Directional drilling frame

Abstract

A system and method may include receiving real-time downhole data from one or more sensors of a drill string disposed in a borehole in a subterranean geological region during a directional drilling operation. The system and method also include selecting a drill string drilling mode from a plurality of drill string drilling modes. The systems and methods may additionally include predicting, in real-time, characteristics of the bottom hole of the borehole using the drilling pattern model and at least a portion of the real-time downhole data. The system and method may also include using one or more characteristics to control directional drilling operations.

Description

[0001] Cross-reference paragraphs

[0002] This application claims the benefit of U.S. non-provisional application No. 18 / 451288 entitled “DIRECTIONAL DRILLING FRAMEWORK”, filed on August 17, 2023, the disclosure of which is incorporated herein by reference. Background Technology

[0003] A reservoir can be a subsurface stratum that can be characterized at least in part by its porosity and fluid permeability. As an example, a reservoir can be part of a basin, such as a sedimentary basin. A basin can be a depression in which sediments accumulate (e.g., caused by plate tectonics, subsidence, etc.). As an example, when source rocks are present in combination with appropriate burial depth and duration, petroleum systems can be developed within a basin, which can form reservoirs containing hydrocarbon fluids (e.g., oil, gas, etc.).

[0004] In oil and gas exploration, interpretation involves analyzing data to identify and locate various subsurface structures (e.g., stratigraphy, faults, geological bodies, etc.) within a geological environment. Various types of structures (e.g., formations) can indicate hydrocarbon traps or flow channels, and may be associated with one or more reservoirs (e.g., fluid reservoirs). In the field of resource extraction, enhanced interpretation can allow for the construction of more accurate models of subsurface areas, which in turn improves the characterization of these areas for resource extraction purposes. The characterization of one or more subsurface areas within a geological environment can guide the execution of, for example, one or more operations (e.g., field operations, etc.). As an example, a more accurate model of a subsurface area can allow for more accurate drilling operations regarding the borehole trajectory, where the borehole will have a trajectory penetrating reservoirs, etc., through which fluids can be generated (e.g., as well completions, etc.). As an example, one or more computational frameworks and / or one or more devices can be used to perform one or more workflows, said devices including features for planning, analysis, acquisition, model building, control, etc., for exploration, interpretation, drilling, fracturing, production, etc. Summary of the Invention

[0005] The method may include receiving real-time downhole data from one or more sensors on a drill string positioned in a borehole in a subsurface geological area during a directional drilling operation, wherein the drill bit of the drill string breaks up rock in the subsurface geological area to extend the borehole. The method may also include selecting a drill string drilling mode from a plurality of drill string drilling modes. The drill string drilling mode may include an associated drilling mode model for the directional drilling operation. The method may additionally include using the drilling mode model and at least a portion of the real-time downhole data to predict bottom-hole characteristics in real time. The method may also include using one or more of these characteristics to control the directional drilling operation. Various other apparatuses, systems, methods, etc., are also disclosed.

[0006] This summary is provided to introduce some concepts that will be further described in the following detailed description. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to help limit the scope of the claimed subject matter. Attached Figure Description

[0007] The following detailed description refers to the accompanying drawings. The convenient features and advantages of the described embodiments can be more easily understood by referring to the following description taken in conjunction with the accompanying drawings.

[0008] Figure 1 An example of the system is shown;

[0009] Figure 2 An example of the system is shown;

[0010] Figure 3 An example of the system is shown;

[0011] Figure 4 An example of the system is shown;

[0012] Figure 5 An example of the system is shown;

[0013] Figure 6 An example of the system is shown;

[0014] Figure 7 An example of the system is shown;

[0015] Figure 8 An example of the workflow is shown;

[0016] Figure 9 An example of the system is shown;

[0017] Figure 10 An example of a drill string is shown;

[0018] Figure 11 An example of a drilling pattern is shown;

[0019] Figure 12An example of a frame is shown;

[0020] Figure 13 An example of the method is shown;

[0021] Figure 14 An example of the method is shown;

[0022] Figure 15 Examples of adaptive filters and predictors are shown;

[0023] Figure 16 An example of a graphical user interface is shown;

[0024] Figure 17 An example of a plot showing bottom-hole characteristics is shown; and

[0025] Figure 18 An example of the method is shown. Detailed Implementation

[0026] This description should not be considered limiting, but rather is made solely for the purpose of describing the general principles of the embodiments. The scope of the described embodiments should be determined with reference to the published claims.

[0027] Figure 1 An example of a system 100 is shown, including a workspace framework 110 that can provide instantiation, rendering, and interaction with a graphical user interface (GUI) 120. Figure 1 In the example, GUI 120 may include graphical controls for a computing framework (e.g., an application, etc.) 121, a project 122, a visualization feature 123, one or more other features 124, data access 125, and data storage 126.

[0028] exist Figure 1 In the example, the workspace framework 110 can be customized for a specific geological environment (such as example geological environment 150). For example, geological environment 150 may include layers (e.g., strata) containing reservoir 151 and intersecting with fault 153. As an example, geological environment 150 may be equipped with various sensors, detectors, actuators, etc. For example, device 152 may include communication circuitry configured to receive and transmit information about one or more networks 155. Such information may include information associated with downhole device 154, which may be a device for acquiring information, assisting in resource recovery, etc. Other devices 156 may be located remotely from the well site and include sensing, detection, transmission, or other circuitry. Such devices may include storage and communication circuitry for storing and transmitting data, instructions, etc. As an example, one or more satellites may be provided for communication, data acquisition, and other purposes. For example, Figure 1The satellite is shown communicating with a network 155 that can be configured for communication. Note that the satellite may additionally or alternatively include circuitry for imaging (e.g., spatial, spectral, temporal, radiometric, etc.).

[0029] Figure 1 The geological environment 150 is also shown as optionally including equipment 157 and 158 associated with a well, the well comprising a substantially horizontal portion that may intersect with one or more fractures 159. For example, consider a well in a shale formation, which 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 laterally extending reservoir. In such an example, there may be lateral variations in properties, stresses, etc., where assessment of such variations can aid in planning, operations, etc., to develop the laterally extending reservoir (e.g., through fracturing, injection, extraction, etc.). As an example, equipment 157 and / or 158 may include components, a system, multiple systems, etc., for fracturing, seismic sensing, seismic data analysis, assessment of one or more fractures, etc.

[0030] exist Figure 1 In the examples, GUI 120 shows some examples of computing frameworks, including DRILLPLAN, DRILLOPS, PETREL, TECHLOG, PETROMOD, ECLIPSE, PIPESIM, and INTERSECT frameworks (SLB, Houston, Texas).

[0031] The DRILLPLAN framework provides digital well construction planning and includes features for automating repetitive tasks and validating workflows, enabling the rapid generation of improved quality drilling procedures (e.g., digital drilling plans) while ensuring consistency.

[0032] The DRILLOPS framework enables the execution of digital drilling plans and ensures plan adherence, while providing goal-based automation. The DRILLOPS framework can automatically generate activity plans for individual operations, whether they are monitored and / or controlled on the drilling rig or in town. Automation can leverage data analytics and learning systems to assist and optimize tasks, such as setting the ROP (Recovery Point of Operation) for the drill stand. Preset menus for automatable drilling tasks can be presented, and using data analytics and models, plans can be executed in a manner that achieves specified objectives, where, for example, measurements can be used for calibration. The DRILLOPS framework provides the flexibility to dynamically modify and replan activities, for example, based on real-time assessments of various factors, such as equipment, personnel, and supplies. Well construction activities (e.g., tripping, drilling, cementing, etc.) can be continuously monitored and dynamically updated using feedback from operational activities. The DRILLOPS framework can provide various levels of automation based on planning and / or replanning (e.g., via the DRILLPLAN framework), feedback, etc.

[0033] The PETREL framework can be part of the DELFI environment for use in earth sciences and geoengineering, for example, analyzing subsurface data from exploration to fluid production from reservoirs. 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.

[0034] The PETREL framework provides components that allow for the optimization of various exploration, development, and production operations. The PETREL framework includes seismic-to-simulation software components that can output information for improving reservoir performance, for example, by increasing asset team productivity. By using such a framework, various professionals (e.g., geophysicists, geologists, and reservoir engineers) can develop collaborative workflows and integrate operations to streamline processes (e.g., regarding one or more geological environments). Such a framework can be considered an application (e.g., executable using one or more devices) and can be considered a data-driven application (e.g., where data is input for modeling, simulation, etc.).

[0035] The TECHLOG framework can handle and process field and laboratory data from various geological environments (e.g., deepwater exploration, shale, etc.). The TECHLOG framework can construct wellbore data for analysis, planning, and other purposes.

[0036] The PETROMOD framework provides petroleum system modeling capabilities, allowing the combination of one or more seismic, well, and geological information to model the evolution of sedimentary basins. The PETROMOD framework can predict whether and how reservoirs become hydrocarbon-rich, including the source and timing of hydrocarbon generation, migration routes, quantities, and hydrocarbon types under subsurface or surface conditions.

[0037] The ECLIPSE framework provides numerical solutions for reservoir simulators (e.g., as a computational framework) to quickly and accurately predict the dynamic behavior of various types of reservoirs and development scenarios.

[0038] The INTERSECT framework provides a high-resolution reservoir simulator for simulating detailed geological features and quantifying uncertainties. For example, by creating accurate production scenarios and integrating precise models of surface facilities and field operations, the INTERSECT framework can produce reliable results that are continuously updated through real-time data exchange (e.g., from one or more types of data acquisition devices in the field that can acquire data during one or more types of field operations). The INTERSECT framework can provide completion configurations for complex wells that can be built in the field, detailed enhanced oil recovery (EOR) formulations that can be implemented in the field, analysis of the application of steam injection and other thermal EOR technologies for field implementation, advanced production control in reservoir connectivity and flexible field management, and the flexibility to write custom solutions to improve modeling and field management control. Like other example frameworks, the INTERSECT framework can be used as part of the DELFI environment, for example, for rapid simulation of multiple concurrent scenarios. For example, workflows can leverage one or more of the reservoir simulation features in the DELFI environment on demand.

[0039] The aforementioned DELFI environment provides workflows with various features related to underground analysis, planning, construction, and production, as illustrated in workspace frame 110. Figure 1 As shown, the output from the workspace frame 110 can be used to guide, control, or otherwise manage one or more processes in the geological environment 150, and the feedback 160 can be received via one or more interfaces in one or more forms (e.g., data on operating conditions, equipment conditions, environmental conditions, etc.).

[0040] As an example, the workflow can proceed to a geological and geophysical (“G&G”) service provider, which can generate well trajectories that may involve the execution of one or more G&G frameworks (e.g., consider the PETREL framework, etc.).

[0041] exist Figure 1In the example, visualization feature 123 can be implemented via workspace framework 110, for example, to perform one or more tasks associated with subsurface areas, planned operations, construction of wells and / or surface fluid networks, and production from reservoirs.

[0042] As an example, a visualization feature can provide visualizations of various Earth models, properties, etc., in one or more dimensions. As an example, a visualization feature can provide rendering of information in multiple dimensions, which may optionally include multi-resolution rendering. In such an example, the rendered information may be associated with one or more frames and / or one or more data stores. As an example, a visualization feature may include one or more control features for controlling equipment, which may include, for example, field equipment capable of performing one or more field operations. As an example, a workflow may utilize one or more frames to generate information that can be used to control one or more types of field equipment (e.g., drilling equipment, cable equipment, fracturing equipment, etc.).

[0043] Regarding reservoir models potentially suitable for simulator use, consider the acquisition of seismic data through reflection seismology, which can be used in geophysics, for example, to estimate the characteristics of subsurface strata. As an example, reflection seismology can provide seismic data representing elastic energy waves (e.g., emitted by P-waves and S-waves, in a frequency range of approximately 1 Hz to approximately 100 Hz). Seismic data can be processed and interpreted, for example, to better understand the composition, fluid content, extent, and geometry of subsurface rocks. Such interpretation results can be used to plan, simulate, execute, etc., one or more operations for producing fluids from a reservoir (e.g., reservoir rocks, etc.).

[0044] As an example, the model can be a simulated version of a geological environment. As an example, the simulator can include features for simulating physical phenomena in a geological environment, at least in part, based on one or more models. A simulator, such as a reservoir simulator, can simulate fluid flow in a geological environment, at least in part, based on a model that can be generated via a framework receiving seismic data. The simulator can be a computerized system (e.g., a computing system) that can use one or more processors to execute instructions to solve a set of equations describing physical phenomena subject to various constraints. In such an example, the set of equations can be spatially defined (e.g., numerically discretized) according to a spatial model including rock layers, geological bodies, etc., having corresponding locations that can be interpreted based on seismic and / or other data. The spatial model can be a cell-based model, where cells are defined by a grid (e.g., a mesh). Cells in a cell-based model can represent physical regions or volumes in a geological environment, where cells can be assigned physical properties (e.g., permeability, fluid properties, etc.) that may be closely related to one or more physical phenomena (e.g., fluid volume, fluid flow rate, pressure, etc.). The reservoir simulation model can be a cell-based spatial model.

[0045] Although Figure 1Several simulators are shown in the examples, but additionally or alternatively, one or more other simulators may be used. For example, consider the VISAGE geomechanical simulator (SLB, Houston, Texas) or the PIPESIM network simulator (SLB, Houston, Texas). The VISAGE simulator includes a finite element numerical solver that provides simulation results such as compaction and settlement of the geological environment, well and completion integrity of the geological environment, caprock and fault sealing integrity of the geological environment, fracture behavior of the geological environment, heat recovery of the geological environment, CO2 treatment, etc. The PIPESIM simulator includes a solver that provides simulation results such as multiphase flow results (e.g., from reservoir to wellhead and beyond), flow pipeline and surface facility performance, etc. The PIPESIM simulator can be integrated with, for example, the AVOCET production operations framework (SLB, Houston, Texas). As an example, one or more reservoirs can be simulated with respect to one or more enhanced recovery technologies (e.g., thermal processes such as steam-assisted gravity drainage (SAGD)). As an example, the PIPESIM simulator can be an optimizer that can optimize one or more operational scenarios, at least in part, through the simulation of physical phenomena. The MANGROVE simulator (SLB, Houston, Texas) provides optimization for production enhancement designs (e.g., production enhancement operations such as hydraulic fracturing) in reservoir-centric environments. The MANGROVE framework can combine scientific and experimental work to predict the geomechanical propagation of hydraulic fractures, the reactivation of natural fractures, and production predictions in 3D reservoir models (e.g., production from reservoir drainage areas where fluids move into and / or out of the well through one or more types of fractures). The MANGROVE framework can provide results relating to the heterogeneous interactions between hydraulic and natural fracture networks, which can help optimize the number and location of fracture treatment stages (e.g., production enhancement processes) to, for example, improve perforation efficiency and recovery.

[0046] As an example, tools can be positioned to acquire information within a portion of the borehole. Analysis of this information can reveal voids, dissolution surfaces (e.g., dissolution along bedding planes), stress-related features, dip events, and so on. As an example, tools can acquire information that helps characterize fractured reservoirs, optionally where fractures can be natural and / or man-made (e.g., hydraulic fractures). Such information can aid in well completion, production enhancement treatments, and so on. As an example, a framework such as the TECHLOG framework described above can be used to analyze the information acquired by the tools.

[0047] As an example, a workflow can utilize one or more types of data from one or more processes (e.g., formation modeling, basin modeling, well completion design, drilling, production, injection, etc.). As an example, one or more tools can provide data that can be used in one or more workflows that can implement one or more frameworks (e.g., PETREL, TECHLOG, PETROMOD, ECLIPSE, etc.).

[0048] exist Figure 1 In the example, drilling can be performed in geological environment 150, for example, to access reservoir 151, which can be accessed from land or sea. Figure 1 In this configuration, downhole equipment 154 may be, for example, part of a bottom hole assembly (BHA). The BHA is used for drilling. Downhole equipment 154 can transmit information to equipment at the surface. Downhole equipment 154 can receive instructions and information from equipment at the surface. During the well construction process, various operations (such as cementing, cable assessment, testing, etc.) can be performed. In such embodiments, data collected by tools and sensors and used for purposes such as reservoir characterization can be collected and transmitted.

[0049] A well may include a substantially horizontal portion (e.g., a transverse portion) that may intersect one or more fractures. For example, a well in a shale formation may pass through natural fractures, man-made fractures (e.g., hydraulic fractures), or a combination thereof. Such wells can be constructed using directional drilling techniques as described herein. However, these same techniques can be used in conjunction with other types of directional wells (e.g., inclined wells, S-shaped wells, deep inclined wells, etc.) and are not limited to horizontal wells.

[0050] Figure 2 An example of a well site system 200 is shown (e.g., at a well site that may be onshore or offshore). As shown, the well site system 200 may include: a mud tank 201 for containing mud and other materials (e.g., the mud may be drilling fluid); a suction line 203 that serves as the inlet for a mud pump 204 to pump mud from the mud tank 201, allowing the mud to flow to a vibratory hose 206; a winch 207 for winding one or more drill lines 212; a riser 208 that receives mud from the vibratory hose 206; and a kelly hose 209 that receives mud from the riser 208. Mud; one or more gooseneck pipes 210; traveling block 211; overhead crane 213 for carrying the traveling block 211 via one or more drill ropes 212; derrick 214; kelly 218 or top drive 240; kelly drive bushing 219; rotary table 220; drill rig 221; bell sub 222; one or more blowout preventers (BOPs) 223; drill string 225; drill bit 226; casing head 227; and flow pipe 228 for conveying mud and other materials to, for example, mud tank 201.

[0051] exist Figure 2 In the exemplary system, a borehole 232 is formed in the underground formation 230 by rotary drilling; note that various example embodiments may also use one or more directional drilling techniques, devices, etc.

[0052] like Figure 2 As shown in the example, drill string 225 is suspended within borehole 232 and has drill string assembly 250, which includes drill bit 226 at its lower end. As an example, drill string assembly 250 may be a bottom hole assembly (BHA).

[0053] The well site system 200 can provide operation of the drill string 225 and other operations. As shown, the well site system 200 includes a traveling block 211 and a derrick 214 positioned above the borehole 232. As described above, the well site system 200 may include a rotary table 220 through which the drill string 225 passes.

[0054] like Figure 2 As illustrated in the example, the well site system 200 may include a crisscross drill pipe 218 and associated components, or a top drive 240 and associated components. Regarding the crisscross drill pipe example, the crisscross drill pipe 218 may be a square or hexagonal metal / alloy bar with holes drilled in it to serve as a mud flow path. The crisscross drill pipe 218 can be used to transmit rotational motion from the rotary table 220 to the drill string 225 via a crisscross drill pipe drive bushing 219, while allowing the drill string 225 to be lowered or raised during rotation. The crisscross drill pipe 218 may pass through the crisscross drill pipe drive bushing 219, which may be driven by the rotary table 220. As an example, the rotary table 220 may include a main bushing operatively coupled to the crisscross drill pipe drive bushing 219, such that rotation of the rotary table 220 can rotate the crisscross drill pipe drive bushing 219 and thus rotate the crisscross drill pipe 218. The square drill pipe drive bushing 219 may include an internal profile that matches the external profile (e.g., square, hexagonal, etc.) of the square drill pipe 218; however, it has a slightly larger size so that the square drill pipe 218 can move freely up and down within the square drill pipe drive bushing 219.

[0055] Regarding the top drive example, top drive 240 can provide functionality performed by the kauri and rotary table. Top drive 240 can rotate drill string 225. As an example, top drive 240 may include one or more motors (e.g., electric and / or hydraulic) connected via suitable transmissions to a short section of tubing called a casing shaft, which can in turn screw into a protective joint or the drill string 225 itself. Top drive 240 can be suspended on traveling block 211, so the rotating mechanism can move freely up and down along derrick 214. As an example, top drive 240 may allow drilling to be performed using more joint stands than the kauri / rotary table method.

[0056] exist Figure 2 In this example, mud tank 201 can contain mud, which can be one or more types of drilling fluid. As an example, a wellbore can be drilled to generate fluid, inject fluid, or both (e.g., hydrocarbons, minerals, water, etc.).

[0057] exist Figure 2 In the example, drill string 225 (e.g., including one or more downhole tools) may consist of a series of pipes threaded together to form a long tube with a drill bit 226 at its lower end. As drill string 225 advances into the wellbore for drilling, at some point before or concurrent with drilling, mud may be pumped by pump 204 from mud tank 201 (e.g., or other source) via lines 206, 208, and 209 to a port of kelly 218, or, for example, to a port of top drive 240. The mud may then flow through channels (e.g., or multiple channels) in drill string 225 and out of the port located on drill bit 226 (see, for example, directional arrows). As the mud exits drill string 225 through the port in drill bit 226, it may then circulate upwards through an annular region between the outer surface of drill string 225 and the surrounding wall (e.g., open borehole, casing, etc.), as indicated by the directional arrows. In this way, the mud lubricates the drill bit 226 and carries heat energy (e.g., friction or other energy) and formation cuttings to the surface, where the mud (e.g., and cuttings) can be returned to the mud tank 201, for example for recycling (e.g., by treatment to remove cuttings, etc.).

[0058] The mud pumped into the drill string 225 by pump 204 forms a mud cake lining the wellbore after leaving the drill string 225. This reduces friction between the drill string 225 and the surrounding walls (e.g., borehole, casing, etc.), among other functions. This reduced friction facilitates the advance or retraction of the drill string 225. During drilling operations, the entire drill string 225 can be pulled out of the wellbore and optionally replaced, for example, with a new or sharper drill bit, a smaller diameter drill string, etc. As described above, the action of pulling the drill string out of the hole or putting it back into the hole is called tripping in or out. Depending on the direction of tripping in or out, tripping in or out can be referred to as tripping up, tripping outward, tripping down, or tripping inward.

[0059] As an example, consider drilling downwards, where, when the drill bit 226 of the drill string 225 reaches the bottom of the wellbore, mud is pumped to lubricate the drill bit 226 so that drilling can enlarge the wellbore. As described above, the mud can be pumped by pump 204 into the channels of the drill string 225, and while filling the channels, the mud can be used as a transmission medium for energy, for example, energy that can encode information as in mud pulse telemetry.

[0060] As an example, a mud pulse telemetry device may include a downhole device configured to realize pressure changes in the mud to generate one or more acoustic waves that can modulate information. In such an example, information from downhole equipment (e.g., one or more modules of drill string 225) can be transmitted to a surface device, which can relay such information to other devices for processing, control, etc.

[0061] As an example, the telemetry device can operate via energy transmission through the drill string 225 itself. For example, consider a signal generator that transmits coded energy signals to the drill string 225 and a repeater that can receive such energy and repeat it to further transmit coded energy signals (e.g., information, etc.).

[0062] As an example, drill string 225 may be equipped with telemetry device 252, which includes: a rotatable drive shaft; a turbine impeller mechanically coupled to the drive shaft such that 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 rotation of the modulator rotor; a modulator stator mounted adjacent to or near the modulator rotor such that rotation of the modulator rotor relative to the modulator stator generates pressure pulses in the mud; and a controllable brake for selectively braking the rotation of the modulator rotor to modulate the pressure pulses. In such an example, an alternator may be coupled to the aforementioned drive shaft, wherein the alternator includes at least one stator winding electrically connected to a control circuit to selectively short-circuit at least one stator winding to electromagnetically brake the alternator, thereby selectively braking the rotation of the modulator rotor to modulate the pressure pulses in the mud.

[0063] exist Figure 2 In one example, the well-ground control and / or data acquisition system 262 may include circuitry to sense pressure pulses generated by the telemetry device 252, and, for example, transmit the sensed pressure pulses or information derived therefrom for processing, control, etc.

[0064] The component 250 shown in the example includes various modules 254, 256, and 258, which may be or include a logging-while-drilling (LWD) module (e.g., an LWD tool), a measurement-while-drilling (MWD) module (e.g., a MWD tool), and / or one or more other modules. As an example, module 260 may be or include a rotary steerable system (RSS) (e.g., an RSS or RSS tool) and / or a motor (e.g., a mud motor, etc.). In various examples, the drill string may include an RSS tool, a mud motor, or both an RSS tool and a mud motor. As shown, component 250 includes a drill bit 226. Such components or modules may be referred to as tools, and the drill string may include multiple tools.

[0065] As for RSS, it relates to techniques used in directional drilling. Directional drilling involves drilling into the ground to create an skewed hole, such that the hole's trajectory is not vertical; instead, the trajectory deviates from the vertical along one or more sections of the hole. As an example, consider a target located at a lateral distance from the ground location where the drilling rig can be placed. In such an example, the borehole could begin at a vertical section and then deviate from that section, so that the hole is aimed at the target and eventually reaches it. Directional drilling can be implemented where the target may not be accessible from a vertical position on the Earth's surface, where there are materials in the Earth that could hinder drilling or otherwise harm it (e.g., consider salt domes), where the formation extends laterally (e.g., consider relatively thin but laterally extending reservoirs), where multiple boreholes need to be drilled from a single surface borehole, where a decompression well is required, etc.

[0066] One approach to directional drilling involves mud motors; however, mud motors can present several challenges depending on factors such as the rate of penetration (ROP) and the transfer of weight to the drill bit due to friction (e.g., pressure on drill bit, WOB). A mud motor can be a positive displacement motor (PDM) that operates to drive the drill bit (e.g., during directional drilling). The PDM operates as drilling fluid is pumped through it, converting the hydraulic power of the drilling fluid into mechanical power to rotate the drill bit.

[0067] As an example, a mud motor (e.g., a PDM) can operate in different modes, which may include a rotary mode and a sliding mode. The sliding mode involves drilling with a mud motor that rotates the drill bit downhole without rotating the drill string from the surface. This operation can be performed when the BHA is already equipped with a bent-end or bent-shell mud motor, or both, for directional drilling. Sliding can be used to build and control or adjust the hole angle. In directional drilling, the pointing of the drill bit can be achieved by a bent-end and a measuring device for determining the direction of offset, which can have a relatively small angular offset from the axis of the drill string. Without rotating the drill string, the drill bit can rotate with the flow of mud through the mud motor to drill in the direction it is pointing. With a steerable motor, the entire drill string can be rotated to drill in a straight line rather than at an angle when the desired wellbore orientation is obtained. By controlling the amount of hole drilled in sliding mode versus the amount drilled in rotary mode, the wellbore trajectory can be controlled quite precisely.

[0068] As an example, PDM can combine rotary mode operation, where the drill string bit is rotated by rotating the entire drill string using surface equipment (e.g., rotary table, top drive, etc.), and the drill string bit is rotated using drilling fluid. In this example, the surface RPM (SRPM) can be determined using surface equipment, and the downhole RPM of the mud motor can be determined using various factors related to drilling fluid flow rate, mud motor type, etc. As an example, in combined rotary mode, assuming the SRPM and mud motor RPM are in the same direction, the bit RPM can be determined or estimated as the sum of the SRPM and mud motor RPM.

[0069] As an example, when the drill string is not rotating from the surface (e.g., as in rotary mode), the PDM mud motor can operate in a so-called slippery mode. In such an example, the drill bit RPM can be determined or estimated based on the mud motor's RPM. As an example, the drill string including the mud motor can be oscillated using a surface mechanism (e.g., a top drive). In this example, the top drive can cause the drill string to oscillate clockwise and counterclockwise as drilling fluid drives the mud motor to rotate. In such an example, one or more techniques can be employed to control the drilling direction (e.g., drill bit orientation), the degree of oscillation, etc. Because the oscillation involves clockwise and counterclockwise motion, this oscillation is not the rotation used in rotary drilling.

[0070] RSS (Resistant Side Controller) allows for directional drilling in the presence of continuous rotation from surface equipment, which can mitigate slippage of the steerable motor (e.g., PDM). RSS can be deployed during directional drilling (e.g., deviated, horizontal, or extended reach wells). RSS can be designed to minimize interaction with the borehole wall, which can help maintain borehole quality. RSS may be designed to apply a relatively consistent lateral force, similar to a stabilizer rotating with the drill string, or to orient the drill bit in the desired direction while rotating continuously at the same rate as the drill string.

[0071] Module 254 may be an LWD module, which can be housed in a suitable type of drill collar and may contain one or more logging tools of a selected type. It should also be understood that more than one LWD module and / or one MWD module may be employed, for example, as represented by module 256 of drill string assembly 250. When referring to the location of an LWD module, by way of example, it may refer to the module located at the position of module 254, module 256, etc. An LWD module may include capabilities for measuring, processing, and storing information, as well as for communicating with surface equipment. In the example shown, module 254 may include a seismic measurement device.

[0072] In the case that module 256 is an MWD module (e.g., an MWD tool), it can be housed in a suitable type of drill collar and may contain one or more devices for measuring the characteristics of drill string 225 and drill bit 226. As an example, an MWD tool may include devices for generating electricity, for example, to power various components of drill string 225. As an example, an MWD tool may include telemetry device 252, for example, where one or more turbine impellers can generate electricity via mud flow; it should be understood that other power sources and / or battery systems may be used to power the various components. As an example, module 256 may include one or more measuring devices of the following types: drill pressure measuring device, torque measuring device, vibration measuring device, impact measuring device, stick-slip measuring device, direction measuring device, and tilt measuring device.

[0073] Figure 2 Some examples of the types of holes that can be drilled are also shown. For example, consider inclined hole 272, S-shaped hole 274, deep inclined hole 276, and horizontal hole 278.

[0074] As an example, drilling operations may include directional drilling, where, for example, at least a portion of the well includes a curved axis. For instance, consider defining a radius of curvature where the inclination relative to the vertical direction can vary up to an angle between approximately 30 degrees and approximately 60 degrees, or, for example, an angle of approximately 90 degrees or possibly greater than approximately 90 degrees.

[0075] As an example, directional wells can include several shapes, each designed to meet specific operational requirements. As an example, when information is relayed to a drilling engineer, that information can be used to perform the drilling process. As an example, the inclination and / or direction can be modified based on information received during the drilling process.

[0076] As an example, borehole deviation can be achieved in part by using downhole motors and / or turbines. Regarding motors, for example, the drill string may include a positive displacement motor (PDM).

[0077] As an example, the system can be a maneuverable system and includes equipment for performing methods such as geological steering. As mentioned above, the steerable system can be or include an RSS (Resistant Steering System). As an example, the steerable system can include a PDM (Precision Damping Device) or turbine located on the lower portion of the drill string, just above the drill bit, where a bend can be mounted. As an example, above the PDM, an MWD (Modulation-Driven Drilling) device and / or LWD (Low-Distance Driving) device can be mounted to provide real-time or near-real-time data of interest (e.g., inclination, direction, pressure, temperature, actual weight on the drill bit, torque stress, etc.). For the latter, the LWD device can transmit various types of data of interest to the surface, including, for example, geological data (e.g., gamma-ray logging, resistivity, density, and sonic logging, etc.).

[0078] Sensors that provide real-time or near-real-time information about the well trajectory, coupled with one or more logs, such as those characterizing strata from a geological perspective, can enable geologically guided approaches. These approaches can include navigating subsurface environments, for example, to follow a desired route to one or more desired targets.

[0079] As an example, a drill string may include an azimuth density neutron (ADN) tool for measuring density and porosity; a MWD tool for measuring dip, azimuth, and impact; a compensated dual resistivity (CDR) tool for measuring resistivity and gamma-ray related phenomena; one or more variable diameter stabilizers; one or more bend joints; and a geological guidance tool that may include a motor and, optionally, devices for measuring and / or responding to one or more of dip, resistivity, and gamma-ray related phenomena.

[0080] As an example, geological steering can include intentional directional control of a wellbore based on the results of downhole geological logging measurements in a manner aimed at keeping the directional wellbore within a desired area, zone (e.g., production area), etc. As an example, geological steering can include guiding the wellbore to keep it within a specific portion of the reservoir, for example, to minimize gas and / or water breakthrough, and for example, to maximize economic production from the well that includes the wellbore.

[0081] Refer again Figure 2 Well site system 200 may include one or more sensors 264 operatively coupled to control and / or data acquisition system 262. As an example, one or more sensors may be located at a surface location. As an example, one or more sensors may be located at a downhole location. As an example, one or more sensors may be located at one or more remote locations not within approximately one hundred meters of well site system 200. As an example, one or more sensors may be located at an off-site well site, wherein well site system 200 and the off-site well site are located in a common oil field (e.g., an oil field and / or a gas field).

[0082] As an example, one or more of the sensors 264 may be provided for tracking the movement of the tube, tracking the movement of at least a portion of the drill string, etc.

[0083] As an example, system 200 may include one or more sensors 266 that can sense signals and / or transmit signals to a fluid conduit such as a drilling fluid conduit (e.g., a drilling mud conduit). For example, in system 200, one or more sensors 266 may be operatively coupled to a portion of riser 208 through which mud flows. As an example, a downhole tool may generate pulses that can travel through the mud and be sensed by one or more of the sensors 266. In such an example, the downhole tool may include associated circuitry, such as encoding circuitry that can encode signals, for example, to reduce the need for transmission. As an example, surface circuitry may include decoding circuitry to decode encoded information transmitted at least partially via mud pulse telemetry. As an example, surface circuitry may include encoder and / or decoder circuitry, and downhole circuitry may include encoder and / or decoder circuitry. As an example, system 200 may include a transmitter that can generate signals that can be transmitted downhole via mud (e.g., drilling fluid) as a transmission medium.

[0084] As an example, one or more portions of the drill string may become stuck. The term "stuck" can refer to varying degrees of inability to move or remove one or more portions of the drill string from the borehole. As an example, in a stuck state, the tube may be rotated or lowered back into the borehole, or, for example, in a stuck state, axial movement of the drill string within the borehole may be impossible, although some degree of rotation is possible. As an example, in a stuck state, at least a portion of the drill string may be impossible to move axially and rotationally.

[0085] The term "stuck" can refer to a portion of the drill string that cannot rotate or move axially. As an example, a condition known as "differential sticking" can be a situation where the drill string may not move along the axis of the borehole (e.g., rotate or reciprocate). Differential sticking can occur when high contact forces, caused by low reservoir pressure, high borehole pressure, or both, are applied over a sufficiently large area of ​​the drill string. Differential sticking can have time and financial costs.

[0086] As an example, the sticking force can be the product of the pressure differential between the wellbore and the reservoir and the area over which the pressure differential acts. This means that a relatively low pressure differential (ΔP) applied over a large working area can stick the pipe as effectively as a high pressure differential applied over a small area.

[0087] As an example, a condition referred to as "mechanical jamming" can occur when drill string movement is restricted or prevented by a mechanism different from differential jamming. Mechanical jamming can be caused by one or more of the following: debris in the wellbore, wellbore geometry anomalies, cement, keyways, or drill cuttings accumulation in the annulus. One or more types of jamming can introduce one or more types of risks, which may be directed against the borehole wall, equipment, mud, mud flow, etc. In various cases, jamming can introduce non-productive time (NPT), for example, depending on the degree of jamming, the frequency of jamming, and one or more actions taken to reduce jamming, etc.

[0088] Figure 3 A schematic diagram of a computing or processor system 300 according to one embodiment is shown. The processor system 300 may include one or more processors 302 with different core configurations (including multiple cores) and clock frequencies. The one or more processors 302 may be operable to execute instructions, application logic, etc. It should be understood that these functions may be provided by multiple processors or multiple cores on a single chip operating in parallel and / or communicatively linked together. In at least one embodiment, the one or more processors 302 may be or include one or more GPUs.

[0089] 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 having different physical dimensions, accessibility, storage capacity, etc., such as flash drives, hard disk drives, magnetic disks, random access memory, etc., for storing data, such as images, files, and program instructions executed by the processor 302. In one 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 methods described above.

[0090] The processor system 300 may also include one or more network interfaces 306. Network interface 306 may include any hardware, application, and / or other software. Therefore, network interface 306 may include an Ethernet adapter, a wireless transceiver, a PCI interface, and / or a serial network component for communicating via wired or wireless media using protocols such as Ethernet or Wireless Ethernet.

[0091] As an example, processor system 300 may be a mobile device including one or more network interfaces for information communication. For example, the 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, the mobile device may include components such as a main processor, memory, display, display graphics circuitry (e.g., optionally including touch and gesture circuitry), SIM slot, audio / video circuitry, motion processing circuitry (e.g., accelerometer, gyroscope, etc.), wireless LAN circuitry, smart card circuitry, transmitter circuitry, GPS circuitry, and a battery. As an example, the mobile device may be configured as a cellular phone, tablet computer, etc. As an example, the method may be implemented using a mobile device (e.g., wholly or partially). As an example, the system may include one or more mobile devices.

[0092] The processor system 300 may also include one or more peripheral interfaces 308 for communicating with displays, projectors, keyboards, mice, touchpads, sensors, and other types of input and / or output peripherals. In some embodiments, the components of the processor system 300 do not need to be enclosed in a single housing or even very close to each other; however, in other embodiments, components and / or other components may be housed in a single housing. As an example, the system may be a distributed environment, such as a so-called "cloud" environment, in which various devices, components, etc., interact for purposes such as data storage, communication, and computation. As an example, a method may be implemented in a distributed environment (e.g., wholly or partially as a cloud-based service).

[0093] exist Figure 3 In the example, memory device 304 may be physically or logically arranged or configured to store data on one or more storage devices 310. Storage device 310 may include one or more file systems or databases of any suitable format. Storage device 310 may also include one or more software programs 312, which may contain interpretable and / or executable instructions (e.g., processor-executable instructions that may be stored in memory 304 and executed to instruct system 300 to perform one or more actions) for performing one or more of the disclosed procedures. When requested by processor 302, one or more software programs 312 or portions thereof may be loaded from storage device 310 into memory device 304 for execution by processor 302.

[0094] Those skilled in the art will understand that the above-described components are merely one example of a hardware configuration, as the processor system 300 may include any type of hardware components for performing the disclosed embodiments, including any accompanying firmware or software. 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).

[0095] Processor system 300 can be configured to receive directional well plan 320 (e.g., and / or generate directional drilling plan). As described above, a well plan is a description of a proposed wellbore used by the drilling team during drilling. A well plan typically includes information about shape, orientation, depth, completion, and assessment, as well as information about the equipment to be used, actions to be taken at different points in the well construction process, and other information that the team planning the well deems relevant / helpful to the drilling team. A directional drilling plan may also include information about how to manipulate and manage the direction of the well.

[0096] The processor system 300 can be configured to receive drilling data 322. Drilling data 322 may include data collected by one or more sensors associated with surface or downhole equipment. Drilling data 322 may include information such as data related to the location of the BHA (e.g., survey data or continuous location data), drilling parameters (e.g., weight on bit (WOB), rate of drilling (ROP), torque, or others), textual information entered by individuals working at the well site, or other data collected during well construction.

[0097] In one embodiment, the processor system 300 is part of a drill rig control system (RCS) for the drill rig (e.g., including downhole equipment operatively coupled to the drill rig). In another embodiment, the processor system 300 is a separately installed computing unit that includes a display installed at the drill rig site and receiving data from the RCS. In such an embodiment, software on the processor system 300 may be installed on the computing unit, brought to the well site, and installed and communicatively connected to the drill rig control system to prepare for constructing a well or a portion thereof.

[0098] In another embodiment, the processor system 300 may be located remotely from the well site and receive drilling data 322 via a communication medium using protocols such as Well Site Information Transmission 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 accessible to a user using a web browser. In such an embodiment, the processor system 300 may be located remotely from the well site where the well is being constructed, and the user may be at or away from the well site.

[0099] Well plan 320 typically includes information about the direction and shape of the well to be drilled. Well plan 320 may include information about the parameters and tools used to achieve the desired shape and location. However, during drilling, the actual trajectory may deviate from the plan, or unexpected situations may arise. In such and other cases, it may be necessary to adjust the plan to account for changing conditions and circumstances. For example, consider methods that may require replanning to generate a revised well plan.

[0100] In one embodiment, the system includes a drilling planning component for monitoring and updating the drilling plan, wherein the well plan can be in digital format, for example, as a digital data structure stored in the memory of a computing device, computing system, etc. For example, consider a controller that includes a memory capable of storing the well plan as one or more digital files. The well planning component can derive a work plan when the team conducts reconnaissance or otherwise determines the location of the well. In one embodiment, the work plan is essentially a spatial trajectory in multiple dimensions to construct a path from the current drill bit position (e.g., the bottom of the well) to the next position, which can be referred to as the target, and can be an intermediate or final target. The path construction takes into account a variety of considerations. These may include, but are not limited to: the target; permissible deviations from the original plan in terms of position and / or angular deviations; the maximum dogleg capability of the steering components; constraints set by the user at the outset based on preferences; permissible tortuosity, risk metrics, hole quality, confidence levels, etc.; and others.

[0101] The generation of a work plan can involve generating a series of trajectory candidates that meet multiple specified conditions, and evaluating the candidates based on trajectory environment, different characteristics, constraint violations, and levels. Trajectories can be sorted according to different optimization objectives. Users can allow the system to present one or more available candidates for selection.

[0102] As an example, the path or trajectory of a wellbore can be determined by acquiring direction and inclination (D&I) measurements at various points along the wellbore; these can be referred to as survey measurements or survey information. Regarding surveying, the location of the wellbore (e.g., borehole, etc.) can be referenced to some vertical and / or horizontal reference (e.g., wellhead location and height reference). One or more inertial measurement techniques can be used to obtain the location. Regarding azimuth, it can be considered, for example, the azimuth angle relative to a reference direction (such as north) at the measurement location. As for inclination, it can be considered the angular deviation of the borehole from a vertical direction, for example, with reference to the direction of gravity. Regarding the measured depth, it can be considered the distance measured from the surface location along the wellbore (e.g., borehole, etc.). The measured depth can include the driller's depth and can also include a depth correction algorithm that takes into account the elastic stretching and compression of the drill string along its length.

[0103] Directional wellbore can be drilled through the formation along a selected trajectory. Various factors can combine to unpredictably affect the wellbore trajectory. Accurate measurement of the wellbore trajectory is desired to guide the wellbore to its geological and / or locational target. Therefore, it is desirable to measure the wellbore's inclination, azimuth, and depth during wellbore operation to estimate whether the selected trajectory has been maintained.

[0104] The drilling trajectory of a wellbore can be estimated via acquisition through wellbore or directional surveys, which in this context may be referred to as surveys not based on extended surfaces, but rather as seismic data cubes of the Earth's volume. Wellbore surveys can consist of a collection or a group of survey stations. Survey stations can be generated by taking measurements at individual locations within the wellbore (e.g., boreholes, etc.) to estimate location and / or wellbore orientation. The act of performing these measurements and generating survey data can be referred to as performing a survey or surveying a wellbore or borehole.

[0105] Wellbore measurements can be performed using downhole measurement instruments (e.g., drill string equipment). Such instruments may include, for example, one or more orthogonal accelerometers, magnetometers, and / or gyroscopes. Survey instruments can be used to measure the direction and magnitude of local gravity, magnetic fields, and / or the Earth's spin rate vector (e.g., collectively referred to as the Earth vector). Various measurements can correspond to the instrument position and orientation within the wellbore relative to the Earth vector. As an example, wellbore position, inclination, and / or azimuth can be estimated based on instrument measurements.

[0106] One or more survey stations can be generated using discrete or continuous measurement modes. Discrete or static wellbore surveys can be performed by creating survey stations along the wellbore when drilling stops or is interrupted, for example, to add additional joints or standoffs to the drill string at the surface. Continuous wellbore surveys may involve various measurements of the Earth vector and / or the angular velocity of downhole tools obtained for each section of the wellbore using one or more survey instruments. Continuous measurements of these vectors during drilling operations may be spaced out by fractions of a meter and depend on the rate of change of the vectors during drilling; such measurements can be considered continuous or discrete.

[0107] Figure 4 and Figure 5 An embodiment of a system 400 for work plan generation (e.g., a work plan generator (WPG)) is shown. As illustrated, system 400 may include an application layer 410, a data service 412, a state estimation component 414, a trajectory generator component 416, a user runtime parameter component 418, a drilling command scheduler component 420, a sorting system component 422, an activity plan management component 424, and a state manager component 426.

[0108] In one embodiment, system 400 includes a state estimation component 414 for inferring the state of the system using input data from data service 412. Figure 4 As shown in the example, the state estimation component 414 may include various features, such as one or more features for static exploration, bottom hole estimation, drilling parameter estimation, trend estimation, continuous direction and inclination (D&I) estimation, downlink detection, trajectory deviation estimation, etc. Regarding bottom hole estimation, it can be performed in one or more ways. As an example, a framework for bottom hole estimation can be utilized, which can implement one or more types of filters, which may be model-dependent. In such an example, the framework can operate dynamically to automatically select specific filters and / or specific models. For example, the model may be a predictive model that can be utilized by filters including a prediction-correction architecture. As an example, the bottom hole estimation process can use data that may include data acquired during drilling operations to estimate the orientation (e.g., attitude) of the drill bit in the drill string. As an example, the estimation process may include filtering or no filtering. As an example, the estimation process may utilize linear regression filters, piecewise linear filters with changes in steering settings, multivariate piecewise linear filters, multivariate piecewise linear filters with uncertainty, one or more types of Kalman filters (e.g., extended Kalman filters, unscented Kalman filters, etc.), particle filters, basic median filters, Gaussian process-based filters, etc. As an example, one or more machine learning techniques can be used to implement one or more filters. For instance, consider a neural Kalman filter, where one or more neural networks can be used to parameterize the modeling of process dynamics and sensory observations.

[0109] As an example, bottom-hole estimation, as part of the state estimation process, can provide improved drilling operations. For instance, consider improved drill bit steering, which can be designed to keep the drill bit in a desired formation (e.g., like a reservoir) (e.g., to increase reservoir contact with the borehole, etc.). As an example, bottom-hole estimation can improve candidate generation, trajectory selection, command selection and / or command scheduling, recommendation, etc. As an example, bottom-hole estimation can improve trend estimation of trajectory interpolation. As an example, bottom-hole estimation can be utilized in the generation process of candidate trajectories, where candidate trajectories extend from the estimated bottom-hole depth and orientation to one or more targets. Therefore, by estimating the bottom-hole depth and orientation more accurately, candidate trajectories can be generated more reliably.

[0110] As an example, the state manager component 426 can be configured to process multiple parallel states to determine the effects of certain actions that a user (e.g., or a machine) might want to take or that might occur, and to infer states from these "hypothetical" scenarios. Figure 4 In the example, the trajectory generator component 416 can interface with multiple trajectory creation sources / states and manage multiple trajectory candidates.

[0111] Regarding the drill command scheduler component 420, it can generate a hardware-specific sequence of drill commands for each trajectory (e.g., command scheduling for each trajectory). Regarding the ranking system component 422, it can evaluate constraint violations and feature ranking candidates based on user-defined optimization objectives. Figure 4 In the example, the Activity Planning Manager component 424 can monitor ongoing actions and make / suggest corrections, trigger rescheduling of actions, and request user intervention.

[0112] In one embodiment, such as Figure 5 The trajectory evaluation and ranking method shown can evaluate constraint violations of the generated candidates; note that it can also evaluate the cost function of multiple candidate features. In some embodiments, the user can prioritize and / or weight the optimized parameters. The component can also generate a priority list of candidates for the user to select.

[0113] In one embodiment, the trajectory evaluation and ranking solver takes the trajectory and drilling command schedule from the command scheduler as input; note that it may also receive constraint configurations, constraint violation penalties, and candidate feature weights. In one embodiment, the output may be a prioritized list of candidates.

[0114] Figure 6 An example of a system 600 is shown, comprising off-site device 601 (e.g., remote) and field device 602 (e.g., local). As shown, off-site device 601 may include a drilling operations framework 610, a drilling planning framework 620, and a database 630, and field device 602 may include a controller 640 that can receive real-time data and output suggestions such as control commands to control the field device. In such an example, drilling operations framework 610 may provide steering tables, execution parameters, etc., and drilling planning framework 620 may provide steering response and statistical evaluations. As shown, controller 640 may output information to drilling operations framework 610 and receive information from drilling planning framework 620. System 600 may include planning generation features for real-time plan generation during the drilling operations execution phase and / or plan generation during the planning phase. System 600 may be used for one or more types of drilling (e.g., rotary, mud motor, RSS, ABSS, etc.). System 600 may operate loops that may include at least one real-time loop providing control of the equipment to perform drilling operations.

[0115] Systems such as System 600 can utilize various functions and penalties to generate plans that can provide single or multiple objectives. As explained, plans designed to provide drilling operations targeting multiple objectives simultaneously can be generated. As an example, System 600 may include... Figure 4and Figure 5 System 400, one or more other systems described herein, etc., have one or more characteristics.

[0116] Figure 7 An example of a well site system 700 is shown, specifically, Figure 7 Block diagrams of well site system 700 and system 770 are shown in approximate side view and approximate plan view.

[0117] exist Figure 7 In the example, well site system 700 may include a compartment 710, a rotary table 722, a winch 724, a mast 726 (e.g., optionally carrying a top drive, etc.), a mud tank 730 (e.g., having one or more pumps, one or more vibrating screens, etc.), one or more pump buildings 740, a boiler building 742, an HPU building 744 (e.g., having a rig fuel tank, etc.), a combined building 748 (e.g., having one or more generators, etc.), a pipe rack 762, a catwalk 764, a flare 768, etc. Such equipment may include one or more associated functions and / or one or more associated operational risks, which may be risks related to time, resources, and / or people.

[0118] like Figure 7 As illustrated in the example, well site system 700 may include system 770, which includes one or more processors 772, memory 774 operatively coupled to at least one of the processors 772, instructions 776 that may be stored, for example, in memory 774, and one or more interfaces 778. As an example, system 770 may include one or more processor-readable media comprising processor-executable instructions executable by at least one of the processors 772 to cause system 770 to control one or more aspects of well site system 700. In such an example, memory 774 may be or include one or more processor-readable media, wherein processor-executable instructions may be or include instructions. As an example, processor-readable media may be computer-readable storage media that is not a signal and not a carrier wave.

[0119] Figure 7 A battery 780 is also shown, which can be operatively coupled to system 770, for example, to power system 770. As an example, battery 780 can be a backup battery that operates when another power source is unavailable to power system 770. As an example, battery 780 can be operatively coupled to a network, which can be a cloud network. As an example, battery 780 can include smart battery circuitry and can be operatively coupled to one or more devices via SMBus or other types of buses.

[0120] exist Figure 7In the example, service 790 is shown to be available, for example, via a cloud platform. Such services may include data service 792, query service 794, and drilling service 796. As an example, service 790 could be such as Figure 6 This is part of system 600, another system described herein, etc. As an example, service 790 may include one or more services for directional drilling, which may include, for example, one or more steering trend services (e.g., consider a computational framework that can provide one or more services that utilize survey information to estimate one or more steering response parameters, etc.).

[0121] As an example, system 770 can be used to generate one or more drilling rate drilling parameter values, which can be used, for example, to control one or more drilling operations.

[0122] As an example, the method may include automating the operation of one or more types of downhole tools. For example, consider automating the operation of one or more of a mud motor, a rotary steerable system (RSS), and an ABSS (Abstract Steering System at Bit). As an example, one could use... Figure 2 The system 200 may incorporate one or more features of these types of devices, systems, etc. For example, the drill string assembly 250 may include one or more of a mud motor, RSS, ABSS, etc.

[0123] As an example, a steerable system at the drill bit (ABSS) may include actuators with pressure drop range, tilt and azimuth (HIA) holding capabilities, and dual downlink capability. As an example, an ABSS may include an onboard near-bit sensor capable of acquiring, for example, continuous six-axis tilt and azimuth measurements with a 6-foot range, and, for example, optional natural gamma-ray and azimuth images with a 9-foot range. As an example, an ABSS may include one or more features of one or more NEOSTEER series ABSS (SLB, Houston, Texas).

[0124] As an example, the framework can provide information from planning with offset analysis and adjust the hybrid model for real-time execution; consider various downhole automation possibilities at a given time to optimize recommended worktrack execution, leveraging tool capabilities and minimizing unnecessary surface actions; and consider real-time data and derived tool health status, as well as tool state estimates at a given time point, to optimize the currently ongoing recommendation and recommend real-time corrections to handle deviations when they occur. This approach can involve various calculations and actions that can output, for example, the best recommendation with the fastest path that minimizes risk, based on drilling constraints and the drilling environment.

[0125] Regarding the optimal path recommendation, the derivation can be done via WPG, for example, as regarding... Figure 4 and Figure 5 The explanation provided can offer single-objective and / or multi-objective approaches, and for example, it can consider various factors, which may include energy, emissions, etc.

[0126] Figure 8 An example of a workflow 800 is shown, including data acquisition, status calculation, work plan generation, sorting and command scheduling, and user selection. As illustrated, such a workflow can be implemented during drilling operations in the field. For example, the acquired data can be real-time data, and status calculation can determine the status of the location of the BHA or other tools within the wellbore. Regarding work plan generation, it can answer the question of where to proceed, which can be based on the current plan, constraints, and environment. As explained, sorting and command scheduling can be performed, where commands can be adapted for automatic and / or manual execution. Recommendations from such a workflow can be presented to one or more displays, where, for example, one or more GUIs can provide user interaction.

[0127] As explained, a work plan can be or includes a trajectory for constructing a path from the current drill bit position (e.g., bottom hole (HB) point) to the next target (e.g., another bottom hole (HB) point). This path construction can be performed according to the target, where, for example, various trajectory constraints can be considered. For example, one or more of the following constraints may be considered: permissible deviations from the original plan in terms of position and angle; maximum dogleg capability of the steering components; recommended constraints from automated plan analysis that can be adjusted manually and / or automatically (e.g., based on user preferences, etc.); and permissible tortuosity, risk metrics, hole quality, confidence levels, etc.

[0128] As explained, 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 environment, different characteristics, constraint violations, etc.) can be used to perform work plan generation. In this approach, WPG can output a single best candidate or several top-ranked candidates.

[0129] Regarding the ranking system, it can operate based on a list of categorical items defined as features selected for ranking the candidates. For example, consider candidate features, some examples of which may include: track length, ROP, total steering length, tool face (TF) orientation, maximum steering ratio, average deviation from the plan, risk level, target constraints, angular deviation, tortuosity and one or more other torque and resistance constraints, direction difficulty index (DDI), hole quality, tool wear, number of downlinks, geomechanics, confidence level, and production level index. For each feature i utilized (e.g., from i=1 to I, where I is the total number of features), weights can be defined based on the track environment, basin location, client type, rig type, etc. In such an example, weights can be associated with the cost function of the candidates to produce the total cost for each candidate trajectory, as follows:

[0130]

[0131] In the above text, each feature denoted as i can have a cost Ci and an associated weight Wi, where the weight Wi can be environment-dependent weights, and the total cost of the candidate features of the candidate trajectory can be a sum C. prop Such ranking systems can be modular and scalable. Defining a ranking system in this way facilitates the addition of additional candidate characteristics (e.g., based on mathematical and / or logical descriptions). For example, using machine learning methods, the system can identify the ease or difficulty of drilling paths from historical data and automatically define a drilling difficulty index based on surface conditions, adding it to the aforementioned equation. In such an example, one or more cost functions can be optimized in a way that takes into account the ease and / or difficulty of drilling. As an example, the system may optionally include a cost function that estimates greenhouse gas (GHG) emissions for each path (e.g., a candidate). In such an example, when the cost function is associated with carbon emissions or GHG emissions, the ranking system can operate in a mode (e.g., an emission pattern) where weights can be selected to minimize emissions first (e.g., before other minimizations).

[0132] As an example, once the optimal path has been selected and the steering commands to implement that path have been defined, there may be an additional optimization problem of defining the links with surface automation equipment to efficiently execute the optimal path. This approach can be performed iteratively, for example, by deriving the optimal drilling parameters after the work plan has been generated, or by incorporating surface automation constraints within the sequencing system (e.g., in a scalable manner, etc.). As an example, the system could use an AI-based planner to determine a set of possible drilling parameters to use when the work plan has already been generated.

[0133] As described above, the intelligent actuator can control steering commands, whether they are for motor steering, RSS steering, or ABSS steering, or one or more of these. In some embodiments, a control layer (e.g., regarding the availability of direct downhole trajectory automation) can be provided when running RSS or ABSS tools.

[0134] Regarding all aspects of drilling, consider the following terms.

[0135] Rotary Guided System (RSS): A specific downhole tool that can deflect the wellbore using electronic commands.

[0136] Dogleg severity (DLS): A measure of the variation in wellbore orientation over a defined length, typically measured in degrees per 100 feet of length.

[0137] Output (Y): Maximum DLS capacity.

[0138] Real-time output (RTY): Output at a specific time.

[0139] Tool face (TF): The angle between the reference direction on the drill string and the fixed reference, measured in a plane perpendicular to the drill string axis.

[0140] Expected command: The expected command sent to the downhole tool.

[0141] Actual command: The command executed by the downhole tool.

[0142] Tool face offset (TFo): The angle measured between the desired TF and the actual TF.

[0143] Inclination rate (BR): DLS projected onto the vertical plane at the attachment tool location. It is also the rate of change of inclination.

[0144] Turning rate (TR): DLS projected onto the horizontal plane. It is also the rate of change of azimuth.

[0145] Swimming rate (WR): The rate of change of the azimuth angle associated with the tool reference axis.

[0146] Steering Ratio (SR): The percentage of time an RSS tool spends steering (biased) versus attempting to become neutral (unbiased).

[0147] BRo and WRo: BR and WR during the neutral phase.

[0148] As an example, automated methods can estimate the directional trend parameters of the RSS during well construction. In such an example, parameters may include output (e.g., the maximum DLS capability of the directional tool), neutral construction (e.g., the trend of the angle of construction or descent during the neutral phase when no particular direction is privileged), neutral turning (e.g., the trend of turning during the neutral phase), and toolface offset (e.g., the angle difference between the target and the actual).

[0149] Figure 9 An example of a system 900 is shown, comprising a trajectory generator 910 and a sorting system 920. As shown, the trajectory generator 910 can generate candidates and command schedules, while the sorting system 920 includes a weight and penalty box 930, a constraint evaluator box 940, a cost function box 950, and a sorting box 960. The system 900 can generate output as indicated by the output box 970 for a sorted candidate list (e.g., sorted candidates). As an example, Figure 4 System 400 may include a sorting system 920, for example, as a sorting system component 422, and may include a trajectory generator 910, for example, as a trajectory generator component 416. Figure 5 As shown, the sorting system component 422 can be a system for handling sorting and constraint violations. As explained, weights can be used to perform sorting; for example, weights can be associated with a cost function of the candidates to produce a total cost for each candidate trajectory. For example, in system 900, the weights and penalties box 930 can provide and / or generate appropriate weights, penalties (e.g., constraints), etc.

[0150] As an example, the system may include one or more components (e.g., boxes, etc.) capable of automatically deriving weight values ​​for the sorting system. As explained, such a sorting system may be part of or otherwise operatively coupled to a Work Plan Generator (WPG). As explained, such a WPG may be used for field operations, such as directional drilling. As an example, a WPG may be part of a directional drilling consulting system.

[0151] As an example, a ranking system may utilize one or more machine learning techniques to derive appropriate values ​​for the weights to be used based on behavior observed from actual directional drilling (DD) operations, such as as set up and performed by one or more people and / or one or more automated systems on the drilling rig.

[0152] As explained, the system can implement an automated method to derive weight values ​​for the sequencing process, which can be included as part of the work plan generation for a directional drilling consultant (DDA).

[0153] Due to the complexity of the various wells being drilled, there are considerable risk and reward scenarios for the proper planning and execution of directional drilling (DD). Systems can be designed to de-technically and de-humanize the DD process while ensuring efficiency and consistency. As an example, a DD framework can provide various levels of de-technical and de-humanization of the DD process while ensuring efficiency and consistency. In such an example, a DDA framework can provide optimal decisions in real time (e.g., perform real-time optimal decision formulation). As an example, a DDA framework can provide outputs for one or more of motors, trajectories, commands, and downlink recommendations. For example, consider a DDA framework that provides outputs for RSS tools and / or one or more other types of tools used for directional drilling. Such a framework can provide outputs from start to finish for various types of wells, for example, by automatically providing the next action sequence at each survey point.

[0154] The DDA framework enables well construction with minimal human intervention and provides monitoring and / or intervention both locally and / or remotely (e.g., at the rig or from a town). As explained, the DDA framework may include a WPG system that determines the optimal path from the current state to one or more target objective states.

[0155] WPG can be implemented as a system within a DDA framework (e.g., consider the RSS Advisor framework), where WPG is responsible for deriving the work plan to be followed, for example, in response to conducting surveys and updating the location of wells (e.g., bottom hole location).

[0156] In practice, a work plan can be a trajectory that constructs a path from the current drill bit position (e.g., bottom of the well (HB) position) to the next target. This path construction can be done based on the target and optionally also by considering one or more trajectory constraints, such as: permissible deviations from the original plan in terms of position and angle; maximum dogleg capability of the steering components; constraints set by the user at the time of initiation (e.g., based on his / her preferences); permissible tortuosity; risk metrics; hole quality; confidence level; ROP; carbon emissions; eco-optimal path (e.g., with minimum energy consumption); and so on.

[0157] As explained, the generation of the work plan may include trajectory generation, which may be designed to generate an appropriate number of trajectory candidates under different conditions, and sorting, which may be designed to evaluate each candidate based on one or more of trajectory environment, different characteristics, constraint violations, etc., to sort the available candidates according to a defined optimization objective (e.g., optionally defined by the user).

[0158] Regarding the output from the sorting process (e.g., the sorting system), the output may be a single best candidate, or several best candidates that may be exposed to the user for selection, optionally using one or more techniques, such as, for example, the Pareto technique, to select a candidate when none of the several best candidates is substantially better than another of the several best candidates (e.g., a trade-off selection process).

[0159] Refer again Figure 9 An exemplary system 900 is provided, which can be used in RSS applications, slurry motor applications, and / or one or more other types of DD applications. As shown, the sorting system 920 includes a constraint evaluator box 940 and a cost function box 950. The constraint evaluator box 940 can provide evaluation trajectory constraints and apply penalties for each violation, while the cost function box 950 can provide evaluation of candidate features and apply a cost to each feature. As an example, the sorting box 960 can receive candidates and costs, and sort the candidates, for example, in ascending order of cost (e.g., sorted by cost).

[0160] Regarding what can be done by Figure 9 The weight and penalty box 930 of the sorting system 920 performs weight generation, which can generate weights including feature weights that can be used to sort a number of candidates.

[0161] As explained, the system can be used to derive the optimal path to one or more targets from the current hole location (e.g., the current HB location). In such an example, a user might want to know the optimal path to one or more targets given the current hole location and constraints associated with the current environment. Regarding constraints, consider one or more of, for example, output, allowable deviation from the original plan, attitude constraints, etc. In various examples, the system may at least provide the depth and orientation of the HB, where, for example, the depth can be, a measured depth or true vertical depth (TVD), and the orientation can include tilt and azimuth. When referring to the HB location, it can refer to both the HB depth and orientation. In this approach, the depth can be a one-dimensional location or a multi-dimensional location. For example, the TVD can be one-dimensional, and the measured depth can be one-dimensional or multi-dimensional.

[0162] As an example, a function can consume HB location (e.g., depth and orientation) and one or more targets as input, and develop the optimal path to one or more targets as output. In such an example, the input may include, for example, HB estimate (HBE), trend, and one or more targets. In such an example, the output may include one or more work plans. As an example, the configuration may include using the original plan along with trajectory constraints and tool type (e.g., RSS or mud motor).

[0163] As an example, during geosteering, the function can use the output HBE to better understand the borehole's position relative to the reservoir, and then suggest appropriate geosteering commands to return to a safe zone within the reservoir, or, when the borehole is already within the reservoir, to derive steering commands to remain in a higher producing area of ​​the reservoir. This approach can improve directional drilling in reservoirs that may be relatively thin, where drilling outside the reservoir can be unproductive and wasteful of energy and time. As an example, geosteering can be implemented to keep the drill bit within a specific layer defined between the top (e.g., upper layer) and bottom (e.g., lower layer), which may be defined by boundaries or interfaces (e.g., with other rock layers, etc.). In various cases, directional drilling aims to meet the desired amount of contact between the borehole and the reservoir.

[0164] Figure 10 Examples of drill strings 1010 and 1020 with various BHA features are shown. As examples, drill strings 1010 and 1020 may include... Figure 2 One or more of the features of the drill string assembly 250. For example... Figure 10 As illustrated in the example, drill string 1010 includes a drill bit 1012 and a set of orientation and inclination (D&I) sensors 1014 positioned relatively close to the drill bit 1012, while drill string 1020 includes a drill bit 1022, a set of D&I sensors 1024 positioned relatively close to the drill bit 1022, one or more other D&I sensors 1026, a D&I gyroscope sensor 1027, and one or more D&I MWD sensors 1028. In such an example, the closer the sensors are to the drill bit, the more accurately the sensors can provide an indication of the downhole position of the drill bit, which, as explained, can provide an HB estimate (HBE). As explained with respect to system 400, data service 412 can acquire data for one or more purposes, which may include data utilized by state estimation component 414, which can provide an HBE.

[0165] Regarding gyroscope sensors, as an example, consider a gyroscope sensor incorporating one or more features of a GYROSPHERE tool (SLB, Houston, Texas). As an example, the gyroscope sensor can provide acquisition of gyroscope measurement data in a manner that can contribute to elliptic uncertainty. As an example, the gyroscope sensor can include microelectromechanical systems (MEMS) technology that can utilize the Coriolis effect; for example, consider using a deterministic vibrating structure that can provide a planetary rotation rate. As an example, such a rate can be sensor data that can be used to determine one or more of tilt, azimuth, and toolface orientation. As an example, the gyroscope sensor can provide survey data during drill pipe connection. For example, measurements can be taken during connection, where, since MEMS technology does not require rotation and stabilization, measurements can be taken immediately after the mud pump is turned on (e.g., making data available more quickly). As an example, two surveys can be performed in the time it takes for a single survey to be initiated with a non-MEMS gyroscope. As an example, the gyroscope sensor can be a MEMS-based sensor capable of handling relatively severe shocks and vibrations. As an example, a single sensor can be used to survey at a certain inclination, depth, and higher latitude without requiring battery changes or recalibration between runs, which can make batch drilling operations more efficient. As an example, one or more gyroscope sensors can be included on the drill string. As an example, an RSS tool can include a gyroscope sensor. As an example, drilling can include a gyroscope sensor in a module or unit that can be assembled on the drill string (e.g., a tool with a length that constitutes part of the drill string length). As an example, a MWD tool can include a gyroscope sensor.

[0166] As an example, an MWD tool may include various sensors for acquiring data, such as survey data like direction and inclination (D&I) data. The MWD tool may be electrically powered using one or more mechanisms. For example, consider batteries, fluid turbine generators, etc. Including multiple mechanisms provides redundancy and increased uptime. For example, batteries can provide operation during intermittent drilling fluid flow conditions. Battery power can also provide logging during running-in (RIH) or pulling-out (POOH) operations. Therefore, when the MWD tool on the drill string passes the same location during drilling, RIH, POOH, etc., the MWD tool can acquire data at that location multiple times.

[0167] Regarding sensors, MWD tools may include orientation sensor technology, which may utilize, for example, an array of three orthogonal fluxgate magnetometers and three accelerometers. While standard orientation sensors can provide acceptable surveying, more sophisticated sensor technologies may help reduce uncertainty in the presence of bottom-hole location. However, as explained, even with more sophisticated sensor technologies, uncertainty may still exist, which may be exacerbated by the recent trend of drilling longer and more complex wells. Various types of errors may also exist in MWD measurements, which may include one or more of, for example, sensor errors, magnetic interference from the BHA, tool misalignment, and magnetic field uncertainties.

[0168] Regarding MWD telemetry, mud pulse telemetry is the standard method in various commercial MWD and LWD systems. It should be noted that one or more other types of telemetry may be used alternatively or as a substitute. The need for telemetry may be imposed by real-time azimuth correction, which involves transmitting raw data to the ground. Furthermore, when compression / decompression (e.g., lossy or lossless) is used, telemetry may introduce uncertainties and general types of transmission errors (e.g., noise, physical events, etc.).

[0169] Regarding MWD surveys, MD, dip, and borehole orientation can be recorded at survey stations, with multiple survey stations along the path. Such measurements can be used together to calculate 3D coordinates, which can then be presented as a digital table called a survey report. Measurements can be taken during drilling, at RIH (Recovery After Hit), during tripping, and after drilling is completed. MWD surveys using drill string MWD tools require stopping the drill bit from breaking rock (e.g., pausing drilling) so that the MWD tools can remain stationary in a noise-reduced environment to acquire sensor data for the MWD survey. MWD surveys can be used for one or more purposes, such as determining bottom hole location to monitor reservoir performance, monitoring the actual path to help ensure targets are met, orienting and deflecting tools to navigate the path, reducing the risk of intersections with nearby wells, calculating TVD for various formations to allow for geological mapping, assessing DLS (Drilling Performance Status), and meeting one or more requirements of regulatory agencies (such as the Mineral Resources Management Service (MMS) in the United States). For the latter, if the ability to use MWD tools for exploration on the drill string becomes impractical or impossible, drilling can be terminated until the problem is resolved, for example, to ensure compliance with regulations and reduce the risk of collisions with other boreholes, wellbores, etc.

[0170] When using an RSS tool, one or more of a downlink and an uplink can be employed. The downlink can be a command sent to be received by the RSS tool. Such a downlink can employ rotational techniques, such as adjusting the drill string RPM to a signal encoding the command (e.g., via a top drive), and / or flow techniques, such as adjusting the flow rate of drilling fluid (e.g., mud) to a signal encoding the command (e.g., via one or more mud pumps). As an example, one or more techniques can involve using a surface listener as a type of device capable of sensing RPM and / or flow regulation. For example, a surface listener can sense pressure and then correlate the sensed pressure data with the downlink code. In such an example, the surface listener can understand and acknowledge the downlink to the RSS tool (e.g., know what command may have been sent). A surface listener can be helpful when the uplink is impossible or unreliable for one or more reasons. For example, the uplink can be a signal generated by the RSS tool, intended to be received by a MWD tool, where the MWD tool can employ mud pulse telemetry to transmit the signal (e.g., its contents) to the surface. Therefore, various points of failure may exist in the uplink. For example, the RSS tool may not be able to generate enough uplink that can be received by the MWD tool, or the MWD tool may not be able to adequately receive and / or interpret the uplink. In the presence of one or more problems, a ground listener can provide a record of the commands sent to the RSS tool (downlink) to help understand the current state of the RSS tool (e.g., assuming the commands have been received and executed). Thus, a blind operation mode can be defined where the MWD tool is operable to provide at least reconnaissance information, and the uplink from the RSS tool is unavailable. In this mode, information from the ground listener can be used as a substitute for uplink information (e.g., to understand the state of the RSS tool). As an example, a blind mode can be defined as a mode in which signals originating from the RSS tool are not received or are unreceiveable at the ground (e.g., due to one or more reasons).

[0171] As an example, the state of an RSS tool can be inferred using ground listeners and / or other techniques. Such inference can be utilized during one or more modes. For example, this inference can be performed during both non-blind and / or blind modes. In the case of inference during non-blind mode, the inference can be compared to the actual state that can be based on uplink information. Such comparisons can be used to improve the ability to infer the state of an RSS tool (or multiple RSS tools), which can help improve blind mode operation. In some cases, commands may be misunderstood by the RSS tool, for example, due to degradation of the RPM and / or flow rate sequences (e.g., high, low, etc.) encoded in the command. For example, when a ground listener infers that the downlink from the RSS is “left turn,” the uplink from the RSS indicating a “right turn” is considered. In such an example, the discrepancy can be evaluated to determine whether another command should be sent to ensure correct operation. In such an example, if the number and / or type of discrepancies rise to or exceed one or more thresholds, the system can trigger blind mode operation and / or trigger an evaluation of why the downlink may be experiencing one or more problems if the RSS uplink information is deemed unreliable.

[0172] As an example, an RSS tool may include sensors that can provide measurements of one or more of the following: tilt offset relative to the tool bottom, azimuth offset relative to the tool bottom, average gamma rays, gamma ray offset relative to the tool bottom, vibration axis, vibration radial direction, impact, triaxial impact and vibration axis, magnetic field exclusion cone, etc. As an example, sensors may include one or more of the following: gyroscope sensors, accelerometers, magnetometers, gamma ray sensors, impact and vibration sensors, pressure sensors, temperature sensors, etc. As an example, sensors may be arranged in groups or packages. As explained, one or more sensors may be positioned along a drill string, which may be one or more distances from the drill bit of the drill string.

[0173] As explained, an RSS tool may include a D&I sensor and / or one or more other sensors for acquiring data, wherein the data may be stored locally and / or transmitted. As explained, an RSS tool may utilize uplink technology to transmit data from the RSS tool to a surface MWD tool, which may be located at a distance from the RSS tool on the common drill string. As explained, a blind mode may be used when the uplink from the RSS tool to the MWD tool is “disconnected”; note that a lack of telemetry information from the MWD tool to the surface may be a cause of drilling termination (e.g., lack of ability to receive MWD survey information at the surface). Regarding the type of technology used for uplink transmission, the RSS tool may include a wired interface for connecting to the MWD tool. In the case of such a wired connection being external, it may be exposed to various forces, which may cause wear or otherwise impede transmission over time. As an example, uplink transmission may utilize electromagnetic radiation telemetry as a wireless form of transmission. Therefore, uplink transmission from the RSS tool to the MWD tool can be achieved through one or more wired and wireless technologies. Furthermore, one approach can provide unidirectional or bidirectional transmission from RSS to MWD. ​​In the bidirectional case, the MWD tool can issue commands to the RSS tool, such as to query status, sensor data, etc. In various examples, wired methods can provide bidirectional transmission, while wireless methods can provide only unidirectional transmission. With unidirectional transmission, the RSS tool can repeatedly send information until the RSS tool's state changes (e.g., new sensor data, new commands, etc.).

[0174] As an example, in the case of using a mud motor on a drill string with an MWD tool but no RSS tool, data from the MWD tool can be utilized in mud motor mode. In various cases, the drill string may include an MWD tool and may include both a mud motor and an RSS tool; however, typically, either a mud motor or an RSS tool will be present for directional drilling.

[0175] As explained, a borehole can have a direction and a borehole orientation (BH) can have an orientation. For example, consider a borehole orientation that can be described using inclination and azimuth. Inclination typically refers to a vertical angle measured downwards, where downwards, horizontals, and upwards have inclinations of 0 degrees, 90 degrees, and 180 degrees, respectively. Azimuth typically refers to a horizontal angle measured clockwise from north, which can be a type of "north" or a defined "north." Typically, north, east, south, and west have azimuths of 0 degrees, 90 degrees, 180 degrees, and 270 degrees, respectively. In drilling, azimuth can be defined as the compass direction of a directional survey or the compass direction of the wellbore as planned or measured by a directional survey, where, for example, the azimuth can be specified in degrees relative to geographic north, magnetic north, or another defined "north." As an example, BH can be defined as a flat surface (e.g., a planar surface) with an orientation that can be defined by a vector pointing towards the direction normal to the flat surface. In such an example, BH can be defined by location (e.g., measured depth) and orientation (e.g., direction). As an example, the system can provide appropriate references for maintaining one or more directions (e.g., north, south, east, west, etc.). Maintaining appropriate references can facilitate directional drilling in relatively thin reservoirs, which may have upper and lower limits for true vertical depth (TVD). Geological steering in such reservoirs can be challenging, although this is improved when appropriate references are maintained (e.g., to ensure proper reservoir contact between the borehole and the reservoir). As explained, the system can help maintain appropriate references by forming a series of estimated borehole heights (BHs) (e.g., location and orientation) along the borehole.

[0176] As an example, one or more types of measurements can provide information for assessing the uncertainty of one or more other types of measurements. For example, temperature can be used to assess the uncertainty of a sensor relative to its operating temperature range. In such an example, if the measured temperature is outside the sensor's operating temperature range, the measurement from that sensor may have greater uncertainty. As an example, modes can be selected in part based on uncertainty; for example, if the uncertainty is above an uncertainty threshold, a blind mode or another mode that can operate without one or more specific measurements can be considered. As another example, shock and vibration can affect one or more types of measurements, where shock and / or vibration can be used as a type of measurement that can help assess uncertainty. As an example, such uncertainty can be continuously incorporated into the calculation of HB location (e.g., depth and orientation).

[0177] As an example, an Earth model can provide pressure and temperature modeling with respect to depth (e.g., true vertical depth (TVD)). In such an example, the measured pressure and / or measured temperature can be compared with the Earth model's values, gradients, etc., which can help increase the accuracy of HB locations (e.g., HBE) and / or otherwise verify HB locations (e.g., HBE).

[0178] As described above, a work plan can be or includes a trajectory that constructs a path from the current drill bit position (e.g., the HB position) to the next target position (e.g., the desired HB position). As an example, the framework may include features that enable an automated method for estimating the location of the bottom of the well (HB) during well construction execution. For example, along the HB, the locations of one or more sensors that can be used to estimate the location of the borehole may be within three meters of the drill bit (e.g., less than approximately three meters but greater than approximately 20 cm), or they may be at a considerable distance from the drill bit (e.g., greater than 3 m, 5 m, 10 m, 30 m, etc.). In such examples, where sensor measurements are used, some type of predictive model is typically required to estimate the exact actual location of the bottom of the well (HB). For example, even when a set of sensors is within one meter of the drill bit, HBE may still need to be estimated or predicted. As an example, the framework may include one or more features that can improve HBE, wherein such one or more features can provide a more accurate and automated estimate of the exact actual location of the bottom of the well (HB).

[0179] As an example, the framework may include one or more features for optimal filtering, which consume one or more types of downhole information (e.g., D&I, etc.) in real time (RT) to provide estimates of one or more HB parameters, such as with uncertainty and continuous trajectory interpolation and extrapolation output. In such an example, the framework can provide estimates of HB location and / or drill bit location during directional drilling activities.

[0180] As mentioned, modern wells can be relatively complex, thus presenting an increased number of risk-reward scenarios for proper planning and execution. Regarding automation, whether in planning and / or execution, automation can aim to de-technically and de-humanize the directional drilling process while ensuring efficiency and consistency. For example, automation can reduce the need for field personnel (e.g., fewer people) and / or reduce and / or transfer the skill level of field personnel (e.g., transferring to automated supervision and directional drilling decision-making).

[0181] As explained, an autonomous directional drilling (DD) system can be designed to achieve one or more objectives, for example, by using an automated directional drilling advisor framework that provides real-time best decisions. As an example, an autonomous DD system can provide various levels of automation for workflows. For instance, consider one or more workflow motor controls, trajectories, commands, and / or downlink suggestions for one or more RSS feeds. Such an autonomous DD system can be applied to one or more types of wells, where it can automatically provide the appropriate sequence of next actions from the beginning to the end of a segment at each exploration point.

[0182] As an example, during one or more geosteering applications, the next sequence of actions may be highly relevant, such as the relative location of the borehole with respect to the reservoir, for instance, to achieve the desired reservoir contact. In such an example, forward guidance via geosteering can lead to improved work plans for directional drilling to remain within the reservoir's producing area.

[0183] As explained, an autonomous DD system can include a DDA that enables well construction with minimal human intervention from the drill rig or from a location remote from the drill rig (e.g., an office location, etc.). As mentioned above, an autonomous DD system, which may be a computational framework, can be performed incrementally by automatically evaluating the current bit position, which may be based on an initial plan or a revised plan. In such an example, the evaluated current bit position may be the bottom position, which may be equal to or otherwise used for estimating the HB position. This HBE process can provide the core parameters driving the DDA. As an example, for RSS applications, the framework can utilize an RSS tool orientation and tilt (D&I) sensor set, which tends to be closer / closer to the bit compared to the MWD tool D&I sensor set (see example). Figure 10 However, RSS D&I sensors exhibit relatively low azimuth measurement accuracy in various situations, particularly when drilling around restricted areas, as is often the case in various North American sites. Such accuracy issues can have a substantial impact on DDA estimation.

[0184] As explained, methods for estimating the location and orientation of the HB (Headboard Indicator) can be implemented automatically. In such an example, the method could utilize one or more sensors positioned at one or more distances from the drill bit of the drill string. For instance, consider a method that combines RSS D&I, MWD D&I, and trend estimation to output an accurate HB location, even when drilling through restricted areas. This method can provide acceptable accuracy even in challenging situations, such as when directional drilling involves drilling parallel to the Earth's magnetic field.

[0185] For example, the DDA may include functions for performing HBE, such that the DDA is responsible for locating the HB position to understand its relative position with respect to the initial plan and one or more upcoming drilling targets.

[0186] As an example, DDA can provide a relatively continuous and automated output of HB locations. In such an example, DDA can provide the drill bit position and orientation, while outputting HB location estimates (e.g., D&I and HBE). As an example, DDA can output information at a frequency of 15 cm (e.g., 0.5 ft) per directional drilling interval. As an example, the framework can provide predictions of future HB locations based on current and / or future commands, which can be specified as part of a digital plan for directional drilling. In such an example, environmental conditions, mechanical conditions, one or more other well locations, etc., can be considered.

[0187] For example, a framework can generate information about the drilling portion of a well, where such information may include detailed information about the actual depth and orientation of the drill bit at a given point in time. Consider, for instance, a framework that can generate a graphical user interface (GUI) showing the trajectory of at least one portion of the borehole, where a user can hover over or click on the trajectory to instruct the GUI to display information such as the actual depth and orientation of the drill bit, thus displaying the longitudinal axis of the borehole. Consider, for example, outputting a vector with a base point at the actual location, where the direction the vector points may correspond to the orientation of the drill bit that drilled the trajectory at that base point.

[0188] As an example, the framework can provide continuous estimates of borehole orientation by fusing measurements from different systems and sensors, where the output can be at a frequency of approximately every 15 cm (e.g., approximately 0.5 feet). In this example, the framework can provide projections of future borehole locations deeper (e.g., relative to the measurement depth) than the current borehole location (e.g., the BH location). As an example, the framework can support collision-avoidance drilling, enabling directional drilling to occur with reduced risk of drilling into or near one or more other existing boreholes. As an example, the framework can provide true trajectory recovery at selected measurement depths less than the current borehole depth (e.g., the HB location). As an example, the framework can support a blind mode estimation process that can operate in response to the occurrence of one or more issues, triggers, etc., and / or can operate in a background manner, where, for example, a comparison can be made between a blind mode estimate and a non-blind mode estimate of the HB location. Regarding the non-blind mode estimate of the HB location, it can be a mode that operates at least partially on at least one sensor measurement. As an example, at least the complete operating mode of HBE can involve acquiring multiple sensor measurements. As an example, the framework can provide one or more advanced exploration workflows.

[0189] As an example, blind mode can operate intermittently, for example, when one or more measurements are unavailable. As an example, blind mode can be operated in a planned manner or unplanned manner. Regarding the planned manner, it can involve one or more telemetry-related scenarios where, for example, information from the RSS sensor array cannot be obtained in a timely manner. Regarding the unplanned manner, it can be implemented when one or more problems occur. For example, consider one or more of the following: sensor failure during drilling operations, shocks and / or vibrations that may adversely affect the level of one or more sensor measurements, telemetry failures or interruptions that cause one or more sensor measurements to be unreceived and / or received outside the time window. Regarding the case where one or more measurements are delayed (e.g., outside the time window), the framework can utilize one or more delayed measurements to reconstruct the HBE, and as explained, the HBE can be stored in a database so that the actual location and orientation can be presented after drilling has occurred.

[0190] As an example, directional drilling can occur where at least a portion of the drilling trajectory can be drilled with the aid of a frame (e.g., DDA) operating at least partially in a non-blind mode. As an example, directional drilling can occur with the aid of a frame (e.g., DDA) operating in at least a high-beta-intervention (HBE) mode. In such examples, directional drilling can use a drill string without RSS tools, where, for example, measurements from one or more sensors positioned at a distance from the drill bit can be used for at least HBE. As an example, the frame can perform at least HBE without information from RSS. In various examples where data from RSS (e.g., RSS tools) is unavailable, a blind mode, "blind" due to the unavailability of data from RSS, can be utilized.

[0191] As explained, the frame can provide projections of future locations or multiple locations, where such projections can be used for one or more purposes. For example, consider projections extending beyond approximately 10 meters (e.g., 30 m, 60 m, etc.) to help reduce the risk of the trajectory approaching or intersecting with existing boreholes.

[0192] As an example, HBE can include the location of HB (e.g., depth in one or more dimensions along the longitudinal axis of the borehole) and the orientation of HB (e.g., bottom hole orientation (HBO)). As explained, orientation can be represented by a vector that is normal to the plane representing the HB at the measured depth. As an example, HBO can be specified using inclination and azimuth. Inclination, a measure of deviation from the vertical direction, independent of compass direction, is expressed in degrees. Inclination can initially be measured using a pendulum mechanism and can be confirmed, for example, by measurements from one or more MWD accelerometers or gyroscopes. For most vertical wellbores, inclination is the only measurement of the wellbore path. Orientation information can also be measured for intentionally deviated wellbores or wells near legal boundaries. In directional drilling, azimuth can be the compass direction of the directional survey or the compass direction of the wellbore measured by a directional survey plan. As mentioned, azimuth can be specified in degrees relative to geographic north, magnetic north, or another convention (e.g., grid north, etc.).

[0193] As explained, a frame can assist in directional drilling, where one or more types of tools (e.g., mud motors, RSS, etc.) can be used to perform directional drilling. Regarding mud motor tools, directional drilling can involve sliding and rotation, where sliding can be used to create a curved borehole. As explained, during sliding (e.g., sliding mode), the top drive can oscillate the drill string clockwise and counterclockwise, while during rotation (e.g., rotation mode), the top drive can rotate the drill string in a single direction. As an example, a frame can provide various directional drilling modes. As an example, the drill string can include a mud motor and an RSS, in which, for example, one or the other alone, is used to steer the drill bit along a curve.

[0194] As an example, a hybrid system can be utilized, which can be configured to use RSS (Resistant Slippery Surface) for drilling with the assistance of power from a mud motor (e.g., consider a linearly locked, non-bending mud motor). In such an example, the RSS can be responsible for guidance (e.g., not using slippery mode). For example, consider the POWER DRIVE VORTEX system (SLB in Houston, Texas), which has an integrated power section that converts mud hydraulic power into mechanical energy to help maximize power, for example, to drill into hard formations.

[0195] Figure 11Examples of mud motor mode 1110 and RSS mode 1120 are shown, where mud motor mode 1110 includes rotation and sliding, and where RSS mode 1120 includes PowerV (e.g., vertical), manual, automatic curve, tilt hold (IH), hold tilt and azimuth (HIA), and one or more other modes. As an example, the framework can provide mode selection, where a mode is associated with a model. For example, the mode could be a drilling mode associated with a drilling mode model. In this approach, adaptive filtering can be employed, where such filtering can consume downhole information (e.g., direction and inclination (D&I) etc.) in real time (RT) to provide estimates of, for example, bottom hole parameters with uncertainties. This approach can provide continuous trajectory interpolation and / or extrapolation outputs. As explained, a model can be selected for a specific mode, which could be a drilling mode. In this approach, the selected model can utilize data used for bottom hole estimation. For example, the selected model can be used for the current drilling mode, such that the data can be appropriately used for bottom hole estimation (HBE). This approach can be dynamic because the model used for HBE may change if the drilling mode changes.

[0196] Figure 12 An example of at least a portion of a frame 1200 including an HB estimator 1210 is shown. As illustrated, the HB estimator 1210 can be initialized and configured, for example, using numerical planning information. Regarding input, in Figure 12 In the example, the HB estimator 1210 can receive surface parameters, downhole measurements, mechanical behavior, steering patterns, and static surveys (e.g., surveys conducted during temporary drilling stops, such as during the time it takes to add a standoff to the drill string). Regarding the output, in Figure 12 In the example, the HB estimator 1210 can generate HB depth, HB orientation, prediction accuracy, continuous measurement correction, and drilling behavior. As for static surveys, these can increase drilling time, which may be considered non-productive time (NPT). Therefore, the amount of static surveys can be minimized. As an example, static surveys can provide orientation information (e.g., inclination and azimuth) at the depth of one or more sensors.

[0197] Regarding surface parameters, consider one or more of the following: timestamp, hole depth, bit depth, ROP, RPM, tool face (TF), hook load (HKLD), standpipe pressure (SPP), differential pressure (DiffP or ΔP), torque (TOR), WOB, and vehicle position (BPOS). Regarding downhole measurements, consider one or more of the following: continuous MWD survey, continuous gyroscope sensor survey, continuous RSS survey, desired tool face, desired steering ratio, actual steering ratio, tool condition, downlink, attitude targets (e.g., inclination and azimuth), downhole temperature, measurement accuracy, RPM at the bit, and downhole pressure. Regarding mechanical behavior, consider one or more of the following: shock and vibration, drill string buckling, borehole diameter, BHA specifications, and steering trend. Regarding steering patterns, consider, for example... Figure 11 One or more modes are shown. Regarding static measurements, consider one or more of, for example, static measurement, gyroscope sensor measurement, MWD measurement, and measurement accuracy.

[0198] Regarding HBO as an output, consider one or more of the following: measured depth, inclination, azimuth, true vertical depth (TVD), north-south (e.g., northward), east-west (e.g., eastward), and vertical segment. Regarding prediction accuracy as an output, consider one or more of the following: measured depth accuracy, inclination accuracy, and azimuth accuracy. Regarding continuous measurement correction as an output, consider one or more of the following: MWD / gyroscope tilt correction, MWD / gyroscope azimuth correction, RSS tilt correction, and RSS azimuth correction. Regarding drilling behavior as an output, consider one or more of the following: dogleg severity (DLS), build-up rate (BR), turning rate (TR), and tool face (TF).

[0199] Figure 13 An example of method 1300, which can be implemented by a framework for performing corrections on one or more measurements, is shown. For example, as explained, the drill string can be run down (run-in hole (RIH)) and pulled out (pull-out hole (POOH)) multiple times during drilling operations. Therefore, one or more sensors can pass through one or more points in the borehole multiple times, making multiple measurements available for one or more points in the borehole. As an example, method 1300 may include retrieving the sensor depth estimate state, calculating the error, updating the sensor depth estimate based on the new measurement, and predicting the state, such as up to the drill bit depth. Figure 13 As shown, the error (e) can be calculated relative to the new measurement (e.g., at t2) for the old measurement (e.g., at t1) and / or the old prediction (e.g., associated with t1). In such an example, the new measurement can be considered more accurate than the old measurement and / or the old prediction and / or an additional measurement used for averaging purposes. Figure 13In the example, the error (e) at a specific trajectory location can be propagated forward from that trajectory location to HB, where HB can be the drill bit depth. In such an example, method 1300 can provide an updated prediction, as explained, which can be a projection of one or more points in the formation onto the drill bit's trajectory that the drill bit can make at one or more future times. In such an example, the one or more points can be the projected HB points.

[0200] As an example, method 1300 can be used for a drill string that includes one or more sensors at different distances from the drill bit. As explained, the RSS sensor group is initially located at one point during drilling, and one or more sensors of the MWD unit are located at that point when the drilling progresses to a point that extends the distance between the RSS sensor group and the MWD unit, thus increasing the drilling depth. In such an example, measurements from the RSS sensor group can be taken at time t1, while measurements from the MWD unit can be taken at time t2, where such later measurements can be used to make one or more adjustments to one or more HBEs and / or projections. As explained, during RIH or POOH, one or more sensor groups can be used at one or more points where previously acquired measurements have been obtained. In such an example, measurements can be taken at different times (e.g., t1, t2, t3, ..., tN). After the borehole is fully drilled, a final POOH operation can be performed, where the acquired measurements can be used to generate a final set of HBEs. As an example, the framework can adjust the HBEs once or multiple times, which can make the workflow dynamic and responsive to various aspects of directional drilling.

[0201] As explained, once drilled, the spatial path and orientation of the borehole will not change (e.g., unless a collapse, subsidence, earthquake, etc., occurs). However, by moving equipment into and out of the borehole, there is an opportunity to acquire additional data, which can be obtained during operations not involving actual drilling (e.g., breaking rock with a drill bit). As an example, the framework can provide data cascading, fusion, etc., which can occur online and / or offline to obtain the optimal HBE value for the borehole. For example, for the purpose of real-time online control, specific measurements acquired during directional drilling involving breaking rock with a drill bit can be used, optionally along with one or more static surveys during which drilling is temporarily suspended. Regarding post-drilling processes, a database of various measurements that can be acquired during drilling, during tripping, etc., can be accessed to select and process the selected measurements to derive a more accurate HBE value for the drilled borehole.

[0202] As an example, during drilling, the RSS sensor group (if present) can be the first sensor passing through a point, where one or more sensors of the MWD unit can pass through that same point as drilling progresses. In such an example, the MWD unit measurements are time-delayed, but can be used to update one or more previous HBEs, which can be based solely on measurements from the RSS sensor group. In such an example, there are opportunities to compare and / or otherwise evaluate the measurements, which can provide information for evaluating one or more sensors, for example, regarding operating conditions, uncertainties, etc. As an example, in the case where the MWD unit passes through a point measured by the RSS sensor group, one or more uncertainties can be updated, at least in part, based on measurements from the MWD unit. In such an example, uncertainties regarding the HBE can be updated while the inclination and azimuth at a specific measurement depth of the HBE can remain unchanged. In this way, information that may have been used to control drilling can be preserved, while uncertainties about that information (e.g., with time delays) can be updated.

[0203] As explained, during directional drilling, there is an opportunity to acquire multiple measurements at one or more points along the borehole. As an example, multiple measurement methods can provide an assessment that can be used to trigger a mode change. For example, consider comparing measurements to determine if one or more sensors are functioning correctly. In such an example, if one or more sensors are not functioning correctly, the operating mode (e.g., the HBE process) can be adjusted to not use one or more such sensors. As explained, a blind mode and / or one or more other modes can operate as background processes, where, for example, one or more comparisons can be made between a selected mode of the HBE and one or more background modes of the HBE. As an example, the blind mode or another mode that relies on fewer measurements than the full mode can be continuously evaluated and / or optionally updated to improve accuracy based on a more complete HBE mode.

[0204] As an example, the framework may include evaluating sensors and their measurements, which can provide options for including and / or excluding such measurements when performing HBE. Such an approach can operate using one or more criteria, which may be related to one or more portions of the planned trajectory. For example, measurements from one or more problematic sensors may be excluded in situations where the collision risk is likely high; however, such measurements may be included in the HBE in situations where the risk is low. As explained, the framework can provide quantified uncertainties, which can be used for measurements from one or more sensors and / or for the HBE. As an example, the framework may provide quantified uncertainties based on one or more factors, which may include drill string and formation interactions (e.g., friction, vibration, shock, etc.), temperature, pressure, etc.

[0205] Figure 14 An example of the process 1400 is shown, illustrating a plot of tilt versus depth measured by tilt surveys at two depths, a series of solution tilts predicted at seven depths at various time points, and an estimation process of three raw RSS continuous tilts at the corresponding sensor depths at each time point. Although Figure 14 The example shows tilt, but one or more other properties (e.g., azimuth, etc.) can be utilized. Figure 14 In the example, the depth distance is not necessarily drawn to scale and is primarily for illustrative purposes. As shown, at a specific depth, at 9:05 AM, the solution incl (Incl(1)) at that depth can be updated based on the original RSS incl measurement of a depth located between two solution incls but at a common time (e.g., approximately 9:05 AM). In such an example, the original RSS incl measurement can be evaluated relative to one or more criteria to determine whether it is reliable and suitable for updating the predicted depth. For example, one of the original RSS incl measurements is considered reliable, while another of the original RSS incl measurements is considered unreliable and therefore not used to update the solution incl.

[0206] exist Figure 14 In the example, from left to right, MWD static survey points are provided from the MWD tool (e.g., and / or gyroscope tool) and the known distance between the MWD tool and the RSS tool (e.g., the distance from the MWD tool to the drill bit). Given the locations of the MWD tool and the RSS tool, the future inclination can be predicted (see Incl(1)). However, the predicted inclination can be updated when RSS tool data is available (see Incl'(1)). Figure 14 In the example, the coarse curve connecting the two MWD static survey points is not known a priori because the leftmost MWD point is unknown. Therefore, the prediction is based on previous predictions and, where available, on RSS tool data (e.g., which may include gyroscope sensor data). Once the leftmost MWD point becomes available, a certain amount of smoothing can be performed to account for the actual physical constraints of the physical drill string in the physical borehole (e.g., each without kinks). Figure 14 In the example, the MWD static survey point can be considered a reliable point, as explained, which can be obtained when drilling has stopped.

[0207] Figure 15 An example of an adaptive filter 1500, which may be part of a framework, is shown. As illustrated, the adaptive filter 1500 may include a predictor 1550, which may receive time and / or depth data according to input box 530, and may output one or more HBEs according to output box 578. Figure 15In the example, predictor 1550 may include switch 1551, which can automatically select one of several different models (e.g., different drilling mode models) corresponding to different operating modes of directional drilling operations. For example, the models may include PowerV model 1552, build and turn model 1553, HI model 1554, HIA model 1555, and one or more other models 1556. As shown, predictor 1550 may proceed to update decision box 572, which determines whether to update the output of predictor 1550 (which may be HBE) from, for example, the survey data. As shown, the "yes" branch for updating the output from predictor 1550 may advance to update box 574 to update the prediction (e.g., HBE) using survey data; however, the "no" branch may advance to output box 578 to output HBE.

[0208] exist Figure 15 In the example, predictor 1550 may include different models already created for each drilling mode. Predictor 1550 may operate switch 1551 based on one or more selection criteria of the model based on the drilling mode. As an example, during drilling, the current mode may be known, therefore, predictor 1550 may receive and utilize this information to select the appropriate model for generating the HBE. Figure 15 As illustrated in the example, if new downhole information is received, this may relate to decision box 572 regarding whether to trigger an update process to adjust the HBE of predictor 1550, for example, starting from the last known static survey. As explained, the HBE may include the bit or HB location, including depth, azimuth, and inclination angle, as well as, for example, estimated variance. As explained, the frame may operate in one or more modes, which may include a blind mode and one or more non-blind modes. As explained, for blind mode, or during periods of downhole signal loss or instability, the process may be able to generate an optimal HBE.

[0209] As described above, the estimation process may include filtering or no filtering. As described above, the estimation process may utilize linear regression filters, piecewise linear filters with varying steering settings, multivariate piecewise linear filters, multivariate piecewise linear filters with uncertainties, one or more types of Kalman filters (e.g., extended Kalman filters, unscented Kalman filters, etc.), particle filters, basic median filters, Gaussian process-based filters, etc.

[0210] As an example, the framework can utilize one or more types of models, which can be or include one or more types of recursive models, machine learning (ML) models, combinations of model types, etc. For example, consider a data-driven Kalman filter as a model, which is an efficient recursive filter that can be used to estimate the state of a dynamic system from a series of measurements that may have associated uncertainties. As an example, a Kalman filter model can be implemented as an optimal online learning technique for systems that may include noise (e.g., Gaussian, etc.). As an example, the model can be a predictive model that can receive inputs and generate outputs as predicted outputs. While Kalman filter models are mentioned, additionally or alternatively, one or more other types of models can be utilized. For example, consider a neural network model as a type of ML model. As an example, the model can include one or more recursive features and / or one or more recursive features. Recursive Neural Networks (RNNs) can be implemented as models by the framework to process sequential data (e.g., time series and / or deep sequences) to generate outputs (e.g., HBE). RNNs can include structures such as Long Short-Term Memory (LSTM). RNNs can include connections between nodes that can create recurrent connections, allowing outputs from some nodes to influence subsequent inputs to the same node. This structure allows RNNs to exhibit time-dynamic behavior. Derived from feedforward neural networks, RNNs can use their internal states (e.g., memory) to process input sequences of variable length.

[0211] As explained, various types of filters can include predictive correction architectures, where predictions can utilize one or more types of models (e.g., predictive models, etc.). As an example, a filter can provide a prediction of the future state of a system based on past estimates. As an example, a filter can provide one or more predictions that can be very similar to what one or more measurements should be, with little or no uncertainty than one or more corresponding actual measurements. As explained, actual measurements (e.g., sensor data, results based on sensor data, etc.) can include uncertainties due to one or more factors (e.g., sensor mechanics and / or electronics, temperature, vibration, shock, etc.).

[0212] As an example, filter-based methods can be designed to improve results based on sensor data. For instance, sensor data may contain uncertainties attributable to one or more factors, causing the results based on sensor data to also contain uncertainty. As an example, filter-based methods can provide efficient smoothing, which can be based on the use of models such as predictive models. As an example, optimal state estimation can be based in part on predicted state estimates and sensor data. As an example, in a predictive-correction architecture, sensor data can provide corrections that can be beneficial to the optimal state estimation. As an example, in various examples, correction can be considered as updates based on sensor data. As an example, filters can operate by performing state vector prediction, covariance prediction, gain calculation, and updating the state estimate and covariance by receiving sensor data. In such examples, the result can be an estimated state and the covariance of the estimated state (e.g., uncertainty, etc.).

[0213] exist Figure 15 In the example, predictor 1550 may include one or more types of features for making predictions, which may include features for both prediction and correction. As explained, predictions may be model-based, where the model may be a physics-based model, a data-driven model (e.g., an ML model), a hybrid model (e.g., physics and data-driven), etc. As explained, various modes can be used to perform drilling. As an example, one or more types of models can be used to model such modes. For example, a model for a slip mode may differ from a model for a rotation mode, where one or more differences may depend on controls, operations, parameters, equipment, interactions between the equipment and rock and / or fluids, etc. Regarding the prediction-correction architecture described above, the prediction and / or correction portions may depend on the mode. For example, as mentioned above, correction may depend on sensor data, where, for example, a particular mode may provide specific sensor data that may differ from sensor data of another mode in one or more aspects.

[0214] As an example, one or more models may depend on parameters such as, for example, walking rate (WR), sloping rate (BR), output (Y), tool surface (TF), ROP, etc. As an example, parameters may include one or more trend parameters, one or more steering ratio parameters, one or more tool surface parameters, etc. As explained, models may differ for different modes. As an example, parameters may differ for different models. As an example, one or more models may provide estimated variations in orientation (e.g., slope and / or azimuth).

[0215] As an example, gyroscope sensor data can be utilized, where such data can improve the determination of orientation. For instance, gyroscope sensor data (e.g., consider GYROSPHERE tool data, etc.) can provide a more accurate azimuth mapping, making the orientation of the HBE more precise. As another example, gyroscope sensor data can help reduce orientation uncertainty (e.g., reduce azimuth uncertainty, etc.).

[0216] exist Figure 15 In the example, the adaptive filter 1500 can facilitate robust, automated operation. For instance, the adaptive filter 1500 can operate to automatically detect operating patterns and then automatically select an appropriate model (e.g., a filter) for the detected patterns. This approach can reduce the need for human intervention (e.g., requiring Human-Machine Loop (HITL)). This approach can also operate more robustly and objectively than humans, for example, by making more consistent and timely decisions about the model to be used. As an example, the adaptive filter 1500 can receive time and / or depth data according to input box 530, where such data can be processed, for example, for outlier removal, for reconciliation, etc.

[0217] exist Figure 15 In the example, predictor 1550 may also include one or more models for mud motor types used in drill strings, for modes such as sliding and rotation. Figure 15 In the examples, each model can be trained, configured, etc., for a specific mode. For example, consider using data acquired during one or more modes to train one or more ML models. In such an example, data acquired during HI directional drilling could be used to train HI model 1554. As explained, Figure 15 The adaptive filter 1500 can be part of a larger system or framework that can provide one or more levels of autonomous directional drilling.

[0218] As an example, the framework can utilize one or more inference techniques to determine patterns. For instance, consider a framework receiving both downhole and surface data, where the framework can detect the steering pattern used for directional drilling. In this example, the model can detect whether the drill string equipped with a mud motor is in slippery or rotary mode. Similarly, in the case where the drill string includes an RSS (Reverse Slip Spectrum), the framework can detect the current RSS pattern. As an example, directional drilling can be operated according to a digital plan to drill multiple standoffs under a specific pattern. In such an example, the framework can be able to confirm the pattern and, if not confirmed, perform HBE (High-Performance Behavior Optimization) using the detected pattern. This approach provides enhanced automated supervision to ensure that the actual patterns used are confirmed, and that the appropriate model used by the framework for the purpose of HBE ensures that the predicted HBE is accurate.

[0219] As an example, blind mode can utilize one or more types of ML models. As explained, blind mode can operate even when some data is unavailable. As an example, for each mode of the predictor, there can be a blind mode model and a non-blind mode model. As explained, in cases where the drill string includes RSS (e.g., an RSS tool), blind mode can be implemented if the data is unavailable and / or unreliable for RSS (e.g., too uncertain, etc.). As explained, blind mode can operate as a background mode, optionally using one or more types of available information, such as information from ground listeners, for example. As explained, information from ground listeners can be used to infer the state of the RSS. As an example, one or more ML models can be used to perform such inference. In such examples, when inference is performed as part of a background process, some information can be used for purposes such as labeling, validation, etc., allowing for improvements in ML model training and / or testing. For example, consider using information from ground listeners and information from the RSS uplink (if available) to improve ML model training and / or testing so that an improved ML model can be implemented as needed, which may be in blind mode where the RSS uplink is unavailable or uncertain (e.g., unreliable).

[0220] Figure 16 An example of a graphical user interface (GUI) 1600 that can be presented to a display for interaction with a human-machine interface (HMI) is shown. Figure 16 In the example, GUI 1600 shows reservoir 1602 and trajectory 1604, where, for example, a cursor can be positioned at a selected point on trajectory 1604, allowing the depth and orientation of trajectory 1604 to be displayed. For example, consider example GUI 1610, which can show a representation of the trajectory, which may have been generated as a BHE, along with depth and orientation (e.g., inclination and azimuth). As explained, the system can provide appropriate reference to maintain during drilling operations to ultimately orient the borehole toward one or more desired targets. GUI 1600 can be associated with a data structure for trajectory 1604, which includes information about the location and orientation of trajectory 1604 at various points, and this data structure can be relatively continuous (e.g., via smoothing, etc.).

[0221] Figure 17Exemplary plots 1710 and 1720 are shown, respectively, of inclination versus measured depth and azimuth versus measured depth. In each of plots 1710 and 1720, the corresponding solutions are shown as the output of a framework from which HB estimation can be performed, where the HBE essentially covers the survey point (see points covered by circles). Furthermore, the raw RSS inclination is shown in plot 1710, and the raw RSS azimuth is shown in plot 1720. Regarding these raw RSS values ​​acquired by the RSS sensor array, variations in deviation are shown at lower depths (e.g., 10,000 to 15,000 feet), followed by substantially constant and sporadic outliers in subsequent depth ranges (e.g., 15,000 to 20,000 feet). As an example, such values ​​could be evaluated according to one or more criteria and considered unreliable, making them unsuitable for updating predictions (e.g., HBE).

[0222] Furthermore, in Figure 1720, the offset between values ​​is shown, which can be considered as an azimuth offset. As shown, the azimuth offset remains relatively constant at depths ranging from approximately 15,000 feet to approximately 30,000 feet.

[0223] As explained, the survey can be a static survey, which can be performed, for example, during a period when drilling is temporarily stopped to add standoffs (e.g., one or more lengths of drill pipe) or at another time when drilling is temporarily stopped. Regarding standoffs, each standoff can be two or three single joints of drill pipe or drill collar, which can be added during drilling operations to extend the borehole. As an example, the length of a single joint of drill pipe can be approximately 9.6 m (e.g., approximately 31.6 feet), allowing static surveys of standoffs to be performed at intervals of approximately 20 m to approximately 30 m. As an example, if there is uncertainty regarding the location of the drill bit, drilling can be stopped to perform a static survey.

[0224] In example drawings 1710 and 1720, the raw RSS values ​​can indicate one or more issues (e.g., noise, offset, etc.) regarding measurements from the RSS sensor array. As shown, the solutions for tilt and azimuth generated by the frame can be acceptablely accurate even without RSS measurements. As explained, one or more criteria can be used to exclude one or more types of measurements, which can be, or include, for example, RSS measurements. In this approach, noisy measurements can be excluded.

[0225] In example drawings 1710 and 1720, where an offset does exist, it can be flagged and / or tracked. For example, in drawing 1720, the azimuth offset can be calculated by the frame, where the azimuth offset can be an indicator of one or more issues and / or can be used to adjust measurements in response to the presence of an offset. As explained, an RSS sensor array can generate measurements of the offset to the bottom of the tool (e.g., to the drill bit); however, the measured azimuth itself may have an offset, which can be adjusted as discussed with respect to the offset in drawing 1720. As an example, the offset can occur in the tilt and is referred to as the tilt offset; however, typically, the tilt offset tends to be relatively small and smaller than the azimuth offset.

[0226] Regarding the final set of values, the framework can perform smoothing so that the values ​​of the drilled borehole are consistent, for example, with respect to one or more types of continuity measures. For example, consider using one or more parametric continuity measures, such as C0, C1, C2, etc. With C0, it means the zeroth derivative is continuous (curve continuous). With C1, it means the zeroth and first derivatives are continuous. With C2, it means the zeroth, first, and second derivatives are continuous. With Cn, it means the zeroth to nth derivatives are continuous. Smoothing may be suitable, especially when using a drill string to form the borehole, which is a continuous string of devices with characteristics and shapes that do not provide sharp bends; it should be noted that the mud motor may include bends that may be slightly sharper (e.g., discontinuous at one or more derivatives) compared to the curvature achievable by the drill string. As an example, smoothing can smooth the HB depth and HB orientation. As an example, one or more interpolation techniques can be utilized for smoothing and other purposes. As an example, the minimum curvature interpolation technique can be employed.

[0227] As an example, the framework can provide an estimate of the position of HB in terms of tilt and azimuth, for example, using one or more optimal and adaptive filtering techniques with uncertainties that can be used as outputs.

[0228] As an example, the framework can provide estimation of HB by combining RSS continuous data measurements, MWD continuous data measurements, exploration measurements, and one or more types of additional downhole D&I measurements and / or surface information.

[0229] As an example, the framework can provide HB estimation when drilling using a drill string with RSS enabled.

[0230] As an example, the framework can provide an estimate of HB when drilling using a mud motor as a steerable tool.

[0231] As an example, the framework can provide a trajectory for estimating HB, which can also interpolate the wellbore at a given depth between the ground and the current HB location.

[0232] As an example, the framework can provide a path for estimating HB, which can also extrapolate the trajectory of the wellbore at a given depth from the current bottom position to one or more next targets or further.

[0233] As an example, the framework can provide a way to estimate HB that can handle outliers in sensor output while still generating accurate predictions of HB.

[0234] As an example, the framework can provide a way to estimate HB even when RSS communication of the drill string is lost.

[0235] As an example, the framework can provide an estimate of HB even when drilling is substantially parallel to the exclusion zone.

[0236] As an example, the framework can provide a means to obtain a high-resolution wellbore trajectory, which can be part of a post-drilling process (e.g., post-processing). As explained, some time after drilling, various types of data that can be acquired at different times and / or depths can be used to generate an optimal HBE (High-Definition Wellbore Path), which can then be correlated with a digital file of the well. In such an example, the digital file can be used for one or more purposes, which can include well completion, injection, production, enhancement, collision avoidance for one or more other wells to be drilled, etc.

[0237] As an example, the framework can generate high-resolution borehole trajectories that can be used for one or more purposes, such as, for instance, deriving accurate 3D positioning, including more accurate TVD estimates, more accurate N / S estimates (northward estimates), and / or more accurate E / W estimates (eastward estimates). This approach can be particularly useful in geologically guided scenarios, where, as explained, directional drilling within reservoirs can present particular challenges.

[0238] Figure 18 An example of method 1800 is shown, which may include a receiving box 810 for receiving real-time downhole data from one or more sensors of a drill string located in a borehole in a subsurface geological area during a directional drilling operation, wherein the drill bit of the drill string breaks up rock in the subsurface geological area to extend the borehole; a selection box 820 for selecting a drill string drilling mode from a plurality of drill string drilling modes, wherein the drill string drilling modes include an associated drilling mode model for the directional drilling operation; a prediction box 830 for predicting in real-time characteristics of the bottom of the borehole using the drilling mode model and at least a portion of the real-time downhole data, wherein, for example, the bottom of the borehole characteristics may include depth and orientation; and a control box 840 for controlling the directional drilling operation using one or more characteristics.

[0239] like Figure 18As shown, method 1800 can be implemented via one or more computer-readable media (CRMs) for each of boxes 1811, 1821, 1831, and 1841, which can, for example, use a computing system (see example...). Figure 3 Example system 300 Figure 7 This can be implemented using systems such as the example system 770, etc. Such a frame can include processor-executable instructions.

[0240] As explained, various systems, methods, etc., can implement one or more ML models. Regarding the types of ML models, consider one or more of the following: Support Vector Machine (SVM) models, k-Nearest Neighbor (KNN) models, ensemble classifier models, neural network (NN) models, incremental learning, Q-learning, etc. As examples, machine learning models can be deep learning models (e.g., deep Boltzmann machines, deep belief networks, convolutional neural networks, stacked autoencoders, etc.), ensemble models (e.g., random forests, gradient boosting machines, bootstrap aggregation, adaptive boosting (AdaBoost), stacked generalization, gradient boosting regression trees, etc.), neural network models (e.g., radial basis function networks, perceptrons, backpropagation, Hopfield networks, etc.), regularization models (e.g., ridge regression, minimum absolute shrinkage and selection operators, elastic networks, minimum angle regression), rule system models (e.g., cube, one-rule, zero-rule, repeated incremental pruning to produce error reduction), and regression models (e.g., linear regression, ordinary least squares regression, stepwise regression, multivariate adaptive regression splines, local estimation scatter plot smoothing, logistic regression). Examples of models include: Bayesian models (e.g., Naive Bayes, Average Dependency Estimator, Bayesian Belief Network, Gaussian Naive Bayes, Multinomial Naive Bayes, Bayesian Network), Decision Tree models (e.g., Classification and Regression Trees, Iterative Bisection 3, C4.5, C5.0, Chi-square Automatic Interaction Detection, Decision Stumps, Conditional Decision Trees, M5), Dimensionality Reduction models (e.g., Principal Component Analysis, Partial Least Squares Regression, Sammon Mapping, Multidimensional Scaling, Projective Pursuit, Principal Component Regression, Partial Least Squares Discriminant Analysis, Mixed Discriminant Analysis, Quadratic Discriminant Analysis, Regularized Discriminant Analysis, Flexible Discriminant Analysis, Linear Discriminant Analysis, etc.), Instance models (e.g., k-Nearest Neighbors, Learned Vector Quantization, Self-Organizing Map, Locally Weighted Learning, etc.), and Clustering models (e.g., k-means, k-median, Expectation Maximization, Hierarchical Clustering, etc.).

[0241] As an example, the system can utilize one or more recurrent neural networks (RNNs). One type of RNN is called Long Short-Term Memory (LSTM), which can be a unit or component (e.g., one or more units) that can be located in one or more layers. An LSTM component can be an artificial neural network (ANN) designed to recognize patterns in a sequence of data (e.g., time-series data). When time-series data is provided, LSTMs consider both time and sequence, allowing them to include a temporal dimension. For example, consider using one or more RNNs to process temporal data from one or more sources, optionally combined with spatial data. This approach can identify temporal patterns, which can be used for predictions (e.g., one or more patterns about future times, etc.).

[0242] As examples, the TENSORFLOW framework (Google LLC, Mountain View, California) can be implemented. It is an open-source software library for dataflow programming, including a symbolic mathematics library, which can be implemented for machine learning applications that may include neural networks. As an example, the CAFFE framework can be implemented, a DL framework developed by Berkeley AI Research (BAIR) (University of California, Berkeley). As another example, consider utilizing the SCIKIT platform (e.g., scikit-learn) of the Python programming language. As an example, frameworks such as the APOLLO AI framework (APOLLO.AI GmbH, Germany) can be utilized. As mentioned above, frameworks such as the PYTORCH framework can be used.

[0243] As an example, training methods can include various actions that can be performed on the dataset to train the ML model. As another example, the dataset can be split into training and testing data, where the testing data can be provided for evaluation. One approach could include cross-validation of parameters and optimal parameters, which can be provided for model training.

[0244] The TENSORFLOW framework can run on multiple CPUs and GPUs (with optional CUDA (NVIDIA, Santa Clara, California) and SYCL (Khronos Group Inc., Beaverton, Oregon) extensions for general-purpose computing on graphics processing units (GPUs). TENSORFLOW is available on 64-bit Linux, macOS (Apple, Cupertino, California), Windows (Microsoft, Redmond, Washington), and mobile computing platforms including Android (Google, Mountain View, California) and iOS (Apple).

[0245] TENSORFLOW computation can be represented as a stateful data flow graph; note that the name TENSORFLOW derives from the operation performed by this neural network on a multidimensional data array. Such an array can be called a "tensor".

[0246] As an example, an ML model can run online using cloud computing resources, and then there's a method for automatically feeding data into the target well of the ML model, allowing it to be updated at a given frequency. As another example, an ML model can run offline, where one or more results can be sent to a planning workflow.

[0247] As an example, a method may include: receiving real-time downhole data from one or more sensors of a drill string positioned in a borehole in a subsurface geological area during a directional drilling operation, wherein the drill bit of the drill string breaks up rock in the subsurface geological area to lengthen the borehole; selecting a drill string drilling mode from a plurality of drill string drilling modes, wherein the drill string drilling mode includes an associated drilling mode model for the directional drilling operation; using the drilling mode model and at least a portion of the real-time downhole data to predict, in real-time, bottomhole characteristics of the borehole; and using one or more of the characteristics to control the directional drilling operation.

[0248] In such an example, the characteristics of the bottom of the well may include depth and orientation, wherein, for example, depth includes the measured depth and orientation includes inclination and azimuth.

[0249] As an example, a drilling pattern model for directional drilling operations may include one or more machine learning models. As another example, a drilling pattern model may be a filter that includes one or more machine learning models.

[0250] As an example, one approach may include controls that can adjust the orientation of the drill bit in a drill string to drill to a target location in an underground geological region.

[0251] As an example, one or more sensors on the drill string may include one or more measurement-while-drilling (MWD) sensors and / or one or more rotary steerable system (RSS) sensors.

[0252] As an example, one or more sensors in the drill string may include one or more microelectromechanical system (MEMS) gyroscope sensors that generate gyroscope sensor data that can improve the accuracy of bottom-hole orientation predictions for the borehole. As explained, a series of bottom-hole predictions (e.g., estimates) can be used to form a model of the borehole, including its depth and orientation characteristics. As an example, such a model of the borehole can be used for one or more purposes, which may include, for example, planning one or more wells, performing collision avoidance processes (e.g., during planning, drilling, etc.).

[0253] As an example, the drill string may include a mud motor and may not include a rotary steerable system (RSS), wherein multiple drill string drilling modes may include a sliding mode and a rotary mode.

[0254] As an example, the method may include controls that can control geological steering. For example, consider geological steering, which can keep the drill bit of the drill string within a reservoir partially defined by an upper depth (e.g., the top) and a lower depth (e.g., the bottom). As an example, the layers may be defined by interfaces or boundaries, where, for example, a reservoir may exist between two other layers, wherein the reservoir has an interface or boundary with one layer and an interface or boundary with the other layer. As an example, the reservoir may include a fluid, such as a hydrocarbon fluid.

[0255] As an example, a method may include estimating the true vertical depth based at least in part on one or more characteristics of the bottom of the well.

[0256] As an example, the method may include estimating one or more of the north and east directions based at least in part on one or more features at the bottom of the well.

[0257] As an example, multiple drill string drilling modes can include one or more hold-in-tilt modes. As an example, one or more models can be used to model such hold-in-tilt modes.

[0258] As an example, the method may include receiving real-time static survey data acquired during a period in which directional drilling operations can be stopped. As explained, directional drilling may include adding drill pipe to a drill string, wherein a connection is formed between the drill pipe and the drill string. During the connection, directional drilling operations may be stopped. For example, the drill bit of the drill string may be stopped from breaking rock to extend the directional drilling operation of the borehole. As explained, when directional drilling operations are stopped, one or more types of static surveys may be performed.

[0259] As an example, one approach could include prediction, which could include predicting at least one characteristic of the future bottom of the borehole. In such an example, considering the actual time at which the future bottom of the borehole is created, additional real-time downhole data is received and the prediction of at least one characteristic is updated based at least in part on the additional real-time downhole data.

[0260] As an example, a method may include pulling the drill string out of the borehole after performing a directional drilling operation and acquiring data during the drill string pulling out of the borehole, wherein one or more characteristics may be adjusted to generate a set of features of the borehole, wherein the adjustment utilizes at least a portion of the acquired data. As an example, the method may also include running the drill string into the borehole after pulling the drill string out of the borehole, acquiring data during the drill string running into the borehole, and adjusting one or more characteristics to generate a modified set of features of the borehole.

[0261] As an example, the system may include one or more processors; at least one of the processors has processor-accessible memory; processor-executable instructions stored in the memory and executable to instruct the system to: receive real-time downhole data from one or more sensors of a drill string disposed in a borehole in a subsurface geological region during a directional drilling operation, wherein the drill bit of the drill string breaks rocks in the subsurface geological region to extend the borehole; select a drill string drilling mode from a plurality of drill string drilling modes, wherein the drill string drilling mode includes an associated drilling mode model for the directional drilling operation; predict the bottom hole characteristics of the borehole in real time using the drilling mode model and at least a portion of the real-time downhole data; and control the directional drilling operation using one or more of the characteristics.

[0262] As an example, one or more non-transitory computer-readable storage media may include processor-executable instructions to instruct a computing system to: receive real-time downhole data from one or more sensors of a drill string disposed in a borehole in a subsurface geological region during a directional drilling operation, wherein the drill bit of the drill string breaks rock in the subsurface geological region to lengthen the borehole; select a drill string drilling mode from a plurality of drill string drilling modes, wherein the drill string drilling mode includes an associated drilling mode model for the directional drilling operation; use the drilling mode model and at least a portion of the real-time downhole data to predict in real-time characteristics of the bottom of the borehole; and use one or more of the characteristics to control the directional drilling operation.

[0263] As an example, a computer program product may 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., partially, wholly, and / or in various combinations).

[0264] The embodiments disclosed in this disclosure are provided 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 precise embodiments of this disclosure may still be within the scope of the claims.

[0265] Similarly, the described steps need not be performed in the same order or with the same degree of separation as discussed. Various steps may be appropriately omitted, repeated, combined, or divided. Therefore, this disclosure is not limited to the embodiments described above, but is defined by the appended claims in their entirety according to their equivalents. In the above description and the following claims, unless otherwise stated, the term "execution" and variations thereof should be interpreted as relating to any operation of program code or instructions on the device, whether compiled, interpreted, or operated using other techniques.

[0266] Some of the following claims may include a list of numbers. Numbers are provided as an organizational tool to aid readability. The numbers themselves do not indicate an intended order of configuration or execution, nor do they have any substantial meaning. For the purposes of the U.S. application, the appended claims do not invoke section 112(f) unless the phrase “means for…” is explicitly used in conjunction with the associated function.

Claims

1. A method (1800) comprising: During directional drilling operations, real-time downhole data is received from one or more sensors in a drill string located in a borehole in an underground geological area, where the drill bit breaks the rock in the underground geological area to extend the borehole (1810). Select a drill string drilling mode from a plurality of drill string drilling modes, wherein the drill string drilling mode includes an associated drilling mode model (1820) for the directional drilling operation. Using the drilling model and at least a portion of the real-time downhole data to predict the bottom-hole characteristics of the borehole in real time (1830); and Use one or more of the features to control the directional drilling operation (1840).

2. The method of claim 1, wherein the features of the well bottom include depth and orientation, wherein the depth includes a measured depth, and the orientation includes inclination and azimuth.

3. The method according to claim 1 or 2, wherein the drilling mode model for the directional drilling operation includes a machine learning model.

4. The method according to any one of the preceding claims, wherein the control includes adjusting the orientation of the drill bit of the drill string to drill to a target location in the underground geological region.

5. The method according to any one of the preceding claims, wherein the one or more sensors of the drill string include one or more measurement-while-drilling (MWD) sensors and one or more rotary steerable system (RSS) sensors.

6. The method according to any one of the preceding claims, wherein, One or more sensors in the drill string include one or more microelectromechanical system (MEMS) gyroscope sensors, which generate gyroscope sensor data that improves the accuracy of orientation prediction at the bottom of the borehole.

7. The method according to any one of the preceding claims, wherein the drill string includes a mud motor and does not include a rotary steerable system (RSS), and wherein the plurality of drill string drilling modes include a sliding mode and a rotary mode.

8. The method according to any one of the preceding claims, wherein the control controls the geological steering, optionally wherein the geological steering maintains the drill bit of the drill string within a reservoir partially defined by an upper depth and a lower depth.

9. The method according to any one of the preceding claims, comprising estimating one or more of the northward depth, eastward depth, and true vertical depth based at least in part on one or more of the characteristics of the well bottom.

10. The method according to any one of the preceding claims, wherein the plurality of drill string drilling modes include one or more inclination maintenance modes.

11. The method according to any one of the preceding claims, comprising receiving real-time static survey data acquired during a period in which the directional drilling operation is stopped.

12. The method according to any one of the preceding claims, wherein, The prediction also includes predicting at least one feature of the future bottom of the borehole, and optionally includes: receiving additional real-time downhole data at the actual time the future bottom of the borehole is created, and updating the prediction of the at least one feature based at least in part on the additional real-time downhole data.

13. The method according to any one of the preceding claims, comprising pulling the drill string out of the borehole after performing the directional drilling operation, and acquiring data during pulling the drill string out of the borehole, wherein one or more of the features are adjusted to generate a set of features of the borehole, wherein the adjustment utilizes at least a portion of the acquired data, and optionally includes feeding the drill string into the borehole after pulling the drill string out of the borehole, acquiring data during feeding the drill string into the borehole, and adjusting one or more of the features to generate a modified set of features of the borehole.

14. A system (300) comprising: One or more processors (302); Memory (304), the memory being accessible by at least one of the one or more processors; Processor-executable instructions (312), which are stored in the memory and executable to instruct the system: During directional drilling operations, real-time downhole data is received from one or more sensors in a drill string located in a borehole in an underground geological area, wherein the drill bit of the drill string breaks the rock in the underground geological area to extend the borehole (1811). Select a drilling string mode from a plurality of drilling string modes, wherein the drilling string mode includes an associated drilling mode model (1821) for the directional drilling operation. Using the drilling model and at least a portion of the real-time downhole data to predict the bottom-hole characteristics of the borehole in real time (1831); and Use one or more of the features to control the directional drilling operation (1841).

15. A computer program product comprising computer-executable instructions to instruct a computing system to perform the method according to any one of claims 1 to 13.

Images