide drilling operation, rather than adjusting the toolface after it is determined that the drilled toolface resulted in a wellbore that is off the desired drill path. Such errors in drilling often only come to light after 90 or more feet have been drilled and a survey has been taken. Often, extra sliding is needed to correct the error. By using a physics model to determine an adjusted target toolface in advance slides may be shortened and the wellbore may be drilled faster and at less cost. It should be noted that the present systems and methods may be used in both well planning and in real time during drilling of a well.

Illustrative examples are given to introduce the reader to the general subject matter discussed herein and are not intended to limit the scope of the disclosed concepts. The following sections describe various additional features and examples with reference to the drawings in which like numerals indicate like elements, and directional descriptions are used to describe the illustrative aspects, but, like the illustrative aspects, should not be used to limit the present disclosure.

FIG. 1A is a depiction of a drilling system 100 including a derrick 102 on a drilling rig 103, in accordance with various embodiments of the present disclosure. The derrick 102 includes a crown block 104. A traveling block 106 is coupled to the crown block 104 via a drilling line 108. In a top drive system (as illustrated), a top drive 110 is coupled to the traveling block 106 and provides the rotational force needed for drilling. A saver sub 112 may sit between the top drive 110 and a drill pipe 114 that is part of a drillstring 116. The top drive 110 may rotate the drillstring 116 via the saver sub 112, which in turn may rotate a drill bit 118 of a BHA 120 in a borehole 122 (e.g., wellbore) passing through a formation 123. The position of the BHA 120 and thereby the drill bit 118 may control the direction of drilling of the borehole 122 (e.g., wellbore). A mud pump 124 may direct a fluid mixture (e.g., mud) 126 from a mud pit or other container 128 into the borehole 122 (e.g., wellbore). The mud 126 may flow from the mud pump 124 into a discharge line 130 that is coupled to a rotary hose 132 by a standpipe 134. The rotary hose 132 is coupled to the top drive 110, which includes a passage for the mud 126 to flow into the drillstring 116 and the borehole 122 (e.g., wellbore). A rotary table 136 may be fitted with a master bushing 138 to hold the drillstring 116 when the drillstring is not rotating.

According to various embodiments, the drilling rig 103 may include various components such as a drawworks 180, power generation equipment 182, and any other auxiliary equipment (not shown). Some or all of a control system 142 may be located at the derrick 102, may be downhole, and/or may be remote from the actual drilling location. For example, the control system 142 may be a system such as is disclosed in U.S. Pat. No. 8,210,283 entitled System and Method for Surface Steerable Drilling, filed on Dec. 22, 2011, and issued on Jul. 3, 2012, which is hereby incorporated by reference in its entirety. Alternatively, the control system 142 may be a standalone system or may be incorporated into other systems at the derrick 102. The control system 142 may communicate via a wired and/or wireless connection (not shown).

In drilling system 100, drilling equipment is used to perform the drilling of the borehole 122 (e.g., wellbore), such as the top drive 110 (or rotary drive equipment) that couples to drillstring 116 and BHA 149 and is configured to rotate drillstring 116 and apply pressure to the drill bit 118. The control system 142 may include a weight-on-bit (WOB)/differential pressure control system, a positional/rotary control system, a fluid circulation control system, and/or a sensor system. Formation detection and evaluation functionality may be provided via the control system 142. The control system 142 may be used to monitor and change drilling rig settings, such as the WOB or differential pressure to alter the rate of penetration (ROP) or the radial orientation of the toolface, change the flow rate of drilling mud, and perform other operations. The sensor system may obtain sensor data about the drilling operation and the drilling system 100, including the downhole equipment. For example, the sensor system may include measurement while drilling (MWD) or logging while drilling (LWD) tools for acquiring information, such as downhole toolface/inclination information, and formation logging information (e.g., geological formation information), that may be saved for later retrieval, transmitted with or without delay using any of various communication methods (e.g., wireless, wireline, or mud pulse telemetry), or otherwise transferred to the steering control system. Information acquired by the sensor system may include information related to hole depth, bit depth, inclination angle, azimuth angle, true vertical depth, gamma count, standpipe pressure, mud flow rate, rotary rotations per minute (RPM), bit speed, ROP, WOB among other information. It is noted that all or part of the sensor system may be incorporated into the control system 142, or in another component of the drilling equipment. As drilling system 100 can be configured in many different implementations it is noted that different control systems and subsystems may be used. It should be noted that while different functionalities of the control system 142 are described herein one or more of those functionalities may be completed by a system separate from the control system 142 without departing from the scope of the present disclosure.

In particular embodiments, at least a portion of control system 142 may be located in downhole tool. In some embodiments, control system 142 may communicate with a separate controller located in the BHA or a downhole tool. In particular, the control system 142 may receive and process measurements received from downhole surveys and may perform the calculations described herein for an adjusted target toolface using information referenced herein. In drilling system 100, to aid in the drilling process, data may be collected from borehole 122 (e.g., wellbore), such as from sensors in BHA 120, a downhole tool or both. The collected data may include the geological characteristics of formation 123 (e.g., geological formation information) in which borehole 122 (e.g., wellbore) was formed, the attributes of drilling system 100, including BHA 120, and drilling information such as weight-on-bit (WOB), drilling speed, and other information pertinent to the formation of borehole 122 (e.g., wellbore). The drilling information may be associated with a particular depth or another identifiable marker to index collected data. For example, the collected data for borehole 122 (e.g., wellbore) may capture drilling information indicating that drilling of the well from 1,000 feet to 1,200 feet occurred at a first rate of penetration (ROP) through a first rock layer with a first WOB, while drilling from 1,200 feet to 1,500 feet occurred at a second ROP through a second rock layer with a second WOB. The collected data may be stored in a database that is accessible via a communication network for example. In some embodiments, the database storing the collected data for borehole 122 (e.g., wellbore) may be located locally at drilling system 100, at a drilling hub that supports a plurality of drilling systems 100 in a region, or at a database server accessible over the communication network that provides access to the database. At drilling system 100, the collected data may be stored at the surface or downhole in drillstring 116 as in a memory device (e.g., memory unit 154) included with BHA 120. Alternatively, at least a portion of the collected data may be stored on a removable storage medium, such as using control system 142 or BHA 120, that is later coupled to the database in order to transfer the collected data to the database, which may be manually performed at certain intervals, for example.

The control system 142 may enable an operator to plan and control drilling operations while drilling is being performed. The control system 142 may itself also be used to perform certain drilling operation, such as controlling certain control systems 142, that in turn, control the actual equipment in drilling system 100. The control of drilling equipment, for example but not limited to the toolface of the BHA 120 and drilling operations by the control system 142 may be manual, manual-assisted, semi-automatic, or automatic, in different embodiments.

Accordingly, control system 142 may receive input information either before drilling, during drilling, or after drilling of borehole 122 (e.g., wellbore). The input information may comprise measurements from one or more sensors, as well as survey information collected while drilling the borehole 122 (e.g., wellbore). The input information may also include a well plan, a regional formation history (e.g., historical data such as geological formation information), drilling engineer parameters, downhole toolface/inclination information, downhole tool gamma/resistivity information, economic parameters, reliability parameters, among various other parameters. Some of the input information, such as the regional formation history (e.g., historical data such as geological formation information), may be available from a drilling hub, which may have respective access to a regional drilling database (DB). Other input information may be accessed or uploaded from other sources to control system 142. For example, a web interface may be used to interact directly with control system 142 to upload the well plan or drilling parameters.

As noted, the input information may be provided to control system 142. After processing by control system 142, control system 142 may generate control information that may be output to drilling system 100 (e.g., to rig controls that control drilling equipment). Accordingly, control system 142 may be configured to modify its output information to the drilling rig 103, in order to achieve the desired results. According to embodiments of the present invention the steering control system may control the toolface of the BHA for providing a delivered toolface that may improve the accuracy of the drilled wellbore as compared to the target drill path. The output information generated by control system 142 may include indications to modify one or more drilling parameters, such as the toolface angle, to the desired deviation. In certain operational modes, such as semi-automatic or automatic, control system 142 may generate output information indicative of instructions to rig controls to enable drilling using the adjusted target toolface angle that has been determined. Therefore, an improved accuracy for drilling a drill path may be provided using control system 142, along with the methods and operations for calculating an adjusted target toolface described herein.

FIG. 1B is a depiction of a computer system 150 (or controller or control system 142), in accordance with various embodiments of the present disclosure. The computer system 150 is one possible example of a system component or device such as the control system 142 of FIG. 1A or a separate system used to perform the various processes described herein. In scenarios where the computer system 150 is on-site, such as within drilling system 100 of FIG. 1A, the computer system 150 may be contained in a relatively rugged, shock-resistant case that is hardened for industrial applications and harsh environments. It is understood that downhole electronics may be mounted in an adaptive suspension system that uses active dampening as described in various embodiments herein.

The computer system 150 may include a central processing unit (“CPU”) 152, a memory unit 154, an input/output (“1/0”) device 156, and a network interface 158. The components 152, 154, 156, and 158 are interconnected by a transport system (e.g., a bus) 160. A power supply (PS) 162 may provide power to components of the computer system 150 via a power transport system 164 (shown with data transport system 160 (e.g., bus), although the power and 164 data transport systems 160 (e.g., bus) may be separate).

It is understood that the computer system 150 may be differently configured and that each of the listed components may actually represent several different components. For example, the CPU 152 may actually represent a multi-processor or a distributed processing system; the memory unit 154 may include different levels of cache memory, main memory, hard disks, and remote storage locations; the I/O device 156 may include monitors, keyboards, and the like; and the network interface 158 may include one or more network cards providing one or more wired and/or wireless connections to a network 166. Therefore, a wide range of flexibility is anticipated in the configuration of the computer system 150.

The computer system 150 may use any operating system (or multiple operating systems), including various versions of operating systems provided by Microsoft (such as WINDOWS), Apple (such as Mac OS X), UNIX, and LINUX, and may include operating systems specifically developed for handheld devices, personal computers, and servers depending on the use of the computer system 150. The operating system, as well as other instructions (e.g., software instructions for performing the functionality described in previous embodiments) may be stored in the memory unit 154 and executed by the processor (e.g., CPU 152). For example, the memory unit 154 may include instructions for performing the various methods and control functions disclosed herein.

The network 166 may be a single network or may represent multiple networks, including networks of different types. For example, the network 166 may include one or more cellular links, data packet networks such as the Internet, local area networks (LANs), and/or wide local area networks (WLAN), and/or Public Switched Telephone Networks (PSTNs). Accordingly, many different network types and configurations may be used to couple the computer system 150 to other components of the drilling system 100 of FIG. 1A and/or to other systems not shown (e.g., remote systems). In some embodiments, the computer system 150 may be communicatively coupled to a remote operation center via a network, including via a wired or wireless connection.

FIG. 2 is a depiction of a schematic representation of a BHA 200 in a downhole environment (e.g., in a borehole 202) as well as indicators of the forces on the BHA 200 in the downhole environment, in accordance with various embodiments of the present disclosure. The schematic representation is provided to aid in illustrating non-limiting examples of methods and operations disclosed herein for determining and drilling with an adjusted target toolface according to aspects of the present disclosure. During drilling the BHA 200 may be set to a target toolface, which may correspond to a target drilling path. For example, as depicted in FIG. 2, the target toolface of 90 left may be selected to drill a target drilling path at 90 degrees inclination in a lateral section. However, in practice, the delivered toolface may not be the same as the target toolface due to various forces imparted on the BHA downhole. As shown in the example of FIG. 2, when drilling horizontally with this toolface (e.g., 90 left in a lateral section as shown in FIG. 2) the mechanical offset in the BHA 200 is facing “left”. While drilling, there may be forces on the BHA 200 that are created by various factors, such as the geometry of the BHA 200, factors associated with the drill bit 204 (e.g., cutting force 208A), factors associated with the kick pad 206 or bent housing (e.g., resistive force 208B), attributes of the BHA such as weight of the BHA (e.g., gravity effect 208C), etc. Such forces are described in more detail below with respect to the example illustrated in FIG. 2.

In the example illustrated in FIG. 2, to direct the BHA 200 to the left, the toolface may be set to 90 left and it would be expected that, while the inclination remains unchanged, the azimuth would turn to the left. However, due to the presence of various forces (e.g., 208A, 208B, 208C) this may not be the case. Specifically, the drill bit 204 (shown in FIGS. 3A and 3B) of the BHA 200 may be in contact largely with the perimeter of a wellbore (e.g., borehole 202) on a first side of the formation 123 (the “left” side as depicted in FIG. 2). While the drill bit 204 is in contact with the perimeter of the wellbore (e.g., borehole 202), the drill bit 204 may rotate in a clockwise direction (as shown by arrow 208A) generating a cutting torque. As a result, of a force is applied to the bit due to engagement with the formation 123 and an opposite force 208A is applied by the bit on the formation 123. Due to the larger force 208A on the formation 123, the drill bit 204 may roll down the side of the borehole 202 (e.g., change effective toolface and thus the wellbore inclination).

On the opposing right side (the “right” side as depicted in FIG. 2) of the wellbore (e.g., borehole 202), a kick pad 206 or bent housing of the BHA may contact the wellbore (e.g., borehole 202) resulting in friction between the kick pad 206 or bent housing and the formation 123. If the friction between the kick pad 206 or bent housing and the wellbore (e.g., borehole 202) has a sufficiently high friction, the kick pad 206 or bent housing may resist the upward motion of the drill bit 204 such that the kick pad 206 or bent housing portion of the drilling system 100 is maintained in the plane (e.g., inclination on the right side does not change). In other words, there may be a net downward (relative to the directions depicted in FIG. 2) effect from the cutting force 208A on the first side (the “left” side as depicted in FIG. 2) and the resisting force 208B on the second side, opposite the first side (the “right” side as depicted in FIG. 2), where the bent housing or kick pad 206 contacts the formation 123. Any “rolling” effect will show up as a recorded toolface change but the combined downward forces of the cutting action on the left and the friction action on the right will exaggerate the weight component delivering a different net toolface of the cutting contact force.

In addition, due to the weight of the BHA 200 and its contact with the wellbore on the lower side of the BHA (caused by the force of gravity (e.g., gravity effect 208C) on the BHA 200) supported by the drill bit 204 at the end of the BHA 200, a further downward component (e.g., gravity effect 208C) of force on the BHA 200 may be present.

As a result of these forces (the cutting force 208A, the resistive force 208B, and the gravity effect 208C), as well as other forces affecting the drilling system 100, the drill bit 204 may travel to a low side of the borehole 202, while the kick pad 206 or bent housing side may remain high. Thus, depending on factors such as the magnitude of forces present, the distance being drilled, the attributes of the wellbore (e.g., borehole 202), etc. unwanted changes in inclination and/or azimuth of the BHA may result, essentially having the effect that an actual or delivered toolface is different than the target toolface and which thereby results in a well path deviation off the planned path during drilling. With respect to the above example, while the target toolface may be set to 90 left, due to the forces on the drill bit 204 the cutting contact may take effect at 100 degrees to the left, instead of 90 degrees. Thus, if forces such as those detailed above are not accounted for during drilling, significant deviations in drilling may occur. Such deviations may result in more severe curvature and tortuosity of the wellbore, more time spent drilling to correct mistakes (if found in time), and possibly missing some or even all of a target formation For example, if the target toolface is set to 90 left, but, during drilling, the effective toolface is actually 100 degrees left, the inclination changes, then the drilling system 100 may have to initiate an additional slide in addition to reorienting the toolface to achieve the desired inclination and azimuth. As a result, the borehole 202 becomes more tortuous and more expensive.

FIG. 3A is a depiction of the BHA 200 from a top view in which the drill bit 204 and kick pad 206 are visible, and FIG. 3B is a depiction of the BHA 200 from a side view in which the drill bit 204 and kick pad 206 are visible, in accordance with various embodiments of the present disclosure. Indeed, in the non-limiting example of FIG. 2, with a target toolface of 90 left in a lateral section (90 degrees inclination), the drill bit 204 (shown in FIGS. 3A and 3B) of the BHA 200 is in contact largely with a first side of the formation 123 (the “left” side as depicted in FIG. 2). However, as the drill bit 204 (see FIGS. 3A and 3B) turns clockwise with a large cutting torque, a large upward force 208A on the formation 123 is created, which may result in a corresponding downward force on the drill bit 204 and may cause the drill bit 204 to be rolled down the side of the wall of the borehole 202 (e.g., wellbore). In addition, on the opposite side (the “right” side as depicted in FIG. 2) the kick pad 206 may have a higher amount of friction with the formation 123, which may help keep the kick pad 206 stabilized in the plane. The friction may result in a force 208B on the drill bit 204 in the downward direction along the side of the wall of the borehole 202 (e.g., wellbore). In other words, there may be a net downward (relative to the directions depicted in FIG. 2) effect from the cutting force 208A on the first side (the “left” side as depicted in FIG. 2) and the resisting force 208B at the opposite contact on the second side opposite the first side (the “right” side as depicted in FIG. 2) where the bent housing or kick pad 206 contacts the formation 123. As illustrated in FIG. 3A, which depicts the BHA 200 including the drill bit 204 and the kick pad 206 from a side view, a cutting force 208A may be present on the first side and a resisting force 208B may be present on the second side.

In addition, there is also the effect of the weight of the BHA 200 (caused by the force of gravity (e.g., gravity effect 208C) on the BHA 200) creating a further downward component (e.g., gravity effect 208C) of force hereinafter referred to as the “gravity effect” 208C. FIG. 3B further depicts the BHA 200 including the drill bit 204 and the kick pad 206 from a side view and indicates the force of gravity (e.g., gravity effect 208C) on the BHA 200.

When these forces (e.g., 208A, 208B, 208C) on the BHA 200 are combined they can result in an actual delivered toolface that is different from the planned or target toolface (which corresponds to the target drilling path). In the example provided in FIG. 2, while the planned or target toolface is 90 left direction, the actual delivered toolface may be about 100-120 left direction. As a result, the wellbore drilled with the planned or target toolface of 90 left may be off target. While an experienced directional driller may know that the delivered toolface may not be 90 left in these circumstances, and may deliberately set the target toolface 10 to 20 degrees off of the desired toolface in an effort to deliver the curvature in the right plane (e.g. 80 left or 70 left), this adjustment is based typically on past experience, as opposed to a physical model and/or measured data, and is often not accurate because the adjustment is not based on the particular forces (e.g. 208A, 208B, 208C) at play in the particular wellbore being drilled. This conventional approach often does not provide for an accurate recalculation of the target toolface and often still results in a delivered toolface that is off target. In addition, not all drillers may be aware that a target toolface may not correspond to a delivered toolface.

Accuracy of the drilling may be improved by modeling the forces (e.g. 208A, 208B, 208C) on the BHA 200 and using the model information to provide an adjusted target toolface that results in a delivered toolface that delivers the curvature in the right plane, thereby increasing accuracy and reducing drilling costs. In determining the adjusted target toolface, the model may consider data and information related to the drilling plan and BHA 200 including but not limited to a well plan, seismic data, geological characteristics of formation 123, attributes of the drilling system 100, including the BHA, the drill bit 204, WOB, drilling speed, BHA location, BHA trajectory, ROP, DP, and other information.

FIG. 4 is a flow chart illustrating a method 400 to determine or calculate an adjusted target toolface for a BHA (e.g., BHA 200) to drill a target (e.g., planned) drill path (e.g., to deliver the curvature of the wellbore in the right plane), in accordance with various embodiments of the present disclosure. As discussed in detail above, the BHA may be exposed to a number of forces (e.g., forces 208A, 208B, 208C) that may cause the BHA to drill in such a way that the delivered toolface (e.g., actual delivered toolface, resulting toolface, etc.) that is different from the target toolface. Thus, the delivered toolface may provide a drill path that deviates from the target drill path by providing a different geometry of the drill path. To address this problem, the method 400 may be used to determine or calculate an adjusted target toolface that, when used by the BHA to drill, results in a delivered toolface that provides for a more accurate drill path; i.e. one that more closely matches the planned or desired well path. In other words, the method 400 may calculate an adjusted target toolface that provides improved drilling results.

In step 402, drilling plan information and current BHA information is obtained for calculating an adjusted target toolface (e.g., true target toolface, adjusted target toolface, adjusted toolface, etc.) that results in a delivered toolface providing a desired geometry of the drill path of the borehole 202 (e.g., wellbore). The drilling plan information and BHA information may include a well plan, seismic data, geological characteristics of the formation (e.g., geological formation information), attributes of the drilling system 100, including the BHA, the drill bit (e.g., drill bit 204), and drilling information such as WOB, drilling speed, BHA information such as location, trajectory, ROP, RPM, torque, mud flow rate, and differential pressure, and the like. Other relevant information may also be obtained so that an adjusted target toolface can be calculated to provide the desired geometry of the drill path. For example, other information, such as geological formation characteristics, like hardness, drift likely to be caused, dip, faulting, etc., may be obtained if not included in the drilling plan information for use in sliding and/or rotation calculations.

In step 404, one or more forces (e.g., forces 208A, 208B, 208C) on the BHA may be modeled using at least some of the drilling plan information and current BHA information. The forces may include one or more of the cutting force of the drill bit 204 and the kick pad 206 resulting from the friction (e.g., bit contact force 208A) between the drill bit 204 and the wall (e.g., the formation 123) of the borehole or wellbore (e.g. borehole 202); the resisting force 208B at where the bent housing or kick pad 206 contacts the formation 123; the force of gravity (e.g. force 208C on the BHA) supported by the drill bit 204 at the end of the BHA 200 creating a further downward component of side force (e.g., the “gravity effect” 208C). For example, known models for the BHA analysis may be used to calculate the forces on the BHA in step 404, models may consider or include drilling plan information and BHA information, such as a well plan, seismic data, geological characteristics of formation 123 (e.g., geological formation information), attributes of the drilling system (e.g., drilling system 100) (e.g., attributes of the BHA 200, the drill bit 204, etc.), drilling information (e.g., WOB, drilling speed, etc.), information associated with the BHA 200 (e.g., location, trajectory, ROP, etc.), and other information. Exemplary methods for modeling the one or more forces on a BHA may be implemented in step 404. Such exemplary descriptions of modeling of two-dimensional and three-dimensional BHA assemblies can be found in the publication entitled “Basic Concepts in Static BHA Analysis for Directional Drilling” by U. Chandra, (presented at the SPE Annual Technical Conference and Exhibition, New Orleans, Louisiana, October 1986, SPE-15467-MS) which is incorporated by reference herein.

In step 406 the adjusted target toolface for drilling the desired drill path may be calculated with reference to the one or more forces on the BHA modeled in step 404.

In step 408 the adjusted target toolface calculated at step 406 may be output to a controller or a control system (e.g., control system 142). In some embodiments, the controller, or the controller system may be part of a drilling system (e.g., drilling system 100), though in other embodiments the control system may be a separate system.

In step 410 the controller or the control system may initiate drilling operations (e.g., drill the wellbore) using the adjusted target toolface for the BHA. The control system may initiate drilling operations automatically, manually via a human operator, or in some aspects in a manner that combines both automatic and manual implementation (e.g. with a human confirmation or override step included). In some aspects, the control system may be located at a remote operations center and may be communicatively coupled (wired or wireless) to one or more systems of the drilling rig.

In step 412 the resulting drill path and/or the delivered toolface is determined. The resulting drill path and/or the delivered toolface may be compared to the target drill path and/or the target toolface. In step 414, the results of the comparison between the resulting drill path and/or the delivered toolface and the target drill path and/or the target toolface may be provided back to the model used in step 406 to further train the model. Thus, the model used in step 406 may be a model which can produce an output based on the input, where the output can then be used to further train the model. For example, a machine learning model may be implemented in step 406 and the output of the model can be used to further train the machine learning model during a subsequent training phase. A non-limiting example of a machine learning model includes but is not limited to the model disclosed in Machine Learning for Improved Directional Drilling, OTC-28633-MS (presented at the Offshore Technology Conference, Houstin, Texas, April 30-May 3, 2018). As another example, the hyperparameters or architecture of the model can be adjusted based on the output. Either or both of these approaches can help improve the accuracy and/or speed of the model. In particular, the data associated with the drilling of a particular wellbore (e.g., borehole 202) can aid in refining the model used for that particular wellbore (e.g., borehole 202). By fine tuning the model to the particular wellbore (e.g., borehole 202) being drilled, the accuracy of the results of the model (e.g., the adjusted target toolface) may be improved.

FIG. 5 is a flow chart illustrating another method 500 for optimizing toolface orientation, in accordance with various embodiments of the present disclosure. The method 500 of FIG. 5 may provide additional, alternative, and/or independent steps and/or details to the method 400 discussed with respect to FIG. 4. The method 500 may be implemented to determine and/or calculate an adjusted target toolface (e.g., an adjusted or compensated target toolface) for a BHA 200 to drill a target (e.g., planned) drill path. As discussed above, during drilling of a wellbore (e.g., borehole 202), the BHA 200 may be exposed to a plurality of forces (e.g., forces 208A, 208B, 208C) such that drilling with the target toolface may result in a delivered toolface that is different from the target toolface. In turn, the delivered toolface may result in a drill path that deviates from the planned (e.g., target) drill path. The method 500 may be used to determined and/or calculate an adjusted target toolface that, when applied, results in a delivered toolface that provides for a drill path having the desired geometry. Thus, the method 500 may calculate an adjusted target toolface that provides for improved drilling results.

In step 502, during the drilling of a wellbore (e.g., borehole 202), drilling plan information for the wellbore and information from the BHA located in the wellbore may be received. The drilling plan information and the information from the BHA may include a well plan, seismic data, geological formation information (e.g., geological characteristics of a formation 123, including but not limited to geological formation characteristics, like hardness, drift likely to be caused, dip, faulting, etc.), attributes of the drilling system (e.g. drilling system 100), BHA information (e.g. BHA location, trajectory), the drill bit (e.g. drill bit 204), and drilling information (e.g., WOB, ROP, RPM, torque, mud flow rate, differential pressure, mud pressure, mud flow rate, drilling speed, and other relevant information that may be used to determine an optimized toolface, etc.), attributes of the drilling system (e.g., drilling system 100) (e.g., drilling information associated with the drill bit 204, etc.), drilling plan(s), etc. Information such as the drilling information and information from the BHA may be received continuously and/or intermittently before, during and/or after drilling of a wellbore. For example, information associated with geological characteristics of a formation (e.g., geological formation information) may be received during drilling of the geological formation. As a result, such information may be utilized to generate optimal toolface orientations throughout the drilling process.

In step 504, a target toolface for drilling a planned path according to the drilling plan information may be determined. For example, the drilling system 100 may calculate a target toolface using geometric algorithms to determine the plane in which the curvature is desired.

In step 506, one or more forces (e.g., forces 208A, 208B, 208C) on the BHA may be modeled based at least in part on the information from the BHA and the drilling plan information. The modeled one or more forces may include one or more of cutting (e.g., 208A), friction (e.g., 208B) force(s) (e.g., cutting forces 208A of the drill bit 204 and kick pad 206 resulting from the friction between the drill bit 204 and the wall of the wellbore), resisting force(s) 208B (e.g., resisting force 208B at the location the bent housing or kick pad 206 contacts the formation 123 being drilled), gravitational force(s) (e.g., gravity effect 208C), and/or other force(s) 208 associated with one or more components of the BHA. Various information from the BHA and the drilling plan information may be utilized when modeling the one or more forces. For example, the cutting force 208B due to contact with the well of the borehole 202 may depend on information such as the shape of the cutters, the longevity of the cutters, the type of drill bit (e.g., drill bit 204) being used, the hardness of the rock (e.g., the formation 123 characteristics), etc. Exemplary methods for modeling forces on a BHA (e.g. forces 208A, 208B, 208C) may be implemented in step 506. As referenced in with respect to step 404 of FIG. 4, such exemplary descriptions of modeling of two-dimensional and three-dimensional BHA assemblies can be found in the publication entitled “Basic Concepts in Static BHA Analysis for Directional Drilling” by U. Chandra, (presented at the SPE Annual Technical Conference and Exhibition, New Orleans, Louisiana, October 1986, SPE-15467-MS) which is incorporated by reference herein.

In step 508, based at least in part on the modeled one or more forces on the BHA, a predicted delivered toolface may be determined. The predicted delivered toolface may be determined when drilling the planned path according to the drilling plan information using the target toolface. The delivered toolface may differ from the target toolface due to the forces on the BHA. For example, even though the target toolface is set to 90 left, the resulting delivered toolface may be 100 left. By predicting the delivered toolface, the resulting path that would be drilled if the target toolface was implemented may be predicted. Thus it can be determined, prior to implementing a target toolface, whether or not the target toolface will result in the desired delivered toolface (corresponding to a delivered drill path) to generate the desired borehole geometry. In the case where the target toolface results in a delivered toolface that varies from the target toolface, the method 500 may proceed to step 510. In some aspects, the method 500 may not proceed to step 510 where the results indicate the delivered toolface is within a threshold value of the target toolface, instead the method 500 may proceed to drill in accordance with the target toolface.

In step 510, responsive to determining a difference between the predicted delivered toolface and the target toolface is greater than a threshold value, an adjusted target toolface (e.g., adjusted toolface) accounting for the one or more forces on the BHA may be determined. For example, in the example where the target toolface is 90 left direction, but the predicted delivered toolface is about 100 left direction (e.g., drilling the wellbore (e.g., borehole 202) with a drill path that deviates from the planned path), an adjusted target toolface may be calculated. In turn, the adjusted target toolface, when implemented during drilling, may result in a delivered toolface of 90 left direction corresponding to a drill path that is on target for the planned path.

In various embodiments, the adjusted target toolface accounting for the one or more forces on the BHA may be determined responsive to the difference between the predicted delivered toolface and the target toolface exceeding a threshold value. For example, in the above example, where the target toolface is 90 left direction but the predicted delivered toolface is 100 left direction, the difference between the target toolface and the predicted delivered toolface is 10. If the threshold value is 5, then the difference between the target toolface and the predicted delivered toolface (e.g., 10) exceeds the threshold value (e.g., 5) and, as a result, the adjusted target toolface accounting for the one or more forces on the BHA may be determined. However, if the threshold value is 20, the difference between the target toolface and the predicted delivered toolface (e.g., 10) does not exceed the threshold value (e.g., 20) and an adjusted target toolface is not determined. In such a scenario, the drilling system may maintain drilling with the target toolface. Consequently, the drilling system may avoid repeated toolface adjustments when there are only minor differences in the target toolface and the predicted delivered toolface, which would not require adjustments such as additional slides and/or toolface reorientations. Thus, aspects such as drilling efficiency, time efficiency, and costs can be weighed to determine whether or not calculating the adjusted target toolface is more efficient and/or cost effective than simply utilizing the original target toolface.

In step 512, one or more control signals may be sent to orient the BHA to the adjusted target toolface to drill the planned path. Sending one or more control signals may, in turn, initiate drilling operations (e.g., drilling the wellbore) using the adjusted target toolface (e.g., adjusted target toolface) for the BHA 200. In various embodiments, the controller, or the controller system 142 may be part of a drilling system 100, though in other embodiments the control system 142 may be a separate system.

In step 512 the controller or the control system may drill (e.g., drill the wellbore) according to the adjusted target toolface.

In step 516, the resulting drill path and/or the delivered toolface is determined. The resulting drill path and/or the delivered toolface may be compared to the target drill path and/or the target toolface.

In step 518, the results of the comparison between the resulting drill path and/or the delivered toolface and the target drill path and/or the target toolface may be provided back to the model used in step 506 to further train the model. Thus, the model used in step 506 may be a model which can produce an output based on the input, where the output can be used to further train the model. For example, a machine learning model may be implemented in step 506 and the output of the model can be used to further train the machine learning model during a subsequent training phase. As another example, the hyperparameters or architecture of the model can be adjusted based on the output. Either or both of these approaches can help improve the accuracy and/or speed of the model. In particular the data associated with the drilling of a particular well (e.g., borehole 202) can aid in refining the model used for that particular wellbore (e.g., borehole 202). By fine tuning the model to the particular wellbore (e.g., borehole 202) being drilled, the accuracy of the results of the model (e.g., the adjusted target toolface) may be improved.

FIG. 6 is a flow chart illustrating a method 600 for training and/or updating a machine learning model implemented to optimize toolface orientation for a BHA (e.g., BHA 200), in accordance with various embodiments of the present disclosure. In step 602, a machine learning model may be trained to model the one or more forces (e.g., forces 208A, 208B, 208C) on the BHA and determine the adjusted target toolface for drilling the planned path according to the drilling plan information. For example, training data may be utilized to train the machine learning model. The training data may include data such as historical data (e.g., data received from drilling one or more previous wellbores (e.g., boreholes 202), data received from drilling one or more previous segments of the wellbore being drilled, etc.), and/or data collected by various systems (e.g., drilling system 100, etc.) associated with drilling the wellbore. For example, data related to the BHA may be collected by sensors included in the BHA. Such training data may be collected and/or stored in a datastore accessible by the drilling system (e.g., drilling system 100). As a result, the training data may be used to train the machine learning model to identify differences between the target toolface and the predicted delivered toolface and/or to output an adjusted target toolface (e.g., true target toolface). For example, the machine learning model may be trained to identify that the target toolface and the predicted delivered toolface differ (e.g., by a threshold amount) and, in turn, the machine learning model may determine and output an adjusted target toolface (e.g., true target toolface).

In step 604 the controller or the control system may drill (e.g., drill the wellbore) according to the adjusted target toolface.

In step 606, the resulting drill path and/or the delivered toolface is determined. The resulting drill path and/or the delivered toolface may be compared to the target drill path and/or the target toolface.

In step 608, responsive to drilling the planned path using the adjusted target toolface (or in some cases using the target toolface), the machine learning model may be updated based on the results of the comparison between the resulting drill path and/or the delivered toolface and the target drill path and/or the target toolface. Thus, the model used in step 602 may be a model which can produce an output based on the input, where the output can be used to further train the model. For example, the machine learning model may be iteratively trained using data continuously and/or intermittently received throughout the drilling process. As another example, a machine learning model may be implemented in step 602 and the output of the model can be used to further train the machine learning model during a subsequent training phase. As another example, the hyperparameters or architecture of the model can be adjusted based on the output. On or a combination of these approaches can help improve the accuracy and/or speed of the model. In particular the data associated with the drilling of a particular well (e.g., borehole 202) can aid in refining the model used for that particular wellbore (e.g., borehole 202). By fine tuning the model to the particular wellbore (e.g., borehole 202) being drilled, the accuracy of the results of the model (e.g., the adjusted target toolface) may be improved.

The machine learning model may then produce an adjusted target toolface (e.g., optimized toolface) based in part on the most up to date information received from drilling the wellbore (e.g., borehole 202). It should be noted that while the system and methods are described herein as utilizing a machine learning model or similar, any suitable machine learning and/or artificial intelligence technique may be used. For example, a machine learning process implementing a neural network as opposed to an alternative machine learning algorithm may be implemented to output an optimized toolface (e.g., adjusted target toolface) for drilling a wellbore (e.g., borehole 202) in accordance with a drilling plan.

It is to be understood that the methods described herein may include more or fewer steps than are described, and that one or more steps may be performed in different ways depending on how the method is implemented, including but not limited to one or more steps overlapping or being combined in some embodiments. It should be understood that the drawings and detailed description herein are to be regarded in an illustrative rather than a restrictive manner, and are not intended to be limiting to the particular forms and examples disclosed. On the contrary, included are any further modifications, changes, rearrangements, substitutions, alternatives, design choices, and embodiments apparent to those of ordinary skill in the art, without departing from the spirit and scope hereof, as defined by the following claims. Thus, it is intended that the following claims be interpreted to embrace all such further modifications, changes, rearrangements, substitutions, alternatives, design choices, and embodiments.