EP4652353A1

EP4652353A1 - Directional drilling framework

Info

Publication number: EP4652353A1
Application number: EP23916821.4A
Authority: EP
Inventors: Samba BA; Lu Jiang
Original assignee: Services Petroliers Schlumberger SA; Geoquest Systems BV
Current assignee: Services Petroliers Schlumberger SA; Geoquest Systems BV
Priority date: 2023-01-20
Filing date: 2023-01-20
Publication date: 2025-11-26
Also published as: CN120752412A; WO2024152343A1; EP4652353A4

Abstract

A method can include receiving digital well plan data for direction drilling of a borehole for a well in a subsurface geologic environment (1510); generating candidate trajectories for the borehole using the digital well plan data (1520); generating a ranking of the candidate trajectories using values derived from inverse reinforcement learning using historical observations for one or more other boreholes(1530); and outputting, based on the ranking, one or more of the candidate trajectories for directional drilling of the borehole (1540).

Description

DIRECTIONAL DRILLING FRAMEWORK

BACKGROUND

A reservoir can be a subsurface formation that can be characterized at least in part by its porosity and fluid permeability. As an example, a reservoir may be part of a basin such as a sedimentary basin. A basin can be a depression (e.g., caused by plate tectonic activity, subsidence, etc. ) in which sediments accumulate. As an example, where hydrocarbon source rocks occur in combination with appropriate depth and duration of burial, a petroleum system may develop within a basin, which may form a reservoir that includes hydrocarbon fluids (e.g., oil, gas, etc. ) .
In oil and gas exploration, interpretation is a process that involves analysis of data to identify and locate various subsurface structures (e.g., horizons, faults, geobodies, etc. ) in a geologic environment. Various types of structures (e.g., stratigraphic formations) may be indicative of hydrocarbon traps or flow channels, as may be associated with one or more reservoirs (e.g., fluid reservoirs) . In the field of resource extraction, enhancements to interpretation can allow for construction of a more accurate model of a subsurface region, which, in turn, may improve characterization of the subsurface region for purposes of resource extraction. Characterization of one or more subsurface regions in a geologic environment can guide, for example, performance of one or more operations (e.g., field operations, etc. ) . As an example, a more accurate model of a subsurface region may make a drilling operation more accurate as to a borehole’s trajectory where the borehole is to have a trajectory that penetrates a reservoir, etc., where fluid may be produced via the borehole (e.g., as a completed well, etc. ) . As an example, one or more workflows may be performed using one or more computational frameworks and/or one or more pieces of equipment that include features for one or more of planning, analysis, acquisition, model building, control, etc., for exploration, interpretation, drilling, fracturing, production, etc.
SUMMARY
A method can include receiving digital well plan data for direction drilling of a borehole for a well in a subsurface geologic environment; generating candidate trajectories for the borehole using the digital well plan data; generating a ranking of the candidate trajectories using values derived from inverse reinforcement learning using historical observations for one or more other boreholes; and outputting, based on the ranking, one or more of the candidate trajectories for directional drilling of the borehole. A system can include one or more processors; memory accessible to at least one of the one or more processors; processor-executable instructions stored in the memory and executable to instruct the system to: receive digital well plan data for direction drilling of a borehole for a well in a subsurface geologic environment; generate candidate trajectories for the borehole using the digital well plan data; generate a ranking of the candidate trajectories using values derived from inverse reinforcement learning using historical observations for one or more other boreholes; and output, based on the ranking, one or more of the candidate trajectories for directional drilling of the borehole. One or more non-transitory computer-readable storage media can include processor-executable instructions to instruct a computing system to: receive digital well plan data for direction drilling of a borehole for a well in a subsurface geologic environment; generate candidate trajectories for the borehole using the digital well plan data; generate a ranking of the candidate trajectories using values derived from inverse reinforcement learning using historical observations for one or more other boreholes; and output, based on the ranking, one or more of the candidate trajectories for directional drilling of the borehole. Various other apparatuses, systems, methods, etc., are also disclosed.
This summary is provided to introduce a selection of concepts that are further described below in the detailed description. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used as an aid in limiting the scope of the claimed subject matter.

BRIEF DESCRIPTION OF THE DRAWINGS

The following detailed description refers to the accompanying drawings. Wherever convenient Features and advantages of the described implementations can be more readily understood by reference to the following description taken in conjunction with the accompanying drawings.
Fig. 1 shows an example of a system;
Fig. 2 shows an example of a system;
Fig. 3 shows an example of a system;
Fig. 4 shows an example of a system;
Fig. 5 shows an example of a system;
Fig. 6 shows an example of a system;
Fig. 7 shows an example of a system;
Fig. 8 shows an example of a workflow;
Fig. 9 shows an example of a system;
Fig. 10 shows an example of a reinforcement learning process and an example of an inverse reinforcement learning process;
Fig. 11 shows an example of a method;
Fig. 12 shows an example of a table;
Fig. 13 shows an example of a method;
Fig. 14 shows an example of a method; and
Fig. 15 shows an example of a method.

DETAILED DESCRIPTION

This description is not to be taken in a limiting sense, but rather is made merely for the purpose of describing the general principles of the implementations. The scope of the described implementations should be ascertained with reference to the issued claims.
Fig. 1 shows an example of a system 100 that includes a workspace framework 110 that can provide for instantiation of, rendering of, interactions with, etc., a graphical user interface (GUI) 120. In the example of Fig. 1, the GUI 120 can include graphical controls for computational frameworks (e.g., applications, etc. ) 121, projects 122, visualization 123, one or more other features 124, data access 125, and data storage 126.
In the example of Fig. 1, the workspace framework 110 may be tailored to a particular geologic environment such as an example geologic environment 150. For example, the geologic environment 150 may include layers (e.g., stratification) that include a reservoir 151 and that may be intersected by a fault 153. As an example, the geologic environment 150 may be outfitted with a variety of sensors, detectors, actuators, etc. For example, equipment 152 may include communication circuitry to receive and to transmit information with respect to one or more networks 155. Such information may include information associated with downhole equipment 154, which may be equipment to acquire information, to assist with resource recovery, etc. Other equipment 156 may be located remote from a wellsite and include sensing, detecting, emitting or other circuitry. Such equipment may include storage and communication circuitry to store and to communicate data, instructions, etc. As an example, one or more satellites may be provided for purposes of communications, data acquisition, etc. For example, Fig. 1 shows a satellite in communication with the network 155 that may be configured for communications, noting that the satellite may additionally or alternatively include circuitry for imagery (e.g., spatial, spectral, temporal, radiometric, etc. ) .
Fig. 1 also shows the geologic environment 150 as optionally including equipment 157 and 158 associated with a well that includes a substantially horizontal portion that may intersect with one or more fractures 159. For example, consider a well in a shale formation that may include natural fractures, artificial fractures (e.g., hydraulic fractures) or a combination of natural and artificial fractures. As an example, a well may be drilled for a reservoir that is laterally extensive. In such an example, lateral variations in properties, stresses, etc. may exist where an assessment of such variations may assist with planning, operations, etc. to develop a laterally extensive reservoir (e.g., via fracturing, injecting, extracting, etc. ) . As an example, the equipment 157 and/or 158 may include components, a system, systems, etc. for fracturing, seismic sensing, analysis of seismic data, assessment of one or more fractures, etc.
In the example of Fig. 1, the GUI 120 shows some examples of computational frameworks, including the DRILLPLAN, DRILLOPS, PETREL, TECHLOG, PETROMOD, ECLIPSE, PIPESIM, and INTERSECT frameworks (SLB, Houston, Texas) .
The DRILLPLAN framework provides for digital well construction planning and includes features for automation of repetitive tasks and validation workflows, enabling improved quality drilling programs (e.g., digital drilling plans, etc. ) to be produced quickly with assured coherency.
The DRILLOPS framework can execute a digital drilling plan and ensures plan adherence, while delivering goal-based automation. The DRILLOPS framework can generate activity plans automatically individual operations, whether they are monitored and/or controlled on the rig or in town. Automation can utilize data analysis and learning systems to assist and optimize tasks, such as, for example, setting ROP to drilling a stand. A preset menu of automatable drilling tasks can be rendered, and, using data analysis and models, a plan can be executed in a manner to achieve a specified goal, where, for example, measurements can be utilized for calibration. The DRILLOPS framework provides flexibility to modify and replan activities dynamically, for example, based on a live appraisal of various factors (e.g., equipment, personnel, and supplies) . Well construction activities (e.g., tripping, drilling, cementing, etc. ) can be continually monitored and dynamically updated using feedback from operational activities. The DRILLOPS framework can provide for various levels of automation based on planning and/or re-planning (e.g., via the DRILLPLAN framework) , feedback, etc.
The PETREL framework can be part of the DELFI environment for utilization in geosciences and geoengineering, for example, to analyze subsurface data from exploration to production of fluid from a reservoir. The DELFI cognitive exploration and production (E&P) environment (SLB, Houston, Texas) , referred to herein as the DELFI environment or DELFI framework, is a secure, cognitive, cloud-based collaborative environment that integrates data and workflows with digital technologies, such as artificial intelligence and machine learning.
The PETREL framework provides components that allow for optimization of various exploration, development and production operations. The PETREL framework includes seismic to simulation software components that can output information for use in increasing reservoir performance, for example, by improving asset team productivity. Through use of such a framework, various professionals (e.g., geophysicists, geologists, and reservoir engineers) can develop collaborative workflows and integrate operations to streamline processes (e.g., with respect to one or more geologic environments, etc. ) . Such a framework may be considered an application (e.g., executable using one or more devices) and may be considered a data-driven application (e.g., where data is input for purposes of modeling, simulating, etc. ) .
The TECHLOG framework can handle and process field and laboratory data for a variety of geologic environments (e.g., deepwater exploration, shale, etc. ) . The TECHLOG framework can structure wellbore data for analyses, planning, etc.
The PETROMOD framework provides petroleum systems modeling capabilities that can combine one or more of seismic, well, and geological information to model the evolution of a sedimentary basin. The PETROMOD framework can predict if, and how, a reservoir has been charged with hydrocarbons, including the source and timing of hydrocarbon generation, migration routes, quantities, and hydrocarbon type in the subsurface or at surface conditions.
The ECLIPSE framework provides a reservoir simulator (e.g., as a computational framework) with numerical solutions for fast and accurate prediction of dynamic behavior for various types of reservoirs and development schemes.
The INTERSECT framework provides a high-resolution reservoir simulator for simulation of detailed geological features and quantification of uncertainties, for example, by creating accurate production scenarios and, with the integration of precise models of the surface facilities and field operations, the INTERSECT framework can produce reliable results, which may be continuously updated by real-time data exchanges (e.g., from one or more types of data acquisition equipment in the field that can acquire data during one or more types of field operations, etc. ) . The INTERSECT framework can provide completion configurations for complex wells where such configurations can be built in the field, can provide detailed enhanced-oil-recovery (EOR) formulations where such formulations can be implemented in the field, can analyze application of steam injection and other thermal EOR techniques for implementation in the field, advanced production controls in terms of reservoir coupling and flexible field management, and flexibility to script customized solutions for improved modeling and field management control. The INTERSECT framework, as with the other example frameworks, may be utilized as part of the DELFI environment, for example, for rapid simulation of multiple concurrent cases. For example, a workflow may utilize one or more of the DELFI environment on demand reservoir simulation features.
The aforementioned DELFI environment provides various features for workflows as to subsurface analysis, planning, construction and production, for example, as illustrated in the workspace framework 110. As shown in Fig. 1, outputs from the workspace framework 110 can be utilized for directing, controlling, etc., one or more processes in the geologic environment 150 and, feedback 160, can be received via one or more interfaces in one or more forms (e.g., acquired data as to operational conditions, equipment conditions, environment conditions, etc. ) .
As an example, a workflow may progress to a geology and geophysics ( “G&G” ) service provider, which may generate a well trajectory, which may involve execution of one or more G&G frameworks (e.g., consider the PETREL framework, etc. ) .
In the example of Fig. 1, the visualization features 123 may be implemented via the workspace framework 110, for example, to perform tasks as associated with one or more of subsurface regions, planning operations, constructing wells and/or surface fluid networks, and producing from a reservoir.
As an example, a visualization process can implement one or more of various features that can be suitable for one or more web applications. For example, a template may involve use of the JAVASCRIPT object notation format (JSON) and/or one or more other languages/formats. As an example, a framework may include one or more converters. For example, consider a JSON to PYTHON converter and/or a PYTHON to JSON converter. Such an approach can provide for compatibility of devices, frameworks, etc., with respect to one or more sets of instructions.
As an example, visualization features can provide for visualization of various earth models, properties, etc., in one or more dimensions. As an example, visualization features can provide for rendering of information in multiple dimensions, which may optionally include multiple resolution rendering. In such an example, information being rendered may be associated with one or more frameworks and/or one or more data stores. As an example, visualization features may include one or more control features for control of equipment, which can include, for example, field equipment that can perform one or more field operations. As an example, a workflow may utilize one or more frameworks to generate information that can be utilized to control one or more types of field equipment (e.g., drilling equipment, wireline equipment, fracturing equipment, etc. ) .
As to a reservoir model that may be suitable for utilization by a simulator, consider acquisition of seismic data as acquired via reflection seismology, which finds use in geophysics, for example, to estimate properties of subsurface formations. As an example, reflection seismology may provide seismic data representing waves of elastic energy (e.g., as transmitted by P-waves and S-waves, in a frequency range of approximately 1 Hz to approximately 100 Hz) . Seismic data may be processed and interpreted, for example, to understand better composition, fluid content, extent and geometry of subsurface rocks. Such interpretation results can be utilized to plan, simulate, perform, etc., one or more operations for production of fluid from a reservoir (e.g., reservoir rock, etc. ) .
Field acquisition equipment may be utilized to acquire seismic data, which may be in the form of traces where a trace can include values organized with respect to time and/or depth (e.g., consider 1 D, 2D, 3D or 4D seismic data) . For example, consider acquisition equipment that acquires digital samples at a rate of one sample per approximately 4 ms. Given a speed of sound in a medium or media, a sample rate may be converted to an approximate distance. For example, the speed of sound in rock may be on the order of around 5 km per second. Thus, a sample time spacing of approximately 4 ms would correspond to a sample “depth” spacing of about 10 meters (e.g., assuming a path length from source to boundary and boundary to sensor) . As an example, a trace may be about 4 seconds in duration; thus, for a sampling rate of one sample at about 4 ms intervals, such a trace would include about 1000 samples where latter acquired samples correspond to deeper reflection boundaries. If the 4 second trace duration of the foregoing example is divided by two (e.g., to account for reflection) , for a vertically aligned source and sensor, a deepest boundary depth may be estimated to be about 10 km (e.g., assuming a speed of sound of about 5 km per second) .
As an example, a model may be a simulated version of a geologic environment. As an example, a simulator may include features for simulating physical phenomena in a geologic environment based at least in part on a model or models. A simulator, such as a reservoir simulator, can simulate fluid flow in a geologic environment based at least in part on a model that can be generated via a framework that receives seismic data. A simulator can be a computerized system (e.g., a computing system) that can execute instructions using one or more processors to solve a system of equations that describe physical phenomena subject to various constraints. In such an example, the system of equations may be spatially defined (e.g., numerically discretized) according to a spatial model that that includes layers of rock, geobodies, etc., that have corresponding positions that can be based on interpretation of seismic and/or other data. A spatial model may be a cell-based model where cells are defined by a grid (e.g., a mesh) . A cell in a cell-based model can represent a physical area or volume in a geologic environment where the cell can be assigned physical properties (e.g., permeability, fluid properties, etc. ) that may be germane to one or more physical phenomena (e.g., fluid volume, fluid flow, pressure, etc. ) . A reservoir simulation model can be a spatial model that may be cell-based.
A simulator can be utilized to simulate the exploitation of a real reservoir, for example, to examine different productions scenarios to find an optimal one before production or further production occurs. A reservoir simulator does not provide an exact replica of flow in and production from a reservoir at least in part because the description of the reservoir and the boundary conditions for the equations for flow in a porous rock are generally known with an amount of uncertainty. Certain types of physical phenomena occur at a spatial scale that can be relatively small compared to size of a field. A balance can be struck between model scale and computational resources that results in model cell sizes being of the order of meters; rather than a lesser size (e.g., a level of detail of pores) . A modeling and simulation workflow for multiphase flow in porous media (e.g., reservoir rock, etc. ) can include generalizing real micro-scale data from macro scale observations (e.g., seismic data and well data) and upscaling to a manageable scale and problem size. Uncertainties can exist in input data and solution procedure such that simulation results too are to some extent uncertain. A process known as history matching can involve comparing simulation results to actual field data acquired during production of fluid from a field. Information gleaned from history matching, can provide for adjustments to a model, data, etc., which can help to increase accuracy of simulation.
As an example, a simulator may utilize various types of constructs, which may be referred to as entities. Entities may include earth entities or geological objects such as wells, surfaces, reservoirs, etc. Entities can include virtual representations of actual physical entities that may be reconstructed for purposes of simulation. Entities may include entities based on data acquired via sensing, observation, etc. (e.g., consider entities based at least in part on seismic data and/or other information) . As an example, an entity may be characterized by one or more properties (e.g., a geometrical pillar grid entity of an earth model may be characterized by a porosity property, etc. ) . Such properties may represent one or more measurements (e.g., acquired data) , calculations, etc.
As an example, a simulator may utilize an object-based software framework, which may include entities based on pre-defined classes to facilitate modeling and simulation. As an example, an object class can encapsulate reusable code and associated data structures. Object classes can be used to instantiate object instances for use by a program, script, etc. For example, borehole classes may define objects for representing boreholes based on well data. A model of a basin, a reservoir, etc. may include one or more boreholes where a borehole may be, for example, for measurements, injection, production, etc. As an example, a borehole may be a wellbore of a well, which may be a completed well (e.g., for production of a resource from a reservoir, for injection of material, etc. ) .
While several simulators are illustrated in the example of Fig. 1, one or more other simulators may be utilized, additionally or alternatively. For example, consider the VISAGE geomechanics simulator (SLB, Houston Texas) or the PIPESIM network simulator (SLB, Houston Texas) , etc. The VISAGE simulator includes finite element numerical solvers that may provide simulation results such as, for example, results as to compaction and subsidence of a geologic environment, well and completion integrity in a geologic environment, cap-rock and fault-seal integrity in a geologic environment, fracture behavior in a geologic environment, thermal recovery in a geologic environment, CO2 disposal, etc. The PIPESIM simulator includes solvers that may provide simulation results such as, for example, multiphase flow results (e.g., from a reservoir to a wellhead and beyond, etc. ) , flowline and surface facility performance, etc. The PIPESIM simulator may be integrated, for example, with the AVOCET production operations framework (SLB, Houston Texas) . As an example, a reservoir or reservoirs may be simulated with respect to one or more enhanced recovery techniques (e.g., consider a thermal process such as steam-assisted gravity drainage (SAGD) , etc. ) . As an example, the PIPESIM simulator may be an optimizer that can optimize one or more operational scenarios at least in part via simulation of physical phenomena. The MANGROVE simulator (SLB, Houston, Texas) provides for optimization of stimulation design (e.g., stimulation treatment operations such as hydraulic fracturing) in a reservoir-centric environment. The MANGROVE framework can combine scientific and experimental work to predict geomechanical propagation of hydraulic fractures, reactivation of natural fractures, etc., along with production forecasts within 3D reservoir models (e.g., production from a drainage area of a reservoir where fluid moves via one or more types of fractures to a well and/or from a well) . The MANGROVE framework can provide results pertaining to heterogeneous interactions between hydraulic and natural fracture networks, which may assist with optimization of the number and location of fracture treatment stages (e.g., stimulation treatment (s) ) , for example, to increased perforation efficiency and recovery.
As an example, data can include geochemical data. For example, consider data acquired using X-ray fluorescence (XRF) technology, Fourier transform infrared spectroscopy (FTIR) technology and/or wireline geochemical technology.
As an example, one or more probes may be deployed in a bore via a wireline or wirelines. As an example, a probe may emit energy and receive energy where such energy may be analyzed to help determine mineral composition of rock surrounding a bore. As an example, nuclear magnetic resonance may be implemented (e.g., via a wireline, downhole NMR probe, etc. ) , for example, to acquire data as to nuclear magnetic properties of elements in a formation (e.g., hydrogen, carbon, phosphorous, etc. ) .
As an example, lithology scanning technology may be employed to acquire and analyze data. For example, consider the LITHO SCANNER technology (SLB, Houston, Texas) . As an example, a LITHO SCANNER tool may be or include a gamma ray spectroscopy tool.
As an example, a tool may be positioned to acquire information in a portion of a borehole. Analysis of such information may reveal vugs, dissolution planes (e.g., dissolution along bedding planes) , stress-related features, dip events, etc. As an example, a tool may acquire information that may help to characterize a fractured reservoir, optionally where fractures may be natural and/or artificial (e.g., hydraulic fractures) . Such information may assist with completions, stimulation treatment, etc. As an example, information acquired by a tool may be analyzed using a framework such as the aforementioned TECHLOG framework.
As an example, a workflow may utilize one or more types of data for one or more processes (e.g., stratigraphic modeling, basin modeling, completion designs, drilling, production, injection, etc. ) . As an example, one or more tools may provide data that can be used in a workflow or workflows that may implement one or more frameworks (e.g., PETREL, TECHLOG, PETROMOD, ECLIPSE, etc. ) .
In the example of Fig. 1, drilling may be performed in the geologic environment 150, for example, to access the reservoir 151, which may be accessed from land or offshore. In Fig. 1, the downhole equipment 154 may be, for example, part of a bottom hole assembly (BHA) . The BHA may be used to drill a well. The downhole equipment 154 may communicate information to equipment at the surface, and may receive instructions and information from the equipment at the surface. During a well construction process, a variety of operations (such as cementing, wireline evaluation, testing, etc. ) may be conducted. In such embodiments, data collected by tools and sensors and used for reasons such as reservoir characterization may be collected and transmitted.
A well may include a substantially horizontal portion (e.g., lateral portion) that may intersect with one or more fractures. For example, a well in a shale formation may pass through natural fractures, artificial fractures (e.g., hydraulic fractures) , or a combination thereof. Such a well may be constructed using directional drilling techniques as described herein. However, these same techniques may be used in connection with other types of directional wells (such as slant wells, S-shaped wells, deep inclined wells, and others) and are not limited to horizontal wells.
Fig. 2 shows an example of a wellsite system 200 (e.g., at a wellsite that may be onshore or offshore) . As shown, the wellsite system 200 can include a mud tank 201 for holding mud and other material (e.g., where mud can be a drilling fluid) , a suction line 203 that serves as an inlet to a mud pump 204 for pumping mud from the mud tank 201 such that mud flows to a vibrating hose 206, a drawworks 207 for winching drill line or drill lines 212, a standpipe 208 that receives mud from the vibrating hose 206, a kelly hose 209 that receives mud from the standpipe 208, a gooseneck or goosenecks 210, a traveling block 211, a crown block 213 for carrying the traveling block 211 via the drill line or drill lines 212, a derrick 214, a kelly 218 or a top drive 240, a kelly drive bushing 219, a rotary table 220, a drill floor 221, a bell nipple 222, one or more blowout preventors (BOPs) 223, a drillstring 225, a drill bit 226, a casing head 227 and a flow pipe 228 that carries mud and other material to, for example, the mud tank 201.
In the example system of Fig. 2, a borehole 232 is formed in subsurface formations 230 by rotary drilling; noting that various example embodiments may also use one or more directional drilling techniques, equipment, etc.
As shown in the example of Fig. 2, the drillstring 225 is suspended within the borehole 232 and has a drillstring assembly 250 that includes the drill bit 226 at its lower end. As an example, the drillstring assembly 250 may be a bottom hole assembly (BHA) .
The wellsite system 200 can provide for operation of the drillstring 225 and other operations. As shown, the wellsite system 200 includes the traveling block 211 and the derrick 214 positioned over the borehole 232. As mentioned, the wellsite system 200 can include the rotary table 220 where the drillstring 225 pass through an opening in the rotary table 220.
As shown in the example of Fig. 2, the wellsite system 200 can include the kelly 218 and associated components, etc., or a top drive 240 and associated components. As to a kelly example, the kelly 218 may be a square or hexagonal metal/alloy bar with a hole drilled therein that serves as a mud flow path. The kelly 218 can be used to transmit rotary motion from the rotary table 220 via the kelly drive bushing 219 to the drillstring 225, while allowing the drillstring 225 to be lowered or raised during rotation. The kelly 218 can pass through the kelly drive bushing 219, which can be driven by the rotary table 220. As an example, the rotary table 220 can include a master bushing that operatively couples to the kelly drive bushing 219 such that rotation of the rotary table 220 can turn the kelly drive bushing 219 and hence the kelly 218. The kelly drive bushing 219 can include an inside profile matching an outside profile (e.g., square, hexagonal, etc. ) of the kelly 218; however, with slightly larger dimensions so that the kelly 218 can freely move up and down inside the kelly drive bushing 219.
As to a top drive example, the top drive 240 can provide functions performed by a kelly and a rotary table. The top drive 240 can turn the drillstring 225. As an example, the top drive 240 can include one or more motors (e.g., electric and/or hydraulic) connected with appropriate gearing to a short section of pipe called a quill, that in turn may be screwed into a saver sub or the drillstring 225 itself. The top drive 240 can be suspended from the traveling block 211, so the rotary mechanism is free to travel up and down the derrick 214. As an example, a top drive 240 may allow for drilling to be performed with more joint stands than a kelly/rotary table approach.
In the example of Fig. 2, the mud tank 201 can hold mud, which can be one or more types of drilling fluids. As an example, a wellbore may be drilled to produce fluid, inject fluid or both (e.g., hydrocarbons, minerals, water, etc. ) .
In the example of Fig. 2, the drillstring 225 (e.g., including one or more downhole tools) may be composed of a series of pipes threadably connected together to form a long tube with the drill bit 226 at the lower end thereof. As the drillstring 225 is advanced into a wellbore for drilling, at some point in time prior to or coincident with drilling, the mud may be pumped by the pump 204 from the mud tank 201 (e.g., or other source) via a the lines 206, 208 and 209 to a port of the kelly 218 or, for example, to a port of the top drive 240. The mud can then flow via a passage (e.g., or passages) in the drillstring 225 and out of ports located on the drill bit 226 (see, e.g., a directional arrow) . As the mud exits the drillstring 225 via ports in the drill bit 226, it can then circulate upwardly through an annular region between an outer surface (s) of the drillstring 225 and surrounding wall (s) (e.g., open borehole, casing, etc. ) , as indicated by directional arrows. In such a manner, the mud lubricates the drill bit 226 and carries heat energy (e.g., frictional or other energy) and formation cuttings to the surface where the mud (e.g., and cuttings) may be returned to the mud tank 201, for example, for recirculation (e.g., with processing to remove cuttings, etc. ) .
The mud pumped by the pump 204 into the drillstring 225 may, after exiting the drillstring 225, form a mudcake that lines the wellbore which, among other functions, may reduce friction between the drillstring 225 and surrounding wall (s) (e.g., borehole, casing, etc. ) . A reduction in friction may facilitate advancing or retracting the drillstring 225. During a drilling operation, the entire drillstring 225 may be pulled from a wellbore and optionally replaced, for example, with a new or sharpened drill bit, a smaller diameter drillstring, etc. As mentioned, the act of pulling a drillstring out of a hole or replacing it in a hole is referred to as tripping. A trip may be referred to as an upward trip or an outward trip or as a downward trip or an inward trip depending on trip direction.
As an example, consider a downward trip where upon arrival of the drill bit 226 of the drillstring 225 at a bottom of a wellbore, pumping of the mud commences to lubricate the drill bit 226 for purposes of drilling to enlarge the wellbore. As mentioned, the mud can be pumped by the pump 204 into a passage of the drillstring 225 and, upon filling of the passage, the mud may be used as a transmission medium to transmit energy, for example, energy that may encode information as in mud-pulse telemetry.
As an example, mud-pulse telemetry equipment may include a downhole device configured to effect changes in pressure in the mud to create an acoustic wave or waves upon which information may modulated. In such an example, information from downhole equipment (e.g., one or more modules of the drillstring 225) may be transmitted uphole to an uphole device, which may relay such information to other equipment for processing, control, etc.
As an example, telemetry equipment may operate via transmission of energy via the drillstring 225 itself. For example, consider a signal generator that imparts coded energy signals to the drillstring 225 and repeaters that may receive such energy and repeat it to further transmit the coded energy signals (e.g., information, etc. ) .
As an example, the drillstring 225 may be fitted with telemetry equipment 252 that includes a rotatable drive shaft, a turbine impeller mechanically coupled to the drive shaft such that the mud can cause the turbine impeller to rotate, a modulator rotor mechanically coupled to the drive shaft such that rotation of the turbine impeller causes said modulator rotor to rotate, a modulator stator mounted adjacent to or proximate to the modulator rotor such that rotation of the modulator rotor relative to the modulator stator creates pressure pulses in the mud, and a controllable brake for selectively braking rotation of the modulator rotor to modulate pressure pulses. In such example, an alternator may be coupled to the aforementioned drive shaft where the alternator includes at least one stator winding electrically coupled to a control circuit to selectively short the at least one stator winding to electromagnetically brake the alternator and thereby selectively brake rotation of the modulator rotor to modulate the pressure pulses in the mud.
In the example of Fig. 2, an uphole control and/or data acquisition system 262 may include circuitry to sense pressure pulses generated by telemetry equipment 252 and, for example, communicate sensed pressure pulses or information derived therefrom for process, control, etc.
The assembly 250 of the illustrated example includes a logging-while-drilling (LWD) module 254, a measurement-while-drilling (MWD) module 256, an optional module 258, a rotary-steerable system (RSS) and/or motor 260, and the drill bit 226. Such components or modules may be referred to as tools where a drillstring can include a plurality of tools.
As to a RSS, it involves technology utilized for directional drilling. Directional drilling involves drilling into the Earth to form a deviated bore such that the trajectory of the bore is not vertical; rather, the trajectory deviates from vertical along one or more portions of the bore. As an example, consider a target that is located at a lateral distance from a surface location where a rig may be stationed. In such an example, drilling can commence with a vertical portion and then deviate from vertical such that the bore is aimed at the target and, eventually, reaches the target. Directional drilling may be implemented where a target may be inaccessible from a vertical location at the surface of the Earth, where material exists in the Earth that may impede drilling or otherwise be detrimental (e.g., consider a salt dome, etc. ) , where a formation is laterally extensive (e.g., consider a relatively thin yet laterally extensive reservoir) , where multiple bores are to be drilled from a single surface bore, where a relief well is desired, etc.
One approach to directional drilling involves a mud motor; however, a mud motor can present some challenges depending on factors such as rate of penetration (ROP) , transferring weight to a bit (e.g., weight on bit, WOB) due to friction, etc. A mud motor can be a positive displacement motor (PDM) that operates to drive a bit (e.g., during directional drilling, etc. ) . A PDM operates as drilling fluid is pumped through it where the PDM converts hydraulic power of the drilling fluid into mechanical power to cause the bit to rotate.
As an example, a mud motor (e.g., PDM) can be operated in different modes, which can include a rotating mode and a sliding mode. A sliding mode involves drilling with a mud motor rotating the bit downhole without rotating the drillstring from the surface. Such an operation can be conducted when a BHA has been fitted with a bent sub or a bent housing mud motor, or both, for directional drilling. Sliding can be used in building and controlling or adjusting hole angle. In directional drilling, pointing of a bit can be accomplished through a bent sub, which can have a relative small angle offset from the axis of a drillstring, and a measurement device to determine the direction of offset. Without turning the drillstring, the bit can be rotated with mud flow through the mud motor to drill in the direction it is pointed. With steerable motors, when a desired wellbore direction is attained, the entire drillstring can be rotated to drill straight rather than at an angle. By controlling the amount of hole drilled in the sliding mode versus the rotating mode, a wellbore trajectory can be controlled rather precisely.
As an example, a PDM may operate in a combined rotating mode where surface equipment is utilized to rotate a bit of a drillstring (e.g., a rotary table, a top drive, etc. ) by rotating the entire drillstring and where drilling fluid is utilized to rotate the bit of the drillstring. In such an example, a surface RPM (SRPM) may be determined by use of the surface equipment and a downhole RPM of the mud motor may be determined using various factors related to flow of drilling fluid, mud motor type, etc. As an example, in the combined rotating mode, bit RPM can be determined or estimated as a sum of the SRPM and the mud motor RPM, assuming the SRPM and the mud motor RPM are in the same direction.
As an example, a PDM mud motor can operate in a so-called sliding mode, when the drillstring is not rotated from the surface. In such an example, a bit RPM can be determined or estimated based on the RPM of the mud motor.
A RSS can drill directionally where there is continuous rotation from surface equipment, which can alleviate the sliding of a steerable motor (e.g., a PDM) . A RSS may be deployed when drilling directionally (e.g., deviated, horizontal, or extended-reach wells) . A RSS can aim to minimize interaction with a borehole wall, which can help to preserve borehole quality. A RSS can aim to exert a relatively consistent side force akin to stabilizers that rotate with the drillstring or orient the bit in the desired direction while continuously rotating at the same number of rotations per minute as the drillstring.
The LWD module 254 may be housed in a suitable type of drill collar and can contain one or a plurality of selected types of logging tools. It will also be understood that more than one LWD and/or MWD module can be employed, for example, as represented at by the module 256 of the drillstring assembly 250. Where the position of an LWD module is mentioned, as an example, it may refer to a module at the position of the LWD module 254, the module 256, etc. An LWD module can include capabilities for measuring, processing, and storing information, as well as for communicating with the surface equipment. In the illustrated example, the LWD module 254 may include a seismic measuring device.
The MWD module 256 may be housed in a suitable type of drill collar and can contain one or more devices for measuring characteristics of the drillstring 225 and the drill bit 226. As an example, the MWD tool 254 may include equipment for generating electrical power, for example, to power various components of the drillstring 225. As an example, the MWD tool 254 may include the telemetry equipment 252, for example, where the turbine impeller can generate power by flow of the mud; it being understood that other power and/or battery systems may be employed for purposes of powering various components. As an example, the MWD module 256 may include one or more of the following types of measuring devices: a weight-on-bit measuring device, a torque measuring device, a vibration measuring device, a shock measuring device, a stick slip measuring device, a direction measuring device, and an inclination measuring device.
Fig. 2 also shows some examples of types of holes that may be drilled. For example, consider a slant hole 272, an S-shaped hole 274, a deep inclined hole 276 and a horizontal hole 278.
As an example, a drilling operation can include directional drilling where, for example, at least a portion of a well includes a curved axis. For example, consider a radius that defines curvature where an inclination with regard to the vertical may vary until reaching an angle between about 30 degrees and about 60 degrees or, for example, an angle to about 90 degrees or possibly greater than about 90 degrees.
As an example, a directional well can include several shapes where each of the shapes may aim to meet particular operational demands. As an example, a drilling process may be performed on the basis of information as and when it is relayed to a drilling engineer. As an example, inclination and/or direction may be modified based on information received during a drilling process.
As an example, deviation of a bore may be accomplished in part by use of a downhole motor and/or a turbine. As to a motor, for example, a drillstring can include a positive displacement motor (PDM) .
As an example, a system may be a steerable system and include equipment to perform method such as geosteering. As mentioned, a steerable system can be or include an RSS. As an example, a steerable system can include a PDM or of a turbine on a lower part of a drillstring which, just above a drill bit, a bent sub can be mounted. As an example, above a PDM, MWD equipment that provides real time or near real time data of interest (e.g., inclination, direction, pressure, temperature, real weight on the drill bit, torque stress, etc. ) and/or LWD equipment may be installed. As to the latter, LWD equipment can make it possible to send to the surface various types of data of interest, including for example, geological data (e.g., gamma ray log, resistivity, density and sonic logs, etc. ) .
The coupling of sensors providing information on the course of a well trajectory, in real time or near real time, with, for example, one or more logs characterizing the formations from a geological viewpoint, can allow for implementing a geosteering method. Such a method can include navigating a subsurface environment, for example, to follow a desired route to reach a desired target or targets.
As an example, a drillstring can include an azimuthal density neutron (ADN) tool for measuring density and porosity; a MWD tool for measuring inclination, azimuth and shocks; a compensated dual resistivity (CDR) tool for measuring resistivity and gamma ray related phenomena; one or more variable gauge stabilizers; one or more bend joints; and a geosteering tool, which may include a motor and optionally equipment for measuring and/or responding to one or more of inclination, resistivity and gamma ray related phenomena.
As an example, geosteering can include intentional directional control of a wellbore based on results of downhole geological logging measurements in a manner that aims to keep a directional wellbore within a desired region, zone (e.g., a pay zone) , etc. As an example, geosteering may include directing a wellbore to keep the wellbore in a particular section of a reservoir, for example, to minimize gas and/or water breakthrough and, for example, to maximize economic production from a well that includes the wellbore.
Referring again to Fig. 2, the wellsite system 200 can include one or more sensors 264 that are operatively coupled to the control and/or data acquisition system 262. As an example, a sensor or sensors may be at surface locations. As an example, a sensor or sensors may be at downhole locations. As an example, a sensor or sensors may be at one or more remote locations that are not within a distance of the order of about one hundred meters from the wellsite system 200. As an example, a sensor or sensor may be at an offset wellsite where the wellsite system 200 and the offset wellsite are in a common field (e.g., oil and/or gas field) .
As an example, one or more of the sensors 264 can be provided for tracking pipe, tracking movement of at least a portion of a drillstring, etc.
As an example, the system 200 can include one or more sensors 266 that can sense and/or transmit signals to a fluid conduit such as a drilling fluid conduit (e.g., a drilling mud conduit) . For example, in the system 200, the one or more sensors 266 can be operatively coupled to portions of the standpipe 208 through which mud flows. As an example, a downhole tool can generate pulses that can travel through the mud and be sensed by one or more of the one or more sensors 266. In such an example, the downhole tool can include associated circuitry such as, for example, encoding circuitry that can encode signals, for example, to reduce demands as to transmission. As an example, circuitry at the surface may include decoding circuitry to decode encoded information transmitted at least in part via mud-pulse telemetry. As an example, circuitry at the surface may include encoder circuitry and/or decoder circuitry and circuitry downhole may include encoder circuitry and/or decoder circuitry. As an example, the system 200 can include a transmitter that can generate signals that can be transmitted downhole via mud (e.g., drilling fluid) as a transmission medium.
As an example, one or more portions of a drillstring may become stuck. The term stuck can refer to one or more of varying degrees of inability to move or remove a drillstring from a bore. As an example, in a stuck condition, it might be possible to rotate pipe or lower it back into a bore or, for example, in a stuck condition, there may be an inability to move the drillstring axially in the bore, though some amount of rotation may be possible. As an example, in a stuck condition, there may be an inability to move at least a portion of the drillstring axially and rotationally.
As to the term “stuck pipe” , this can refer to a portion of a drillstring that cannot be rotated or moved axially. As an example, a condition referred to as “differential sticking” can be a condition whereby the drillstring cannot be moved (e.g., rotated or reciprocated) along the axis of the bore. Differential sticking may occur when high-contact forces caused by low reservoir pressures, high wellbore pressures, or both, are exerted over a sufficiently large area of the drillstring. Differential sticking can have time and financial cost.
As an example, a sticking force can be a product of the differential pressure between the wellbore and the reservoir and the area that the differential pressure is acting upon. This means that a relatively low differential pressure (delta p) applied over a large working area can be just as effective in sticking pipe as can a high differential pressure applied over a small area.
As an example, a condition referred to as “mechanical sticking” can be a condition where limiting or prevention of motion of the drillstring by a mechanism other than differential pressure sticking occurs. Mechanical sticking can be caused, for example, by one or more of junk in the hole, wellbore geometry anomalies, cement, keyseats or a buildup of cuttings in the annulus.
Fig. 3 shows a schematic view of a computing or processor system 300, according to an embodiment. The processor system 300 may include one or more processors 302 of varying core configurations (including multiple cores) and clock frequencies. The one or more processors 302 may be operable to execute instructions, apply logic, etc. It will be appreciated that these functions may be provided by multiple processors or multiple cores on a single chip operating in parallel and/or communicably linked together. In at least one embodiment, the one or more processors 302 may be or include one or more GPUs.
The processor system 300 may also include a memory system, which may be or include one or more memory devices and/or computer-readable media 304 of varying physical dimensions, accessibility, storage capacities, etc., such as flash drives, hard drives, disks, random access memory, etc., for storing data, such as images, files, and program instructions for execution by the processor 302. In an embodiment, the computer-readable media 304 may store instructions that, when executed by the processor 302, are configured to cause the processor system 300 to perform operations. For example, execution of such instructions may cause the processor system 300 to implement one or more portions and/or embodiments of the method (s) described above.
The processor system 300 may also include one or more network interfaces 306. The network interfaces 306 may include any hardware, applications, and/or other software. Accordingly, the network interfaces 306 may include Ethernet adapters, wireless transceivers, PCI interfaces, and/or serial network components, for communicating over wired or wireless media using protocols, such as Ethernet, wireless Ethernet, etc.
As an example, the processor system 300 may be a mobile device that includes one or more network interfaces for communication of information. For example, a mobile device may include a wireless network interface (e.g., operable via one or more IEEE 802.11 protocols, ETSI GSM, BLUETOOTH, satellite, etc. ) . As an example, a mobile device may include components such as a main processor, memory, a display, display graphics circuitry (e.g., optionally including touch and gesture circuitry) , a SIM slot, audio/video circuitry, motion processing circuitry (e.g., accelerometer, gyroscope) , wireless LAN circuitry, smart card circuitry, transmitter circuitry, GPS circuitry, and a battery. As an example, a mobile device may be configured as a cell phone, a tablet, etc. As an example, a method may be implemented (e.g., wholly or in part) using a mobile device. As an example, a system may include one or more mobile devices.
The processor system 300 may further include one or more peripheral interfaces 308, for communication with a display, projector, keyboards, mice, touchpads, sensors, other types of input and/or output peripherals, and/or the like. In some implementations, the components of processor system 300 need not be enclosed within a single enclosure or even located in close proximity to one another, but in other implementations, the components and/or others may be provided in a single enclosure. As an example, a system may be a distributed environment, for example, a so-called “cloud” environment where various devices, components, etc. interact for purposes of data storage, communications, computing, etc. As an example, a method may be implemented in a distributed environment (e.g., wholly or in part as a cloud-based service) .
As an example, information may be input from a display (e.g., a touchscreen) , output to a display or both. As an example, information may be output to a projector, a laser device, a printer, etc. such that the information may be viewed. As an example, information may be output stereographically or holographically. As to a printer, consider a 2D or a 3D printer. As an example, a 3D printer may include one or more substances that can be output to construct a 3D object. For example, data may be provided to a 3D printer to construct a 3D representation of a subterranean formation. As an example, layers may be constructed in 3D (e.g., horizons, etc. ) , geobodies constructed in 3D, etc. As an example, holes, fractures, etc., may be constructed in 3D (e.g., as positive structures, as negative structures, etc. ) .
The memory device 304 may be physically or logically arranged or configured to store data on one or more storage devices 310. The storage device 310 may include one or more file systems or databases in any suitable format. The storage device 310 may also include one or more software programs 312, which can contain interpretable and/or executable instructions for performing one or more of the disclosed processes (e.g., processor-executable instructions storable in the memory 304 and executable to instruct the system 300 to perform one or more actions) . When requested by the processor 302, one or more of the software programs 312, or a portion thereof, may be loaded from the storage devices 310 to the memory devices 304 for execution by the processor 302.
Those skilled in the art will appreciate that the above-described componentry is merely one example of a hardware configuration, as the processor system 300 may include any type of hardware components, including any accompanying firmware or software, for performing the disclosed implementations. The processor system 300 may also be implemented in part or in whole by electronic circuit components or processors, such as application-specific integrated circuits (ASICs) or field-programmable gate arrays (FPGAs) .
The processor system 300 may be configured to receive a directional drilling well plan 320 (e.g., and/or to generate a directional drilling well plan) . As discussed above, a well plan is to the description of the proposed wellbore to be used by the drilling team in drilling the well. The well plan typically includes information about the shape, orientation, depth, completion, and evaluation along with information about the equipment to be used, actions to be taken at different points in the well construction process, and other information the team planning the well believes will be relevant/helpful to the team drilling the well. A directional drilling well plan can also include information about how to steer and manage the direction of the well.
The processor system 300 may be configured to receive drilling data 322. The drilling data 322 may include data collected by one or more sensors associated with surface equipment or with downhole equipment. The drilling data 322 may include information such as data relating to the position of the BHA (such as survey data or continuous position data) , drilling parameters (such as weight on bit (WOB) , rate of penetration (ROP) , torque, or others) , text information entered by individuals working at the wellsite, or other data collected during the construction of the well.
In one embodiment, the processor system 300 is part of a rig control system (RCS) for the rig (e.g., including downhole equipment operatively coupled to the rig) . In another embodiment, the processor system 300 is a separately installed computing unit including a display that is installed at the rig site and receives data from the RCS. In such an embodiment, the software on the processor system 300 may be installed on the computing unit, brought to the wellsite, and installed and communicatively connected to the rig control system in preparation for constructing the well or a portion thereof.
In another embodiment, the processor system 300 may be at a location remote from the wellsite and receives the drilling data 322 over a communications medium using a protocol such as well-site information transfer specification or standard (WITS) and markup language (WITSML) . In such an embodiment, the software on the processor system 300 may be a web-native application that is accessed by users using a web browser. In such an embodiment, the processor system 300 may be remote from the wellsite where the well is being constructed, and the user may be at the wellsite or at a location remote from the wellsite.
A well plan 320 typically includes information about the direction and shape of a well to be drilled. The well plan 320 may include information about parameters and tools to use to achieve the desired shape and position. However, as the well is being drilled, the actual trajectory may deviate from the plan or unanticipated conditions may be encountered. In such instances, and others, the plan may need to be adjusted to account for changing conditions and circumstances. For example, consider a method that can call for re-planning to generate a revised well plan.
In one embodiment, a system includes a well plan component for monitoring and updating the well plan where the well plan can be in a digital format, for example, as a digital data structured stored in memory of a computing device, a computing system, etc. For example, consider a controller that includes memory that can store a well plan as a digital file or digital files. The well plan component may derive a working plan when a team takes a survey or otherwise determines a position of a well. In one embodiment, the working plan is, in effect, a spatial trajectory in multiple dimensions to construct a path from a current bit location (e.g., hole bottom position) to a next location, which can be referred to as a target, which may be an intermediate target or a final target. The construction of the path takes into account a variety of considerations. These may include, but are not limited to: the target; the allowable deviation from the original plan in terms of position and/or angular deviation; the maximum dogleg capability of the steering assembly; constraints set by the user at the beginning based on preference; allowable tortuosity, risk measures, hole quality, confidence level, etc.; and others.
The generation of the working plan may involve generating a range of trajectory candidates that satisfy a number of the different conditions specified and evaluating the candidates based on the trajectory context, different properties, constraint violations, and rank. The trajectories may be ranked according to different optimization objectives. The user may have the system present one or more of the available candidates for selection.
As an example, the path of a wellbore, or its trajectory, may be determined by acquiring direction and inclination (D&I) measurements at various points along the wellbore, which may be referred to as survey measurements or survey information. With respect to a survey, position of a wellbore (e.g., a borehole, etc. ) , can be referenced to some vertical and/or horizontal datum (e.g., a well-head position and elevation reference) . The position may be obtained using one or more inertial measurement techniques. As to azimuth, it may be considered to be a directional angular heading, for example, relative to a reference direction, such as North, at the position of measurement. As to inclination, it may be considered to be an angular deviation of a borehole from vertical, for example, with reference to the direction of gravity. As to measured depth, it may be considered to be a distance measured along a wellbore (e.g., a borehole, etc. ) from a surface location. Measured depth may include a driller’s depth, and it may also include depth correction algorithms, that account for the elastic stretching and compression of a drillstring along its length.
Directional wellbores can be drilled through earth formations along a selected trajectory. Various factors may combine to unpredictably influence the trajectory of a wellbore. It is desirable to accurately measure the wellbore trajectory in order to guide the wellbore to its geological and/or positional target. Thus, it is desirable to measure the inclination, azimuth and depth of the wellbore during wellbore operations to estimate whether the selected trajectory is being maintained.
The drilled trajectory of a wellbore may be estimated via acquisition of a wellbore or directional survey, which may be referred to herein as a survey that is not an expansive surface-based seismic survey that acquires a seismic cube of data for a volume of earth. A wellbore survey can be made up of a collection or a set of survey stations. A survey station may be generated by taking measurements used for estimation of position and/or wellbore orientation at a single position in a wellbore (e.g., a borehole, etc. ) . The act of performing these measurements and generating the survey data can be referred to as performing a survey or surveying a wellbore or a borehole.
Surveying of wellbores can be performed using downhole survey instruments (e.g., drillstring equipment) . Such instruments can include, for example, one or more orthogonal accelerometers, magnetometers and/or gyroscopes. Survey instruments may be used to measure the direction and magnitude of the local gravitational, magnetic field and/or earth spin rate vectors respectively (e.g., collectively earth vectors) . Various measurements can correspond to instrument position and orientation in a wellbore, with respect to earth vectors. As an example, wellbore position, inclination and/or azimuth may be estimated from instrument measurements.
One or more survey stations may be generated using discrete or continuous measurement modes. Discrete or static wellbore surveys can be performed by creating survey stations along a wellbore when drilling is stopped or interrupted, for example, to add additional joints or stands of drillpipe to the drillstring at the surface. Continuous wellbore surveys may relate to various measurements of the earth’s vectors and/or angular velocity of a downhole tool obtained for each wellbore segment using one or more survey instruments. Successive measurements of these vectors during drilling operations may be separated by fractions of a meter and, depending on rate of change of the vectors in drilling a wellbore, such measurements may be considered continuous or they may be considered discrete.
Fig. 4 and Fig. 5 illustrate one embodiment of a system 400 for working plan generation (e.g., a working plan generator (WPG) ) . As shown, the system 400 can include an application layer 410, a data service 412, a state estimation component 414, a trajectory generator component 416, a user runtime parameters component 418, a drill command scheduler component 420, a ranking system component 422, an active plan management component 424 and a state manager component 426.
In one embodiment, the system 400 includes the state estimation component 414 for inferring the state of a system using incoming data from the data service 412. As an example, the state manager component 426 may be configured to handle multiple parallel states for determining the effects of certain actions that a user (e.g., or machine) may want to take or that may occur and infer the state from these ‘what-if’ scenarios. In the example of Fig. 4, the trajectory manager component 416 may interface with multiple trajectory creation sources/states and manage multiple trajectory candidates.
As to the drill command scheduler component 420, it may generate hardware specific drill command sequences for each trajectory (e.g., command schedules for each trajectory) . As to the ranking system component 422, it may evaluate constraint violations and properties sort candidates according to user-defined optimization objectives. In the example of Fig. 4, the active plan manager component 424 may monitor in-progress actions and make/suggestion corrections, trigger replanning actions, and request user intervention.
In one embodiment, the trajectory evaluation and ranking approach as illustrated in Fig. 5 can evaluate constraint violations for the generated candidates; noting that it may also evaluate the cost functions for multiple candidate properties. In certain embodiments, a user can prioritize and/or weight parameters being optimized. A component may also generate a prioritized list of candidates for the user to choose from.
In one embodiment, the trajectory evaluation and ranking solver takes as input the trajectories and drill command schedules from the command scheduler; noting that it may also receive constraint configurations, constrain violation penalties, and candidate property weights. The output may be, in one embodiment, a prioritized list of candidates.
Fig. 6 shows an example of a system 600 that includes offsite equipment 601 (e.g., remote) and onsite equipment 602 (e.g., local) . As shown, the offsite equipment 601 can include a drill operations framework 610, a drill planning framework 620 and a database 630 and the onsite equipment 602 can include a controller 640 that can receive real-time data and output recommendations such as control instructions to control onsite equipment. In such an example, the drill operations framework 610 can provide for steering sheets, execution parameters, etc., and the drill plan framework 620 can provide for evaluation of steering responses and statistics. As shown, the controller 640 can output information to the drill operations framework 610 and receive information from the drill plan framework 620. The system 600 can include plan generation features for real-time plan generation during drilling operations execution phase and/or plan generation during a planning phase. The system 600 can be utilized for one or more types of drilling (e.g., rotary, mud motor, RSS, ABSS, etc. ) . The system 600 can operate loops, which can include at least one real-time loop that provides for control of equipment to perform drilling operations.
A system such as the system 600 may utilize various functions and penalties for generation of plans, which may provide for single or multiple target aiming. As explained, a plan can be generated that aims to provide for drilling operations that aim for multiple targets simultaneously. As an example, the system 600 may include one or more features of the system 400 of Figs. 4 and 5, one or more other systems described herein, etc.
Fig. 7 shows an example of a wellsite system 700, specifically, Fig. 7 shows the wellsite system 700 in an approximate side view and an approximate plan view along with a block diagram of a system 770.
In the example of Fig. 7, the wellsite system 700 can include a cabin 710, a rotary table 722, drawworks 724, a mast 726 (e.g., optionally carrying a top drive, etc. ) , mud tanks 730 (e.g., with one or more pumps, one or more shakers, etc. ) , one or more pump buildings 740, a boiler building 742, an HPU building 744 (e.g., with a rig fuel tank, etc. ) , a combination building 748 (e.g., with one or more generators, etc. ) , pipe tubs 762, a catwalk 764, a flare 768, etc. Such equipment can include one or more associated functions and/or one or more associated operational risks, which may be risks as to time, resources, and/or humans.
As shown in the example of Fig. 7, the wellsite system 700 can include a system 770 that includes one or more processors 772, memory 774 operatively coupled to at least one of the one or more processors 772, instructions 776 that can be, for example, stored in the memory 774, and one or more interfaces 778. As an example, the system 770 can include one or more processor-readable media that include processor-executable instructions executable by at least one of the one or more processors 772 to cause the system 770 to control one or more aspects of the wellsite system 700. In such an example, the memory 774 can be or include the one or more processor-readable media where the processor-executable instructions can be or include instructions. As an example, a processor-readable medium can be a computer-readable storage medium that is not a signal and that is not a carrier wave.
Fig. 7 also shows a battery 780 that may be operatively coupled to the system 770, for example, to power the system 770. As an example, the battery 780 may be a back-up battery that operates when another power supply is unavailable for powering the system 770. As an example, the battery 780 may be operatively coupled to a network, which may be a cloud network. As an example, the battery 780 can include smart battery circuitry and may be operatively coupled to one or more pieces of equipment via a SMBus or other type of bus.
In the example of Fig. 7, services 790 are shown as being available, for example, via a cloud platform. Such services can include data services 792, query services 794 and drilling services 796. As an example, the services 790 may be part of a system such as the system 600 of Fig. 6, another system described herein, etc. As an example, the services 790 can include one or more services for directional drilling, which can include, for example, a steering tendency service or services (e.g., consider a computational framework that can provide for one or more services that utilize survey information to estimate one or more steering response parameters, etc. ) .
As an example, the system 770 may be utilized to generate one or more rate of penetration drilling parameter values, which may, for example, be utilized to control one or more drilling operations.
As an example, a method can include automating operations of one or more types of downhole tools. For example, consider automating operations of one or more of mud motors, rotary steerable systems (RSSs) and at-bit steerable systems (ABSSs) . As an example, one or more of such types of equipment, systems, etc., may be implemented using one or more features of the system 200 of Fig. 2.
As an example, an ABSS can include an actuator with a pressure drop range, hold inclination and azimuth (HIA) , and dual downlinking capabilities. As an example, an ABSS can include onboard near-bit sensors that can acquire continuous six-axis inclination and azimuth measurements with a 6-ft range, and optional natural gamma ray and azimuthal images with a 9-ft range. As an example, an ABSS can include one of more features of one or more of the NEOSTEER family of ABSSs (SLB, Houston, Texas) .
As an example, a framework can provide for considering information from planning with offset analysis and adapting a hybrid model for real time execution; considering various downhole automation possibilities at a given time to optimize a recommended working trajectory execution, taking advantage of tool capabilities and minimizing unnecessary surface actions; considering real-time data information and derived tool health as well as tool state estimation at a given point in time to optimize current ongoing recommendation and recommend real time correction to handle deviations when it occurs. Such an approach can involve different computations and actions that can output an optimal recommendation, for example, for a fastest path with minimized risk based on the drilling constraints and the drilling context.
As to an optimal path recommendation, derivation can be via a WPG, for example, as explained with respect to Fig. 4 and Fig. 5, which may provide for a single-target approach and/or a multi-target approach and, for example, which may account for various factors, which may include energy, emissions, etc.
Fig. 8 shows an example of a workflow 800 that includes data acquisition, state computation, working plans generation, ranking and command scheduling and user selections. As shown, such a workflow may be implemented during drilling operations at a site. For example, data acquired can be real-time data and state computation can compute a state of where a BHA or other tool is located in a wellbore. As to working plan generation, it can answer the question of where to proceed, which can be based on a current plan, constraints and context. As explained, ranking and command scheduling can be performed where commands can be suitable for automated and/or manual execution. Recommendations from such a workflow can be rendered to one or more displays where, for example, one or more GUIs can provide for user interactions.
As explained, a working plan can be or include trajectory to construct a path from a current bit location (hole bottom (HB) point) to a next target. The construction of such a path may be performed in accordance of aiming at a target where, for example, various trajectory constraints can be considered. For example, consider one or more of the following constraints: allowable deviation from an original plan both in terms of position but also angular deviation; maximum dogleg capability of a steering assembly; recommended constraints by an automatic plan analysis that may be adjustable manually and/or automatically (e.g., according to user preferences, etc. ) ; and allowable tortuosity, risk measures, hole quality, confidence level, etc.
As explained, working plan generation can be performed using a trajectory generator (e.g., for generating multiple trajectory candidates with different conditions) and a ranking system (e.g., for evaluating each of the generated candidates based on trajectory context, different properties, constraint violations, etc. ) . In such an approach, a WPG can output a single best candidate or few top ranked candidates.
As to the ranking system, it may operate based on a list of classification items that define features selected in order to rank the candidates. For example, consider candidate properties where some examples of these properties can include: trajectory length, ROP, total steering length, toolface (TF) orientation, maximum steering ratio, average deviation from the plan, risk level, target constraints, angular deviation, tortuosity and one or more other torque and drag constraints, DDI, hole quality, tool wear, number of downlinks, geomechanics, confidence level and production level index. For each property, i, utilized (e.g., from i = 1 to I, I being a total number of properties) , a weight W_i can be defined based on trajectory context, basin location, type of client, type of rig, etc. In such an example, the weight can be associated with a cost function of the candidate to produce a total cost for each candidate trajectory as:
Above, each property, denoted i, can have a cost C_i and an associated weight W_i, which can be a context dependent weight, where a total cost for candidate properties of a candidate trajectory can be a sum, C_prop. Such a ranking system may be modular and extensible. Defining a ranking system in such a manner can facilitate adding additional candidate properties (e.g., according to mathematical and/or logical descriptions) . For example, using a machine learning approach, a system may map out from historical data how easy or difficult it was to drill a path and define a drilling difficulty index from surface automation and add it to the foregoing equation. In such an example, one or more cost functions can be optimized in a manner that can account for ease and/or difficulty of drilling. As an example, a system can optionally include a cost function that estimates greenhouse gas (GHG) emissions for each path (e.g., candidate) . In such an example, when a cost function is associated with carbon emissions or GHG emissions, a ranking system may be run in a mode (e.g., emissions mode) where weights can be selected to minimize emissions first (e.g., prior to other minimization (s) ) .
As an example, once an optimal path has been selected and steering commands to achieve the path are defined, there may be an additional optimization problem of defining a link with surface automation equipment to execute the optimal path efficiently. Such an approach can be performed in an iterative manner, for example, by deriving the optimal drilling parameters after the working plan has been generated or it may be performed simultaneously by incorporating surface automation constraints inside a ranking system (e.g., in an extensible manner, etc. ) . As an example, a system may use an artificial intelligence-based planner to determine a set of possible drilling parameters to use when a working plan has been generated.
As mentioned, an intelligent execution component may control steering commands whether it is for one or more of motor steering, RSS steering or ABSS steering. In certain embodiments, a control layer may be provided when running an RSS tool or ABSS tool (e.g., as to availability of direct downhole trajectory automation) .
As to various aspects of drilling, consider the following terms.
Rotary Steerable System (RSS) : Particular downhole tool capable of deviating the wellbore with electronic commands.
Dogleg Severity (DLS) : measure of the change in direction of a well bore over a defined length, normally measured in degrees per 100 feet of length.
Yield (Y) : the maximum DLS capability.
RealTime Yield (RT Y) : the Yield at a particular time.
ToolFace (TF) : The angle measured in a plane perpendicular to the drillstring axis that is between a reference direction on the drillstring and a fixed reference.
Desired Commands: The intended command sent to the downhole tool.
Actual Commands: The resulting command executed by the downhole tool.
ToolFace Offset (TF_O) : The angle measured between the desired TF and the actual TF.
Build Rate (BR) : the DLS projected in the vertical plane attached the tool location.
It is also the rate of change in Inclination.
Turn Rate (TR) : the DLS projected in the horizontal plane. It is also the rate of change in azimuth.
Walk Rate (WR) : the rate of change of Azimuth attached to the tool reference axis.
Steering Ratio (SR) : the percentage of time the RSS tool is spending steering (bias) vs trying to go neutral (unbias) .
BR_O and WR_O: BR and WR during neutral phase.
As an example, an automated method can estimate steering tendency parameters for a RSS during well construction execution. In such an example, parameters can include the yield (the maximum DLS capability of the steering tool) , the neutral build (the tendency to build or drop angle during neutral phase when no particular direction is privileged) , the neutral turn (the tendency to turn during neutral phase) and the toolface offset (the angular discrepancy between where we are aiming and where we end up) .
Fig. 9 shows an example of a system 900 that includes a trajectory generator 910 and a ranking system 920. As shown, the trajectory generator 910 can generate candidates and a command schedule while the ranking system 920 includes a weights and penalties block 930, a constraint evaluator block 940, a cost functions block 950 and a ranking block 960. The system 900 can generate output as indicated by an output block 970 for a sorted candidate list (e.g., ranked candidates) . As an example, the system 400 of Fig. 4 can include the ranking system 920, for example, as the ranking system 422, and can include the trajectory generator 910, for example, as the trajectory generator 416. As shown in Fig. 5, the ranking system 422 can be a system for handling ranking and constraint violations. As explained, ranking may be performed using weights, for example, a weight can be associated with a cost function of a candidate to produce a total cost for each candidate trajectory. For example, in the system 900, the weights and penalties block 930 can provide and/or generate appropriate weights, penalties (e.g., constraints) , etc.
As an example, a system can include one or more components (e.g., blocks, etc. ) that can automatically derive values of weights for a ranking system. As explained, such a ranking system may be part of or otherwise operatively coupled to a working plan generator (WPG) . As explained, such a WPG may be utilized for field operations such as, for example, directional drilling. As an example, a WPG may be part of a directional drilling advisory system.
As an example, a ranking system can utilize a technique referred to as inverse reinforcement learning (IRL) . IRL can operate by learning observed behavior from actual directional drilling (DD) operations, for example, as performed by one or more humans. An IRL approach can be used to map out human DD behaviors with respect to one or more factors such as, for example, consider one or more of particular regions, particular clients, particular formation sub-surfaces, and particular types of rigs.
IRL is a type of paradigm that can utilize Markov decision processes (MDPs) , where the goal of an apprentice agent can be to find a reward function from expert demonstrations that could explain the expert behavior.
In IRL, a goal can be to model an agent taking actions in a given environment. For example, consider a state space S (e.g., the set of states the agent and environment can be in) , an action space A (e.g., the set of actions the agent can take) , and a transition function T (s’ |s, a) , which gives the probability of moving from a state s to a state s’ when taking action a. For instance, for an AI learning to control a car, the state space may be possible locations and orientations of the car, the action space may be a set of control signals that the AI could send to the car, and the transition function may be a dynamics model for the car. In IRL, a tuple of (S, A, T) can be referred to as an MDP\R, which is a Markov decision process without a reward function. As an example, an MDP\R can have a known horizon or a discount rate γ.
An inference problem for IRL can be to infer a reward function R given an optimal policy π *: S →A for the MDP\R. In such a problem, a system can learn about the policy π*from samples (s, a) of states and the corresponding action according to π *(e.g., which may be random) . Such samples may come from a route, which records the history of the agent’s states and actions in a single episode. For example, consider the following: (a₀, s₀) , (a₁, s₁) , ... (a_N, s_N) .
In the aforementioned car example, these can correspond to the actions taken by an expert human driver who is demonstrating desirable driving behavior (e.g., where actions may be recorded as signals to a steering wheel, brakes, etc. ) .
Given the MDP\R and the observed route, the goal can be to infer the reward function R. In a Bayesian framework, if a system specifies a prior on R:
In such an example, the likelihood P (a_i|s_i, R) is πR (s) [a_i] , where πR is the optimal policy under the reward function R. Note that computing the optimal policy given the reward can be non-trivial (e.g., except in very simple cases) . As an example, a system may approximate the policy using reinforcement learning. Due to challenges that may exist in specifying priors, computing optimal policies and integrating over reward functions, IRL can implement an approximation to the Bayesian objective. An article by Piot et al., Bridging the Gap Between Imitation Learning and Inverse Reinforcement Learning, IEEE Transactions on Neural Networks and Learning Systems, 2017, 28 (8) , pp. 1814 –1826, is incorporated by reference herein.
As an example, a ranking system can utilize one or more machine learning techniques to derive appropriate values for weights to use based on observed behavior from actual directional drilling (DD) operations, for example, as performed by one or more humans and/or one or more automated system set-up on a rig.
As explained, a system can implement an automatic methodology to derive values of weights for a ranking process that can be included as part of working plan generation for a directional drilling advisor (DDA) .
Due to the complexity of various wells being drilled, substantial risk and reward scenarios exist for proper planning and execution of DD of wells. A system may aim to so-called de-skill and de-man a DD process while ensuring efficiency and consistency. As an example, a DD framework can provide for various levels of de-skilling and de-manning a DD process while ensuring efficiency and consistency. In such an example, a DDA framework can provide, in real time, optimal decisions (e.g., perform real-time optimal decision making) . As an example, a DDA framework can provide output for one or more of motors, trajectories, commands, and downlink recommendations. For example, consider a DDA framework that provides output for a RSS tool for directional drilling. Such a framework can provide output for various types of wells, for example, from start to end by automatically providing at each survey point a next sequence of actions.
A DDA framework can enable well construction with minimal human intervention and provide for monitoring and/or intervention, locally and/or remotely (e.g., at a rig or from town) . As explained, a DDA framework can include a WPG system that can determine how to construct an optimum path from a present state to one or more target objective states.
A WPG may be implemented as a system within a DDA framework (e.g., consider a RSS Advisor framework) where the WPG is in charge of deriving working plans to be followed, for example, responsive to taking a survey and updating a position of a well (e.g., a hole bottom position) .
A working plan can be, in effect, a trajectory to construct a path from a current bit location (e.g., a hole bottom position) to a next target. The construction of such a path can be accomplished in accordance with aiming for a target and optionally also by taking into account one or more trajectory constraints such as, for example: allowable deviation from an original plan in terms of position and angular deviation; maximum dogleg capability of a steering assembly; constraints set by a user at initiation (e.g., based on his/her preferences) ; allowable tortuosity; risk measures; hole quality; confidence level; ROP; carbon emissions; eco-optimal path (e.g., with minimal energy consumption) ; etc.
As explained, generation of a working plan can include trajectory generation, which may aim to generate an appropriate number of trajectory candidates different conditions, along with ranking, which can aim to evaluate each of the candidates based on one or more of a trajectory context, different properties, constraint violations, etc., to rank available candidates according to a defined optimization objective (e.g., optionally user defined) .
As to output from a ranking process (e.g., a ranking system) , output may be a single best candidate or, for example, a few best candidates that may be exposed to a user for selection, optionally using one or more techniques such as, for example, a Pareto technique to select a candidate when no single candidate of the few best candidates is substantially optimally better than another one of the few best candidates (e.g., a trade-off selection process) .
Referring again to the example system 900 of Fig. 9, such a system may be employed for RSS applications, mud motor applications and/or one or more other types of DD applications. As shown, the ranking system 920 includes a constraint evaluator block 940, which can provide for evaluating trajectory constraints and applying a penalty for each violation, and a cost functions block 950, which can provide for evaluating candidate properties and applying a cost to each property. As an example, the ranking block 960 can receive candidates and costs and sort the candidates, for example, in an order of ascending cost (e.g., ranking by cost) .
As to weight generation, which may be performed by the weights and penalties block 930 of the ranking system 920 of Fig. 9, it can generate weights that include property weights that can be utilized to sort numerous candidates.
As to examples of candidate properties and constraints, consider Table 1, below.
Table 1. Example Candidate Properties and Constraints.
As an example, for each property, a system can associate a default and/or user-defined weight W_i based on trajectory context. Such a weight can be associated with the cost function of the candidate to produce the total cost for each candidate. As an example, each constraint, with associated constraint violation k, may be associated with a constraint value denoted T_k and, in various examples, weights, denoted W_k, may be utilized for constraint values, T_k (see, e.g., Fig. 14) , and weights, denoted, P_k, may be utilized for violations of constraints k, where a cost of a violation of a constraint is denoted V_k (see, e.g., Fig. 11) . Further, in drilling engineering (DE) , performance indicators, denoted KPI_i, may be weighted using weights, denoted Z_i, for purposes of planning (e.g., generation of a well plan) (see, e.g., Fig. 11 and Fig. 13) . Such an approach to weighting can be part of an inverse reinforcement learning (IRL) workflow that can determine values for weights.
As to a weigh factor, consider an example that can utilize a user-defined weight W_i indicating importance of a property where, for example, setting W_i=0 means that property can be ignored. As an example, as to a weigh factor, a method may perform a normalization such that weights are within a desired range (e.g., 0≤W_i and W_i≤1) .
As to a cost function, consider an example that can produces a single scalar cost value C_i; normalized such that 0≤C_i and C_i≤1, where a value may exceed 1 but may be normalized to keep it at below 1; where a lower C_i indicates a lower cost for a property; and where 0 indicates an idealized solution, which may not necessarily be achievable. Such an approach may also be applied to constrain violations.
As an example, each violated constraint, k (e.g., k = 1 to K) can have an associated boundary where a penalty P_k (e.g., a weight for violation of the constraint k) can be applied for each violated constraint k. In such an example, each violated constraint can have a cost of V_k where a corresponding weight P_k can be applied. In such an example, the total property cost for each candidate can be computed as:
C_prop=∑_i C_iW_i+∑_kV_kP_k.
As to trajectory contexts, consider examples of Table 2, below.
Table 2. Examples of Trajectory Contexts.
As an example, members of trajectory contexts may be dynamic. For example, contexts may be added, deleted, changed, etc., which may be based on system feedback and/or user input.
As to examples of weights, for a set of defined contexts, a system may associate a set of default weights. As an example, such weights may be adjusted by a user, if desired or appropriate; noting that use of default weights can be recommended. Table 3, below, shows examples of properties and examples of weight values for a landing context.
Table 3. Examples of Properties and Weight Values (landing context) .
As explained, Table 3 shows examples of weight definitions for properties in a landing context. Such weights can be based on importance attached to each of the properties in the context of landing. For a different context, the weights can differ.
Table 4, below, shows examples of constraint violation types and associated penalty weight values.
Table 4. Example Violation Types and Penalty Weight Values (landing context) .
As explained, a system can act to derive an optimum path to reach one or more targets from a current hole position. In such an example, a user may want to know the optimum path to reach one or more targets given a current hole position and constraints associated with a current context. As to constraints, consider, for example, one or more of yield, allowable deviation from an original plan, attitude constraints, etc.
As an example, a function can consume hole bottom position and one or more targets as inputs and develop an optimum path to the one or more targets as an output. In such an example, inputs can include, for example, one or more of HBE, tendency, and one or more targets. In such an example, output can include one or more working plans. As an example, a configuration can include use of an original plan along with trajectory constraints and type of tool (e.g., RSS or mud motor) .
Fig. 10 shows an example of a reinforcement learning process 1000 and an example of an inverse reinforcement learning (IRL) process 1060. As explained, a reward may drive a reinforcement learning process to generate control action. As shown, the reinforcement learning process 1000 includes a reinforcement learning block 1012 that receives a dynamics model 1004 and a reward function 1008 to generate control action 1016. In contrast, the IRL process 1060 includes an inverse reinforcement learning block 1072 that receives control action 1064 and a dynamic model 1068 to generate a reward function 1076.
As explained, an IRL approach can learn from human behaviors by leveraging an IRL process. For example, consider defining a reward function as follows:
In the foregoing equation for a reward function, W_i and P_k can be unknown values for weights to be derived by an IRL process. For V_k, if a candidate does not violate a constraint k, then V_k= 0 (e.g., cost of constraint violation is zero) . However, if a candidate trajectory violates a constraint k, then V_k>0, with the value depending what extent the constraint is violated. For example, the greater the extent of a violation of a constraint, the larger the value of V_k to a point where a candidate can have very large (e.g., huge) cost; hence, such a candidate would be very unlikely to be selected at the end. As explained, P_k can be a weight that can be applied to a constraint violation k such as, for example, by multiplying P_k with a cost V_k.
As to a DDA framework, for a number of wells drilled directionally successfully, expert DD decisions can be available, which can include, for example, steering commands and drilling parameters used. Such information may be stored in a database that can be a behaviors database where the behaviors can be behaviors associated with successful DD operations. As such, historical data can be leveraged for purposes of improving a framework that includes capabilities for automated directional drilling (e.g., a DDA framework) .
Once proper weights are defined, they can be utilized by a ranking system, which can also allow for improved understanding of behavior of an automated DDA. As an example, a framework can provide for mapping human DD behaviors and/or machine DD behaviors in particular regions, related to particular clients, in particular formation sub-surfaces, for particular types of rigs, etc.
While direction drilling is mentioned, as an example, a framework may, alternatively or additionally, provide for improving planning, which may be a task that is performed by a drilling engineer. For example, one or more drilling engineers may perform drilling engineering (DE) in a manner that generates a digital well plan. As an example, a framework can provide for learning based on behaviors of one or more drilling engineers and/or one or more automated or semi-automated planners (e.g., consider a well planning framework that provides for some level of automation) .
Fig. 11 shows an example of a method 1100 that may be implemented by a framework for purposes of directional drilling (DD) and/or drilling engineering (DE) . In the example of Fig. 11, example reward equations are shown for DD and DE, which include weights. One or more of such equations may be utilized as part of an IRL process to determine weights (e.g., values of weights) .
As shown in the example of Fig. 11, the method 1100 includes a reception block 1112 for receiving a well plan for a subject well (e.g., a digital well plan) , an acquisition block 1114 for acquiring data from one or more offset wells, a performance block 1116 for performing data quality control checks, and a decision block 1118 for deciding if the data quality is acceptable. As shown, if the decision block 1118 decides that the data quality is unacceptable, the method 1100 can continue to a decision block 1120 for deciding whether the data can be refined, where if the data are not amenable to sufficient refinement, the method 1100 can proceed to a default weights block 1122 for using default weights (e.g., default values for weights) ; whereas, if the data are amenable to refinement, a refinement block 1124 may proceed to refine the data and then return to the blocks 1112 and/or 1114, as may be appropriate.
As shown in the example of Fig. 11, if the decision block 1118 decides that the data quality is acceptable, the method 1100 can continue to a filter block 1130 for filtering data by trajectory contexts, which can proceed to a mapping block 1132 for mapping out each run with planned steering tools for directional drilling of the planned well. As shown, a decision block 1134 can provide for deciding if available reward weights exist, which, if deciding that they do not exist, the method 1100 can proceed to a mapping block 1136 for mapping out human DD and/or human DE and/or autonomous system behaviors (e.g., for DD, DE, etc. ) followed by proceeding to a generation block 1138 for generating weights using an IRL technique. As shown, if the decision block 1134 decides that available reward weights exist, the method 1100 can proceed to another decision block 1140 for deciding if information for one or more additional wells is available since the last time a reward was generated. If the decision block 1140 decides that data are not available for one or more additional wells, the method 1100 can proceed to a use block 1142 for using available weights as previously generated; whereas, if the decision block 1140 decides that data are available for one or more additional wells (e.g., due to activity, availability of data in one or more data stores, etc. ) , the method 1100 can proceed to a mapping block 1144 for mapping out data for the one or more additional wells followed by proceeding to a generation block 1146 for generating weights using an IRL technique.
In the example of Fig. 11, an example of a reward function is shown that includes W_i and P_k, which can be unknown values (e.g., weight values) to be derived by an IRL technique (e.g., an IRL process) :
As explained, an IRL technique (see, e.g., the IRL process 1060 of Fig. 10) can utilize knowledge of control actions as types of behaviors (e.g., historical observations of behaviors, etc. ) that may be taken in certain contexts. Such knowledge may be from a current well and/or from one or more offset wells. As explained, a method such as the method 1100 may utilize an IRL technique to determine weights for costs of properties and weights for costs of violations of constraints. As explained, such an approach may be utilized in drilling (e.g., directional drilling (DD) ) .
In the example of Fig. 11, another equation for a reward is shown as follows:
In such an example, a performance indicator (e.g., KPI) can be denoted KPI_i and can have a corresponding value and can also have a corresponding weight, denoted Z_i in the above equation. As explained, a method such as the method 1100 may utilize an IRL technique to determine weights for performance indicators. As explained, such an approach may be utilized in planning (e.g., drilling engineering (DE) ) to generate a digital well plan, etc.
As to observations of control actions, which are observed behaviors for directional drilling of wells, consider, for example, steering commands as types of control actions (e.g., observed behaviors) . In such an example, for mud motor applications, data can indicate a sequence of slides and rotates and for the slides the toolface can be used along with the slide length; whereas, for RSS applications, data can indicate a mode used and the mode parameters. As an example, a method can include extracting drilling parameters, for example, direct and/or indirect indicators of one or more of ROP, flow rate, surface RPM, differential pressure (e.g., when using a mud motor) , etc. As explained, observations can be for decisions, whether control or other decisions, which maybe for DD and/or DE. As an example, observations can be for decisions made by a drilling engineer and/or a planning system where such observations can be utilized to improve a planning process (e.g., a planning framework, etc. ) .
Fig. 12 shows a table 1200 that includes examples of available modes and the mode parameters that are available for one or more types of RSS tools. As shown, modes can include manual, vertical, inclination hold, hold inclination and azimuth and auto curve, where such modes can be abbreviated and classified as manual or automated modes. In such an example, operation rules may be defined along with firmware constraints, mandatory inputs and optional extra inputs.
As an example, a framework can provide for automatically deriving property weights and violations weights for a ranking system that derives an optimum path from a current hole bottom position to one or more intended targets. As an example, a framework can provide for learning and mapping out human and/or machine behavior during directional drilling (DD) applications and/or during drilling engineering (DE) applications.
As an example, a framework may provide for deriving acceptable directional drilling practices related to particular basins (e.g., for DD and/or for DE) . For example, consider an analysis of weights, etc., that can determine what practices are acceptable and/or improve directional drilling for one or more contexts. Such an approach can provide for deriving good directional drilling practices related to one or more of particular regions, particular client’s preferences, particular formation sub-surfaces, particular types of rigs, and/or particular types of well profiles.
As an example, a framework can be operable to evaluate and/or improve one or more practices. As an example, a framework may remove one or more practices, for example, on the basis of lack of contribution, inefficiency, etc.
As an example, a framework can provide for deriving acceptable directional drilling practices related to particular types of wells in terms of sight mode or blind modes (e.g., optionally without measurement data from the RSS tools) and/or related to particular types of BHAs including particular drill bit behaviors.
As an example, a framework can provide for characterizing human behaviors, particularly human decision making as to control actions for directional drilling (e.g., generated by a weighted ranking system based on human behaviors) . As an example, a framework can provide for deriving reward functions using human behaviors when data scarcity exists.
Fig. 13 shows an example of a method 1300 that may be implemented by a framework. As shown, the method 1300 includes a reception block 1310 for receiving a new trajectory design task. In response, the method 1300 can proceed to one or more blocks 1312, 1314 and 1316 where the block 1312 provides for automated trajectory generation (ATD) to generate multiple trajectories satisfying given constraints and computing performance indicators (e.g., KPIs) for each trajectory, where the block 1314 can extract data from one or more relevant offset wells in one or more databases, and where the block 1316 can extract data from one or more previous versions of a well plan, if available. As shown, the method 1300 can proceed to a decision block 1320 that can decide if data quality is acceptable (e.g., data quality OK or not OK) . Where quality is acceptable, the method 1300 can proceed to a generation block 1322 for generating weights using an IRL technique where the method 1300 can then proceed to an initialization block 1324 to initialize a counter such as a counter X, which may be set to an appropriate value (e.g., 1, etc. ) . In a block 1326, which can be part of a loop with blocks 1328 and 1332, the method 1300 can recommend X candidates based on weights (e.g., noting that where X is equal to one, one candidate can be recommended) . Next, in the loop, the block 1328, a decision block, can decide whether or not to accept the recommended candidate (s) . If the decision block 1328 indicates acceptance (yes branch) , the method 1330 can save the X candidate (s) and the weights in a database; otherwise, for non-acceptance (no branch) , the method 1300 can increment the counter by an appropriate number (e.g., 10, etc. ) , and proceed to the recommendation block 1326.
Referring again to the decision block 1320, if the decision block 1320 indicates that data quality is unacceptable, the method 1300 can proceed to a block 1340 that can implement a trajectory analytical recommender, which may recommend ten or more candidates per a recommendation block 1342. A decision block 1344 can follow that decides whether the candidates are acceptable where, if so, a save block 1346 can provide for saving recommender parameters; whereas, if the candidates are unacceptable, the method 1300 can proceed to a true recommender block 1348 for recommendation of true parameters for the recommendation block 1340.
As shown in the example of Fig. 13, various tailoring options exist, including tailoring options for client, field, location, human DE preferences, types of trajectories, formations, etc.
In the example of Fig. 13, an equation for a reward is shown as follows:
In such an example, a performance indicator (e.g., KPI) can be denoted KPI_i and can have a corresponding value and can also have a corresponding weight (e.g., Z_i in the above equation, as shown in Fig. 13) . As explained, a method such as the method 1300 may utilize an IRL technique to determine weights for performance indicators.
Fig. 14 shows an example of a method 1400 that includes a reception block 1410 for receiving a new trajectory design and/or working plan generation task request. In response to such a request, the method 1400 can automatically proceed to extraction blocks 1412 and 1414 for extraction of data from relevant offset wells in a database and/or for extraction of data for one or more previous versions of one or more well plans, if available. For example, the request may pertain to an existing well plan such that data can be extracted from a prior version of that well plan (e.g., as a digital well plan that may be stored in a database) . As shown, the method 1400 can continue to an extraction block 1420 for extracting constraints from historical data, followed by a decision block 1422 that can decide if reward weights are available. In the example of Fig. 14, if the decision block 1422 decides that reward weights are available, the method 1400 can continue to a use block 1424 for using the available weights as previously generated followed by a recommendation block 1426 for recommending constraints. However, if the decision block 1422 decides that reward weights are not available, the method 1400 can enter a generation block 1428 that can generate constraints analytically, followed by a continuation to the recommendation block 1426.
As shown, given constraints, the method 1400 can proceed to a decision block 1430 that can decide whether to accept the recommended constraints. Where the decision block 1430 accepts, the method 1400 can continue to a save block 1432 to save the constraints in a database, followed by a continuation to a generation block 1440 for generating weights using an IRL technique. As shown, if the decision block 1430 decides that the constraints are not acceptable (e.g., unacceptable) , the method 1400 can continue to a manual input block 1434 for manual input of one or more constraints where the method 1400 can then continue to the save block 1432 and the generation block 1440 (e.g., generation of weights using one or more constraints entered per the block 1434) .
As an example, a constraint may be an allowable deviation from a plan (e.g., in one or more directions) as to execution of the plan (e.g., directional drilling) . As an example, a constraint may be a DLS limit for one or more portions of a trajectory.
In the example of Fig. 14, an equation for a reward is shown as follows:
As explained, a constraint can be denoted k with an associated constraint value T_k and can also have a corresponding weight (e.g., W_k in the above equation, as shown in Fig. 14) . As explained, a method such as the method 1400 may utilize an IRL technique to determine weights for constraints.
As explained, P_k are weights (e.g., for k = 1 to K, with K being a total number of constraint or constraint violations) and V_k are costs of constraint violations (e.g., k = 1 to K) . When a constraint is defined to have a value T_k, the following scenarios can exist: (1) if V_k < T_k, then no penalty is applied and the violation cost of that constraint violation k can be zero; and (2) if V_k ≥ T_k, then the violation cost of that property would be the weight P_k times the difference between V_k and T_k (e.g., V_k-T_k) . Such an approach helps to ensure that the greater the deviation from a constraint, the greater the cost of a property.
As an example, a framework can account for sustainability concerns. For example, consider carbon emissions and/or GHG emissions for each candidate being taken into account as part of a ranking system. As explained, a ranking system may have an eco-path mode that can select a most ecological path or privilege a low emission path over others. As an example, a framework can include a performance mode where a ranking system can focus on a highest ROP candidate more than others to finish a well as fast as possible. As an example, a ranking system can be evaluated with different drilling parameters where human behavior is mapped out by taking into accounts such parameters. As explained, Table 1 lists various examples of constraints.
As an example, one or more machine learning and/or artificial intelligence techniques may be utilized to derive weights of a ranking system by mapping out at least some human behaviors. While IRL is mentioned, a framework may utilize an optimization technique that can implement one or more genetic algorithms. As an example, a framework may generate weights based on an iterative technique that can start with default weights and gradually derive the weights that best mimic one or more human behaviors (e.g., consider a projection technique) .
As explained, values for weights can be applied to determine costs associated with each of a number of candidate trajectories for drilling execution and/or for well planning.
Fig. 15 shows an example of a method 1500 that can include a reception block 1510 for receiving digital well plan data for direction drilling of a borehole for a well in a subsurface geologic environment; a generation block 1520 for generating candidate trajectories for the borehole using the digital well plan data; a generation block 1530 for generating a ranking of the candidate trajectories using values derived from inverse reinforcement learning using historical observations for one or more other boreholes; and an output block 1540 for outputting, based on the ranking, one or more of the candidate trajectories for directional drilling of the borehole.
As shown in Fig. 15, the method 1500 may be implemented via one or more computer-readable media (CRM) per blocks 1511, 1521, 1531 and 1541, which may, for example, be implemented using a system such as a computing system (see, e.g., the example system 300 of Fig. 3, the example system 770 of Fig. 7, etc. ) . Such blocks can include processor-executable instructions.
As an example, a computational framework can include a solver, which may be implemented via executable instructions. For example, consider a computational framework that includes a processor and memory accessible to the processor where executable instructions can be stored in the memory and accessed for execution by the processor to cause the computational framework to perform one or more actions. Such a computational framework can include one or more interfaces for receipt of information such as survey information and/or for output of information, which can include values of parameters, an instruction, etc. As an example, a computational framework may be part of a controller. As an example, a computational framework may be part of a system (see, e.g., the computing systems of Fig. 3 and Fig. 7) .
As explained, various systems, methods, etc., can implement one or more ML models. As to types of ML models, consider one or more of a support vector machine (SVM) model, a k-nearest neighbors (KNN) model, an ensemble classifier model, a neural network (NN) model, incremental learning, Q-learning, etc. As an example, a machine learning model can be a deep learning model (e.g., deep Boltzmann machine, deep belief network, convolutional neural network, stacked auto-encoder, etc. ) , an ensemble model (e.g., random forest, gradient boosting machine, bootstrapped aggregation, AdaBoost, stacked generalization, gradient boosted regression tree, etc. ) , a neural network model (e.g., radial basis function network, perceptron, back-propagation, Hopfield network, etc. ) , a regularization model (e.g., ridge regression, least absolute shrinkage and selection operator, elastic net, least angle regression) , a rule system model (e.g., cubist, one rule, zero rule, repeated incremental pruning to produce error reduction) , a regression model (e.g., linear regression, ordinary least squares regression, stepwise regression, multivariate adaptive regression splines, locally estimated scatterplot smoothing, logistic regression, etc. ) , a Bayesian model (e.g., Bayes, average on-dependence estimators, Bayesian belief network, Gaussian Bayes, multinomial Bayes, Bayesian network) , a decision tree model (e.g., classification and regression tree, iterative dichotomiser 3, C4.5, C5.0, chi-squared automatic interaction detection, decision stump, conditional decision tree, M5) , a dimensionality reduction model (e.g., principal component analysis, partial least squares regression, Sammon mapping, multidimensional scaling, projection pursuit, principal component regression, partial least squares discriminant analysis, mixture discriminant analysis, quadratic discriminant analysis, regularized discriminant analysis, flexible discriminant analysis, linear discriminant analysis, etc. ) , an instance model (e.g., k-nearest neighbor, learning vector quantization, self-organizing map, locally weighted learning, etc. ) , a clustering model (e.g., k-means, k-medians, expectation maximization, hierarchical clustering, etc. ) , etc.
As an example, a system may utilize one or more recurrent neural networks (RNNs) . One type of RNN is referred to as long short-term memory (LSTM) , which can be a unit or component (e.g., of one or more units) that can be in a layer or layers. A LSTM component can be a type of artificial neural network (ANN) designed to recognize patterns in sequences of data, such as time series data. When provided with time series data, LSTMs take time and sequence into account such that an LSTM can include a temporal dimension. For example, consider utilization of one or more RNNs for processing temporal data from one or more sources, optionally in combination with spatial data. Such an approach may recognize temporal patterns, which may be utilized for making predictions (e.g., as to a pattern or patterns for future times, etc. ) .
As an example, the TENSORFLOW framework (Google LLC, Mountain View, California) may be implemented, which is an open source software library for dataflow programming that includes a symbolic math library, which can be implemented for machine learning applications that can include neural networks. As an example, the CAFFE framework may be implemented, which is a DL framework developed by Berkeley AI Research (BAIR) (University of California, Berkeley, California) . As another example, consider the SCIKIT platform (e.g., scikit-learn) , which utilizes the PYTHON programming language. As an example, a framework such as the APOLLO AI framework may be utilized (APOLLO. AI GmbH, Germany) . As mentioned, a framework such as the PYTORCH framework may be utilized.
As an example, a training method can include various actions that can operate on a dataset to train a ML model. As an example, a dataset can be split into training data and test data where test data can provide for evaluation. A method can include cross-validation of parameters and best parameters, which can be provided for model training.
The TENSORFLOW framework can run on multiple CPUs and GPUs (with optional CUDA (NVIDIA Corp., Santa Clara, California) and SYCL (The Khronos Group Inc., Beaverton, Oregon) extensions for general-purpose computing on graphics processing units (GPUs) ) . TENSORFLOW is available on 64-bit LINUX, MACOS (Apple Inc., Cupertino, California) , WINDOWS (Microsoft Corp., Redmond, Washington) , and mobile computing platforms including ANDROID (Google LLC, Mountain View, California) and IOS (Apple Inc. ) operating system based platforms.
TENSORFLOW computations can be expressed as stateful dataflow graphs; noting that the name TENSORFLOW derives from the operations that such neural networks perform on multidimensional data arrays. Such arrays can be referred to as “tensors” .
As an example, an ML model may be run online using cloud computation resources followed by an on-target well delivery approach that can automatically feed data to the ML model, which may be updated at a given frequency. As an example, a ML model may be run in an offline manner where a result or results may be transmitted to a planning workflow.
As an example, a method can include receiving digital well plan data for direction drilling of a borehole for a well in a subsurface geologic environment; generating candidate trajectories for the borehole using the digital well plan data; generating a ranking of the candidate trajectories using values derived from inverse reinforcement learning using historical observations for one or more other boreholes; and outputting, based on the ranking, one or more of the candidate trajectories for directional drilling of the borehole. In such an example, the values derived from inverse reinforcement learning can include values for weights where, for example, the values for the weights are applied to determine costs associated with each of the candidate trajectories for the directional drilling after commencement of the directional drilling and/or where the values for the weights are applied to determine costs associated with each of the candidate trajectories for generation of a digital well plan for the directional drilling.
As an example, historical observations can include observations of one or more of human decisions for control of directional drilling and human decisions for planning of directional drilling.
As an example, historical observations can include observations of autonomous control system decisions for control of directional drilling and/or autonomous planning system control decisions for generation of a plan for directional drilling. For example, an autonomous control system can be a computational control framework that can make at least some automated decisions and, for example, an autonomous planning system can be a computational planning framework that can make at least some automated decisions.
As an example, values derived from inverse reinforcement learning can be derived from historical observations of mud motor based directional drilling and/or derived from historical observations of rotary steerable system based directional drilling.
As an example, a method can include classifying historical observations by context from a group of predefined contexts. In such an example, the predefined contexts can include, for example, one or more of mud motor contexts and rotary steerable system contexts, a landing context, and at least one nudge context.
As an example, a method can include updating values responsive to receipt of one or more additional historical observations. For example, a computational framework may be an online framework that can access and/or receive observations from one or more operations, optionally in real-time. In such an example, observations may be for directional drilling and/or for drilling engineering. As an example, an updated value may be suitable for use in control of directional drilling and/or for planning of directional drilling (e.g., generating a digital well plan, etc. ) .
As an example, values derived via inverse reinforcement learning (IRL) can include values for weights applicable to context dependent costs and can include values for weights applicable to violations of constraints costs.
As an example, inverse reinforcement learning can include utilizing a reward function defined by a sum of context dependent costs and a sum of costs of violations of constraints for each of a number of candidate trajectories.
As an example, a method can include using one of one or more candidate trajectories for directional drilling from a current hole bottom position of a borehole to a target position for the borehole. In such an example, the method can include repeating generating for new candidate trajectories for the borehole and generating a ranking of the new candidate trajectories responsive to receipt of survey data from a downhole survey performed by downhole survey equipment in the borehole.
As an example, generating of candidate trajectories for a borehole and generating a ranking of the candidate trajectories can occur automatically responsive to receipt of survey data from a downhole survey performed by downhole survey equipment in the borehole. For example, consider a downhole survey that generates survey data that can be transmitted via telemetry from a downhole location to a surface location where a computational framework at the surface can receive the survey data and respond to receipt of the survey data automatically to generate candidate trajectories and to rank the generated candidate trajectories, which can be for directional drilling from a survey location determined using the survey data to a target location, which may be specified, for example, in a digital well plan.
As an example, a system can include one or more processors; memory accessible to at least one of the one or more processors; processor-executable instructions stored in the memory and executable to instruct the system to: receive digital well plan data for direction drilling of a borehole for a well in a subsurface geologic environment; generate candidate trajectories for the borehole using the digital well plan data; generate a ranking of the candidate trajectories using values derived from inverse reinforcement learning using historical observations for one or more other boreholes; and output, based on the ranking, one or more of the candidate trajectories for directional drilling of the borehole.
As an example, one or more non-transitory computer-readable storage media can include processor-executable instructions to instruct a computing system to: receive digital well plan data for direction drilling of a borehole for a well in a subsurface geologic environment; generate candidate trajectories for the borehole using the digital well plan data; generate a ranking of the candidate trajectories using values derived from inverse reinforcement learning using historical observations for one or more other boreholes; and output, based on the ranking, one or more of the candidate trajectories for directional drilling of the borehole.
As an example, a computer program product that can include computer-executable instructions to instruct a computing system to perform one or more methods such as one or more of the methods described herein (e.g., in part, in whole and/or in various combinations) .
The embodiments disclosed in this disclosure are to help explain the concepts described herein. This description is not exhaustive and does not limit the claims to the precise embodiments disclosed. Modifications and variations from the exact embodiments in this disclosure may still be within the scope of the claims.
Likewise, the steps described need not be performed in the same sequence discussed or with the same degree of separation. Various steps may be omitted, repeated, combined, or divided, as appropriate. Accordingly, the present disclosure is not limited to the above-described embodiments, but instead is defined by the appended claims in light of their full scope of equivalents. In the above description and in the below claims, unless specified otherwise, the term “execute” and its variants are to be interpreted as pertaining to any operation of program code or instructions on a device, whether compiled, interpreted, or run using other techniques.
Certain of the claims below may include numbered lists. The numbers are provided as an organizational tool to aid in readability. The numbers themselves do not indicate an expected order of configuration or execution or otherwise have substantive meaning. For United States applications, the claims that follow do not invoke section 112 (f) unless the phrase “means for” is expressly used together with an associated function.

Claims

A method (1500) comprising:

receiving digital well plan data for direction drilling of a borehole for a well in a subsurface geologic environment (1510) ;

generating candidate trajectories for the borehole using the digital well plan data (1520) ;

generating a ranking of the candidate trajectories using values derived from inverse reinforcement learning using historical observations for one or more other boreholes (1530) ; and

outputting, based on the ranking, one or more of the candidate trajectories for directional drilling of the borehole (1540) .
The method of claim 1, wherein the values derived from inverse reinforcement learning comprise values for weights, wherein the values for the weights are applied to determine costs associated with each of the candidate trajectories for the directional drilling after commencement of the directional drilling and/or wherein the values for the weights are applied to determine costs associated with each of the candidate trajectories for generation of a digital well plan for the directional drilling.
The method of claims 1 or 2, wherein the historical observations comprise observations of one or more of human decisions for control of directional drilling and human decisions for planning of directional drilling.
The method of any preceding claim, wherein the historical observations comprise observations of autonomous control system decisions for control of directional drilling.
The method of any preceding claim, wherein the values derived from inverse reinforcement learning are derived from historical observations of mud motor based directional drilling.
The method of any preceding claim, wherein the values derived from inverse reinforcement learning are derived from historical observations of rotary steerable system based directional drilling.
The method of any preceding claim, comprising classifying the historical observations by context from a group of predefined contexts, optionally wherein the predefined contexts comprise mud motor contexts and rotary steerable system contexts.
The method of any preceding claim, wherein the predefined contexts comprise a landing context, and/or wherein the predefined contexts comprise at least one nudge context.
The method of any preceding claim, comprising updating the values responsive to receipt of one or more additional historical observations.
The method of any preceding claim, wherein the values comprise values for weights applicable to context dependent costs and comprise values for weights applicable to violations of constraints costs.
The method of any preceding claim, wherein the inverse reinforcement learning utilizes a reward function defined by a sum of context dependent costs and a sum of costs of violations of constraints for each of the candidate trajectories.
The method of any preceding claim, comprising using one of the one or more candidate trajectories for directional drilling from a current hole bottom position of the borehole to a target position for the borehole, optionally comprising repeating the generating for new candidate trajectories for the borehole and generating a ranking of the new candidate trajectories responsive to receipt of survey data from a downhole survey performed by downhole survey equipment in the borehole.
The method of any preceding claim, wherein the generating of the candidate trajectories for the borehole and the generating the ranking of the candidate trajectories occurs automatically responsive to receipt of survey data from a downhole survey performed by downhole survey equipment in the borehole.
A system (300) comprising:

one or more processors (302) ;

memory (304) accessible to at least one of the one or more processors;

processor-executable instructions (312) stored in the memory and executable to instruct the system to:

receive digital well plan data for direction drilling of a borehole for a well in a subsurface geologic environment (1511) ;

generate candidate trajectories for the borehole using the digital well plan data (1521) ;

generate a ranking of the candidate trajectories using values derived from inverse reinforcement learning using historical observations for one or more other boreholes (1531) ; and

output, based on the ranking, one or more of the candidate trajectories for directional drilling of the borehole (1541) .
A computer program product that comprises computer-executable instructions to instruct a computing system to perform a method according to any of claims 1 to 13.