Well drilling frame

Abstract

A method may include generating an optimal operating window (OOW) specifying operating parameter values for a drilling operation using equipment at a drilling rig site based on data indicative of rig status and formation characteristics and based on a mutation-based optimization of the operating parameter values; and instructing the control system to perform a drilling operation according to the OOW using a device at the drilling rig site.

Description

[0001] Related Applications

[0002] This application claims priority to and the benefit of U.S. Provisional Application Serial No. 63 / 368,981, filed on July 21, 2022, the entire contents of which are incorporated herein by reference. Background Art

[0003] A reservoir can be an underground formation that can be characterized, at least in part, by its porosity and fluid penetration rate. 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 tectonic activity, subsidence, etc.). As an example, in the presence of source rocks in combination with appropriate burial depth and duration, a petroleum system can be developed within a basin, which can form a reservoir including hydrocarbon fluids (e.g., oil, gas, etc.). In the case where a reservoir includes a producible hydrocarbon fluid, one or more wells drilled at one or more well sites can provide production of such hydrocarbon fluids.

[0004] Operations at a wellsite involve a range of activities using many different tools and equipment. During planning and operations, the wellsite team decides what parameters to use for the equipment when performing various well construction tasks, which may depend on factors such as the condition of the equipment, the characteristics of the formation, the objectives, etc. For example, if a stick-slip condition is encountered, the equipment may be controlled to reduce the weight on bit (WOB) and increase the rotational speed of the drill bit (e.g., drill bit RPM); note that the drill bit may be rotated via one or more mechanisms (e.g., top drive, mud motor, etc.).

[0005] Experienced personnel know how to set appropriate parameters, the trade-offs associated with different parameter values, and a lot of knowledge about how different parameters lead to different results. Therefore, less experienced personnel may not have the experience of making the same decisions as experienced personnel. And, even in experienced teams, the team's understanding is based on its own experience and may not be suitable for every situation. Therefore, the parameters actually implemented to perform field operations may vary in a way that may lead to inconsistent results and quality. For example, in the case where two teams are operating a drilling rig to drill two different wellbores at two different well sites in a common reservoir, depending on expertise, conventions, etc., the selected parameters and / or parameter values ​​may be different, which may lead to differences in the resulting wellbores, which may involve wellbore quality. One or more of a variety of metrics can be used to determine the quality of the borehole. For example, consider one or more of borehole stability (e.g., geomechanical stability), reservoir contact, relative to the planned drilling trajectory, etc. Wellbore quality may affect completion, including completion operations and completion equipment, as well as the production of hydrocarbon fluids. Summary of the invention

[0006] A method may include generating an optimal operating window (OOW) based on data indicating a rig state and formation characteristics and based on a mutation-based optimization of operating parameter values, the OOW specifying operating parameter values ​​for a drilling operation using equipment at a rig site. The method may also include instructing a control system to perform a drilling operation in accordance with the OOW using equipment at the rig site. A system may include: at least one processor; a memory accessible to at least one of the at least one processors; processor-executable instructions stored in the memory and executable to instruct the system to: generate an optimal operating window (OOW) based on data indicating a rig state and formation characteristics and based on a mutation-based optimization of operating parameter values, the optimal operating window specifying operating parameter values ​​for a drilling operation using equipment at the rig site. The system may also include instructions for instructing the control system to perform a drilling operation in accordance with the OOW using equipment at the rig site. One or more non-transitory computer-readable storage media may include processor-executable instructions to instruct a computing system to generate an optimal operating window (OOW) based on data indicating a drilling rig state and formation characteristics and based on mutation-based optimization of operating parameter values, the OOW specifying operating parameter values ​​for a drilling operation using equipment at the rig site. The one or more non-transitory computer-readable storage media may also include instructions for instructing a control system to perform a drilling operation in accordance with the OOW using equipment at the rig site. Various other apparatus, systems, methods, etc. are also disclosed.

[0007] This Summary is provided to introduce a selection of concepts that are further described below in the Detailed Description. This Summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used as an aid in limiting the scope of the claimed subject matter. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The following detailed description refers to the accompanying drawings. Any convenient features and advantages of the described embodiments may be more readily understood by referring to the following description taken in conjunction with the accompanying drawings.

[0009] Figure 1 An example of a system is shown;

[0010] Figure 2 An example of a system is shown;

[0011] Figure 3 An example of a system is shown;

[0012] Figure 4 An example of a workflow is shown;

[0013] Figure 5 An example of a graphical user interface (GUI) is shown;

[0014] Figure 6 An example of a graphical user interface (GUI) is shown;

[0015] Figure 7 An example of a graphical user interface (GUI) is shown;

[0016] Figure 8 An example of a workflow is shown;

[0017] Fig. 9 An example of a graphical user interface (GUI) is shown;

[0018] Fig.10 An example of a process is shown;

[0019] Fig.11 An example of a process is shown;

[0020] Fig.12 An example of a workflow is shown;

[0021] Fig.13 An example of a graphical user interface (GUI) is shown;

[0022] Fig.14 An example of a graphical user interface (GUI) is shown;

[0023] Fig.15 An example of a graphical user interface (GUI) is shown;

[0024] Fig.16 An example of a graphical user interface (GUI) is shown;

[0025] Fig.17 An example of a graphical user interface (GUI) is shown;

[0026] Fig.18 An example of a graphical user interface (GUI) is shown;

[0027] Fig.19 An example of a workflow is shown;

[0028] Fig. 20 An example of a process is shown;

[0029] Fig.21 An example of a process is shown;

[0030] Fig. 22 An example of a graphical user interface (GUI) is shown;

[0031] Fig.23 Examples of graphical user interfaces (GUIs) and examples of methods are shown;

[0032] Fig.24An example of a graphical user interface (GUI) is shown; and

[0033] Fig.25 An example of a method is shown. DETAILED DESCRIPTION

[0034] This description should not be taken in a limiting sense but is merely for the purpose of describing the general principles of implementations. Reference should be made to the issued claims to determine the scope of the described embodiments.

[0035] Figure 1 An example of a system 100 is shown that includes a workspace framework 110 that can provide instantiation, rendering, interaction, etc. of a graphical user interface (GUI) 120. Figure 1 In the example of , GUI 120 may include graphical controls for a computing framework (eg, application, etc.) 121 , projects 122 , visualization 123 , one or more other features 124 , data access 125 , and data storage 126 .

[0036] exist Figure 1 In the example of , the workspace framework 110 can be customized for a specific geological environment (such as the example geological environment 150). For example, the geological environment 150 may include layers (e.g., strata) that include a reservoir 151 and may intersect with a fault 153. As an example, the geological environment 150 may be equipped with various sensors, detectors, actuators, and the like. For example, the device 152 may include communication circuits for receiving and sending information about one or more networks 155. Such information may include information associated with downhole equipment 154, which may be equipment for acquiring information, assisting in resource recovery, and the like. Other equipment 156 may be located away from the well site and include sensing, detection, transmission, or other circuits. Such equipment may include storage and communication circuits for storing and transmitting data, instructions, and the like. As an example, one or more satellites may be provided for purposes of communication, data acquisition, and the like. For example, Figure 1 A satellite is shown in communication with network 155, which may be configured for communications, noting that the satellite may additionally or alternatively include circuitry for imagery (e.g., spatial, spectral, temporal, radiometric, etc.).

[0037] Figure 1Also shown is a geological environment 150 that optionally includes equipment 157 and 158 associated with a well, the well including a substantially horizontal portion that may intersect 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 fractures and artificial fractures. As an example, a well may be drilled for a laterally extending reservoir. In such an example, there may be lateral changes in properties, stresses, etc., where the assessment of such changes may help planning, operations, etc. to develop a laterally extending reservoir (e.g., via fracturing, injection, extraction, etc.). As an example, equipment 157 and / or 158 may include components, a system, multiple systems, etc. for fracturing, seismic sensing, analysis of seismic data, assessment of one or more fractures, etc.

[0038] exist Figure 1 In the example of , GUI 120 shows some examples of computational frameworks, including DRILLPLAN, DRILLOPS, PETREL, TECHLOG, PETROMOD, ECLIPSE, PIPESIM, and INTERSECT frameworks (SLB, Houston, Texas).

[0039] The DRILLPLAN framework provides digital well construction planning and includes features for automation of repetitive tasks and validation workflows, enabling rapid generation of drilling programs (eg, digital drill plans, etc.) of improved quality with guaranteed consistency.

[0040] The DRILLOPS framework can execute digital drilling plans and ensure compliance with plans 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 rig or in town. Automation can use data analysis and learning systems to assist and optimize tasks, such as setting the ROP of the drill column. A preset menu of automatable drilling tasks can be presented, and using data analysis and models, plans can be executed in a way that achieves specified goals, where, for example, measurements can be used for calibration. The DRILLOPS framework provides the flexibility to dynamically modify and re-plan activities, for example, based on real-time assessments of various factors (e.g., equipment, personnel, and supplies). Feedback from operational activities can be used to continuously monitor and dynamically update well construction activities (e.g., tripping, drilling, cementing, etc.). The DRILLOPS framework can provide various levels of automation based on planning and / or re-planning (e.g., via the DRILLPLAN framework), feedback, etc.

[0041] The PETREL framework can be part of the DELFI environment for geoscience and geoengineering, for example, to analyze subsurface data from exploration to production of fluids from reservoirs. The DELFI cognitive exploration and production (E&P) environment (SLB, Houston, Texas), referred to herein as the DELFI environment or the 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.

[0042] The PETREL framework provides components that allow optimization of various exploration, development, and production operations. The PETREL framework includes a seismic-to-simulation software component that can output information for improving reservoir performance, such as by increasing asset team productivity. 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., with respect to one or more geological environments, etc.). 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 purposes of modeling, simulation, etc.).

[0043] 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 structure wellbore data for analysis, planning, etc.

[0044] The PETROMOD framework provides a petroleum system modeling capability that can combine one or more of seismic, well, and geological information to model the evolution of a sedimentary basin. The PETROMOD framework can predict whether and how a reservoir is filled with hydrocarbons, including the source and timing of hydrocarbon generation, migration routes, quantities, and types of hydrocarbons under subsurface or surface conditions.

[0045] The ECLIPSE framework provides numerical solutions for reservoir simulators (eg, as a computational framework) for quickly and accurately predicting the dynamic behavior of various types of reservoirs and development scenarios.

[0046] 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 utilizing the integration of accurate models of surface facilities and field operations, the INTERSECT framework can produce reliable results that can be continuously updated through real-time data exchange (e.g., from one or more types of data acquisition equipment in the field that can acquire data during one or more types of field operations, etc.). The INTERSECT framework can provide completion configurations for complex wells, where such configurations can be built in the field, can provide detailed enhanced oil recovery (EOR) recipes, where such recipes can be implemented in the field, can analyze the application of steam injection and other thermal EOR technologies for implementation in the field, advanced production control in terms of reservoir connection and flexible field management, and the flexibility to prepare customized solutions in advance to improve modeling and field management control. As with other example frameworks, the INTERSECT framework can be used as part of the DELFI environment, for example, for rapid simulation of multiple concurrent situations. For example, a workflow can utilize one or more DELFI environment on-demand reservoir simulation features.

[0047] The DELFI environment described above provides various features for workflows related to subsurface analysis, planning, construction, and production, as shown, for example, in the workspace framework 110. Figure 1 As shown, output from the workspace framework 110 can be used to guide, control, etc. one or more processes in the geological environment 150, and feedback 160 can be received in one or more forms (e.g., data obtained regarding operating conditions, equipment conditions, environmental conditions, etc.) via one or more interfaces.

[0048] As an example, the workflow may proceed to a geological and geophysical ("G&G") service provider, which may generate well trajectories, which may involve executing one or more G&G frameworks (eg, consider the PETREL framework, etc.).

[0049] exist Figure 1 In the example of , visualization features 123 can be implemented via workspace framework 110, for example, to perform tasks associated with one or more subsurface regions, planning operations, constructing wells and / or surface fluid networks, and producing from reservoirs.

[0050] As an example, a visualization feature may provide visualization of various earth models, features, and the like in one or more dimensions. As an example, a visualization feature may provide information rendered in multiple dimensions, which may optionally include multi-resolution rendering. In such an example, the rendered information may be associated with one or more frameworks and / or one or more data repositories. As an example, a visualization feature may include one or more control features for controlling a device, which may include, for example, a field device that may perform one or more field operations. As an example, a workflow may utilize one or more frameworks to generate information that may be used to control one or more types of field devices (e.g., drilling equipment, cable equipment, fracturing equipment, etc.).

[0051] With respect to reservoir models that may be suitable for simulator utilization, consider the acquisition of seismic data acquired via reflection seismology, which finds use in geophysics, for example, for estimating the properties of underground strata. As an example, reflection seismology can provide seismic data representing elastic energy waves (e.g., transmitted by P waves and S waves, in a frequency range of about 1 Hz to about 100 Hz). For example, seismic data can be processed and interpreted to better understand the composition, fluid content, degree, and geometry of underground rocks. Such interpretation results can be used to plan, simulate, perform, etc., one or more operations for producing fluids from a reservoir (e.g., reservoir rock, etc.).

[0052] As an example, the model can be a simulated version of a geological environment. As an example, a simulator can include features for simulating physical phenomena in a geological environment based at least in part on one or more models. A simulator such as a reservoir simulator can simulate fluid flow in a geological environment based at least in part on a model that can be generated via a framework that receives seismic data. A simulator can be a computerized system (e.g., a computing system) that can 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, a set of equations can be spatially defined (e.g., numerically discretized) according to a spatial model that includes layers of rocks, geological bodies, etc. with corresponding positions that can be based on interpretations of seismic and / or other data. A spatial model can be a cell-based model in which a cell is defined by a grid (e.g., a mesh). A cell in a cell-based model can represent a physical region or volume in a geological environment, in which a physical property (e.g., drilling rate, fluid properties, etc.) that may be closely related to one or more physical phenomena (e.g., fluid volume, fluid flow, pressure, etc.) can be assigned to a cell. A reservoir simulation model can be a cell-based spatial model.

[0053] Although in Figure 1Several simulators are shown in the examples, but one or more other simulators may be utilized in addition or alternatively. For example, consider the VISAGE geomechanical simulator (SLB, Houston, Texas) or the PIPESIM network simulator (SLB, Houston, Texas), etc. The VISAGE simulator includes a finite element numerical solver that can provide simulation results, such as the results of compaction and subsidence of the geological environment, the integrity of wells and completions in the geological environment, the integrity of cap rock and fault seals in the geological environment, the behavior of fractures in the geological environment, thermal production in the geological environment, CO2 disposal, etc. The PIPESIM simulator includes a solver that can provide simulation results, such as, for example, multiphase flow results (e.g., from the reservoir to the wellhead and beyond, etc.), flow lines and surface facility performance, etc. The PIPESIM simulator can be integrated, for example, with 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., considering 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 via simulation of physical phenomena. The MANGROVE simulator (SLB, Houston, Texas) provides optimization of stimulation designs (e.g., stimulation treatment operations such as hydraulic fracturing) in a reservoir-centric environment. The MANGROVE framework can combine scientific and experimental work to predict the geomechanical propagation of hydraulic fractures, the reactivation of natural fractures, etc., and production predictions within a 3D reservoir model (e.g., production from drainage areas of a reservoir where fluids move to and / or from a well via one or more types of fractures). The MANGROVE framework can provide results related to heterogeneous interactions between hydraulic and natural fracture networks, which can help optimize the number and location of fracture treatment stages (e.g., stimulation treatments), for example, to improve perforation efficiency and recovery.

[0054] As an example, a tool may be positioned to acquire information in a portion of a borehole. Analysis of such information may reveal cavities, dissolution planes (e.g., dissolution along bedding planes), stress-related features, tilt events, etc. As an example, a tool may acquire information that may help characterize a fractured reservoir, optionally where the fractures may be natural and / or artificial (e.g., hydraulic fractures). Such information may assist in well completions, stimulation treatments, etc. As an example, the information acquired by the tool may be analyzed using a framework such as the TECHLOG framework described above.

[0055] As an example, a workflow may use one or more types of data for one or more processes (e.g., formation modeling, basin modeling, completion design, drilling, production, injection, etc.). As an example, one or more tools may provide data that may be used in one or more workflows that may implement one or more frameworks (e.g., PETREL, TECHLOG, PETROMOD, ECLIPSE, etc.).

[0056] exist Figure 1 In the example of , drilling can be performed in a geological environment 150, for example, to access a reservoir 151 that can be accessed from land or sea. Figure 1 In the embodiment, the downhole equipment 154 can be, for example, part of a bottom hole assembly (BHA). The BHA can be used to drill a well. The downhole equipment 154 can transmit information to equipment at the surface, and can receive instructions and information from equipment at the surface. During the well construction process, various operations (such as cementing, cable evaluation, testing, etc.) can be performed. In such an embodiment, data collected by tools and sensors and used for reasons such as reservoir characterization can be collected and transmitted.

[0057] A well may include a substantially horizontal portion (e.g., a lateral portion) that may intersect one or more fractures. For example, a well in a shale formation may pass through natural fractures, artificial fractures (e.g., hydraulic fractures), or a combination thereof. Such a well may be constructed using directional drilling techniques as described herein. However, these same techniques may be used in conjunction with other types of directional wells (such as deviated wells, S-shaped wells, deep deviated wells, etc.), and are not limited to horizontal wells.

[0058] Figure 2 An example of a wellsite system 200 is shown (e.g., at a wellsite that may be onshore or offshore). As shown, the wellsite system 200 may include a mud tank 201 for holding mud and other materials (e.g., where the mud may be a drilling fluid), a suction line 203 that serves as an inlet for a mud pump 204 for pumping mud from the mud tank 201 so that the mud flows to a vibrating hose 206, a winch 207 for winding one or more drilling lines 212, a riser 208 that receives mud from the vibrating hose 206, and a kelly hose 208 that receives mud from the riser 208. 9. One or more goosenecks 210, a traveling block 211, a crown block 213 for carrying the traveling block 211 via one or more drilling pipelines 212, a derrick 214, a kelly 218 or a top drive 240, a kelly drive bushing 219, a rotary table 220, a drill floor 221, a bell joint 222, one or more blowout preventers (BOPs) 223, a drill string 225, a drill bit 226, a casing head 227, and a flow pipe 228 for conveying mud and other materials to, for example, a mud tank 201.

[0059] exist Figure 2 In the example system, a borehole 232 is formed in a subsurface formation 230 by rotary drilling; note that various example embodiments may also use one or more directional drilling techniques, equipment, etc.

[0060] like Figure 2 As shown in the example of FIG. 2 , a drill string 225 is suspended in a borehole 232 and has a drill string assembly 250 including a drill bit 226 at its lower end. As an example, the drill string assembly 250 may be a bottom hole assembly (BHA).

[0061] The wellsite system 200 can provide for the operation of the drill string 225 and other operations. As shown, the wellsite system 200 includes a traveling carriage 211 and a derrick 214 located above the wellbore 232. As described above, the wellsite system 200 can include a rotary table 220, wherein the drill string 225 passes through an opening in the rotary table 220.

[0062] like Figure 2 As shown in the example of , the wellsite system 200 may include a kelly 218 and associated components, or a top drive 240 and associated components. With respect to the kelly example, the kelly 218 may be a square or hexagonal metal / alloy rod in which the drilled hole serves as a mud flow path. The kelly 218 may be used to transfer rotational motion from the rotary table 220 to the drill string 225 via the kelly drive bushing 219, while allowing the drill string 225 to be lowered or raised during rotation. The kelly 218 may pass through the kelly drive bushing 219, which may be driven by the rotary table 220. As an example, the rotary table 220 may include a main bushing that is operably coupled to the kelly drive bushing 219 so that rotation of the rotary table 220 may rotate the kelly drive bushing 219, thereby rotating the kelly 218. The kelly drive bushing 219 may include an inner profile that matches the outer profile of the kelly 218 (eg, square, hexagonal, etc.); however, has a slightly larger size so that the kelly 218 can move freely up and down within the kelly drive bushing 219 .

[0063] With respect to the top drive example, the top drive 240 can provide the functions performed by the kelly and the rotary table. The top drive 240 can rotate the drill string 225. As an example, the top drive 240 can include one or more motors (e.g., electric and / or hydraulic) connected by an appropriate transmission to a short pipe section called a casing shaft, which in turn can be screwed into a saver sub or the drill string 225 itself. The top drive 240 can be suspended from the traveling block 211 so that the rotating mechanism can freely travel up and down the derrick 214. As an example, the top drive 240 can allow drilling to be performed with more joint columns than the kelly / rotary table method.

[0064] exist Figure 2 In the example of, mud tank 201 can contain mud, which can be one or more types of drilling fluids. As an example, a wellbore can be drilled to produce fluids, inject fluids, or both (e.g., hydrocarbons, minerals, water, etc.).

[0065] exist Figure 2 In the example of FIG. 2 , a drill string 225 (e.g., including one or more downhole tools) can be composed of a series of tubes threaded together to form a long tube with a drill bit 226 at its lower end. As the drill string 225 is advanced into the wellbore for drilling, mud can be pumped from a mud tank 201 (e.g., or other source) to a port of the kelly 218, or, for example, to a port of the top drive 240, via pipelines 206, 208, and 209 by a pump 204, prior to or at some point in time concurrent with the drilling. The mud can then flow out of a port located on the drill bit 226 via a channel (e.g., or multiple channels) in the drill string 225 (see, e.g., directional arrows). When the mud leaves the drill string 225 via the port in the drill bit 226, the mud can then circulate upward through an annular region between the outer surface of the drill string 225 and the surrounding wall (e.g., an open borehole, casing, etc.), as indicated by the directional arrows. In this manner, 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 recirculation (e.g., by processing to remove cuttings, etc.).

[0066] The mud pumped into the drill string 225 by the pump 204 can form a mud cake lining the wellbore after leaving the drill string 225, which, among other functions, can reduce the friction between the drill string 225 and the surrounding walls (e.g., borehole, casing, etc.). The reduction in friction can help to advance or retract the drill string 225. During the drilling operation, the entire drill string 225 can be pulled out of the wellbore and optionally replaced, for example, with a new or sharpened drill bit, a smaller diameter drill string, etc. As described above, the action of pulling the drill string out of the hole or replacing it in the hole is called tripping. Depending on the tripping direction, tripping can be called tripping up or tripping out or tripping down or tripping in.

[0067] As an example, consider drilling down, 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 for the purpose of drilling to expand the wellbore. As described above, the mud can be pumped into the channel of the drill string 225 by the pump 204, and when filling the channel, the mud can be used as a transmission medium to transmit energy, for example, energy that can encode information, such as in mud pulse telemetry.

[0068] As an example, a mud pulse telemetry device may include a downhole device configured to implement pressure changes in the mud to generate one or more acoustic waves on which information may be modulated. In such an example, information from the downhole device (e.g., one or more modules of the drill string 225) may be transmitted uphole to the uphole device, which may relay such information to other equipment for processing, control, etc.

[0069] As an example, the telemetry equipment may operate by transmitting energy through the drill string 225 itself. For example, consider a signal generator that imparts a coded energy signal to the drill string 225 and a repeater that may receive such energy and relay it for further transmission of the coded energy signal (e.g., information, etc.).

[0070] As an example, the drill string 225 may be equipped with a telemetry device 252, the telemetry device 252 including a rotatable drive shaft; a turbine wheel mechanically coupled to the drive shaft so that mud can cause the turbine wheel to rotate; a modulator rotor mechanically coupled to the drive shaft so that rotation of the turbine wheel causes the modulator rotor to rotate; a modulator stator mounted adjacent to or near the modulator rotor so that rotation of the modulator rotor relative to the modulator stator generates pressure pulses in the mud; and a controllable brake for selectively braking rotation of the modulator rotor to modulate the pressure pulses. In such an example, an alternator may be coupled to the drive shaft, wherein the alternator includes at least one stator winding electrically coupled to a control circuit to selectively short-circuit the at least one stator winding to electromagnetically brake the alternator, thereby selectively braking rotation of the modulator rotor to modulate pressure pulses in the mud.

[0071] exist Figure 2 In an example of, the uphole control and / or data acquisition system 262 may include circuitry that senses pressure pulses generated by the telemetry device 252 and transmits the sensed pressure pulses or information derived therefrom for use in a process, control, or the like, for example.

[0072] The assembly 250 of the illustrated example includes a logging while drilling (LWD) module 254, a measurement while drilling (MWD) module 256, an optional module 258, a rotary steerable system (RSS) and / or motor 260, and a drill bit 226. Such components or modules may be referred to as tools, wherein a drill string may include multiple tools.

[0073] With respect to RSS, it relates to techniques for directional drilling. Directional drilling involves drilling into the earth to form a deflected hole so that the trajectory of the hole is not vertical; rather, the trajectory deviates from vertical along one or more portions of the hole. As an example, consider a target located at a lateral distance from a surface location where a drill rig may be located. In such an example, the borehole may begin with a vertical portion and then deviate from vertical so that the hole is aimed at the target and ultimately reaches the target. Directional drilling may be implemented where the target may not be accessible from a vertical position at the surface of the earth, where there are materials in the earth that may impede drilling or be otherwise harmful (e.g., consider salt domes, etc.), where formations are laterally extended (e.g., consider relatively thin but laterally extended reservoirs), where multiple holes are to be drilled from a single surface hole, where relief wells are required, etc.

[0074] One method of directional drilling involves a mud motor; however, there may be some challenges with a mud motor, depending on factors such as rate of penetration (ROP), weight transferred to the drill bit due to friction (e.g., weight on bit, WOB), etc. The mud motor may be a positive displacement motor (PDM) that operates to drive the drill bit (e.g., during directional drilling, etc.). The PDM operates when drilling fluid is pumped through it, where the PDM converts the hydraulic power of the drilling fluid into mechanical power to rotate the drill bit.

[0075] As an example, a mud motor (e.g., a PDM) can be operated in different modes, which may include a rotation mode and a sliding mode. The sliding mode involves drilling with a mud motor rotating 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 curved joint or a curved housing 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 curved joint and a measuring device, which can have a relatively small angular offset relative to the axis of the drill string, and the measuring device is used to determine the offset direction. Without rotating the drill string, the drill bit can be rotated as the mud flows through the mud motor to drill in the direction it is pointing. With a steerable motor, when the desired wellbore direction is obtained, the entire drill string can be rotated to drill in a straight line instead of at an angle. By controlling the amount of holes drilled in the sliding mode versus the rotation mode, the wellbore trajectory can be controlled quite accurately.

[0076] As an example, the PDM may be operated in a combined rotation mode, where surface equipment is used to rotate the drill bit of the drill string by rotating the entire drill string (e.g., a rotary table, a top drive, etc.), and where drilling fluid is used to rotate the drill bit of the drill string. In such an example, the surface RPM (SRPM) may be determined by using the surface equipment, and the downhole RPM of the mud motor may be determined using various factors related to the flow rate of the drilling fluid, the type of mud motor, etc. As an example, in the combined rotation mode, the drill bit RPM may be determined or estimated as the sum of the SRPM and the mud motor RPM, assuming that the SRPM and the mud motor RPM are in the same direction.

[0077] As an example, when the drill string is not rotating from the surface, the PDM mud motor can be operated in a so-called sliding mode. In such an example, the drill bit RPM can be determined or estimated based on the RPM of the mud motor.

[0078] The RSS can drill directionally where there is continuous rotation from the surface equipment, which can mitigate slippage of the steerable motor (e.g., PDM). The RSS can be deployed when drilling directionally (e.g., deviated, horizontal, or extended reach wells). The RSS can be designed to minimize interaction with the borehole wall, which can help maintain borehole quality. The RSS can be designed to apply a relatively consistent lateral force similar to a stabilizer that rotates with the drill string or orients the drill bit in the desired direction while continuously rotating at the same RPM as the drill string.

[0079] The LWD module 254 (e.g., LWD tool) can be housed in a suitable type of drill collar and can include one or more selected types of logging tools. It should also be understood that more than one LWD and / or MWD module can be employed, for example, as shown in the module 256 of the drill string assembly 250. Where the location of an LWD module is mentioned, it can refer to a module at the location of the LWD module 254, the module 256, etc., as an example. The LWD module can include capabilities for measuring, processing, and storing information, as well as for communicating with surface equipment. In the example shown, the LWD module 254 can include a seismic measurement device.

[0080] The MWD module 256 (e.g., MWD tool) can be housed in a suitable type of drill collar and can include one or more devices for measuring characteristics of the drill string 225 and the drill bit 226. As an example, the MWD tool 256 can include a device for generating electricity, for example, to power various components of the drill string 225. As an example, the MWD tool 256 can include a telemetry device 252, for example, where a turbine wheel can generate electricity from mud flow; it should be understood that other power and / or battery systems can be used to power various components. As an example, the MWD module 256 can include one or more of the following types of measurement devices: a bit pressure measurement device, a torque measurement device, a vibration measurement device, an impact measurement device, a stick-slip measurement device, a direction measurement device, and an inclination measurement device.

[0081] Figure 2 Also shown are some examples of the types of holes that can be drilled. For example, consider an angled hole 272, an S-shaped hole 274, a deep angled hole 276, and a horizontal hole 278.

[0082] As an example, the drilling operation may include directional drilling, where, for example, at least a portion of the well includes a curved axis. For example, consider a radius of curvature defined where the inclination relative to the vertical may vary until an angle between about 30 degrees and about 60 degrees is reached, or, for example, an angle of about 90 degrees or possibly greater than about 90 degrees is reached.

[0083] As an example, a directional well can include several shapes, each of which can be designed to meet specific operational requirements. As an example, a drilling process can be performed based on the information and once relayed to a drilling engineer. As an example, the inclination and / or direction can be modified based on the information received during the drilling process.

[0084] As an example, deviation of the hole may be achieved in part by using a downhole motor and / or turbine.With respect to motors, for example, the drill string may include a positive displacement motor (PDM).

[0085] As an example, the system may be a steerable system and include equipment for performing methods such as geological steering. As described above, the steerable system may be or include an RSS. As an example, the steering system may include a PDM or turbine on the lower portion of the drill string, the lower portion of the drill string just above the drill bit, where a curved joint may be installed. As an example, above the PDM, MWD equipment and / or LWD equipment that provide real-time or near real-time data of interest (e.g., inclination, direction, pressure, temperature, true drilling pressure, torque stress, etc.) may be installed. With respect to the latter, the LWD equipment may make it possible to send various types of data of interest to the ground, including, for example, geological data (e.g., gamma ray logging, resistivity, density, and sonic logging, etc.).

[0086] Coupling sensors that provide information about the route of a well trajectory in real time or near real time with one or more well logs that characterize the formation from a geological point of view, for example, can allow for geosteering methods to be implemented. Such methods can include navigating a subsurface environment, for example, to follow a desired route to one or more desired targets.

[0087] As an example, the drill string may include an azimuthal density neutron (ADN) tool for measuring density and porosity; an MWD tool for measuring inclination, azimuth, and shock; a compensated dual resistivity (CDR) tool for measuring resistivity and gamma-ray related phenomena; one or more variable gauge stabilizers; one or more bend joints; and a geosteering tool, which may include a motor and optional equipment for measuring and / or responding to one or more of inclination, resistivity, and gamma-ray related phenomena.

[0088] As an example, geosteering may include intentional directional control of a wellbore based on the results of downhole geological logging measurements in a manner intended to maintain the directional wellbore within a desired area, zone (e.g., a producing zone), etc. As an example, geosteering may include directing the wellbore to maintain the wellbore in a particular well section of a reservoir, such as to minimize gas and / or water penetration, and, for example, to maximize economic production from a well that includes the wellbore.

[0089] Reference again Figure 2 , the wellsite system 200 may include one or more sensors 264 operably coupled to the control and / or data acquisition system 262. As an example, the one or more sensors may be at a surface location. As an example, the one or more sensors may be located at a downhole location. As an example, the one or more sensors may be at one or more remote locations that are not within a distance of about one hundred meters from the wellsite system 200. As an example, the one or more sensors may be at an offset wellsite, where the wellsite system 200 and the offset wellsite are in a common oil and gas field (e.g., an oil field and / or a gas field).

[0090] As an example, one or more of sensors 264 may be provided for tracking a pipe, tracking movement of at least a portion of a drill string, etc.

[0091] As an example, the 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 the system 200, one or more sensors 266 may be operably coupled to a portion of the riser 208 through which mud flows. As an example, a downhole tool may generate pulses that may travel through the mud and be sensed by one or more of the one or more sensors 266. In such an example, the downhole tool may include associated circuitry, such as, for example, an encoding circuit that may encode the signal, for example, to reduce the need for transmission. As an example, the circuitry at the surface may include a decoding circuit to decode encoded information transmitted at least in part via mud pulse telemetry. As an example, the circuitry at the surface may include an encoder circuit and / or a decoder circuit, and the downhole circuitry may include an encoder circuit and / or a decoder circuit. As an example, the system 200 may include a transmitter that may generate a signal that may be transmitted downhole via mud (e.g., drilling fluid) as a transmission medium.

[0092] As an example, one or more portions of the drill string may be stuck. The term stuck may refer to one or more of varying degrees of inability to move the drill string or remove the drill string from the borehole. As an example, in a stuck condition, the pipe may be rotated or lowered back into the hole, or, for example, in a stuck condition, the drill string may not be moved axially in the hole, although some amount of rotation may be possible. As an example, in a stuck condition, at least a portion of the drill string may not be moved axially and rotationally.

[0093] With respect to the term "stuck pipe," this may refer to a portion of a drill string that may not rotate or move axially. As an example, a condition known as "differential stuck pipe" may be a condition where the drill string cannot move (e.g., rotate or reciprocate) along the axis of the hole. Differential stuck pipe may occur when high contact forces caused by low reservoir pressure, high wellbore pressure, or both are applied over a sufficiently large area of ​​the drill string. Differential stuck pipe may have both time and financial costs.

[0094] 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 workspace domain may be just as effective in sticking the pipe as a high pressure differential applied over a small area.

[0095] As an example, a condition known as "mechanical stuck drill" may be a condition in which movement of the drill string is restricted or prevented by a mechanism other than differential pressure sticking. Mechanical stuck drill may be caused, for example, by one or more of debris in the hole, abnormal wellbore geometry, cement, keyway, or accumulation of cuttings in the annulus.

[0096] Regarding stick-slip, it can be a form of torsional vibration that occurs when the drill bit, bottom hole assembly (BHA), and / or drill string experience a rotational speed that is different from what is expected. For example, during a "sticking" phase, rotation at the drill bit may slow down or even stop, where a reaction torque may accumulate in the drill string. This accumulation of torque and / or one or more other forces may result in a "slipping" phase, where the drill string (e.g., or a portion thereof) does not stick and rotates. Stick-slip may exhibit an oscillatory type of behavior. In the case of a mud motor included on the drill string, stick-slip associated with the drill bit may be slightly reduced, however, stick-slip above the mud motor may still occur. In various examples, the stick-slip behavior and where it occurs may depend on the equipment utilized, such as whether a mud motor is utilized, etc.

[0097] Figure 3 A schematic diagram of a computing or processor system 300 according to an 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 are operable to execute instructions, application logic, etc. It should be understood that these functions can 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, one or more processors 302 may be or include one or more GPUs.

[0098] The processor system 300 may also include a memory system, which may be or include one or more memory devices and / or computer-readable media 304 of different physical sizes, accessibility, storage capacity, etc., such as flash drives, hard drives, disks, random access memories, etc., for storing data, such as images, files, and program instructions, for execution by the processor 302. In an embodiment, the computer-readable medium 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.

[0099] The processor system 300 may also include one or more network interfaces 306. The network interface 306 may include any hardware, application, and / or other software. Thus, the network interface 306 may include an Ethernet adapter, a wireless transceiver, a PCI interface, and / or a serial network component for communicating over a wired or wireless medium using protocols such as Ethernet, wireless Ethernet, and the like.

[0100] As an example, the 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., it may be operated via one or more IEEE802.11 protocols, ETSIGSM, BLUETOOTH, satellite, etc.). As an example, the mobile device may include components such as a main processor, a memory, a display, a display graphics circuit (e.g., optionally including a touch and gesture circuit), a SIM slot, an audio / video circuit, a motion processing circuit (e.g., an accelerometer, a gyroscope), a wireless LAN circuit, a smart card circuit, a transmitter circuit, a GPS circuit, and a battery. As an example, the mobile device may be configured as a cellular phone, a tablet computer, etc. As an example, the method may be implemented using a mobile device (e.g., in whole or in part). As an example, the system may include one or more mobile devices.

[0101] The processor system 300 may also include one or more peripheral interfaces 308 for communicating with a display, projector, keyboard, mouse, touchpad, sensor, other types of input and / or output peripherals, etc. In some embodiments, the components of the processor system 300 need not be enclosed within a single housing or even located in close proximity to each other, but in other embodiments, the components and / or other components may be disposed 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 the purpose of data storage, communication, computation, etc. As an example, the method may be implemented in a distributed environment (e.g., in whole or in part as a cloud-based service).

[0102] exist Figure 3 In the example of , the memory device 304 can be physically or logically arranged or configured to store data on one or more storage devices 310. The storage device 310 can include one or more file systems or databases in any suitable format. The storage device 310 can also include one or more sets of instructions 312, which can contain interpretable and / or executable instructions for performing one or more disclosed processes (e.g., processor-executable instructions that can be stored in the memory 304 and can be executed to instruct the system 300 to perform one or more actions). When requested by the processor 302, one or more of the one or more sets of instructions 312 or a portion thereof can be loaded from the storage device 310 to the memory device 304 for execution by the processor 302.

[0103] Those skilled in the art will appreciate that the above components are merely one example of a hardware configuration, as the processor system 300 may include any type of hardware components for executing 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 an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

[0104] The processor system 300 may be configured to receive a directional drilling plan 320 (e.g., and / or generate a directional drilling plan). As described above, a well plan is a description of a proposed wellbore for use by a drilling team in drilling the well. A well plan typically includes information about the shape, orientation, depth, completion, and evaluation, as well as information about 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 believes will be relevant / helpful to the team drilling the well. A directional drilling plan may also include information about how to steer and manage the direction of the well.

[0105] The processor system 300 may be configured to receive drilling data 322. The drilling data 322 may include data collected by one or more sensors associated with surface equipment or downhole equipment. The drilling data 322 may include information such as data related to the position of the BHA (such as survey data or continuous position data), drilling parameters (such as weight on bit (WOB), rate of penetration (ROP), torque, etc.), text information entered by individuals working at the well site, or other data collected during the construction of the well.

[0106] In one embodiment, the processor system 300 is part of a rig control system (RCS) of a drilling rig (e.g., including downhole equipment operably coupled to the drilling rig). In another embodiment, the processor system 300 is a separately installed computing unit including a display that is installed at the drilling rig site and receives data from the RCS. In such an embodiment, the software on the processor system 300 can be installed on the computing unit, brought to the well site, and installed and communicatively coupled to the rig control system in preparation for construction of a well or a portion thereof.

[0107] In another embodiment, the processor system 300 may be located at a location remote from the well site and receive the drilling data 322 over a communication medium using a protocol such as the Well Site Information Transfer Specification or Standard (WITS) and Markup Language (WITSML). In such an embodiment, the software on the processor system 300 may be a web-native application accessed by a user using a web browser. In such an embodiment, the processor system 300 may be remote from the well site where the well is being constructed, and the user may be at the well site or at a location remote from the well site.

[0108] Well plan 320 typically includes information about the direction and shape of the well to be drilled. Well plan 320 may include information about parameters and tools used to achieve the desired shape and position. However, when drilling, the actual trajectory may deviate from the plan, or unexpected conditions may be encountered. In such cases and others, it may be necessary to adjust the plan to account for changing conditions and circumstances. For example, consider methods that may require re-planning to generate a revised well plan.

[0109] In one embodiment, the system includes a well plan component for monitoring and updating the well plan, wherein the well plan can be in a digital format, for example, as digital data structured into a memory stored in a computing device, a computing system, etc. For example, consider a controller including a memory that can store the well plan as one or more digital files. When the team conducts a survey or otherwise determines the location of the well, the well plan component can derive a work plan. In one embodiment, the work plan is actually a multi-dimensional spatial trajectory to construct a path from the current drill bit position (e.g., the bottom of the hole position) to the next position, which can be referred to as a target, which can be an intermediate target or a final target. The construction of the path takes into account various considerations. These may include, but are not limited to: targets; allowable deviations from the original plan in terms of position and / or angular deviation; maximum sharp turn capabilities of the steering assembly; constraints set by the user based on preferences at the beginning; allowable curvature, risk metrics, hole quality, confidence level, etc.; and others.

[0110] As an example, a computational framework can provide an automatic optimal operating window (OOW) that is data-driven and utilizes domain knowledge. For example, consider a framework that can implement a workflow that utilizes historical data from offset wells and drilling domain knowledge to systematically and automatically create OOWs for planning wells that consider shock and vibration (S&V) optimization. Such a workflow can include multiple stages. For example, consider the first stage, in which data for processing and visualization is received via a well construction data foundation platform (WCDF) and presented using a cloud-based platform (e.g., MICROSOFT AZURE, AMAZON AWS, GOOGLECLOUD, etc.). As an example, in subsequent stages, framework features for drilling dynamics interpretation (e.g., considering the features of the TECHLOG framework) can provide OOW information for transmission to one or more well sites, optionally without introducing additional network-based applications. In this method, the framework can utilize data such as depth-based data, formation tops, and drilling domain knowledge to establish appropriate drilling parameters for OOW. In such a method, depth-based data can be cleaned up, for example, by removing outliers and unreal values ​​using domain knowledge. As an example, the formation top naming process can be based on a defined dictionary. As an example, one or more alignment processes can be used to create a combined data set of selected offset wells between depth channels and formation tops. As an example, the data can be processed to generate a statistical range (P0, P10... to P90, P100) for each of one or more parameters, where, for example, various channels can be processed for each formation (and into sub-formations) and one or more shock and vibration states. The framework can utilize domain knowledge in a process designed to find appropriate OOW parameters for each formation, which can be considered appropriate based on one or more shock and vibration (S&V) metrics (e.g., considering the lowest actual shock and vibration). The resulting OOW from the offset well can then be mapped into the planned well. In various examples, OOW can be generated in a manner that considers the rate of penetration (ROP) as a performance metric and / or steerability (e.g., predictive steering) of the drill bit. As explained, OOW can be transmitted to the well site for implementation, so that the wellbore can be drilled or further drilled with improved guarantees about consistency between boreholes in the field, wellbore quality, operating procedures, etc.

[0111] Utilizing a framework for OOW generation can help bring manual conventional drilling roadmaps into a field daily monitoring and / or control system that can operate using one or more frameworks, such as one or more frameworks including features of one or more of the TECHLOG framework, the PERFORM TOOL KIT (PTK) framework (SLB, Houston, Texas), the DRILLPLAN framework, and the DRILLOPS framework. In this approach, OOW can help improve performance and reduce equipment damage due to shock and vibration.

[0112] As an example, OOW can provide values ​​for various drilling parameters, which can include, for example, WOB, RPM, and flow (e.g., mud flow). As an example, the OOW generation framework can be operated using offset well data from one or more regions and / or well types. For example, consider using data from Middle Eastern gas wells that have data available from the OPTIDRILL framework (SLB, Houston, Texas) in multiple well sections (e.g., well sections of different diameters, etc.). As another example, consider data from wells in the Permian Basin. The data can include, for example, data from one or more surface sensors and / or one or more downhole sensors or sensor packages. For example, with respect to downhole sensor data, consider MWD sensor data, LWD sensor data, RSS sensor data, etc. As an example, the OOW framework can be customized for equipment. For example, consider customizing an OOW framework for outputting OOW for use with a drill string that includes an MWD tool without one or more additional sensors, or, for example, the drill string includes an MWD tool and an RSS tool that provides additional sensors.

[0113] Figure 4 An example of an OOW workflow 400 including various framework features is shown. As shown, the workflow 400 can proceed from parameter (P) information from a WCDF and / or other data source, where mutations can be generated to provide enhanced domain assessment and / or modeling. In such an example, the mutations can be variants, such as genetic types of variants in the P information, so that a more complete range of domain assessment and / or modeling can be performed. For example, consider utilizing one or more types of models, which can be physically based, data driven, hybrid, etc. In Figure 4 In the example of FIG. 1 , a drilling simulation model (e.g., IDEAS simulator, SLB, Houston, Texas) and a hydraulic simulator (e.g., drilling fluid simulator, etc.) are shown. By using mutations, the effects of different parameter values, such as P explore shown.

[0114] As an example, the mutation process can be aimed at exploring parameter values that can provide improved drilling, which can be improved drilling time, improved ROP, less non-productive time (NPT), improved wellbore quality, improved equipment utilization (e.g., less equipment damage, etc.). In this method, the mutation can be biased towards improved drilling. As Figure 4 shown, the exploration can be aimed at determining whether parameter values for providing more aggressive drilling (e.g., higher ROP, etc.) are likely to experience fewer failures. Thus, as an example, the mutation-based method can consider risk while also being biased towards improved drilling.

[0115] In Figure 4 the example, workflow 400 can proceed to shock and vibration (S&V) assessment. Such an assessment can be aimed at determining whether stick-slip is likely to occur and, if so, reducing WOB and increasing RPM. In the case of using a mud motor, workflow 400 can include an assessment of motor efficiency, where if the efficiency is low and the differential pressure is too low, WOB can be increased. As an example, workflow 400 can include a formation-based assessment, which can provide an assessment of parameters for drilling into relatively hard formations. For example, if the formation is hard and abrasive, one or more parameter values can be adjusted, e.g., to reduce RPM, which can provide bit optimization, where workflow 400 implements bit optimization system (DBOS) features. In Figure 4 the example, workflow 400 can include RSS-related assessment. For example, consider an assessment based on comparing the RSS steering (SR) parameter with a threshold (e.g., SR > 80%) and comparing the actual DLS with a threshold (e.g., DLS < the nominal DLS production of RSS) or the planned borehole trajectory DLS to determine whether to adjust one or more parameter values (e.g., lower WOB, lower RPM, etc.).

[0116] In Figure 4 the example, the output can be directed to one or more destinations. For example, consider real-time monitoring and / or control destinations, planning destinations, etc. As an example, in the case where the implementation of OOW at the wellsite for a drilling operation occurs, parameter values, data, etc. can be used as feedback and / or offset well data.

[0117] As explained, Figure 4 the workflow 400 of

[0118] In one embodiment, the framework may provide for implementing a workflow involving performing data synchronization. In some embodiments, data (e.g., surface and tool dump data) may be misaligned due to, for example, time differences, power generation cycles, or other reasons. The time synchronization process may automatically synchronize pairs of surface and downhole data. In some embodiments, synchronized data sets may be selected for processing.

[0119] As an example, a workflow may include data enrichment. For example, for data enrichment purposes, information about the status of the rig may be included. For example, the data may be enhanced with information about the status of the rig, HKLD from bottom, DWOB, DTOR, differential pressure, etc. Information for enrichment may also include motor efficiency and degradation information, such as motor efficiency, degradation, power, and torque. Further enrichment data may include mechanical specific energy (MSE), downhole MSE (DMSE), torque loss, etc. As an example, the enrichment data may include drill bit characteristic indices, such as aggressiveness, formation stiffness, drilling per revolution, etc.

[0120] Regarding MSE, it is a measure of drilling efficiency and can be defined as the energy required to remove a unit volume of rock. For optimal drilling efficiency, the goal can be to minimize MSE and maximize ROP. To control MSE, one or more of WOB, torque, ROP, and drill bit RPM can be adjusted.

[0121] As an example, the framework may provide for receiving data indicating a state (e.g., a rig state), as well as one or more S&V-type data and one or more energy-type data, which may include, for example, one or more MSE-type data (e.g., energy experienced by a drill bit, etc.). As an example, the framework may generate an OOW using data indicating a state, one or more S&V statistics, a bit index, formation stiffness, and a DMSE. As an example, a bit index (BI) may be a metric that characterizes a drill bit, which may be applied to a new type of formation and a drill bit database (e.g., considering a formation drillability catalog (FDC)). As explained, motor efficiency and degradation may be utilized. As an example, the framework may operate using multiple surface channels (e.g., WOB, ROP, STOR, FLWI, etc.); note that downhole sensor data may supplement such surface channel data. As an example, the framework may include receiving data from a controller such as an automatic driller controller. For example, consider control commands, control feedback, control adjustments, etc., which may be used for one or more boreholes drilled using an automatic drilling controller.

[0122] As an example, the OOW may be suitable for consumption by one or more components of a rig control system (RCS), which may include one or more automatic drilling controller components. As an example, an automatic driller controller may operate at one or more different automation levels, where, for example, more automation is possible where the confidence level may be high enough. In such an example, the confidence level may be high due to one or more factors that may be related to one or more of the equipment, downhole conditions, etc. As an example, the OOW may help increase the confidence level and therefore increase the level of automation so that drilling can be performed with less human involvement. For example, where the OOW can provide appropriate information to the controller (e.g., values ​​regarding drilling parameters, tuning, responses, etc.), the controller can operate with less intervention from humans. As explained, OOW implementations in the art may generate feedback, which, as explained, may be used as a basis for further drilling operations, whether at the same well site or at one or more different well sites. As an example, a framework may provide a transformation of OOW information into command information suitable for utilization by one or more types of controllers.

[0123] As an example, the framework can operate dynamically, where data is processed as they become available. For example, consider a site where a borehole is to be drilled at multiple locations. In such an example, when several boreholes are completed, there may be data sufficient to generate one or more OOWs for drilling or further drilling of the borehole. As an example, the framework can analyze the available data and / or output to determine when the OOW is reliable for a given amount of data or when the OOW can become reliable (e.g., once a certain amount of future data is generated and received). As an example, the framework can implement statistical methods to determine when the OOW is sufficient for deployment. As an example, the framework can operate according to one or more risk assessments, where the ability to assess risk and / or manage risk can be increased when additional data is received. Therefore, as more data becomes available, an OOW can be generated that is intended to manage the increased amount of risk to achieve improved drilling (e.g., improved ROP, less equipment wear, improved wellbore quality, etc.). As explained, since the increased data can drive improved statistics, the increased data can drive improved drilling with improved risk management. As an example, OOW may be provided on a segment-by-segment basis or other incremental basis so that drilling operations may be associated with specific characteristics of the subsurface region to be drilled.

[0124] As explained, the framework can link the rig status to the formation characteristics, which can improve directional drilling operations, which can provide vertical, curved, horizontal, etc. types of drilling using one or more types of modes (e.g., vertical mode, sliding mode, rotational mode, etc.). Although vertical drilling may present fewer challenges than curved drilling (e.g., depending on the desired DLS, etc.), vertical drilling can be optimized, for example, to reduce the risk of excessive equipment wear, etc. As explained, the framework can implement a mutation process designed to improve drilling, for example, so that drilling can be more aggressive while ensuring that wear is acceptable. Regarding equipment wear, in the case of utilizing a mud motor, drill bit wear and mud motor wear may be a problem. In various cases, a drill string with a single BHA and a single drill bit can be used to drill a borehole with a vertical portion, a curved portion, and a lateral portion. In such an example, an OOW designed to maintain the life of the drill bit can be generated so that the drill bit can drill the entire borehole without having to pull the drill string out of the hole (POOH). As an example, the OOW may be segmented based on one or more factors, which may be by section, by diameter, by type of formation to be drilled, by expected S&V, etc.

[0125] As an example, a framework can implement one or more types of data science platforms. For example, consider the Dataiku platform (Dataiku, New York, New York), which includes various libraries for data processing.

[0126] Figure 5 An example of a graphical user interface (GUI) 500 is shown that includes various types of data that can be rendered with respect to time and / or depth. As shown, the GUI 500 includes rig status, car position (BPOS), block height (HDTH), surface WOB (SWOB), RPM, motor torque, surface torque (STOR), flow rate (FLWI), standpipe pressure (SPPA), differential pressure (DPRES_RC), motor efficiency, and motor degradation (e.g., wear of one or more downhole motor components).

[0127] Figure 6 An example of a GUI 600 including data for various drill bit types is shown. As shown, the GUI 600 may include drill bit wear data as well as equipment information about the drilling operation.

[0128] Figure 7 An example of a GUI 700 is shown that includes a graph of a histogram of radial shock RMS (RADHKRMS) values ​​from over 10,000 rotational steerable tool (RSS drill string) runs. Such statistics can be used to assess shock and vibration severity by comparing a single job to a large number of jobs. As an example, the risk information (e.g., statistical data, etc.) in such a graph can be used in an OOW generation workflow.

[0129] Figure 8 An example of a method 800 is shown, which includes an input box 810 for inputting surface and dump time series channels, a synchronization box 820 for synchronizing the surface and dump times of data, an automatic state calculation box 830 for automatically calculating states (e.g., drilling states, rig states, etc.) using surface channel data, a filtering box 840 for filtering time series data and extracting data points related to different drilling modes (e.g., rotational or sliding modes) and data validity confirmation, a partitioning box 850 for partitioning measured depth (MD) sections into desired incremental distances (e.g., 0.5 feet, etc.) to group the filtered data into corresponding MD sections, a calculation box 860 for calculating statistical metrics for each MD group and for selecting representative statistical results (e.g., average, minimum, maximum, etc.) to provide MD sequence data, and an output box 870 for outputting tool dump MD sequence data. As explained, the method 800 can convert data from a time series to a depth series (e.g., MD or true vertical depth (TVD)).

[0130] Fig. 9 An example of a GUI 900 including various types of data is shown. For example, consider direction and inclination (D&I) data, which may include inclination and azimuth data. As shown, the GUI 900 may include various types of surface data, which may include STOR, RPM, SWOB, minimum RPM, maximum RPM, average RPM, FLWI, SPPA, and ROP. As shown in the GUI 900, impact RMS shake data (e.g., axial vibration and / or radial and / or tangential impact data from downhole sensors) may be included, which may include radial data and axial data. As shown, impact rate metrics (e.g., T1, T2, T3, T4, etc.) may be determined and presented. As shown, turbine data for one or more RSS tool turbines may be presented in combination with RPM to diagnose RSS tool health, for example, for an upper torquer (UT) and a lower torquer (LT), which may represent the operation of two turbines of the RSS tool. As an example, steering (SR), toolface (or toolface (TF)), and mode (e.g., hold inclination and azimuth (HIA), etc.), as well as final azimuth setpoint (FINAL_AZI) and final inclination setpoint (FINAL_INC) may be included in the GUI 900. As an example, such data may be obtained from an RSS tool.

[0131] exist Fig. 9In the example of , GUI 900 shows data for a drilling operation where a wellbore is being drilled with a curvature and then horizontally. For example, the D&I data track shows this transition occurring at approximately 9,700 feet. When processing offset data, various types of drilling can be identified and segmented. For example, consider identifying a vertical section, a curved section, and a horizontal section. In such an example, the drilling operation can be different for each section. As explained, OOW can consider different sections of the borehole to be drilled.

[0132] Fig.10 An example of a process 1000 for exploring parameter values ​​is shown, which may be part of a mutation process intended to improve drilling while accounting for factors such as equipment wear, damage, etc. As shown, a mud motor may be quantified with respect to efficiency as a function of flow rate (FLWI) and differential pressure (DPRES). As shown, the process 1000 may include associated graphics, for example, to provide one or more individual assessments that may guide mutations, approve mutations, etc. For example, a mutation may be generated using guidelines for differential pressure ratings and / or for power ratings that may be specific to a selected mud motor or family of mud motors.

[0133] exist Fig.10 In an example of FIG. 1 , process 1000 can utilize data in the form of an efficiency contour plot, where a mud motor can be operated according to a pressure differential rating and a power rating and efficiency within a range that takes into account equipment safety (e.g., wear, etc.), e.g., operating at high efficiency. As shown, the operation of the mud motor can be explored with respect to a range from 0 to a maximum rating of one or more parameters of the mud motor.

[0134] Fig.11 An example of a process 1100 for adjusting one or more OOW parameter values ​​is shown, which may be in the form of a step transition (see STEP), a smooth transition (see SMOOTH), etc. As shown, a safety margin D may be used to ramp up or down parameter values ​​based at least in part on one or more formation characteristics. As shown, a formation (Formation X4) may be different than an adjacent formation (Formation X5). As explained, the formation may be hard and abrasive (e.g., hard abrasive sandstone, etc.), which may result in increased drill bit wear. Increased drill bit wear may result in NPT, for example, where the drill bit does not have sufficient remaining life to complete the well. As Fig.11 As shown, process 1100 can implement one or more types of metrics to adjust for changes in one or more parameter values. For example, parameter values ​​can be ramped up or down to account for changes in formation types. As explained, the framework can generate OOWs, where the OOWs take into account formation types, changes, etc.

[0135] As explained, various techniques, processes, etc. may be utilized to generate one or more OOWs. With respect to data, the system may employ depth gating. In certain embodiments, a defined depth gating technique for a dump channel may be utilized. In various cases, a dump channel may refer to a channel in which data is stored in a memory and then dumped (e.g., transferred, accessed, read, etc.). For example, a downhole tool may include a memory from which the memory may be read once the downhole tool is brought to a ground station. In such an example, the downhole tool may include features for real-time or near real-time transmission while downhole, but such transmission may be limited by bandwidth, transmission technology, conditions, etc. As an example, the memory of a downhole tool may store an amount of data and / or one or more types of data that may not be available via downhole telemetry. As an example, depth gating may be used for one or more types of data and may be used to synchronize dump files.

[0136] As explained, surface data and dump data may be processed and aggregated. Such data may also be enhanced with metadata, e.g., to facilitate data searching and / or other processing. For example, consider metadata such as job number, location and offset, BHA, drill bit, operator, etc.

[0137] As explained, the data can be used to determine one or more OOWs, which can be used for certain tools and / or operations. OOWs can have a life cycle that passes through multiple wells in the same field or basin. Therefore, OOWs can evolve with accumulated drilling data and domain learning. OOWs can be used to perform to promote improved performance of well site operations. In certain embodiments, OOWs can be specific to a certain formation and hole size. As an example, OOWs can change with the introduction of one or more changes in new drill bits, new tools and / or technologies. Therefore, OOWs may need to be aligned or realigned during execution. As an example, OOWs can be in the same field based on one or more different priorities. For example, different operators may have different business models and / or requirements that may result in different OOWs.

[0138] As about Figure 4As explained, OOWs can be generated in a data-driven and domain-driven evolutionary manner (e.g., using mutations, etc.). In one embodiment, offset well statistics can be used to facilitate the creation of OOWs. Offset well parameter channels can be depth-gated, aligned, or otherwise prepared for generating OOWs by depth or formation top. As an example, values ​​such as mean, 25%, 75%, etc. can be calculated in a moving window of depth along the well section. Values ​​such as mean and standard deviation of MSE, DMSE, S&V, and one or more other values ​​can be calculated to measure overall risk and formation changes. As an example, optional weights can be applied to different wells based on one or more factors (e.g., one or more of distance, drilling time, BHA similarity, etc.).

[0139] As about Figure 4 As explained, the OOW generation workflow can involve exploration with parameter values ​​that can improve performance. For example, consider establishing a baseline by using offset well statistics. In one embodiment, small steps to higher range values ​​can be applied to one or more operating parameters. For example, if the MSE and DMSE are relatively low, a relatively large incremental change (e.g., P+DP, where DP is the step change of parameter P) can be used. As an example, if the MSE, DMSE, S&V are high, a smaller step increase can be used. As an example, if the drill bit blunt grade is severe or the failure event is high, a smaller step or downward step can be used. This approach can be used to evolve parameters and migrate parameters to a more effective range within a specific area. As an example, the migration (e.g., mutation) process can be stopped or reversed based on actual drilling performance.

[0140] As about Fig.10 As explained, mud motor efficiency may be affected by flow, differential pressure, and motor power section configuration. As an example, OOW may be selected to achieve good efficiency while operating within an appropriate differential pressure range. For example, considering a mutation process, it may include: if the differential pressure is less than 25% of the recommended differential pressure limit for the power section, then increase WOB and / or use the WOB / DTOR ratio and the power section specifications to determine the appropriate WOB increment.

[0141] As an example, one or more techniques can be employed to consider bit life. For example, PDC bit damage can occur with wear due to hard sandstone and abrasive sandstone, impact damage in hard rock, impact damage in the interbeds, etc. As an example, the OOW can be adjusted, for example: use a lower RPM when drilling hard abrasive sandstone to reduce wear due to frictional heat; use an appropriate WOB to avoid bit rotation (WOB too low, RPM too high) or cutter overload (WOB too high); avoid aggressive parameters when drilling in the interbeds; if the entire section has a high impact strength, use a less aggressive WOB / RPM (decrease proportionally to the impact strength factor); and so on.

[0142] As an example, an evolutionary approach can be used in combination with RSS directional performance. For example, the directional behavior trend can be obtained from the drilling data, and the OOW can be adjusted, for example, as follows: if DLS < DLS_norm (e.g., where the DLS achieved by the BHA is less than the normal expected DLS based on the drilling data), then one or more of WOB, ROP, and RPM are adjusted based on the lessons learned from the drilling data to improve DLS; and CRPM max (e.g., the maximum RPM expected by the RSS tool) is within the tool limits: 2xSPRM + RPM_motor < 350.

[0143] As an example, the OOW target priorities can be considered. For example, when adjusting the parameters of the OOW, the targets can have different priorities. For example, when drilling a curve with marginal DLS capabilities, it may be desirable to adjust and select parameters to meet the DLS requirements. In this case, the adjusted parameters can be locked after the adjustment, unless a higher risk is identified. In some embodiments, the adjustment can be selectively performed based on applications such as risk tolerance, operator preference, business model, common failure events, etc.

[0144] As explained, the OOW generation workflow can employ mutation as an evolutionary technique. For example, with a substantial change in the bit, mud motor, RSS tool, drill pipe, or other subsystems or drilling practices for a new operation, a mutation can be introduced into the OOW evolution process. In this case, the OOW starting curve can be shifted based on historical data from offset wells. Physical modeling, simulation, and / or domain knowledge can be utilized to reform the starting curve, thus allowing selective application of the OOW logic. For example, if a more powerful motor is introduced with a higher torque limit, the OOW can obtain a higher WOB. As an example, the increment can be based on the WOB / DTOR relationship from historical data and / or product specifications (e.g., product labels, manuals, spec sheets, etc.).

[0145] As an example, an OOW workflow may involve alignment of offset wells. For example, offset wells may be aligned on depth (e.g., when the formation is relatively uniform in the application), depth and trajectory (e.g., when trajectory profiles are to be considered), formation logs (e.g., gamma), or MSE (e.g., when gamma is available or MSE has clear features), and / or depth stretching and compression, smart depth alignment (e.g., when the depth of the top of the formation varies). As an example, alignment may be performed automatically, manually, and / or semi-automatically.

[0146] In one example, the alignment of the formation top may require special handling when the depth of the formation top varies. One approach may be to map the formation top using the offset well and predict the formation top of the target well based on this map. As an example, the offset well statistics can be obtained using the normalized formation depth mapped to the target well. In such an example, the OOW can then be adjusted based on appropriate logic. As an example, the OOW can be actively aligned during execution based on the actual formation top (e.g., based on information sensed by one or more sensors, whether at the surface and / or downhole).

[0147] As an example, the OOW workflow may take into account compositional changes, such as hard veinlets and inter-layer. In one embodiment, the strategy may involve parameter changes with gradual transitions, safe areas for hard veinlets, and / or gradual increases or decreases in parameters near veinlets. Fig.11 As explained, various types of ramps may be utilized. For example, in the presence of many veinlets with high UCS contrast (especially in combination with high S&V, frequent bit damage, tool damage, etc.), less aggressive drilling parameters may be planned for the OOW.

[0148] As an example, the OOW may be available in one or more of a variety of formats. In one embodiment, a hard copy of the OOW chart may be generated and provided to the wellsite team. As explained, the OOW may be generated in digital form, which may be suitable for use as part of a digital drilling program that includes parameters to be used during the automated execution of portions of the drilling program. As an example, the OOW may be a set of automatic driller set points and limits (e.g., optionally including tuning parameter values, etc.). As an example, at each depth, the automation method may include using the OOW parameter window min / max for the automatic driller limits, e.g., using the median, OOW parameter recommendations, etc. as the set points.

[0149] As an example, the OOW generation workflow may consider OOW regarding shock and vibration mitigation starting from a selected well, regarding shock and vibration mitigation starting from one or more dominant shock and vibration modes of an offset well, and the like.

[0150] Fig.12An example of a workflow 1200 for shock and vibration mitigation starting with one or more dominant shock and vibration modes of a deviated well is shown; note that the workflow 1200 may additionally, alternatively, etc. be adjusted, modified, etc. for one or more other types of considerations.

[0151] exist Fig.12 In the example, OOW is the optimal operating window, OW is the offset well, SVR is the shock & vibration rating, OWDPL is the offset well drilling parameter level, DSDPL is the dominant S&V state drilling parameter level, DSVS is the dominant S&V state, SSI is the stick-slip index, AXLSHKRMS is the axial shock RMS, and RADSHKRMS is the radial shock RMS.

[0152] As shown, the workflow 1200 may include a receiving block 1210 for receiving an MD range of interest, a calculation block 1212 for statistics in a moving window for depth intervals, an iteration block 1214 for evaluating each statistical window to determine whether S&V data is available according to a determination block 1216 and whether there is more than one offset well in the depth window (e.g., data from more than one offset well (OW) is available) according to another determination block 1218. As shown, according to the "no" branch, the workflow 1200 may skip a window, while according to the "yes" branch, the workflow 1200 may continue.

[0153] As shown, according to the rating system of SVR values ​​0 for low, 1 for medium, 2 for high, and 3 for severe, the workflow 1200 may proceed to a rating block 1222 for rating the severity of the S&V of the offset well data in the window. In this example, a determination block 1224 may determine the primary SVR state (DSVS) with the highest data count. In a calculation block 1226, various statistics (e.g., P10, P90, etc.) of the operating parameters may be calculated, such as RPM and WOB in the offset wells in the window where the RPM may be constrained to a range and the WOB may be constrained to a range. In a segmentation block 1228, the workflow 1200 may equally segment the offset well range (e.g., P10, P90) of RPM and WOB into four parameter levels (DPL), which may be represented as OWDPL: 0 for low, 1 for medium, 2 for high, and 3 for very high. Next, the workflow 1200 may proceed to another determination block 1230 to determine a relative parameter level of the DSVS, which may be a level of OWDPL of a P50 drop of the DSVS, which may be represented as DSDL: 0 for low, 1 for medium, 2 for high, and 3 for very high.

[0154] As shown, the workflow 1200 can proceed to a recommendation block 1232 of recommended parameters, which can be based on a process 1250 of evaluating axial SHKRMS (AXLSHKRMS) and radial SHK RMS (RADSHKRMS). As shown, values ​​for the primary S&V state (DSVS) can be evaluated for DSDPL and SVR. In such an approach, the process 1250 can provide an output of appropriate values ​​for WOB and RPM for a particular window, where these values ​​can be part of the OOW.

[0155] Fig.13 An example graphical user interface (GUI) 1300 of output from an OOW workflow generated using offset well data is shown. The GUI 1300 may include various graphical indicators, such as shading, color, etc. For example, consider color coding of green areas with blue lines for recommended parameters, and yellow areas based on P10 and P90 statistics or other statistics, or, for example, one or more user-defined statistics, limits, etc. In the example GUI 1300, the output may reference various areas, such as high S&V areas (HSV), normal homogeneous formation areas (NF), etc.

[0156] Fig.14 An example graphical user interface (GUI) 1400 of output from an OOW workflow generated using offset well data mapped to a target well is shown. The GUI 1400 may include various graphical indicators, such as shading, color, etc. For example, consider color coding of green areas with blue lines for recommended parameters, and yellow areas based on P10 and P90 statistics or other statistics, or one or more user-defined statistics, etc. In the example GUI 1400, the output may reference various areas, such as high S&V areas (HSV), normal homogeneous formation areas (NF), etc. As an example, the content in the GUI 1400 may be output in digital form, which may be used, for example, to control operations for drilling a target well.

[0157] Fig.15 An example graphical user interface (GUI) 1500 of output from an OOW workflow as generated using specific coding is shown, which can help guide a user and / or machine to perform one or more field operations.

[0158] Fig.16 An example graphical user interface (GUI) 1600 for a synthetic day versus depth curve is shown, where, for example, the system can estimate drilling time (eg, without flat time) to demonstrate efficiency gains through generated OOW.

[0159] Fig.17An example graphical user interface (GUI) 1700 is shown of a method that can provide a stable operating window search using one or more S&V heat maps to generate OOW for a specific zone and / or portion of a specific well, labeled DZ6 (e.g., a target well). Fig.17 In the example of , a response surface of S&V with respect to a parameter (e.g., taken from offset data, from mutations and simulations, etc.) can be evaluated, for example, to determine a normalized S&V risk level, where a stack of response surfaces (e.g., a combined response surface) can construct an overall S&V risk heat map. As shown, the method can include searching for a stable operating window that, for example, is intended to minimize one or more types of risk. Although S&V information is shown in GUI 1700, the heat map and search-based method can be applied to one or more other types of behavior (e.g., ROP, MSE, etc.) and / or one or more other types of risk.

[0160] like Fig.17 As shown in the example of , GUI1700 may provide for assessing one or more types of risks, which may include, for example, drill string and formation interaction risks. For example, consider the bending risk of the drill string bending in the wellbore, the drill bit bounce risk of the drill string bouncing in the wellbore, and the sliding stuck risk of the drill string getting stuck and / or sliding in the wellbore. As explained, the workflow for generating OOW may consider various types of risks, which may be used to arrive at optimal operating parameter values. For example, optimization techniques may include optimizing parameter values ​​in a mutation-based manner, whereby drilling may be optimized (e.g., increasing ROP, etc.) with acceptable risks. In GUI1700, a heat map indicates S&V information associated with specific risks of operating parameters regarding RPM and WOB, noting that one or more other types of operating parameters may be used in conjunction with such a heat map and / or risks and / or one or more other types of heat maps and / or risks.

[0161] Fig.18 An example of a graphical user interface (GUI) 1800 is shown that can provide mitigation of S&V, for example, based on domain knowledge. Fig.18As shown in the example of , factors such as stick-slip, turbulence, ROP, etc. can be considered to help identify optimal areas with respect to parameters such as WOB and RPM. In the example GUI 1800, one or more factors can be risk factors, for example, one or more types of behaviors that pose risks during drilling operations. For example, chaotic turbulence can be a behavior that poses a risk to the drill string in the borehole, which may affect the integrity of the drill string and / or the quality of the borehole. In various cases, the behavior may damage or excessively wear the drill bit, which may affect the ability to complete one or more sections of the borehole. As explained, in the event that the drill bit wears prematurely or is otherwise damaged so that it needs to be replaced, non-productive time (NPT) may be introduced, which may affect the overall ROP, completion time, drilling resource requirements, etc.

[0162] Fig.19 An example of a process 1900 that can provide for determining OOW locations of high risk formations (e.g., high risk areas, etc.) is shown. The process 1900 can integrate heat maps, domain knowledge, etc. The process 1900 can include one or more decision boxes that can determine, for example, whether a stable area can be found in an S&V heat map, and if not, whether the dominant mode has a high S&V level, where if so, the OOW can be generated at least in part via domain knowledge. As shown, the process 1900 can provide for using special logic to handle inter-layer and HDI.

[0163] Fig. 20 An example of a process 2000 for an OOW generation workflow is shown. As shown, for three wells, formation names and formation thicknesses may be considered, for example, to reconcile data from the three wells, which may be offset wells defined relative to a target well. Fig. 20 The process 2000 may be referred to as stratigraphic alignment because the depth of the data (eg, measured depth (MD)) is aligned for the purpose of OOW generation.

[0164] Fig.21 An example of a process 2100 for an OOW generation workflow is shown. As shown, process 2100 can be a portion of process 2000 for three wells. For example, process 2100 can include finding an average length, finding a coefficient, shrinking or expanding information for one or more wells, combining information from the wells, and generating an OOW.

[0165] As an example, process 2000 and / or process 2100 may include determining an average length of formation (j) for a representative well (x) based on its length from selected wells (i) (n=number of wells):

[0166]

[0167] In such an example, the coefficients can be determined for each well in each formation:

[0168]

[0169] Given such coefficients, we can determine the shrinkage (if the coefficient k j >1) or equally spread the data points for each formation (e.g., depth index).

[0170] With respect to formation top alignment, each formation top may exhibit one or more characteristics in terms of geological and / or drilling dynamics (e.g., ROP, S&V, steering, etc.) response. As explained, in order to define drilling parameters for a portion of a well or well section, the process may include dividing the well or well section into smaller segments, which may be at least at the level of the formation top. As explained, when using data from multiple offset wells, the data may be grouped into formation tops and defined relative to representative depths. In various cases, the process may be intended to standardize (e.g., coordinate) formation top names and sequences so that common metadata may be utilized to accelerate processing.

[0171] As an example, a workflow can include alignment of data followed by statistical processing, which can be intended to combine statistical results (e.g., P0 to P100) for selected wells along a depth interval of a list of channels (e.g., data channels). As an example, in the case where the formation top is not available for selecting wells, statistical processing can be performed without alignment of the formation top; note that the output accuracy may be less than with alignment of the formation top. As an example, one or more other alignment techniques can be implemented, for example, considering drilling area alignment, which can be obtained from a framework such as the TECHLOG framework (e.g., considering the use of drilling similarity indices, etc.).

[0172] As explained, after processing per depth interval (e.g., every 0.5 feet on MD or another appropriate incremental value), the data can be smoothed and filled over a larger span (e.g., a 10-foot moving window). If drilling zones are utilized (e.g., for thick formation tops or unavailable formation tops), the entire interval can be divided into sub-layers to represent the response of drilling dynamics. As an example, a workflow can be performed through each formation top and / or drilling zone and the average value (e.g., FLWI, WOB, and RPM) for each OOW channel is calculated, which can be presented as a straight line or a stepped line, optionally with an inclined rise and / or decline. As explained, shock and vibration channels can be combined into categories, modes, or states, such as lateral, axial, and torsional modes. Based on comparing the measurements to thresholds, the workflow can define a severity level for each S&V state, with, for example, Level 3 for lateral modes being the highest. As an example, adjustments to OOW can be applied based on a mitigation process.

[0173] As described above, drilling zones can be utilized. For example, in situations where the top of a formation may be unavailable for offset runs, or where the top of a formation may be thick and overlay multiple sublayers that cause different drilling dynamics and different drilling parameters to effectively drill the sublayers, a workflow can divide a drilling interval (e.g., a thick top of a formation) into thinner drilling zones. As an example, within each drilling zone, the drilling dynamics and parameters can be expected to be one of: uniform or non-uniform. If uniform, there may be a linear response between drilling parameters and performance and S&V, and therefore, the workflow can be designed to maximize the value of the drilling parameters. Conversely, if heterogeneous, prevention and mitigation can be applied, for example, using domain knowledge and / or data-driven approaches.

[0174] As an example, one or more reference channels may be used to define one or more change points. Based on a set of change points, the workflow may label the drilling area (e.g., based on formation unconfined compressive strength, DMSE, formation strength, etc.). The drilling area may be classified as, for example, homogeneous, hard veinlets, and / or interlayer. In this approach, in the case of hard veinlets, interlayer may be considered a subtype of heterogeneous.

[0175] As an example, the reference channel may be the formation unconfined compressive strength (UCS) or confined compressive strength (CCS, which is the UCS with the pressure difference between the borehole and pore pressures); note that one or more other channels may additionally or alternatively be used as the one or more reference channels. For example, consider one or more of MSE, formation strength (e.g., stiffness), formation gamma ray, formation density, etc.

[0176] Regarding DMSE, it can be used as a reference channel, for example, as a proxy for formations and sub-formations. As an example, DMSE can be available in offset well data, for example, as calculated in real time using the OPTIDRILL framework (SLB, Houston, Texas). As an example, DMSE can be calculated as follows:

[0177]

[0178] Or, in the case where the BHA does not include a mud motor:

[0179]

[0180] in:

[0181] MSE mechanical specific energy (psi)

[0182] WOB surf Bit pressure at ground level (lbf)

[0183] RPM SurfRotation speed at ground level (rpm)

[0184] TOR surf Ground torque (ft-lbf)

[0185] ROP penetration rate (ft / hr)

[0186] D Drill bit diameter (in)

[0187] ΔP pressure difference (psi)

[0188] Q Mud flow (GPM)

[0189] K t Motor Torque Factor (ft.lbf / psi)

[0190] K n Motor speed factor (rpm)

[0191] WOB bit Bit pressure at ground level (lbf)

[0192] RPM bit Rotation speed at ground level (rpm)

[0193] TOR bit Torque at ground level (ft-lbf)

[0194] With respect to formation strength (e.g., stiffness), it may be considered that the effects of high fluctuations in torque input due to a high probability of torsional vibration (e.g., in the form of sticking and slipping) are reduced in various operations. For example, consider the use of depth of cut (DOC) in inches per revolution and / or formation strength in psi as follows:

[0195]

[0196] With respect to formation gamma rays, which can be measured using one or more types of tools (e.g., MWD, LWD, RSS, etc.), they can be quite indicative of changes in formation lithology. As an example, formation gamma rays can be used in conjunction with one or more other factors to enhance determinations that can distinguish rock hardness, which can aid in drilling performance and dynamics.

[0197] Regarding formation density, it can be measured by LWD tools (e.g., consider the ADNVISION tool and / or the ECOSCOPE tool (SLB, Houston, TX)). Formation density can be obtained in one or more well sections, which may include a production well section of an offset well.

[0198] Fig. 22An example of a graphical user interface 2200 for change point detection (CPD) is shown. This method can be statistically based, where statistics can be used to detect change points at various depths (e.g., MD). This method can be implemented to evaluate and / or determine OOW, such as when to change OOW.

[0199] As an example, one or more CPD techniques may be implemented, which may include one or more of online and offline methods. For example, an online CPD method may utilize real-time data (e.g., streaming time series data) to detect one or more changes, which may include one or more abnormal events; and an offline CPD method may include using an amount of time series data sufficient to perform one or more statistical analyses, one or more physics-based models, and / or one or more data-driven models.

[0200] As an example, the statistical analysis may utilize a feature (eg, a reference channel) as input, wherein, for example, a histogram of the feature may be generated based on a predefined number of bins subject to optimization.

[0201] As an example, consider defining a range of changes that focuses on one or more distributions and can be intended to reduce time complexity. In such an example, a lower limit on the percentage of data points can be set. For example, consider using DMSE and setting a lower limit (region_threshold) = 0.05 (5%), where a range of changes can be calculated; whereas if the lower limit = 0.01 (1%), a different range of changes can be calculated. Although DMSE is mentioned, formation strength and / or one or more other metrics can be used.

[0202] As an example, one or more of the following may be used: minimum layer segment (integer), which is the minimum drilling layer segment that allows division into smaller drilling areas; moving window (integer), which is the depth layer segment for the moving window; clearing window (integer), which is the depth layer segment for clearing spikes; and regional quantile (floating point) in order to calculate the value within the region compared to a threshold (for example, higher numbers are more sensitive to spikes (noise), lower numbers are less sensitive).

[0203] As explained, OOW generation can include mutation-based optimization. For example, consider optimization that takes into account one or more of S&V, ROP, and steerability. In such an example, depending on the location (e.g., contractual obligations, equipment availability, etc.), the operations team can decide to target one or more goals, such as maximizing ROP without or with less S&V, optimizing ROP with S&V, optimizing ROP for steerability, optimizing ROP for hole stability, etc. As explained, parameter values ​​can be explored via a mutation-based process in an effort to meet one or more goals.

[0204] As explained, the OOW method can have a life cycle through multiple wells in the same field or basin. As an example, the system can provide for evolving the OOW as drilling data and domain learning are accumulated. In various examples, the OOW can be specific to a specific formation and / or hole size. As an example, the OOW may be shifted due to the introduction of a new drill bit, tool, and / or technology. As an example, the OOW can be subjected to one or more processes for alignment and / or realignment during execution. For example, consider data acquired while drilling, which can indicate the location and / or formation characteristics of the formation, so that the OOW can be aligned or realigned based at least in part on such information. As an example, the OOW can have different priorities in the same field, which can depend on factors such as the operator, regulations, business model, etc.

[0205] As explained, the OOWs may be used to control one or more field operations. As an example, a system may provide for selecting RCS parameters based on one or more OOWs. For example, consider a system that may provide for selecting optimal control parameters based on identified optimal drilling parameters, which may be in the form of OOWs generated using analysis based on offset well data, domain knowledge, and one or more models (e.g., physics-based, data-driven, hybrid, etc.). As an example, the RCS parameter selection process may be customized for different desired behaviors in different drilling scenarios (e.g., in different types of formations or at different locations in a given well section).

[0206] As an example, the system can identify wells / runs that are comparable to a target well / run and acquire data from those wells / runs. In such an example, based at least in part on the data, the system can generate an OOW for a drilling parameter in the target well. Given the OOW, the system can select desired values ​​for the drilling parameters in the target well. For example, the OOW can be the basis for input of contextual information about the target well (e.g., such as motor type and control limits). As explained, one or more OOWs can be provided for a region, where control can be implemented on a region-by-region basis. For example, consider a system that selects an RCS set point for a given region based on desired drilling parameters and scenarios.

[0207] As explained, the OOW may include recommended values ​​for drilling control parameters and performance parameters for a given area (eg, a formation, a column, another desired way of dividing trajectories, etc.).

[0208] As explained, the OOW may specify various drilling parameter values ​​for parameters that may include, for example, WOB, top drive RPM, pump flow rate (FLWI), ROP, and STOR.

[0209] As an example, to implement OOW for control, the user and / or machine may provide one or more additional limits to ensure that equipment (e.g., surface or downhole) operates properly (e.g., with reduced risk of damage, etc.) and / or with respect to one or more other undesirable drilling conditions (e.g., considering the setting of ROP set point limits to ensure proper hole cleaning). As an example, the limits may include WOB limits, torque limits, ROP limits, flow limits, differential pressure limits, etc.

[0210] As an example, the system may include a converter where OOW information such as recommended parameter values ​​is converted into appropriate control commands (e.g., RCS set points, etc.). For example, consider top drive torque limit and RPM set points, mud pump flow, auto driller set points (e.g., WOB, ROP, Torque, DiffP), auto driller gains (e.g., tuning parameter values ​​for control techniques such as proportional, integral, derivative, etc., control type).

[0211] As an example, the system may include one or more converters that may be selected based on one or more criteria, such as the type of controller, the level of automatic control, regulations, company practices, etc. As an example, the converter may implement different conversions of recommended parameter values ​​depending on the type of drilling desired in a given formation. As an example, in a hard interlayer formation, it may be desirable to ensure that a maximum depth of cut is not exceeded, which may provide drilling primarily under ROP control (e.g., rather than weight control). In other formations, drilling under WOB control may be more desirable.

[0212] As an example, different types of drilling modes may include a WOB mode, where drilling is expected to be primarily on WOB. In such a mode, the recommended drilling parameters may then be converted to RCS parameters, such as: TD RPM setpoint = RPM recommendation; TD torque limit = torque limit (e.g., set by user, set by machine, etc.); flow setpoint = min (FLWI recommendation, flow limit); activate WOB and torque mode on the automatic driller (AD); send WOB recommendation as AD WOB setpoint; send 1.5*ROP prediction as ROP setpoint; and set AD torque setpoint to torque limit minus margin (e.g., 2000 ft-lbs).

[0213] As an example, another mode may be expected to be primarily concerned with drilling on ROP, which may be referred to as ROP mode. In such an example, the recommended drilling parameters may be converted into RCS parameters, such as: TD RPM setpoint = RPM recommendation; TD torque limit = torque limit (e.g., set by user, set by machine, etc.); flow setpoint = min (FLWI recommendation, flow limit); activate WOB and torque mode on automatic driller (AD); send WOB limit as AD WOB setpoint; send ROP prediction as ROP setpoint; set AD torque setpoint to torque limit minus margin (e.g., 2000 ft-lbs). In this mode, the user may specify a desired maximum depth of cut (e.g., to limit bit cutter damage during formation changes). Such a value may be converted to a maximum ROP, and the ROP setpoint may then be the minimum between this maximum ROP and the ROP prediction to ensure that the maximum depth of cut is not exceeded.

[0214] While two example modes are given, one or more additional or alternative modes may be provided. For example, consider a mode selected based on desired drilling behavior. In such an example, a user may want more or less aggressive settings depending on the current drilling conditions / environment. For example, if evidence indicates that drill bit / tool ​​wear / damage is not a concern, one approach may select a more aggressive drilling mode (e.g., consider a WOB mode, but with a higher ROP setpoint value to ensure that the ROP setpoint does not limit the drilling rate).

[0215] As an example, OOWs and controls may be linked in a workflow including OOW generation and / or in a post-OOW generation process. In various examples where one or more OOW updates (e.g., alignment, realignment, etc.) are desired, a dynamic system may include OOW generation in response to acquired data, control actions, equipment conditions, etc. As an example, there may be a link for planning purposes, where a planner (e.g., see Figure 4 ) can generate an executable plan for the control system. As an example, OOW can be integrated into a plan for drilling / well sections, for example based on the expected target well design (BHA, trajectory, etc.).

[0216] As an example, one or more OOWs may form part of a static plan that may be the basis for further planning. As an example, a user visualization of real-time parameter usage compared to the planned operating window and RCS settings may provide a real-time visualization of the compliance of the actual operation with respect to the plan. In such an example, deviations from the plan may be recorded (e.g., in shadow mode) and / or cause an alarm / flag to be issued (e.g., in advisory mode). As an example, the recorded compliance data may be used to improve the OOW workflow in post-work analysis. For example, consider a scenario in which OOW is used with an automated driller, where the level of automation may be reduced during drilling. This reduction in the level of automation may indicate that the OOW does not provide sufficient confidence for at least a portion of the drilling. For example, the driller may have overridden one or more OOW parameter values ​​due to domain knowledge. In such an example, the driller may provide feedback that may be used to improve the OOW or OOW generation, for example, to increase the confidence of automated drilling.

[0217] As an example, the OOW may be a dynamic OOW such that, when implemented, the dynamic OOW may actively sense actual drilling conditions (e.g., presence or absence of vibration or difficult formation types, etc.) and dynamically adjust the OOW based on real-time data. As an example, in a dynamic implementation, the system may be able to sense that the drilling process reaches a difficult formation earlier than expected and adjust the recommended drilling parameters appropriately. In such an example, one or more recommended RCS settings may be adjusted based on the operating window and the drilling plan.

[0218] Fig.23 An example of a graphical user interface (GUI) 2310 and an example of a method 2320 for controlling a drilling operation, for example, using an RCS, which may include one or more automatic drilling features (e.g., an automatic driller) are shown. As shown, the GUI 2310 may include a list of formations or regions (F1, F2, .FN) and parameter values ​​such as SWOB, SRPM, and FLWI. In such an example, STOR and ROP predictions may be presented along with statistical information such as P10-P90 information. In such an example, the confidence of the recommendation may be assessed, whether via a prediction, a comparison of prediction to actual, etc. As an example, a depth measurement may be an indicator for transitioning from one formation or region to another. Although depth is mentioned, as explained, one or more types of information (e.g., sensor data, etc.) may be utilized to determine when a change is appropriate.

[0219] exist Fig.23In an example of , method 2320 may include: a receiving block 2322 for receiving offset data and / or real-time (RT) data (e.g., from a rig site); a determining block 2324 for determining drilling and formation characteristics and drilling risk; a determining block 2326 for determining different zones (e.g., zones or intervals of a wellbore to be drilled or further drilled); a generating block 2328 for generating one or more OOWs based on the drilling and formation characteristics and drilling risk of one or more of the different zones (e.g., or the remainder of the zone, etc.); and a transmitting block 2330 for transmitting the one or more OOWs for one or more purposes, which may include use as a reference for product and / or service delivery, for generating RCS commands (e.g., recommendations, etc.), for generating commands for automated drilling operations, etc. For example, the transmitting block 2330 may transmit information in a digital form suitable for generating the GUI 2310, which may be used to optionally control the drilling operation in an automatic and / or semi-automatic manner.

[0220] As explained, the generation workflow of one or more OOWs may include performing mutation-based optimization, where, for example, one or more techniques may be used to mutate one or more parameter values ​​to explore possible outcomes, where such possible outcomes may be evaluated relative to one or more objectives to optimize one or more parameter values ​​to meet one or more of the one or more objectives. As an example, mutation techniques may be biased toward improved performance and may be limited by risk. For example, if it is known that a parameter value has a range where the upper end of the range may increase risk, the mutation technique may provide exploration of values ​​that do not extend to or do not extend to the upper end of the range. As an example, risk may also be assessed by using one or more models, which may be or may include one or more simulation models (e.g., simulations of drilling, simulations of geomechanics, etc.). As an example, Fig.23 Method 2320 may be directed to providing one or more OOWs that may have a high likelihood of achieving quality and performance goals (eg, with respect to wellbore quality, equipment quality, etc.) while also achieving an acceptable level of risk.

[0221] Fig.24Examples of graphical user interfaces (GUIs) 2410 and 2420 are shown, wherein GUI 2410 includes WOB, WOB setpoint (SP), vehicle position (BPOS), ROP, and ROP setpoint (SP) versus time for a WOB control mode, and wherein GUI 2420 includes WOB, WOB setpoint (SP), vehicle position (BPOS), ROP, and ROP setpoint (SP) versus time for a ROP control mode. As shown, for the WOB mode, the ROP may be less than the ROP SP, while the WOB is controlled according to the time-varying WOBSP of each one or more OOWs, and for the ROP mode, the WOB may be less than the WOB SP, while the ROP is controlled according to the time-varying ROPSP of each one or more OOWs.

[0222] As explained, one or more data-driven techniques can be implemented. For example, consider a workflow that can acquire data from an offset well, where such data can include a time series of depth information with drilling parameters, drilling dynamics, formation evaluation, etc., as well as data about equipment limitations (e.g., rig, BHA, drill bit, etc.). Such data can be used in one or more ML methods to train one or more ML models, whether supervised and / or unsupervised. ML model-based methods can provide mutation-based optimization, for example, by inputting various parameter values ​​to output information about one or more objectives. As an example, one or more of classification and prediction can be used as part of an optimization scheme. As explained, a hybrid approach combining physics-based techniques and data-driven techniques can be implemented.

[0223] As an example, a workflow may include prediction of hard and soft transition zones using a physics-based and data-driven hybrid ML model. As an example, a workflow may include real-time automatic offset well selection using a multi-dimensional similarity index. As an example, a workflow may include real-time OOW recommendation using a normalized advantage function technique in deep reinforcement learning (DRL). As explained, the workflow may utilize one or more additional, alternative, etc. methods.

[0224] As explained, the workflow can use real-time data to recommend drilling parameters in an updated manner. For example, S&V, ROP, and / or steerability channels can be fed to the OOW system in real time, where, for example, the actual formation top can be input (e.g., automatically by a user, etc.). In such an example, the dynamic OOW workflow can use such information to update one or more OOWs.

[0225] As explained, a dynamic OOW workflow can be implemented to control equipment for one or more drilling operations, for example, in a data-driven manner. As an example, an initial OOW can be utilized to establish an initial state, for example, when a drill bit enters a new formation. As an example, over the course of a predefined interval (e.g., x meters or feet of MD), an automated process can calculate one or more OOW performance indicators to evaluate performance with respect to OOW effectiveness. In this approach, one or more thresholds can be used for OOW effectiveness (e.g., defined by ROP, S&V, DLS, etc.), where the control system can decide to maintain and / or adjust one or more recommended drilling parameter values.

[0226] As an example, adjustments may occur in response to a comparison that considers OOW effectiveness. Such an approach may utilize real-time data acquired for the current formation, optionally along with common portion intervals from one or more selected offset wells, for example, to calculate possible compensations, adjustments, etc. with respect to one or more objectives (e.g., for optimization, etc.). As an example, adjustments may be applied to the remaining, upcoming portion of the current formation, for example, until the next interval (e.g., with an associated OOW recommendation, which may be modified or maintained).

[0227] Fig.25 An example of a method 2500 is shown, which may include: a generation block 2510 for generating an optimal operating window (OOW) based on data indicating a drilling rig state and formation characteristics and based on a mutation-based optimization of operating parameter values, the optimal operating window (OOW) specifying operating parameter values ​​for drilling operations using equipment at the rig site; and an instruction block 2520 for instructing a control system to perform drilling operations according to the OOW using the equipment at the rig site. Fig.25 As shown in the example, method 2500 may include a control box 2530 for controlling the equipment to deepen the borehole by destroying the rock of the formation by the drill bit in response to the indication; and may include a correction box 2540 for receiving field data during the drilling operation and correcting the OOW based at least in part on at least a portion of the field data.

[0228] like Fig.25 As shown, method 2500 may be implemented via one or more computer readable media (CRMs) according to blocks 2511, 2521, 2531, and 2541, which may be implemented, for example, using a system such as a computing system (see, for example, Figure 3 Such blocks may include processor-executable instructions.

[0229] As explained, various systems, methods, etc. can implement one or more ML models, which can be data-driven models and / or hybrid models (e.g., physics-based and data-driven). Regarding the type of ML model, consider one or more of a support vector machine (SVM) model, a k-nearest neighbor (KNN) model, an ensemble classifier model, a neural network (NN) model, incremental learning, Q learning, etc. As examples, the machine learning model can be a deep learning model (e.g., deep Boltzmann machine, deep belief network, convolutional neural network, stacked autoencoder, etc.), an ensemble model (e.g., random forest, gradient boosting machine, bootstrap aggregation, adaptive boosting (AdaBoost), stacked generalization, gradient boosting regression tree, etc.), a neural network model (e.g., radial basis function network, perceptron, back propagation, Hopfield network), a regularization model (e.g., ridge regression, least absolute shrinkage and selection operator, elastic network, least angle regression), a rule system model (e.g., stereo, one rule, zero rule, repeated incremental pruning to produce error reduction), a regression model (e.g., linear regression, ordinary least squares regression, stepwise regression), a multivariate adaptive regression spline, a scatter plot smoothing of local estimates, a logistic regression model (e.g., linear regression, ordinary least squares regression, stepwise regression), a multivariate adaptive regression spline, a scatter plot smoothing of local estimates, a logistic regression model (e.g., linear regression, ordinary least squares regression, stepwise regression), a logistic regression model (e.g., linear regression, ordinary least squares regression, stepwise regression), a logistic regression model (e.g., linear regression, ordinary least squares regression, stepwise regression), a logistic regression model (e.g., logistic regression, a logistic regression model ... Logistic regression, Bayesian models (e.g., Naive Bayes, Average Dependence Estimator, Bayesian Confidence Network, etc.), Gaussian Naive Bayes, Multinomial Naive Bayes, Bayesian Network), decision tree models (e.g., classification and regression trees, Iterative Bipartite 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 map, multidimensional scaling, projection 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, learning vector quantization, self-organizing maps, local weighted learning, etc.), clustering models (e.g., k-means, k-median, expectation-maximization, hierarchical clustering, etc.), etc.

[0230] As an example, the system can utilize one or more recurrent neural networks (RNNs). One type of RNN is called a long short-term memory (LSTM), which can be a unit or component (e.g., one or more units) that can be in one or more layers. The LSTM component can be an artificial neural network (ANN) that is designed to recognize patterns in data sequences such as time series data. When provided with time series data, the LSTM considers time and order, so that the LSTM can include a time dimension. For example, consider utilizing one or more RNNs to process time data from one or more sources, optionally in conjunction with spatial data. This approach can identify temporal patterns that can be used to make predictions (e.g., one or more patterns about future times, etc.).

[0231] As an example, the TENSORFLOW framework (Google LLC of Mountain View, California) can be implemented, which is an open source software library for data flow programming, including a symbolic math library, which can be implemented for machine learning applications that may include neural networks. As an example, the CAFFE framework can be implemented, which is a DL framework developed by Berkeley AI Research (BAIR) (University of California, Berkeley). As another example, consider the SCIKIT platform (e.g., scikit-learn) using the PYTHON programming language. As an example, a framework such as the APOLLO AI framework (APOLLO.AI GmbH, Germany) can be utilized. As described above, a framework such as the PYTORCH framework can be utilized.

[0232] As an example, a training method may include various actions that may be performed on a dataset to train an ML model. As an example, a dataset may be divided into training data and test data, where the test data may be provided for evaluation. A method may include cross-validation of parameters and optimal parameters, which may be provided for model training.

[0233] The TENSORFLOW framework can run on multiple CPUs and GPUs (with optional CUDA (NVIDIA Corporation, Santa Clara, CA) and SYCL (Khronos Group, Beaverton, OR) extensions for general-purpose computing on graphics processing units (GPUs). TENSORFLOW is available on 64-bit LINUX, MACOS (Apple Inc., Cupertino, CA), WINDOWS (Microsoft Corporation, Redmond, WA), and mobile computing platforms including ANDROID (Google LLC, Mountain View, CA) and iOS (Apple Inc.) operating system-based platforms.

[0234] TENSORFLOW computations can be represented as stateful data flow graphs; note that the name TENSORFLOW derives from the operations such neural networks perform on multidimensional data arrays. Such arrays can be called "tensors".

[0235] As an example, the ML model can be run online using cloud computing resources, followed by a target well delivery method that can automatically feed data to the ML model, which can be updated at a given frequency. As an example, the ML model can be run in an offline manner, where one or more results can be transmitted to the planning workflow.

[0236] As an example, a method may include: generating an optimal operating window (OOW) based on data indicating a rig state and formation properties and based on a mutation-based optimization of operating parameter values, the OOW specifying operating parameter values ​​for a drilling operation using equipment at the rig site; and instructing a control system to perform a drilling operation according to the OOW using the equipment at the rig site. In such an example, generating the OOW may include accessing offset well data for a plurality of wells. In such an example, the method may include performing formation alignment on the offset well data with respect to the formation properties.

[0237] As an example, the data may include surface sensor data and / or may include downhole sensor data.As an example, the drilling rig status may be derived from at least the surface sensor data.

[0238] As an example, a method may include instructing a control system by selecting a control mode from a plurality of different control modes (eg, considering a ROP mode, a WOB mode, etc.).

[0239] As an example, a method may include instructing a control system by instructing the control system to operate using one or more set points, one or more gains, or one or more set points and one or more gains specified by one or more OOWs. In such an example, the gain may be a gain of a controller that can perform at least a certain amount of automatic control. For example, consider a proportional controller with a proportional gain (e.g., as a tuning parameter), an integral controller with an integral gain (e.g., as a tuning parameter), etc. In such an example, a set point may be specified, wherein one or more gains may be utilized in an effort to automatically maintain one or more operations at the set point.

[0240] As an example, the method may include mutation-based optimization of operating parameter values, which may include adjusting the values ​​of two or more operating parameters to optimize the drilling operation while considering one or more types of risks. In such an example, the one or more types of risks may include risks associated with shock and vibration (S&V). As an example, the one or more types of risks may include equipment risks, borehole quality risks, drill string and formation interaction risks, mud motor degradation risks, rotary steerable system (RSS) risks, and one or more of drill bit damage risks, stick-slip risks, and hard abrasive formation drilling risks, which may be in addition to or in lieu of risks associated with S&V.

[0241] As an example, a method may include generating an OOW by using one or more of a physics-based model, a data-driven model, and a hybrid physics-based and data-driven model.

[0242] As an example, a method may include, in response to an indication of a control system, controlling equipment to deepen a borehole by breaking rock of a formation with a drill bit.

[0243] As an example, a method may include receiving field data during a drilling operation and modifying an OOW based at least in part on at least a portion of the field data.As an example, a method may include evaluating performance of one or more OOWs and utilizing such evaluation as feedback for generating one or more other OOWs.

[0244] As an example, a system may include at least one processor; a memory accessible to at least one of the at least one processor; processor-executable instructions stored in the memory and executable to instruct the system to: generate an optimal operating window (OOW) based on data indicating a rig state and formation properties and based on a mutation-based optimization of the operating parameter values, the optimal operating window specifying operating parameter values ​​for a drilling operation using equipment at a rig site; and instruct a control system to perform the drilling operation according to the OOW using equipment at the rig site. In such an example, the processor-executable instructions may include instructions executable to instruct the system to: receive field data during performance of one or more drilling operations, and adjust the OOW based at least in part on a portion of the field data. In such an example, the portion of the field data may indicate a difference between one of the formation properties used to generate the OOW and an actual formation property for a particular drilling area of ​​the OOW.

[0245] As an example, the processor executable instructions of the system may include instructions executable to instruct the system to perform the following operations: generate a command for controlling the system, wherein the command includes one or more set points, one or more gains, or one or more set points and one or more gains, wherein the one or more gains may include at least one automatic controller gain (e.g., a proportional gain, an integral gain, etc.).

[0246] As an example, the processor-executable instructions of the system may include instructions executable to instruct the system to perform the following operations: generate commands for controlling the system, wherein the commands include one or more of a rate of penetration (ROP) set point command for a ROP control mode and a weight on bit (WOB) set point command for a weight on bit (WOB) control mode.

[0247] As an example, one or more non-transitory computer-readable storage media may include processor-executable instructions to instruct a computing system to: generate an optimal operating window (OOW) based on data indicating a drilling rig status and formation characteristics, and based on a mutation-based optimization of operating parameter values, the OOW specifying operating parameter values ​​for a drilling operation using equipment at the rig site; and instruct a control system to perform a drilling operation in accordance with the OOW using the equipment at the rig site.

[0248] 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 (eg, in part, in whole, and / or in various combinations).

[0249] The embodiments disclosed in this disclosure are used to help explain the concepts described herein. This specification is not exhaustive and does not limit the claims to the precise embodiments disclosed. Modifications and variations of the exact embodiments in this disclosure may still be within the scope of the claims.

[0250] Likewise, the steps described need not be performed in the same order or with the same degree of separation as discussed. Various steps may be omitted, repeated, combined, or divided as appropriate. Accordingly, the present disclosure is not limited to the above-described embodiments, but is defined by the appended claims in accordance with the full scope of their equivalents. In the above description and in the following claims, unless otherwise indicated, the term "execution" and its variations will be interpreted as relating to any operation of program code or instructions on a device, whether compiled, interpreted, or run using other techniques.

[0251] Some of the following claims may include numbered lists. The numbers are provided as an organizational tool to aid readability. The numbers themselves do not indicate an intended order of configuration or execution or otherwise have substantive meaning. For U.S. applications, the appended claims do not invoke Section 112(f) unless the phrase "means for..." is expressly used in conjunction with an associated function.

Claims

1. A method comprising: generating an optimal operating window (OOW) based on the data indicative of a rig state and formation characteristics and based on the mutation-based optimization of the operating parameter values, the optimal operating window specifying operating parameter values ​​for drilling operations using equipment at the rig site; as well as A control system is instructed to perform the drilling operation in accordance with the OOW using equipment at the rig site.

2. The method of claim 1 , wherein generating the OOW comprises accessing offset well data for a plurality of wells.

3. The method of claim 2, comprising performing stratigraphic alignment on the offset well data with respect to the formation characteristics. The method of claim 1 , wherein the data comprises surface sensor data. The method of claim 4 , wherein the data further comprises downhole sensor data.

6. The method of claim 4, wherein the drilling rig status is derived from at least the surface sensor data.

7. The method of claim 1, wherein instructing the control system comprises selecting a control mode from a plurality of different control modes.

8. The method of claim 1 , wherein the instructing the control system comprises instructing the control system to operate using one or more set points, one or more gains, or one or more set points and one or more gains specified by the OOW.

9. The method of claim 1, wherein the mutation-based optimization of the operating parameter values ​​comprises adjusting the values ​​of two or more operating parameters to optimize the drilling operation while taking into account one or more types of risks.

10. The method of claim 9, wherein the one or more types of risk include risks associated with shock and vibration.

11. The method of claim 9, wherein the one or more types of risk include equipment risk, borehole quality risk, drill string and formation interaction risk, mud motor degradation risk, rotary steerable system (RSS) risk, and one or more of drill bit damage risk, stick-slip risk, and hard abrasive formation drilling risk.

12. The method of claim 1, wherein generating the OOW comprises using one or more of a physics-based model, a data-driven model, and a hybrid physics-based and data-driven model.

13. The method of claim 1, comprising, in response to instructing the control system, controlling the apparatus to deepen the borehole by breaking rock of the formation with the drill bit.

14. The method of claim 1, further comprising receiving field data during the drilling operation and modifying the OOW based at least in part on at least a portion of the field data.

15. A system comprising: at least one processor; a memory accessible to at least one of the at least one processor; processor-executable instructions stored in the memory and executable to instruct the system to: generating an optimal operating window (OOW) based on the data indicative of a rig state and formation characteristics and based on the mutation-based optimization of the operating parameter values, the optimal operating window specifying operating parameter values ​​for drilling operations using equipment at the rig site; as well as A control system is instructed to perform the drilling operation in accordance with the OOW using equipment at the rig site.

16. The system of claim 15, wherein the processor-executable instructions include instructions executable to direct the system to receive field data during performance of one or more of the drilling operations and adjust the OOW based at least in part on a portion of the field data.

17. The system of claim 16, wherein the portion of the field data indicates a difference between one of the formation properties used to generate the OOW and an actual formation property for a particular drilling area of ​​the OOW.

18. The system of claim 15, wherein the processor-executable instructions include instructions executable to instruct the system to generate a command for controlling the system, wherein the command includes one or more set points, one or more gains, or one or more set points and one or more gains, wherein the one or more gains include at least one automatic controller gain.

19. The system of claim 15, wherein the processor-executable instructions include instructions executable to direct the system to generate commands for controlling the system, wherein the commands include one or more of a rate of penetration (ROP) set point command for a ROP control mode and a weight on bit (WOB) set point command for a WOB control mode.

20. One or more non-transitory computer-readable storage media comprising processor-executable instructions to instruct a computing system to: generating an optimal operating window (OOW) specifying operating parameter values ​​for drilling operations using equipment at the rig site based on data indicative of rig status and formation properties and based on the mutation-based optimization of the operating parameter values; and A control system is instructed to perform the drilling operation in accordance with the OOW using equipment at the rig site.

Images