Adaptive drill string condition determination

Abstract

A method can include identifying a threshold for a drill string off bottom condition determination; filtering time series surface data of a back connected drilling state of the drill string using the threshold to generate filtered time series surface data; and statistically determining a drill string off bottom condition value using the filtered time series surface data.

Description

[0001] Related Applications

[0002] This application claims priority and benefit to U.S. Provisional Application No. 63 / 093,022, filed October 16, 2020, which is incorporated herein by reference. Background Technology

[0003] A resource field can be an accumulation, pool, or group of pools of one or more resources (e.g., oil, natural gas, petroleum and natural gas) in a subsurface environment. A resource field may include at least one reservoir. The reservoir may be shaped in a manner capable of capturing hydrocarbons and may be covered by impermeable or sealed rock. A borehole may be drilled in the environment, and a well may be formed using the borehole, which can be used to produce hydrocarbons from the reservoir.

[0004] A drilling rig can be a system of components that can be operated to form a borehole in the environment, transport equipment into or out of the borehole, etc. As an example, a drilling rig can include systems that can be used to drill and obtain information about the environment, about the well, etc. A resource oil field can be an onshore oil field, an offshore oil field, or an onshore and offshore oil field. A drilling rig can include components for performing onshore and / or offshore operations. A drilling rig can be, for example, ship-based, offshore platform-based, onshore, etc.

[0005] Oilfield planning can occur in one or more phases, which may include an exploration phase aimed at identifying and assessing the environment (e.g., potential areas, reservoir play, etc.), which may include drilling one or more boreholes (e.g., one or more exploration wells, etc.). Other phases may include assessment, development, and production phases. Summary of the Invention

[0006] A method may include identifying a threshold for determining drill string bottom-out conditions; filtering time-series surface data of subsequent drilling states of the drill string using the threshold to generate filtered time-series surface data; and statistically determining the drill string bottom-out condition value using the filtered time-series surface data. A system may include a processor; processor-accessible memory; and processor-executable instructions stored in and executable in the memory to instruct the system to: identify a threshold for determining drill string bottom-out conditions; filter time-series surface data of subsequent drilling states of the drill string using the threshold to generate filtered time-series surface data; and statistically determine the drill string bottom-out condition value using the filtered time-series surface data. One or more computer-readable storage media may include processor-executable instructions to instruct a computing system to: identify a threshold for determining drill string bottom-out conditions; filter time-series surface data of subsequent drilling states of the drill string using the threshold to generate filtered time-series surface data; and statistically determine the drill string bottom-out condition value using the filtered time-series surface data. Various other apparatuses, systems, methods, etc., are also disclosed.

[0007] This overview is provided to introduce the selection of concepts that will be further described in the detailed description below. This overview is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used to help limit the scope of the claimed subject matter. Attached Figure Description

[0008] The features and advantages of the described embodiments can be more readily understood by referring to the following description in conjunction with the accompanying drawings.

[0009] Figure 1 An example of equipment in a geological environment is shown;

[0010] Figure 2 Examples of devices and hole types are shown;

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

[0012] Figure 4 An example of the system is shown;

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

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

[0015] Figure 7 An example of the system is shown;

[0016] Figure 8 Examples of the methods and diagrams are shown;

[0017] Figure 9 References are shown Figure 8 Examples of graphic representations;

[0018] Figure 10 Examples of graphs showing various trajectories that include time series data and other information are shown;

[0019] Figure 11 An example of a graph showing time series data is shown;

[0020] Figure 12 An example of a graph showing time series data is shown;

[0021] Figure 13 An example of a graph showing time series data is shown;

[0022] Figure 14 Examples of methods and systems are shown;

[0023] Figure 15 An example of the method is shown;

[0024] Figure 16 An example of the system is shown;

[0025] Figure 17 An example of a graphical user interface is shown;

[0026] Figure 18 An example of a graphical user interface is shown;

[0027] Figure 19 An example of a graphical user interface is shown;

[0028] Figure 20 An example of a graphical user interface is shown;

[0029] Figure 21 An example of a graphical user interface is shown;

[0030] Figure 22 An example of a graphical user interface is shown;

[0031] Figure 23 An example of a graphical user interface is shown;

[0032] Figure 24 An example of a graphical user interface is shown;

[0033] Figure 25 An example of a data table is shown;

[0034] Figure 26 An example of a data table is shown;

[0035] Figure 27 An example of the method is shown;

[0036] Figure 28 An example of a well-constructed ecosystem including one or more machine learning model systems is shown;

[0037] Figure 29 An example of a computing system is shown; and

[0038] Figure 30 Example components of the system and network system are shown. Detailed Implementation

[0039] The following description includes the best mode currently anticipated for practicing the described embodiments. This description should not be construed as restrictive, but is merely for the purpose of describing the general principles of the embodiments. The scope of the described embodiments should be determined with reference to the published claims.

[0040] Figure 1 An example of geological environment 120 is shown. Figure 1 In this context, the geological environment 120 may be a sedimentary basin comprising layers (e.g., strata), including reservoir 121 and potentially traversed by faults 123 (e.g., one or more faults). As an example, the geological environment 120 may be equipped with various sensors, detectors, actuators, etc. As an example, device 122 may include communication circuitry to receive and transmit information about one or more networks 125. This information may include information associated with downhole device 124, which may be a device for acquiring information, assisting in resource recovery, etc. Other devices 126 may be located remotely from the well site and include sensing, detection, transmission, or other circuitry. Such devices may include storage and communication circuitry to store and transmit data, instructions, etc. As an example, one or more devices may provide for the measurement, collection, communication, storage, and analysis of data (e.g., for one or more produced resources). As an example, one or more satellites may be provided for communication, data acquisition, and other purposes. As an example, Figure 1 A satellite communicating with network 125 is shown. This satellite can be configured for communication. Note that the satellite may additionally or alternatively include circuitry for imaging (e.g., spatial, spectral, temporal, radiometric measurements, etc.).

[0041] Figure 1Geological environment 120 is also shown, which optionally includes equipment 127 and 128 associated with a well, the well including a basic horizontal portion that may intersect with one or more fractures 129. As an example, a well in a shale formation is considered, which may include natural fractures, artificial fractures (e.g., hydraulic fractures), or a combination of natural and artificial fractures. As an example, a well may be drilled for a laterally extending reservoir. In such an example, lateral variations in properties, stresses, etc., may exist, where assessment of such variations may aid in planning, operations, etc., to develop the reservoir (e.g., through fracturing, injection, extraction, etc.). As an example, equipment 127 and / or 128 may include components, systems, multiple systems, etc., for fracturing, seismic sensing, seismic data analysis, assessment of one or more fractures, injection, production, etc. As an example, equipment 127 and / or 128 may provide data, such as production data (e.g., for one or more produced resources), for measurement, collection, communication, storage, analysis, etc. As an example, one or more satellites may be provided for communication, data acquisition, etc.

[0042] Figure 1 Examples of devices 170 and 180 are also shown. Such devices can be systems of components suitable for geological environments 120. Although devices 170 and 180 are illustrated as land-based, various components can be adapted to marine systems.

[0043] Equipment 170 includes a platform 171, a derrick 172, a crane 173, a line 174, a traveling block assembly 175, a winch 176, and a landing platform 177 (e.g., a second-level platform). As an example, the line 174 can be controlled at least partially by the winch 176, allowing the traveling block assembly 175 to travel vertically relative to the platform 171. For example, by retracting the line 174, the winch 176 can pass the line 174 through the crane 173 and raise the traveling block assembly 175 upwards and away from the platform 171; however, by allowing the line 174 to extend, the winch 176 can pass the line 174 through the crane 173 and lower the traveling block assembly 175 toward the platform 171. The traveling block assembly 175 carries pipes (e.g., casings, etc.), and the motion tracking of the traveling block 175 can provide an indication of how much pipe has been deployed.

[0044] The derrick can be a structure used to support a crane and a traveling block, the traveling block being at least partially operably connected to the crane via ropes. The derrick can be pyramidal in shape and provide a suitable strength-to-weight ratio. The derrick can be moved as a unit or in pieces (e.g., assembled and disassembled).

[0045] As an example, a winch may include a spool, brake, power supply, and associated auxiliary equipment. The winch can controllably release and retrieve the rope. The rope can be wound around the overhead crane and connected to the traveling block, achieving mechanical benefits in a "pulley block" or "pulley" manner. Releasing and retrieving the rope causes the traveling block (e.g., and anything suspended below it) to be lowered into or raised from the borehole. Releasing the rope can be gravity-driven, while retrieving it can be powered by a motor, engine, etc. (e.g., electric motor, diesel engine, etc.).

[0046] As an example, a crane may include a set of pulleys (e.g., grooved sheaves) located at or near the top of the derrick or mast, through which ropes pass. A traveling block may include a set of grooved sheaves that can move up and down within the derrick or mast via ropes passing through the grooved sheaves of the traveling block and the crane. The crane, traveling block, and ropes can form a pulley system for the derrick or mast that allows the handling of heavy loads (e.g., drill string, pipe, casing, liner, etc.) to be lifted or lowered into the borehole. As an example, the rope diameter may be from approximately one centimeter to approximately five centimeters, such as steel cable. By using a set of grooved sheaves, such a rope can carry a heavier load than a rope as a single strand could support.

[0047] As an example, a derrickman can be a member of the drilling rig personnel working on a platform attached to a derrick or mast. The derrick may include a landing platform on which the derrickman can stand. As an example, such a landing platform may be approximately 10 meters or higher above the rigfloor. In an operation known as tripping out of the borehole (TOH), the derrickman may wear a safety harness that allows him to reach out from the working landing platform (e.g., a second-level platform) to the pipe located at or near the center of the derrick or mast, and to throw a rope around the pipe and pull it back to its storage location (e.g., a finger pole platform), for example, until it may be desired to put the pipe back into the borehole. As an example, the drilling rig may include automated pipe handling equipment, allowing the derrickman to control the machine rather than physically moving the pipe.

[0048] As an example, tripping in and out of the borehole can refer to the action of pulling equipment out of the borehole and / or placing equipment into the borehole. As an example, equipment may include a drill string that can be pulled out of the hole and / or placed or replaced in the hole. As an example, tripping in and out of the drill bit can be performed when the drill bit has become dull or has ceased effective drilling and needs to be replaced.

[0049] Figure 2An example of a well site system 200 is shown (e.g., at a well site that may be onshore or offshore). As shown, the well site system 200 may include a mud tank 201 for containing mud and other materials (e.g., where the mud may be drilling fluid), a suction line 203 serving as the inlet of a mud pump 204 to pump mud from the mud tank 201 to the vibratory hose 206, a winch 207 for pulling one or more drilling ropes 212 with a winch, a riser 208 for receiving mud from the vibratory hose 206, a square drill pipe hose 209 for receiving mud from the riser 208, one or more gooseneck pipes 210, a traveling block 211, and a crane 213 for carrying the traveling block 211 via one or more drilling ropes 212 (e.g., see [link]). Figure 1 (e.g., overhead crane 173), derrick 214 (see, for example, see...) Figure 1 The derrick 172), prism 218 or top drive unit 240, prism drive bushing 219, rotary table 220, drill rig 221, bell sub 222, one or more blowout preventers (BOPs) 223, drill string 225, drill bit 226, casing head 227, and flow pipe 228 for transporting mud and other materials to, for example, mud tank 201.

[0050] exist Figure 2 In the example system, a borehole 232 is formed in the underground formation 230 by rotary drilling; note that directional drilling may also be used in various example embodiments.

[0051] like Figure 2 As shown in the example, drill string 225 is suspended within borehole 232 and has drill string assembly 250, which includes drill bit 226 at its lower end. As an example, drill string assembly 250 may be a bottom hole assembly (BHA).

[0052] Well site system 200 can provide operation of drill string 225 and other operations. As shown, well site system 200 includes a platform 211 and a derrick 214 located above borehole 232. As mentioned, well site system 200 may include a rotary table 220 through which drill string 225 passes.

[0053] like Figure 2As illustrated in the example, the well site system 200 may include a crisscross drill pipe 218 and related components, or a top drive unit 240 and related components. Regarding the example of the crisscross drill pipe, the crisscross drill pipe 218 may be a square or hexagonal metal / alloy bar with holes drilled to serve as a mud flow path. The crisscross drill pipe 218 can be used to transmit rotational motion from the rotary table 220 via the crisscross drill pipe drive bushing 219 to the drill string 225, while allowing the drill string 225 to be lowered or raised during rotation. The crisscross drill pipe 218 may pass through the crisscross drill pipe drive bushing 219, which may be driven by the rotary table 220. As an example, the rotary table 220 may include a main bushing operably coupled to the crisscross drill pipe drive bushing 219, such that rotation of the rotary table 220 can rotate the crisscross drill pipe drive bushing 219 and thus rotate the crisscross drill pipe 218. The square drill pipe drive bushing 219 may include an internal profile (e.g., square, hexagonal, etc.) that matches the external profile of the square drill pipe 218; but the size is slightly larger, so that the square drill pipe 218 can move freely up and down within the square drill pipe drive bushing 219.

[0054] Regarding the example of a top drive unit, top drive unit 240 can provide functions performed by the kelly and rotary table. Top drive unit 240 can rotate drill string 225. As an example, top drive unit 240 may include one or more motors (e.g., electric and / or hydraulic motors) connected via suitable transmissions to a short section of pipe known as a casing shaft, which can in turn be screwed into a protective sub or drill string 225 itself. Top drive unit 240 can be suspended on traveling block 211, so the rotating mechanism can move freely up and down on derrick 214. As an example, top drive unit 240 may allow drilling using more joint stands than the kelly / rotary table method.

[0055] exist Figure 2 In the example, mud tank 201 can contain mud, which can be one or more types of drilling fluid. As an example, a wellbore can be drilled to produce fluid, inject fluid, or both (e.g., hydrocarbons, minerals, water, etc.).

[0056] exist Figure 2In the example, drill string 225 (e.g., including one or more downhole tools) may consist of a series of threaded pipes forming a long tube with drill bit 226 at its lower end. When drill string 225 is advanced into the wellbore for drilling, at some point before or concurrent with drilling, mud may be pumped from mud tank 201 (e.g., or other source) via lines 206, 208, and 209 to a port on crisscross rod 218, or, for example, to a port on top drive unit 240, via pump 204. The mud may then flow out of the port on drill bit 226 via channels (e.g., multiple channels) in drill string 225 (e.g., see directional arrows). As the mud exits drill string 225 via the port on drill bit 226, it may then circulate upwards through an annular region between the drill string 225's outer surface and surrounding walls (e.g., open hole, casing, etc.), as indicated by the directional arrows. In this way, the mud lubricates the drill bit 226 and brings heat (e.g., friction or other energy) and formation cuttings to the surface, where the mud (e.g., and cuttings) can be returned to the mud tank 201, for example, for recycling (e.g., for processing to remove cuttings, etc.).

[0057] The mud pumped into the drill string 225 by pump 204 forms a mud cake lining the wellbore after leaving the drill string 225. The mud cake's primary function is to reduce friction between the drill string 225 and the surrounding walls (e.g., borehole, casing, etc.). This reduction in friction facilitates the advancement or retraction of the drill string 225. During drilling operations, the entire drill string 225 can be pulled out of the wellbore and optionally replaced with, for example, a new or sharp drill bit, a smaller diameter drill string, etc. As mentioned, the act of pulling the drill string out of or back into the hole is called tripping. Depending on the direction of tripping, tripping can be referred to as upward tripping or outward tripping, or downward tripping or inward tripping.

[0058] As an example, consider a down-running drill, where, as the drill bit 226 of the drill string 225 reaches the bottom of the wellbore, the pumping of mud begins to lubricate the drill bit 226 in order to enlarge the wellbore. As mentioned, the mud can be pumped by pump 204 into the channels of the drill string 225, and while filling the channels, the mud can be used as a medium for transmitting energy, for example, energy that can encode information, as in mud pulse telemetry.

[0059] For example, a mud pulse telemetry device may include a downhole device configured to influence pressure changes in the mud to generate acoustic waves or waves that can modulate information. In such an example, information from the downhole device (e.g., one or more modules of drill string 225) can be transmitted to a surface device, which can then relay such information to other devices for processing, control, etc.

[0060] As an example, the telemetry device can operate via energy transmission through the drill string 225 itself. As an example, consider a signal generator that transmits coded energy signals to the drill string 225 and a repeater that can receive and relay such energy for further transmission of coded energy signals (e.g., information, etc.).

[0061] As an example, drill string 225 may be equipped with telemetry device 252, which includes a rotatable drive shaft; a turbine impeller mechanically coupled to the drive shaft such that mud can cause the turbine impeller to rotate; a modulator rotor mechanically coupled to the drive shaft such that rotation of the turbine impeller causes rotation of the modulator rotor; a modulator stator mounted adjacent to or near the modulator rotor such that rotation of the modulator rotor relative to the modulator stator generates pressure pulses in the mud; and a controllable brake for selectively braking the rotation of the modulator rotor to modulate the pressure pulses. In such an example, an alternator may be coupled to the aforementioned drive shaft, wherein the alternator includes at least one stator winding electrically connected to a control circuit to selectively short-circuit the at least one stator winding to electromagnetically brake the alternator, thereby selectively braking the rotation of the modulator rotor to modulate the pressure pulses in the mud.

[0062] exist Figure 2 In one example, the wellhead control and / or data acquisition system 262 may include circuitry to sense pressure pulses generated by the telemetry device 252, and, for example, transmit the sensed pressure pulses or information derived therefrom for processing, control, etc.

[0063] The component 250 shown in the 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 a motor 260, and a drill bit 226. Such a component or module may be referred to as a tool, wherein the drill string may include multiple tools.

[0064] As for RSS, it relates to techniques used in directional drilling. Directional drilling involves drilling into the ground to form an skewed borehole, such that the borehole's trajectory is not vertical; instead, the trajectory deviates from the vertical along one or more sections of the borehole. As an example, consider a target located at a lateral distance from the ground location where the drilling rig might be positioned. In such an example, drilling could begin with a vertical section and then deviate from the vertical, so that the borehole aims at and eventually reaches the target. Directional drilling can be implemented where a target is inaccessible from a vertical location on the ground, where there are substances in the ground that could obstruct drilling or otherwise be harmful (e.g., consider salt domes), where formations extend laterally (e.g., consider relatively thin but laterally extending reservoirs), where multiple boreholes need to be drilled from a single surface borehole, where decompression wells are required, and so on.

[0065] One method of directional drilling involves mud motors; however, mud motors can face several challenges depending on factors such as the rate of penetration (ROP) and the transfer of weight to the drill bit due to friction (e.g., pressure on drill bit, wobble weight). A mud motor can be a positive displacement motor (PDM), which operates to drive the drill bit (e.g., in directional drilling processes). The PDM operates as drilling fluid is pumped through it, converting the hydraulic power of the drilling fluid into mechanical power to rotate the drill bit.

[0066] As an example, PDM can operate in a combined rotary mode, where surface equipment is used to rotate the drill string bit by rotating the entire drill string (e.g., rotary table, top drive, etc.), and drilling fluid is used to rotate the drill string bit. In such an example, the surface RPM (SRPM) can be determined using surface equipment, while the downhole RPM of the mud motor can be determined using various factors related to drilling fluid flow, mud motor type, etc. As an example, in the combined rotary mode, assuming the SRPM and mud motor RPM are in the same direction, the bit RPM can be determined or estimated as the sum of the SRPM and mud motor RPM.

[0067] As an example, when the drill string is not rotating from the ground, the PDM mud motor can operate in a so-called slippery mode. In such an example, the drill bit RPM can be determined or estimated based on the mud motor's RPM.

[0068] RSS (Remote Suspension Spectrometer) allows for directional drilling where the drill bit rotates continuously from the surface equipment, reducing slippage in steerable motors such as PDMs. RSS can be deployed during directional drilling (such as deviated, horizontal, or extended reach wells). RSS minimizes interaction with the borehole wall, helping to maintain borehole quality. RSS can be designed to apply a relatively consistent lateral force, similar to a stabilizer rotating with the drill string, or to orient the drill bit in the desired direction while rotating continuously at the same rate as the drill string.

[0069] LWD module 254 can be housed in a suitable type of drill collar and may contain one or more selected types of logging tools. It should also be understood that more than one LWD and / or MWD module may be used, for example, as shown in module 256 of drill string assembly 250. When referring to the location of an LWD module, by way of example, it may refer to the module located at the location of LWD module 254, module 256, etc. An LWD module may include the ability to measure, process, and store information, as well as the ability to communicate with surface equipment. In the example shown, LWD module 254 may include a seismic measurement device.

[0070] MWD module 256 can be housed in a suitable type of drill collar and may include one or more devices for measuring the characteristics of drill string 225 and drill bit 226. As an example, MWD tool 254 may include devices for generating electricity, for example, to power various components of drill string 225. As an example, MWD tool 254 may include telemetry device 252, for example, where a turbine impeller can generate electricity through the flow of mud; it should be understood that other power sources and / or battery systems may be used to power various components. As an example, MWD module 256 may include one or more measuring devices of the following types: drill pressure measuring device, torque measuring device, vibration measuring device, impact measuring device, stick-slip measuring device, direction measuring device, and tilt measuring device.

[0071] Figure 2 Some examples of the types of holes that can be drilled are also shown. As examples, consider inclined hole 272, S-shaped hole 274, deep inclined hole 276, and horizontal hole 278.

[0072] As an example, drilling operations may include directional drilling, where, for example, at least a portion of the well includes a curved axis. As an example, consider defining a radius of curvature, where the inclination relative to the vertical direction can vary up to an angle between approximately 30 degrees and approximately 60 degrees, or, for example, approximately 90 degrees or possibly greater than approximately 90 degrees.

[0073] As an example, directional wells can include several shapes, each designed to meet specific operational requirements. As an example, the drilling process can be performed based on information passed to the drilling engineer. As an example, the inclination and / or direction can be modified based on information received during the drilling process.

[0074] As an example, borehole deflection can be achieved in part by using one or more of an RSS, a downhole motor, and / or a turbine. For example, for the motor, the drill string may include a positive displacement motor (PDM).

[0075] As an example, the system can be a guided system and includes equipment for performing methods such as geological guidance. As an example, a guided system may include a PDM or turbine located at the bottom of the drill string, with a curved sub mounted directly above the drill string. As an example, above the PDM, an MWD and / or LWD device can be mounted to provide real-time or near-real-time data of interest (e.g., inclination, direction, pressure, temperature, actual weight on the drill bit, torque stress, etc.). For the latter, the LWD device can transmit various types of data of interest to the surface, including, for example, geological data (e.g., gamma-ray logging, resistivity, density, and sonic logging, etc.).

[0076] Linking sensors that provide real-time or near-real-time information about wellbore trajectory with one or more logging operations, such as those characterizing formations from a geological perspective, can enable the implementation of geosteering methods. Such methods can include navigating the subsurface environment, for example, along a desired route to one or more desired targets.

[0077] As an example, a drill string may include an azimuth density neutron (ADN) tool for measuring density and porosity; a MWD tool for measuring tilt, azimuth, and vibration; a compensated dual resistivity (CDR) tool for measuring resistivity and gamma-ray related phenomena; one or more variable thickness stabilizers; one or more bent subs; and a geological guidance tool that may include a motor and optional equipment for measuring and / or responding to one or more of tilt, resistivity, and gamma-ray related phenomena.

[0078] As an example, geological steering can include intentionally directionally controlling a wellbore in a manner based on the results of downhole geological logging measurements, said manner being intended to keep the directional wellbore within a desired area, zone (e.g., oil-producing layer), etc. As an example, geological steering can include guiding the wellbore to keep it within a specific portion of the reservoir, for example, to minimize gas and / or water breakthrough, and, for example, to maximize economic production from the well that includes the wellbore.

[0079] Refer again Figure 2 Well site system 200 may include one or more sensors 264 operatively coupled to control and / or data acquisition system 262. As an example, one or more sensors may be located at a surface location. As an example, one or more sensors may be located at a downhole location. As an example, one or more sensors may be located at one or more remote locations, not within a distance on the order of approximately 100 meters from well site system 200. As an example, one or more sensors may be located at an offset wellsite, where well site system 200 and the offset wellsite are located in a common field (e.g., an oil field and / or a gas field).

[0080] As an example, one or more sensors 264 can be provided to track the movement of pipes, track the movement of at least a portion of the drill string, etc.

[0081] As an example, system 200 may include one or more sensors 266 that can sense and / or transmit signals to fluid conduits, such as drilling fluid conduits (e.g., drilling mud conduits). As an example, in system 200, one or more sensors 266 may be operatively coupled to a portion of riser 208 through which mud flows. As an example, a downhole tool may generate pulses that can pass 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 encoding circuitry, that can encode signals, for example, to reduce the need for transmission. As an example, surface circuitry may include decoding circuitry to decode encoded information transmitted at least partially via mud pulse telemetry. As an example, surface circuitry may include encoder circuitry and / or decoder circuitry, and downhole circuitry may include encoder circuitry and / or decoder circuitry. As an example, system 200 may include a transmitter capable of generating signals that can be transmitted downhole via mud (e.g., drilling fluid) as a transmission medium.

[0082] As an example, one or more portions of the drill string may become stuck. The term "stuck" can refer to one or more different degrees of inability to move or remove the drill string from the borehole. As an example, in a stuck situation, it may be possible to rotate the drill string or lower it back into the borehole, or, for example, in a stuck situation, it may be impossible to move the drill string axially in the borehole, although there may be some degree of rotation. As an example, in a stuck situation, it may be impossible to move at least a portion of the drill string both axially and rotationally.

[0083] The term "stuck pipe" can refer to a portion of the drill string that cannot rotate or move axially. For example, a situation known as "differential pressure sticking" can be a situation where the drill string cannot move along the axis of the borehole (e.g., rotate or reciprocate). Differential pressure sticking occurs when high contact forces caused by low reservoir pressure, high wellbore pressure, or both are applied over a sufficiently large drill string area. Differential pressure sticking is time-consuming and costly.

[0084] As an example, the holding 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 applying a relatively low pressure differential (Δp) over a large working area is just as effective as applying a high pressure differential over a small area.

[0085] As an example, a situation referred to as "mechanical jamming" can be one where the movement of the drill string is restricted or prevented by a mechanism other than differential pressure jamming. Mechanical jamming can be caused by, for example, one or more types of debris in the borehole, wellbore geometry anomalies, cement, keyways, or drill cuttings buildup in the annulus.

[0086] Figure 3An example of system 300 is shown, which includes various devices for evaluation 310, planning 320, engineering 330, and operation 340. For example, drilling workflow framework 301, seismic simulation framework 302, technical data framework 303, and drilling framework 304 can be implemented to perform one or more processes, such as evaluating formation 314, evaluating process 318, generating trajectory 324, verifying trajectory 328, establishing constraints 334, designing equipment and / or processes at least in part based on constraints 338, performing drilling 344, and evaluating drilling and / or formation 348.

[0087] exist Figure 3 In the example, the earthquake simulation framework 302 can be, for example, the PETREL framework (Schlumberger Ltd., Houston, Texas), and the technical data framework 303 can be, for example, the TECHLOG framework (Schlumberger Ltd., Houston, Texas).

[0088] As an example, a framework can include entities, which may include land entities, geological objects, or other objects such as wells, surfaces, reservoirs, etc. Entities can include virtual representations of actual physical entities reconstructed for one or more purposes such as assessment, planning, engineering, operation, etc.

[0089] Entities can include those based on data obtained through sensing, observation, etc. (e.g., seismic data and / or other information). An entity can be characterized by one or more properties (e.g., a geometric columnar mesh entity of a land model can be characterized by porosity properties). Such properties can represent one or more measurements (e.g., acquired data), calculations, etc.

[0090] A framework can be an object-based framework. In such a framework, entities can include entities based on predefined categories, for example, to facilitate modeling, analysis, simulation, etc. An example of an object-based framework is the MICROSOFT .NET Framework (Redmond, Washington), which provides a set of extensible object classes. In the .NET Framework, object classes encapsulate modules of reusable code and related data structures. Object classes can be used to instantiate object instances for use by programs, scripts, etc. For example, a borehole class can define objects used to represent boreholes based on well data.

[0091] As an example, the framework may include analysis components that allow interaction with the model or model-based results (e.g., simulation results). Regarding simulation, the framework may be operatively linked to or include simulators such as the ECLIPSE reservoir simulator (Schlumberger, Inc., Houston, Texas), the INTERSECT reservoir simulator (Schlumberger, Inc., Houston, Texas), etc.

[0092] The aforementioned PETREL framework provides components that allow for the optimization of exploration and development operations. The PETREL framework includes seismic simulation software components that can output information to improve reservoir performance, for example, by increasing the productivity of the asset team. By using such a framework, various professionals (e.g., land physicists, geologists, well engineers, reservoir engineers, etc.) can develop collaborative workflows and integrate operations to streamline processes. This framework can be considered an application, and can also be considered a data-driven application (e.g., where data is input for modeling, simulation, etc.).

[0093] As an example, one or more frameworks can be interoperable and / or run on one or more frameworks. Consider, for instance, the OCEAN Framework Environment (Schlumberger, Inc., Houston, Texas), which allows for the integration of add-ons (or plugins) into the PETREL Framework workflow. The OCEAN Framework Environment leverages .NET tools (Microsoft Corporation, Redmond, Washington) to provide a stable, user-friendly interface for efficient development. In the example embodiment, various components may be implemented as add-ons (or plugins) conforming to the framework environment's specifications (e.g., according to the Application Programming Interface (API) specification) and operating according to those specifications.

[0094] As an example, the framework may include a model simulation layer, as well as a framework service layer, a framework core layer, and a module layer. The framework may include the OCEAN framework, where the model simulation layer may include or be operatively linked to a PETREL model-centric software package that hosts the OCEAN framework application. In the example embodiment, the PETREL software can be considered a data-driven application. The PETREL software may include frameworks for model building and visualization. Such a model may include one or more meshes.

[0095] As an example, the model simulation layer can provide domain objects, act as a data source, provide rendering, and provide various user interfaces. Rendering can provide a graphical environment where applications can display their data, while the user interface can provide a common look and feel for the application's user interface components.

[0096] As an example, a domain object can include entity objects, characteristic objects, and optional other objects. Entity objects can be used to geometrically represent wells, surfaces, reservoirs, etc., while characteristic objects can be used to provide characteristic values, data versions, and display parameters. As an example, an entity object can represent a well, where characteristic objects provide logging information, as well as version information and display information (e.g., showing the well as part of the model).

[0097] As an example, data can be stored in one or more data sources (or data stores, typically physical data storage devices), which may be located at the same or different physical sites and can be accessed via one or more networks. As another example, the model simulation layer can be configured to model a project. This allows specific projects to be stored, where the stored project information can include inputs, models, results, and conditions. Therefore, the user can save the project when the modeling session is complete. Later, the project can be accessed and restored using the model simulation layer, which allows for the re-creation of instances of the relevant domain objects.

[0098] As an example, system 300 can be used to execute one or more workflows. A workflow can be a process that includes many work steps. Work steps can manipulate data, such as creating new data, updating existing data, etc. As an example, a workflow can manipulate one or more inputs and, for example, create one or more results based on one or more algorithms. As an example, the system may include a workflow editor for creating, editing, executing, etc., workflows. In such an example, the workflow editor can provide selections for one or more predefined work steps, one or more custom work steps, etc. As an example, a workflow can be a workflow that is at least partially implementable in PETREL software, for example, manipulating seismic data, seismic properties, etc.

[0099] As an example, seismic data can be data obtained through seismic surveys, where sources and receivers are placed in a geological environment to emit and receive seismic energy, at least a portion of which can be reflected from subsurface structures. As an example, a seismic data analysis framework or multiple frameworks (e.g., consider the OMEGA framework sold by Schlumberger Ltd., Houston, Texas) can be used to determine the depth, extent, characteristics, etc., of subsurface structures. As an example, seismic data analysis can include, for example, forward simulations and / or inversions to iteratively build a model of subsurface areas of the geological environment. As an example, a seismic data analysis framework can be part of or operatively linked to a seismic simulation framework (e.g., the PETREL framework).

[0100] As an example, a workflow can be a process that is at least partially achievable within the OCEAN framework. As an example, a workflow may include one or more work steps that access modules such as plugins (e.g., external executable code).

[0101] As an example, frameworks can provide modeling for petroleum systems. For instance, the PETROMOD framework (Schlumberger Ltd., Houston, Texas) includes features for inputting various types of information (e.g., seismic, well, geological, etc.) to model the evolution of sedimentary basins. The PETROMOD framework provides petroleum system modeling, such as modeling the evolution of sedimentary basins, by inputting various data (e.g., seismic data, well data, and other geological data). The PETROMOD framework can predict whether and how reservoirs are filled with hydrocarbons, including, for example, the source and timing of hydrocarbon generation, migration routes, quantities, pore pressures, and hydrocarbon types under subsurface or surface conditions. By combining frameworks such as the PETREL framework, workflows can be built to provide exploration solutions from basin to prospect scale. Data exchange between frameworks can facilitate model building, data analysis (e.g., analyzing PETROMOD framework data using the capabilities of the PETREL framework), and workflow integration.

[0102] As mentioned, a drill string can include a variety of tools capable of measurement. As an example, measurements can be performed using cable tools or other types of tools. As an example, the tool can be configured to acquire images of the drill hole. As an example, a Full-Hole Formation Microimager (FMI) tool (Schlumberger Ltd., Houston, Texas) can acquire borehole image data. The data acquisition sequence of such a tool can include inserting the tool into the borehole with the acquisition pad closed, opening the acquisition pad and pressing it against the borehole wall, translating the tool within the borehole while simultaneously delivering current to the material defining the borehole, and remotely sensing the current, which changes through interaction with the material.

[0103] Analysis of stratigraphic information can reveal features such as cavities, dissolution surfaces (e.g., dissolution along bedding planes), stress-related characteristics, and tilting events. As an example, tools can acquire information that helps characterize reservoirs, optionally fractured reservoirs where fractures can be natural and / or man-made (e.g., hydraulically fractured). As an example, frameworks such as the TECHLOG framework can be used to analyze information acquired by one or more tools. As an example, the TECHLOG framework can interoperate with one or more other frameworks (e.g., the PETREL framework).

[0104] As an example, various aspects of a workflow can be automated, partially automated, or performed manually, such as by a human user interacting with a software application. As an example, a workflow can be cyclical and may include, for example, four phases: an evaluation phase (e.g., see evaluation device 310), a planning phase (e.g., see planning device 320), an engineering phase (e.g., see engineering device 330), and an execution phase (e.g., see operation device 340). As an example, a workflow may begin at one or more phases and can proceed to one or more other phases (e.g., sequentially, in parallel, cyclically, etc.).

[0105] As an example, the workflow can begin with an assessment phase, which may include the geological service provider assessing the formation (e.g., see Assessment Box 314). As an example, the geological service provider may use a computational system that executes software packages tailored for this activity to perform the formation assessment; or, for example, one or more other suitable geological platforms (e.g., alternative or supplementary geological platforms) may be employed. As an example, the geological service provider may assess the formation using, for example, land models, land physics models, basin models, petroleum technology models, combinations thereof, etc. Such models may take into account a variety of different inputs, including offset well data, seismic data, directional well data, other geological data, etc. The model and / or inputs may be stored in a database maintained by a server and accessed by the geological service provider.

[0106] As an example, the workflow may proceed to a geological and geophysical (“G&G”) service provider, which can generate a well trajectory (e.g., see generation box 324), which may involve the execution of one or more G&G software packages. Examples of such software packages include the PETREL framework. As an example, the G&G service provider may determine the well trajectory, or a portion thereof, based on one or more models provided, for example, by formation assessment (e.g., according to assessment box 314), and / or other data accessed, for example, from one or more databases (e.g., maintained by one or more servers, etc.). As an example, the well trajectory may take into account various “design basis” (BOD) constraints, such as general surface location, target (e.g., reservoir) location, etc. As an example, the trajectory may include information about tools, bottom hole components, casing size, etc., which can be used for drilling. The determination of the well trajectory may take into account various other parameters, including risk tolerance, fluid weight and / or schedule, bottom hole pressure, drilling time, etc.

[0107] As an example, the workflow may proceed to a first engineering service provider (e.g., one or more processors associated with it), which can verify the well trajectory and, for example, the design of a relief well (see, for example, verification box 328). This verification process may include evaluating physical characteristics, calculations, risk tolerance, integration with other aspects of the workflow, etc. As an example, one or more parameters used for this determination may be maintained by a server and / or the first engineering service provider; note that one or more models, well trajectories, etc., may be maintained by the server and accessible to the first engineering service provider. For example, the first engineering service provider may include one or more computing systems executing one or more software packages. As an example, if the first engineering service provider refuses or suggests adjustments to the well trajectory, the well trajectory may be adjusted, or a message requesting such modification or other notification may be sent to the G&G service provider.

[0108] As an example, one or more engineering service providers (e.g., a first, a second, etc.) may provide casing design, bottom hole assembly (BHA) design, fluid design, and / or similar designs to achieve a wellbore trajectory (e.g., see design box 338). In some embodiments, a second engineering service provider may use one or more software applications to perform such a design. This design may be stored in one or more databases maintained by one or more servers, which may employ, for example, STUDIO framework tools, and may be accessible to one or more other service providers in the workflow.

[0109] As an example, a second engineering service provider may seek approval from a third engineering service provider for one or more designs established along with the well trajectory. In such an example, the third engineering service provider may consider various factors regarding the acceptability of the well engineering plan, such as economic variables (e.g., oil production forecasts, cost per barrel, risks, drilling time, etc.), and may request expenditure authorization, such as from representatives of the operating company, representatives of the well owner, etc. (e.g., see formulation box 334). As an example, at least some of the data on which this determination is based may be stored in one or more databases maintained by one or more servers. As an example, the first, second, and / or third engineering service providers may be provided by a single engineering team or even a single engineer, and therefore may or may not be separate entities.

[0110] As an example, in situations where economics may be unacceptable or authorization is denied, the engineering service provider may recommend changes to the casing, bottomhole assembly, and / or fluid design, or otherwise notify and / or return control to different engineering service providers, thereby allowing for adjustments to the casing, bottomhole assembly, and / or fluid design. Where modifying one or more of these designs is not feasible within well constraints, trajectory, etc., the engineering service provider may recommend adjustments to the well trajectory, and / or the workflow may be returned to or otherwise notified to the initial engineering service provider and / or the G&G service provider, enabling either or both parties to modify the well trajectory.

[0111] As an example, a workflow may include consideration of the well trajectory, including the accepted well engineering plan and formation assessment. Such a workflow can then pass control to the drilling service provider, who can implement the well engineering plan, establish safe and efficient drilling, maintain well integrity, and report progress and operating parameters (e.g., see boxes 344 and 348). As an example, operating parameters, encountered formations, and data collected during drilling (e.g., using logging-while-drilling or measurement-while-drilling techniques) can be returned to the geological service provider for evaluation. As an example, the geological service provider can then reassess one or more other aspects of the well trajectory or well engineering plan, and in some cases, and possibly within predetermined constraints, adjust the well engineering plan based on actual drilling parameters (e.g., based on field-obtained data, etc.).

[0112] Depending on the specific implementation, whether the well is fully drilled or only partially completed, the workflow may extend to post-inspection (e.g., see evaluation box 318). As an example, post-inspection may include checking drilling performance. As an example, post-inspection may also include reporting drilling performance (e.g., to one or more relevant engineering, geology, or G&G service providers).

[0113] The various activities of a workflow can be performed sequentially and / or out of order (e.g., filling gaps in information that will be provided by another service provider, based in part on information from templates, nearby wells, etc.). As an example, performing one activity may affect the outcome or basis of another activity, thus potentially requiring changes to one or more workflow activities, work products, etc., manually or automatically. As an example, a server could allow information to be stored in a central database accessible to various service providers, where changes can be sought through communication with the appropriate service providers, changes can be implemented automatically, or they can otherwise appear as recommendations to relevant service providers. Such an approach can be considered a holistic approach to oil well workflows compared to sequential, fragmented methods.

[0114] As an example, various actions in a workflow can be repeated multiple times during well drilling. For instance, in one or more automated systems, feedback from the drilling service provider can be provided in real-time or near real-time, and data acquired during drilling can be fed to one or more other service providers, who can adjust one of their workflows accordingly. Such adjustments can permeate the workflow, for example, automatically, due to dependencies that may exist in other areas. In some embodiments, cyclical processes can be performed additionally or alternatively after a drilling objective is achieved, such as completing a section of the well, and / or after drilling the entire well, or on a daily, weekly, monthly, or other schedule.

[0115] A well plan may include determining pathways for wells that can extend into a reservoir, for example, to economically produce fluids such as hydrocarbons from the reservoir. A well plan may include selecting drilling and / or completion components that can be used to implement the well plan. As an example, various constraints may be imposed as part of the well plan, which affect the well design. As an example, such constraints may be imposed based at least in part on information about the known geology of a subsurface area within a region (e.g., considering collision avoidance), the existence of one or more other wells (e.g., actual and / or planned wells), etc. As an example, one or more constraints may be imposed based at least in part on the characteristics of one or more tools, components, etc. As an example, one or more constraints may be based at least in part on factors associated with drilling time and / or risk tolerance.

[0116] As an example, a system can allow for the reduction of waste, for instance, it can be defined according to LEAN. In the context of LEAN, consider one or more of the following types of waste: transport (e.g., unnecessary movement of items, whether physical or data); inventory (e.g., components, whether physical or informational, as work-in-process and unfinished goods); motion (e.g., unnecessary movement or walking of people or equipment to perform desired processing); waiting (e.g., waiting for information, production interruptions during shift changes, etc.); overproduction (e.g., production exceeding demand for materials, information, equipment, etc.); overprocessing (e.g., caused by poor tooling or product design activities); and defects (e.g., work involved in inspecting and repairing defects in plans, data, equipment, etc.). As an example, a system that allows actions (e.g., methods, workflows, etc.) to be performed collaboratively can help reduce one or more types of waste.

[0117] As an example, a system can be used to implement a method for facilitating distributed well engineering, planning, and / or drilling system design across multiple computing devices, where collaboration can occur among a variety of different users (e.g., some local, some remote, some mobile, etc.). In such a system, various users via appropriate devices can be operatively connected via one or more networks (e.g., local area networks and / or wide area networks, public and / or private networks, land-based, sea-based, and / or regional networks, etc.).

[0118] As an example, the system may allow well engineering, planning, and / or drilling system design to be performed through a subsystem approach, where the well site system comprises various subsystems, which may include equipment subsystems and / or operational subsystems (e.g., control subsystems, etc.). As an example, calculations may be performed using various computing platforms / devices operatively connected via communication links (e.g., network links, etc.). As an example, one or more links may be operatively connected to a public database (e.g., server sites, etc.). As an example, specific servers may manage receiving notifications from and / or issuing notifications to one or more devices. As an example, a system may be implemented for a project whereby the system can output a well plan, e.g., as a digital well plan, a paper well plan, a digital and paper well plan, etc. Such a well plan may be a complete well engineering plan or design for a specific project.

[0119] Figure 4 An example of a system 400 is shown, which includes various components that can be located locally at the well site and various components that can be located remotely at the well site. As shown, system 400 includes a coordination block 402, an integration block 404, a core and services block 406, and a device block 408. These blocks can be used in different ways. Figure 4 The examples illustrate one or more ways to label. Figure 4 In the example, boxes 402, 404, 406, and 408 can be defined by one or more of operational features, functions, relationships in the architecture, etc.

[0120] As an example, boxes 402, 404, 406, and 408 can be described as a pyramid architecture, where, from apex to bottom, the pyramid includes coordination box 402, integration box 404, core and services box 406, and device box 408.

[0121] As an example, the coordination box 402 may be associated with the well management layer (e.g., well planning and / or coordination) and the drilling rig management layer (e.g., drilling rig dynamic planning and / or coordination). As an example, the integration box 404 may be associated with the process management layer (e.g., drilling rig integration execution). As an example, the core and services box 406 may be associated with the data management layer (e.g., sensors, instruments, inventory, etc.). As an example, the equipment box 408 may be associated with the well site equipment layer (e.g., well site subsystems, etc.).

[0122] As an example, coordination box 402 may receive information from the drilling workflow framework and / or one or more other sources that may be located away from the well site.

[0123] exist Figure 4 In the example, coordination box 402 includes a planning / rescheduling box 422, a coordination / arbitration box 424, and a local resource management box 426. Figure 4 In the example, integration box 404 includes integration execution box 444, which may include or be operatively coupled to various subsystems of the well site, such as drilling subsystems, mud management subsystems (e.g., hydraulic subsystems), casing subsystems (e.g., casing and / or completion subsystems), and one or more other subsystems. Figure 4 In the example, core and services box 406 includes data management and real-time services box 464 (e.g., real-time or near-real-time services) and rig and cloud security box 468 (e.g., regarding supply and various types of security measures, etc.). Figure 4 In the example, device box 408 is shown as capable of providing various types of information to core and service box 406. For example, consider information from drilling rig surface sensors, LWD / MWD sensors, mud logging sensors, drilling rig control system, drilling equipment, personnel, materials, etc. Figure 4 In the example, box 470 may provide one or more of the following: data visualization, automatic alerts, automatic reporting, etc. As an example, box 470 may be operatively connected to core and service box 406 and / or one or more other boxes.

[0124] As mentioned, a portion of system 400 can be located remotely from the well site. For example, on one side of the dashed line appear the Remote Operations Command Center box 492, the Database box 493, the Drilling Workflow Framework box 494, the SAP / ERP box 495, and the Field Service Delivery box 496. These various boxes, which can be remote, can be operatively linked to one or more boxes local to the well site system. As an example, in Figure 4 The example illustrates a communication link 412, which can operatively connect blocks 406 and 492 (e.g., for monitoring, remote control, etc.), while... Figure 4The example illustrates another communication link 414, which can operatively connect boxes 406 and 496 (e.g., regarding device delivery, device service, etc.). Various other examples of possible communication links are also shown in... Figure 4 The example is shown.

[0125] As an example, Figure 4 The system 400 can be a field management tool. As an example, Figure 4 System 400 may include a drilling frame (e.g., see drilling frame 304). As an example, Figure 4 The frame in System 400 can be located far from the well site.

[0126] As an example, drilling can be performed based on a drilling plan established before drilling. This drilling plan can be a pre-defined plan or a part thereof, and may specify equipment, pressure, trajectory, and / or other parameters defining the drilling process at the well site. As an example, drilling operations can then be performed based on the drilling plan (e.g., a well plan). As an example, drilling operations may deviate from the drilling plan as information is collected. Furthermore, subsurface conditions may change as drilling or other operations proceed. Specifically, as new information is collected, sensors can transmit data to one or more surface units. As an example, surface units can automatically use such data to update the drilling plan (e.g., locally and / or remotely).

[0127] As an example, the drilling workflow framework 494 may be or include a G&G system and a well planning system. As an example, a G&G system corresponds to hardware, software, firmware, or a combination thereof that supports geology and land physics. In other words, a geologist who understands the reservoir can use a G&G system to decide where to drill, which creates a 3D model of the subsurface formation and includes simulation tools. The G&G system can transmit the well trajectory and other information selected by the geologist to the well planning system. A well planning system corresponds to hardware, software, firmware, or a combination thereof that generates a well plan. In other words, a well plan can be an advanced drilling procedure for a well. A well planning system can also be referred to as a well plan generator.

[0128] exist Figure 4 In the examples, the various boxes can be components corresponding to one or more software modules, hardware infrastructure, firmware, devices, or any combination thereof. Communication between components can be local or remote, direct or indirect, via application programming interfaces and procedure calls, or through one or more communication channels.

[0129] As an example, Figure 4 The various boxes in System 400 can correspond to the granular level of control over operations associated with equipment and / or personnel in the oilfield. For example... Figure 4As shown, system 400 may include coordination box 402 (e.g., for well plan execution), integration box 404 (e.g., process manager collection), core and services box 406, and device box 408.

[0130] Coordination box 402 may be referred to as a well plan execution system. For example, a well plan execution system corresponds to hardware, software, firmware, or a combination thereof, which performs the overall coordination of the well construction process, such as the coordination of the drilling rig and the management of the drilling rig and its equipment. The well plan execution system may be configured to obtain a general well plan from a well plan system and convert the general well plan into a detailed well plan. The detailed well plan may include descriptions of the activities involved in executing the actions in the general well plan, the dates and / or times of the activities, the various resources for the activities, and other information.

[0131] As an example, the well planning execution system may further include functionality to monitor the execution of the well plan to track progress and dynamically adjust the plan. Furthermore, the well planning execution system may be configured to handle logistics and resources both on and off the drilling rig. As an example, the well planning execution system may include multiple sub-components, such as a detail descriptor configured to describe the well planning system plan in detail, a monitor configured to monitor the execution of the plan, a plan manager configured to perform dynamic plan management, and a logistics and resource manager to control the well's logistics and resources. In one or more embodiments, the well planning execution system may be configured to coordinate between different processes managed by a set of process managers (e.g., see integration box 404). In other words, the well planning execution system can communicate and manage resource sharing between processes in the process manager set, while operating at, for example, a higher granularity level than the process manager set.

[0132] As for integration box 404, as mentioned, it can be referred to as a process manager set. In one or more embodiments, the process manager set may include functions that perform process management for various domains of an oilfield (e.g., a drilling rig). For example, different activities may be performed during drilling. Each activity may be controlled by a single process manager in the process manager set. The process manager set may include multiple process managers, whereby each process manager controls different activities (e.g., activities related to the drilling rig). In other words, each process manager may have a set of tasks defined for the process manager that are specific to the physical type involved in the activity. For example, drilling may use drilling mud, which is a fluid pumped into the well to extract drill cuttings from the well. A drilling mud process manager may exist in the process manager set, which manages the mixing and composition of drilling mud, testing of drilling mud properties, determining whether the pressure is accurate, and performing other such tasks. The drilling mud process manager may be separate from the process manager that controls the movement of the drill pipe from the well. Therefore, the process manager set can divide the activities into several different domains and manage each domain separately. Among other possible process managers, the process manager set may include, for example, a drilling process manager, a mud preparation and management process manager, a casing running process manager, a cementing process manager, a drilling rig equipment process manager, and other process managers. Furthermore, the process manager set can provide direct control or advice regarding the aforementioned components. As an example, coordination between process managers within the process manager set can be performed by a well planning execution system.

[0133] As for the core and services frame 406 (e.g., the CS frame), it can include functionality for managing individual devices and / or device subsystems. As an example, the CS frame may include functionality for processing basic data structures of an oilfield (e.g., drilling rigs), acquiring measurement data, generating reports, and managing human and material resources. As another example, the CS frame may include data acquirers and aggregators, rig status identifiers, real-time (RT) drilling services (e.g., near real-time), reporters, cloud services, and inventory managers.

[0134] As an example, data acquirers and aggregators may include the ability to interface with various device components and sensors and acquire data. As another example, data acquirers and aggregators may further include the ability to interface with sensors located in an oil field.

[0135] As an example, a drilling rig status identifier may include the ability to acquire data from a data acquirer and an aggregator and convert that data into status information. As an example, the status information may include the drilling rig's health and operability, as well as information about specific tasks performed by the equipment.

[0136] As an example, an RT drilling service may include the ability to transmit and present information to individuals. Specifically, the RT drilling service may include the ability to transmit information to individuals involved based on roles and, for example, the type of device each individual uses (e.g., mobile device, desktop, etc.). In one or more embodiments, the information presented by the RT drilling service may be context-specific and may include dynamic display of information, allowing human users to view details about items of interest.

[0137] As an example, in one or more embodiments, the reporter may include the functionality to generate reports. As an example, the reports may be generated upon request and / or automatically, and may provide information about the status of devices and / or people.

[0138] As an example, a well site “cloud” framework can correspond to the local information technology infrastructure of an oil field, such as a single drilling rig within the oil field. In such an example, the well site “cloud” framework can be an “Internet of Things” (IoT) framework. As an example, the well site “cloud” framework can be the cloud (e.g., a network of multiple networks) or the edge of a dedicated network.

[0139] As an example, an inventory manager could be a box that includes functionality for managing materials, such as a list and quantity of each resource on a drilling rig.

[0140] exist Figure 4 In the example, device box 408 can correspond to various controllers, control units, control devices, etc., which can be operatively coupled to and / or embedded in physical equipment at the well site, such as drilling rig equipment. For example, device box 408 can correspond to the software and control systems of various items on the drilling rig. As an example, device box 408 can provide monitoring of sensors from multiple subsystems of the drilling rig and provide control commands to multiple subsystems of the drilling rig, such that sensor data from multiple subsystems can be used to provide control commands to different subsystems of the drilling rig and / or other equipment, etc. For example, the system can collect time- and depth-aligned surface and downhole data from the drilling rig and transmit the collected data to data acquirers and aggregators in the core service, which can store the collected data for access at the drilling rig site or off-site via computing resource environments.

[0141] As mentioned, Figure 4 The system 400 can be associated with a plan, wherein, for example, the plan / replan box 422 can provide planning and / or replanning of one or more operations, etc.

[0142] Figure 5An example of a graphical user interface (GUI) 500 is shown, which includes information associated with a well plan. Specifically, GUI 500 includes a panel 510, where ground representations 512 and 514 are presented along with the well trajectory, and location 516 can represent the position of the drill string 517 along the well trajectory. GUI 500 may include one or more editing features, such as a set of editing well plan features 530. GUI 500 may include information about individuals within a team 540 involved in, already involved in, and / or will be involved in one or more operations. GUI 500 may include information about one or more activities 550. Figure 5 As shown in the example, GUI 500 may include graphical control of drill string 560, wherein, for example, various parts of drill string 560 may be selected to display one or more relevant parameters (e.g., equipment type, equipment specifications, operation history, etc.). Figure 5 Table 570 is also shown as a point table specifying information for multiple wells.

[0143] Figure 6 An example of a graphical user interface (GUI) 600 is shown, which includes a calendar displaying dates for various operations that may be part of a schedule. As an example, GUI 600 illustrates rig uprun, casing downrun, cementing, drilling, and rig descent operations that may occur at different times. This GUI can be edited by selecting one or more graphical controls.

[0144] Various types of data associated with field operations can be one-dimensional series data. For example, consider data from one or more of the following: drilling system, downhole condition, formation properties, and surface mechanics, measured as single-channel or multi-channel time-series data.

[0145] Figure 7 Examples of various components of the lifting system 700 are shown, including a cable 701, a winch 710, a traveling block 711, a hook 712, a crane 713, a top drive unit 714, a cable dead-line anchor 720, a cable supply reel 730, one or more sensors 740, and circuitry 750 operatively coupled to the one or more sensors 740. Figure 7 In the example, the lifting system 700 may include various sensors, such as one or more load sensors, displacement sensors, accelerometers, etc. As an example, the cable dead-rope anchor 720 may be equipped with a load unit (e.g., a load sensor).

[0146] The lifting system 700 can be part of the well site system (e.g., see...). Figure 1 and Figure 2In such a system, the measurement channel can be a vehicle position measurement channel, called a BPOS, which provides the measurement of the traveler height. The traveler height can be defined near a dead point (e.g., zero point) and can deviate from that dead point in a positive and / or negative direction. For example, consider a traveler that can move within a range of approximately -5 meters to +45 meters, with a total travel of approximately 50 meters. As an example, a zero point or dead point can be defined to make the scale positive, negative, or both. In such an example, the rig height can be greater than approximately 50 meters (e.g., the overhead crane can be set at a height of more than approximately 50 meters above the ground or drill string). While various examples of land-based field operations (e.g., stationary, truck-based, etc.) are given, various methods are applicable to offshore operations (e.g., ship-based rigs, platform rigs, etc.).

[0147] BPOS is a real-time channel reflecting the surface mechanical performance of a drilling rig. Another example of a channel is hook load, which can be referred to as HKLD. HKLD can be a one-dimensional series of measurements of hook load. Regarding derivatives, the first derivative can be the load velocity, and the second derivative can be the load acceleration. This data channel can be used to infer and monitor various operations and / or conditions. In some examples, the drilling rig can be represented as being in one or more states, which can be referred to as drilling rig states.

[0148] As for the HKLD channel, it helps detect whether the drilling rig is "in slips," while the BPOS channel can be the primary channel for depth tracking during drilling. For example, BPOS can be used to determine the depth measurement within the geological environment (e.g., the borehole being drilled). Regarding the condition or state of being "in slips," the HKLD value is much lower than the condition or state of being "out of slips."

[0149] The term "slips" refers to a device or assembly used to clamp and suspend a drill string (such as drill collars, drill pipe, etc.) on a rotary table in a relatively non-destructive manner. Slips may comprise three or more steel wedges hinged together, forming a near-circular shape around the drill pipe. On the drill pipe side (inside the ground), the slips are fitted with replaceable hardened tool steel teeth that slightly embed into the drill pipe side. The outer side of the slips tapers to match the taper of the rotary table. After the driller has placed the slips around the drill pipe and in the rotary table, the driller can control the rig to slowly lower the drill string. As the teeth on the inner side of the slips grip the drill pipe, the slips are pulled down. This downward force pulls the outer wedges down, providing inward compressive force on the drill pipe and effectively locking the assembly together. The driller can then loosen the upper part of the drill string (e.g., crisscross drill pipe, guard section, joint, or drill string post) while suspending the lower part. After some other parts are screwed to the bottom of the drill string, the driller lifts the drill string to release the slips from their clamping action, and the drilling crew can then remove the slips from the rotary table.

[0150] Hook load sensors can be used to measure the load weight on the drill string and to detect whether the drill string is inside or outside the slips. When the drill string is inside the slips, movement from the carriage or motion compensator has no effect on the bit depth at the end of the drill string (e.g., it will tend to remain stationary). When the movement of the traveling block is via a winch encoder (DWE) that can be mounted on the winch shaft, the acquired DWE information (e.g., BPOS) does not increase the recorded bit depth. When the drill string is outside the slips (e.g., drilling forward), the DWE information (e.g., BPOS) can increase the recorded bit depth. The difference between hook load weight (HKLD) inside and outside the slips is often distinguishable. For offshore operations, the heave and sag of the vessel affect the bit depth regardless of whether the drill string is inside or outside the slips. As an example, a vessel may include one or more heave and sag sensors that can sense data that can be recorded as 1-D series data.

[0151] In maritime operations, vessels may experience one or more of various types of motion, such as heave, roll, and swell. Heave is a linear vertical (up / down) motion, roll is a linear lateral (side-to-side or port-to-starboard) motion, and swell is a linear longitudinal (fore / aft or bow / stern) motion caused by ocean conditions. As an example, a vessel may include one or more heave sensors, one or more roll sensors, and / or one or more swell sensors, each of which can sense data that can be recorded as 1-D series data.

[0152] As an example, BPOS can be used alone or in combination with one or more other channels to detect whether the drilling rig is "at the bottom" drilling or "tripping in and out," etc. The inferred state can be further consumed by one or more systems, such as an automated drilling control system, which can be a dynamic field operating system or part of it. In such an example, conditions, operations, states, etc., as discerned from BPOS and / or other channel data, can be predicates for making one or more drilling decisions, which may include one or more control decisions (e.g., decisions by controllers operatively coupled to one or more field devices, etc.).

[0153] A block can be a set of pulleys used to gain mechanical advantage when lifting or dragging heavy objects. A drilling rig can have two blocks: a top block and a traveling block. Each can include several grooved pulleys equipped with steel drilling cables or ropes, allowing the traveling block to be raised (or lowered) by winding (or unwinding) a coil of drilling cable on the winch. Therefore, block position can refer to the position of the traveling block, which can change over time. Figure 1 The trolley assembly 175 is shown. Figure 2 The tour bus 211 was shown, and Figure 7 The tour bus 711 is shown.

[0154] The hook can be a high-capacity J-shaped device used to suspend various equipment, such as swivels and square drill rods, lifting jacks, or top drive units. Figure 7 The hook 712 is shown to be operatively connected to the top drive unit 714. (See diagram) Figure 2 As shown, the hook can be attached to the bottom of the traveling carriage 211 (e.g., Figure 1 (Part of the traveling block assembly 175). The hook can provide a method for lifting heavy objects with the traveling block. The hook can be locked (e.g., in the normal state) or freely rotated, allowing it to engage or disengage with items such as those located around the drill string.

[0155] The hook load can be the total force exerted by the traveling block to pull the hook downwards. This total force includes the weight of the drill string, drill collars, and auxiliary equipment in the air, minus forces that tend to reduce that weight. Some forces that may reduce weight include friction along the borehole wall (especially in deviated wells) and buoyancy generated on the drill string due to its immersion in drilling fluid (e.g., and / or other fluids). If the blowout preventer (BOP) (e.g., or multiple BOPs) is closed, the borehole pressure acting on the cross-section of the drill string within the BOP can also exert an upward force.

[0156] The riser can be a rigid metal conduit that provides a high-pressure passage for the drilling fluid, allowing it to travel up the derrick for about one-third of the distance before connecting to a flexible high-pressure hose (such as a swivel drill pipe hose). Large drilling rigs may have more than one riser, so that downtime is kept to a minimum if one riser needs maintenance. Figure 2 The riser 208 is shown as a conduit for drilling fluid (e.g., drilling mud). The fluid pressure within the riser 208 may be referred to as the riser pressure.

[0157] Regarding ground torque, this measurement can be provided by equipment at the drilling rig site. As an example, one or more sensors can be used to measure ground torque, which can provide direct and / or indirect measurements of ground torque associated with the drill string. As an example, the equipment may include a drill string torque measurement and control system having one or more analog frequency outputs and digital outputs. As an example, the torque sensor may be associated with a coupling including an elastic element operatively combining an input element and an output element, wherein the elastic element allows the input and output elements to twist relative to each other in response to torque transmitted through the torque sensor, wherein this twisting can be measured and used to determine the transmitted torque. As an example, such a coupling may be located between the drive and the drill string. As an example, torque can be determined by one or more inertial sensors. As an example, equipment at the drilling rig site may include one or more sensors for measuring and / or determining torque (e.g., in Nm, etc.).

[0158] As an example, the device may include a real-time drilling servicing system that can provide data such as weight transfer information, torque transfer information, equivalent circulation density (ECD) information, downhole mechanical specific energy (DMSE) information, motion information (e.g., stall, stick-slip, etc.), bending information, vibration amplitude information (e.g., axial, lateral, and / or torsional), drilling rate (ROP) information, pressure information, differential pressure information, flow rate information, etc. As an example, sensor information may include tilt, azimuth, total vertical depth, etc. As an example, the system can provide information about eddies (e.g., backward eddies, etc.) and may optionally provide information such as one or more alarms (e.g., “Severe backward eddies: Stop and restart at lower surface RPM”, etc.).

[0159] As an example, a drill string can include one or more tools that include a variety of sensors capable of performing various measurements. For instance, consider the OPTIDRILL tool (Schlumberger Ltd., Houston, Texas), which includes strain gauges, accelerometers, magnetometers, gyroscopes, and more. For example, such a tool can use strain gauges (e.g., a 10-second moving window with a bandwidth of 200 Hz) to obtain borehole pressure measurements (WOB), strain gauges (e.g., a 10-second moving window with a bandwidth of 200 Hz) to obtain torque measurements, strain gauges (e.g., a 10-second moving window with a bandwidth of 200 Hz) to obtain bending moment measurements, one or more accelerometers (e.g., a 30-second RMS with a bandwidth of 0.2 to 150 Hz) to obtain vibration, magnetometers and gyroscopes (e.g., a 30-second moving window with a bandwidth of 4 Hz) to obtain rotational speed, one or more strain gauges (e.g., a 1-second average with a bandwidth of 200 Hz) to obtain annular and internal pressure, one or more temperature sensors (a 1-second average with a bandwidth of 10 Hz) to obtain annular and internal temperature, and accelerometers (a 30-second average with a bandwidth of 10 Hz) to obtain continuous tilt.

[0160] As mentioned, the channel for real-time drilling operation data can be received and characterized using generated synthetic data, which can be generated at least in part based on one or more operation parameters associated with the real-time drilling operation. This real-time drilling operation data can include surface data and / or downhole data. As mentioned, data availability may vary over time (e.g., frequency, gaps, etc.) and / or in other aspects (e.g., resolution, etc.). These data may also differ in terms of noise levels and / or noise characteristics. While various types of sensors are mentioned, devices that do not include one or more types of downhole sensors can be used. In this case, methods capable of determining one or more downhole values ​​can be utilized.

[0161] Figure 8An example of method 800 is shown, which includes various boxes that can receive data, perform one or more analyses, perform one or more decisions, etc., to determine one or more states. Figure 8 In the examples, various instances of states are shown regarding color. Figure 8 In the example states, drilling, non-drilling, run-in hole (RIH), pull-out hole (POOH), pre-connected, connected, post-connected, and not present.

[0162] Drilling is the process of increasing the depth of a wellbore. Non-drilling activity can be identified when no other activity is taking place (e.g., drilling, RIH, POOH, pre-connection, connection, post-connection) and the end of the current drill string has not yet been reached. During non-drilling periods, the flow rate of fluid pumped into the drill string may increase and / or decrease, the drill string rotation rate may increase and / or decrease, downhole tools (e.g., the drill bit) may move up and / or down, or a combination thereof. Non-drilling activity can be or includes the time when the drill bit is idle (e.g., not drilling) and the slips are not engaged with the drill string.

[0163] Pre-connection can occur when a downhole tool (e.g., a drill bit) has completed drilling operations on the current section of the tubing, but the slip assembly has not yet begun to move (e.g., radially inward) to engage with the drill string. During pre-connection, the flow rate of fluid pumped into the drill string can be increased and / or decreased, the rotational speed of the drill string can be increased and / or decreased, the downhole tool (e.g., the drill bit) can move up and / or down, or a combination thereof.

[0164] A connection can be a point where slips engage with and support the drill string (e.g., the drill string is "in the slips"). When a connection occurs, a section of tubing (e.g., pipe, stand, etc.) can be added to the drill string to increase its length, or a section of tubing can be removed from the drill string to reduce its length.

[0165] Post-connection can be a point where the drill string is released via slip assembly and the downhole tool (e.g., drill bit) descends to the bottom (e.g., bottom of well or BOH). During post-connection, the flow rate of fluid pumped into the drill string can be increased / and / or decreased, the drill string rotation rate can be increased / and decreased, the downhole tool (e.g., drill bit) can be moved up and / or down, or a combination thereof.

[0166] As for the absence state, it can indicate a scenario where no data has been received (e.g., at least one of multiple inputs is missing).

[0167] As an example, a method can be used to determine the slip state. For example, the slip state may include one or more of the following: inside the slip, where the slip assembly engages with and supports the drill string (“inside the slip”); outside the slip, where the slip assembly does not engage with and does not support the drill string; and absent, where no data is received (e.g., at least one input is lost).

[0168] Figure 8 Method 800 may include various data acquisition or data reception frames 802, 806, 808, etc.; various decision frames 805, 807, 809, 813, 815, 817, and 843; detection frames 812 and 842; and status frames. Measurements may include (1) wellbore depth, (2) bit depth, (3) traveling block position, or combinations thereof. A set of measurements may or may not include hook weight (e.g., HKLD) or drill weight (e.g., WOB). Each set of measurements may be captured / received after a predetermined amount of time following the capture / receive of the previous set of measurements. The predetermined amount of time may be, for example, approximately three seconds; however, the predetermined amount of time may be shorter or longer.

[0169] PCT Publication WO 2017 / 221046A1, dated December 28, 2017, is incorporated herein by reference, entitled "Automatic drilling activity detection" ('046 Publication). '046 Publication describes a method for determining drilling activity, the method comprising receiving a set of measurements at different times. The set of measurements may include wellbore depth, drill bit depth, and traveling block position. The method may further include identifying connections by determining when the traveling block position changes but the drill bit depth remains constant. The method may further include determining when the wellbore depth does not increase between two different connections. The method may further include determining the direction of drill bit movement between two connections.

[0170] Figure 9An example of a graph 900 according to one embodiment is shown, which illustrates time intervals including drilling, pre-connection, connection, post-connection, and non-drilling activities. The time is shown on the X-axis, totaling approximately 3 hours. The top quarter 910 of graph 900 shows the relationship between wellbore depth and time. The next quarter 920 of graph 900 shows the relationship between the position of the traveling block and time. The next quarter 930 of graph 900 shows the time intervals during which downhole tools (e.g., drill bits) are drilling, the time intervals during which pre-connection occurs, the time intervals during connection occur, the time intervals during post-connection occur, and the time intervals during non-drilling activities. The bottom quarter 940 of graph 900 shows the time intervals during which the drill string engages with and is supported by the slip assembly (within the slips), and the time intervals during which the drill string is not engaged with or supported by the slip assembly (outside the slips). As can be seen, the traveling block moves upwards during connection and downwards during drilling. Furthermore, when a connection occurs, the drill string is inside the slips, and when a connection does not occur, the drill string is outside the slips.

[0171] Figure 10 An example of a graphical user interface (GUI) 1000 is shown, which includes sets of data regarding time. Figure 10 In the example, GUI 1000 includes drilling status trajectories using a specific color scheme, where green corresponds to drilling (deepening the wellbore), red to pre-connection status, black to post-connection status, and gray to connection status. Regarding time-series data, BPOS, HKLD, and STOR are shown relative to time. Specifically, BPOS is shown relative to distance (e.g., 10 meters to 40 meters, etc.), HKLD is shown relative to kN (e.g., 500 kN to 1500 kN), and STOR is shown as torque loss in kN·m (e.g., 0 kN·m to 50 kN·m). Figure 10 In the example, various values ​​are labeled AC and various values ​​are labeled RC. Values ​​labeled RC are improved values ​​compared to those labeled AC. As an example, one approach could include machine learning based on surface sensors to detect pull-up (PU) / drop-down (SO) weight and downhole bit weight (DWOB) and torque (TQLS, DTOR, etc.). Such a approach could output improved values ​​for various operations, especially when the equipment may lack one or more types of downhole sensors. For example, consider the scenario of operating without a downhole torque sensor. In such an example, one approach could implement a trained machine model to determine one or more downhole torque values.

[0172] As an example, a method may include an interface for receiving the following inputs: DRILL_STATE, drilling status [unitless]; BPOS, vehicle position [m]; RPM, revolutions per minute [c / min]; HKLD, hook load [kN]; and STOR, surface torque [kN.m]. Such a method can utilize inputs to output the following: HKLD_SO, hook load – lowering [kN], the vehicle is descending; HKLD_PU, hook load – lifting [kN], the vehicle is rising; HKLD_FR, hook load – free rotation [kN]; DWOB, downhole drilling pressure [kN]; TQLS, torque – loss [kN.m]; DTOR, torque – downhole [kN.m], DTOR = STOR - TQLS.

[0173] Refer again Figure 10 The GUI 1000 displays various inputs and outputs. For example, inputs include DRILL_STATE, BPOS, HKLD, and STOR, and outputs include HKLD_SO, HKLD_PU, HKLD_FR, and TQLS, which can be encoded (e.g., colors, shadows, hatches, etc.).

[0174] During drilling, information related to the connections between the drill string and the wellhead can be utilized. Historically, drilling parameters at these connections have been obtained on-site at the drilling rig, and these parameters have become inconsistent due to variations in personnel. Various algorithms have been developed to reduce the influence of human factors and to select measurement points in a more systematic way; however, these algorithms have limitations due to inconsistencies in driller practices and / or due to different processes applied by one drilling company to another.

[0175] As an example, a system may include one or more processors, memory, and instructions that can instruct the system to operate robustly to retrieve bottom-out measurements, such as load, torque, and pressure. Consider, as an example, an algorithm for a mud logging system or an execution toolkit (PTK) with automatic calibration (Schlumberger Ltd., Houston, Texas). Such an algorithm is operable to output values ​​that can be used to determine the hook load at the connection for pull-up (PU) and / or drop-down (SO), as well as downhole drilling parameters for WOB, TAB, and PAB. Calculated downhole drilling parameters can be used when no downhole measurements are performed or are unavailable. These calculated values ​​can be used, for example, in land drilling operations, where the PU and SO values ​​can be the first indication of a stuck pipe during drilling and / or tripping operations.

[0176] In the context of real-time monitoring and drilling data analysis, the calculation of these values ​​can be used to display a broom model relative to actual measurements, as well as for bottom drilling efficiency analysis.

[0177] Drilling analysis software implemented as a computational framework may face challenges in vendor-neutral environments due to low-quality real-time surface data. The data may be relatively low-frequency (e.g., consider a sampling rate of 0.1 Hz), and inconsistent drilling practices at connection points may render certain types of computations unavailable, potentially impacting confidence in the software itself.

[0178] As described with respect to example GUI 1000, a method can provide the determination of various phenomena associated with drilling operations. For example, torque loss and pull-up (PU) / sink (SO) / free rotation (FR) weights on data (e.g., supplier-free data, etc.) can be determined, even in cases of poor quality. Such a method can be operated in an automated manner. Such a method can be used to estimate one or more operating friction coefficients. As an example, a method may include determining one or more values ​​closely related to jamming. As an example, a method may include determining values ​​indicating risk (e.g., the probability of pipe jamming). As an example, a method can be implemented as part of a control system that can operate to reduce the risk of pipe jamming and / or reduce pipe jamming incidents. As an example, a method can provide the detection of jammed pipes. As an example, a method can be implemented as part of a jammed pipe detection workflow. In such an example, the workflow can reduce the occurrence of jammed pipes and / or detect jammed pipes.

[0179] As an example, a method can provide the detection of torque loss and / or one or more of the lifting (PU), lowering (SO), and free rotation (FR) weights in a time-series data. For example, such a method can utilize a trained machine model and may include the training of the machine model. As an example, machine learning techniques can replace manual input of one or more interpretable parameters. As an example, a method can select multiple channels, where the selected channels allow for reduction of user error (e.g., error minimization, etc.) and / or data quality issues. As an example, for each individual output, a method may involve filtering data points with one or more criteria, where such criteria may include one or more process-based physical criteria. In such a method, when applied to the drill string during drilling operations, the final point of each individual string can be statistically taken as, for example, the median of the points. Such a method can work to reduce the influence of noise in data from one or more surface sensors.

[0180] As an example, a standby can be a drill pipe or drill collar with two or three single-joints that remain screwed together during tripping operations. Various medium-depth-capacity rigs can handle three-joint stands, referred to as “triple” or “three-joint.” Some smaller rigs have the capability for two-joint stands, referred to as “double”. As an example, an operation might involve standing the drill pipe or drill collar upright in the derrick and placing it in the finger table to maintain its order. Such methods are often a relatively efficient way to remove the drill string from the well when changing drill bits or adjusting the bottom hole assembly (BHA). As an example, one approach could involve loosening threaded connections. As an example, in some cases, a “standby” can be a single unconnected section of the drill string. While upright placement is mentioned, other orientations can be utilized in some situations. As an example, in operations involving loosening threaded connections, the section can be placed in a horizontal position.

[0181] Although threads are mentioned, various types of equipment can be connected using unthreaded stubs or fittings. A connection can be a threaded stub or fitting connecting two tubular components, or an unthreaded stub or fitting. A connection can be an operation of adding a section, such as adding a stub or a drill pipe post to the top of the drill string (e.g., “making a connection”). The opposite operation can be used to remove a section (e.g., disconnecting the connection, etc.).

[0182] Regarding ground sensor measurements, during operation, movement may be less consistent for approximately connected / disconnected operations. For example, when tripping in or out of the drill string, movement may slow down (e.g., decelerate) and then accelerate (e.g., speed up). Between acceleration and deceleration, movement may be more consistent. Ground sensor data can have a higher signal-to-noise ratio (SNR) in cases of more consistent movement compared to cases of less consistent movement (e.g., deceleration and / or acceleration). As an example, one approach could include processing sensor data to efficiently select data points (e.g., samples) within a time period (e.g., or multiple time periods) where movement is more consistent. While such an approach can reduce the number of data points used, the data points used can have less noise (e.g., higher SNR, etc.). As an example, one approach could involve detecting one or more connection times and selecting a time series data window that is time δ away from that connection time or multiple connection times. For example, consider time series data spanning time period t-total from connection 1 to connection 2, where the selected window is smaller than t-total and excludes data points in time period t-1 after connection 1 and data points in time period t-2 before connection 2. Such methods can select windows based on percentages, the number of data points (e.g., given sampling rate), using speed-based criteria (e.g., average speed, etc.), using total time-based criteria, using acceleration criteria, using deceleration criteria, etc.

[0183] As an example, consider a method that, based on previous experience with columns, uses statistical methods to detect weight and torque.

[0184] As an example, one approach could implement one or more techniques to detect torque loss and lifting / lowering / free-spinning weight in a time-series data dataset. For instance, consider implementing one or more machine learning techniques that could replace and / or enhance manual input and / or interpretation of parameters. As an example, one approach could be designed to utilize a limited number of channels, which could allow for reduction of user errors and / or data quality issues. As an example, for each output, data points could be filtered, for example, using one or more criteria, which could be based on the physical characteristics of the process, where, for example, the final point of each column could be taken as the median of the points. Such an approach could ignore potential noise from one or more ground sensors.

[0185] Such as about Figure 16 As explained in System 1600, machine learning (ML) can be performed using one or more ML models. As an example, one approach could include machine learning during the drilling phase to train an ML model to generate a trained ML model. As another example, one approach could include performing machine learning on data from one or more databases, where such data could include offset well data.

[0186] As an example, one approach could include identifying a threshold for determining drill string bottom-out conditions; filtering time-series surface data of the drill string's post-connection drilling status using the threshold to generate filtered time-series surface data; and statistically determining the drill string bottom-out condition value using the filtered time-series surface data. In such an example, filtering could be performed using one or more filter models that could include one or more parameters. In such an example, data acquired during drilling operations in one or more wells could be used to determine one or more parameter values. The machine model could leverage the filter model, where, for example, the filter model could be dynamically adjusted using one or more thresholds that can be determined during drilling operations. As an example, consider a filter model that includes one or more parameter values ​​that can be learned using offset well data and includes one or more dynamic thresholds that can be identified during drilling. Such a filter model could be applied to acquired data (e.g., post-connection) to determine, for example, drill string bottom-out condition values.

[0187] As an example, one method could operate automatically to determine one or more of the following during drilling: torque loss, weight used for lift-up, lower-down, and free-rotation operations, and pressures (e.g., off-bottom pressure (OFBP), differential pressure (DPRES), etc.). As an example, the inputs could be limited, for example, to multiple inputs selected from a group, such as a group including drilling status, vehicle position, rotational speed, hook load, surface torque, riser pressure, and flow rate (e.g., mud flow, etc.). As explained, the ML method could provide identification of one or more suitable filters for hook load, surface torque, and / or pressure, for example, by looking at previous connections and previous drilling intervals. Such a method might be designed to minimize human user intervention, for example, replacing thresholds that can now be automatically extracted from time series data.

[0188] As an example, the method can operate in an automated manner, which can be vendor-free, vendor-neutral, etc. Regarding data characteristics, as an example, consider using a dataset with a sampling rate of less than approximately 10 seconds (e.g., samples collected at intervals of 10 seconds or less).

[0189] As an example, a method can be implemented using autonomous calculations on the server side and / or the client side. Such a method can be part of one or more workflows (e.g., torque and resistance, tripping loads, stuck pipe, etc.).

[0190] As an example, a computation engine may be suitable for use in or associated with one or more frameworks (e.g., a data framework such as the TECHLOG framework, a drilling interpretation framework, etc.). As an example, methods and / or computation engines can be used in a data framework of type DATAIKU.

[0191] As explained, the method and / or computation engine can use machine learning based on ground sensor data to provide determinations about one or more lift / lower weights and downhole drilling pressure, torque, and pressure.

[0192] Figure 11 An example of a GUI 1100 is shown, which includes a timeline with various states associated with operations, in which associated time-series data may exist. Figure 11 In the example, based on prior experience with the stand, statistical methods can be used for one or more of the weight, torque, and pressure measurements. As shown, the method could include classifying stand types into three categories: RIH, Drilling, and POOH. In such an example, during various well sections of one or more stands, the method could include calculating various statistical values ​​that may be associated with one or more conditions. As an example, torque, hook load, pressure, flow rate, etc., are considered.

[0193] exist Figure 11 The examples illustrate various instances of intermediate values, which may include one or more of, for example, intermediate hook load during drilling (DrHkldMed), intermediate surface torque during drilling (DrStorMed), intermediate riser pressure (e.g., absolute pressure) during drilling (DrSppaMed), and intermediate flow rate during drilling (DrFlwiMed). As an example, one or more such values ​​may be identified and used as one or more thresholds.

[0194] As an example, during the connection of a drilling string in a well section, one approach may include calculating a threshold, which can be used as a filter, for example, in a filter model, to calculate one or more other values ​​(e.g., weight, such as lifting, lowering, free rotation, torque, pressure, flow rate, etc.). In such an example, the filter or filter model may include one or more other types of parameters, which may be determined, for example, by learning from data from one or more databases.

[0195] like Figure 11 As shown, time series data can include surface torque time series data (STOR), hook load time series data (HKLD), riser time series data (SPPA), and flow time series data (FLWI) (such as mud flow rate).

[0196] As an example, during connection (e.g., connecting well sections), one approach may include calculating a median hook load value (ConHkldMed), which can be used as a filter to calculate the lifting weight and / or lowering weight.

[0197] As an example, after identifying one or more of the DrStorMed, DrHkldMed, ConHkldMed, DrSppaMed, and DrFlwiMed thresholds, the method can proceed with one or more detection processes. These processes may include filtering using one or more filter models, which can be machine models that can include one or more parameter values, learned, for example, using offset well data. For instance, the thresholds can be considered dynamic parameters, while one or more other parameters can be determined through learning using offset well data, etc.

[0198] Figure 12 An example of GUI 1200 is shown, which includes a timeline with various states associated with operations, in which associated time-series data may exist. GUI 1200 illustrates some examples of processes that could be detection processes, for example, operations could be performed using one or more thresholds. Figure 12As shown in the example, the GUI 1200 may include portions of three columns, including RIH, Drilling and POOH. The GUI 1200 illustrates methods for detecting TLQS, HKLD_FR, HKLD_SO, HKLD_PU and OFBP (off-bottom pressure).

[0199] As an example, a method may include determining the hookload weight value HKLD_FR after a connection (e.g., post-connection) as follows:

[0200] A. Collect data points during "after a connection" (e.g., post-connection);

[0201] B. Discard negative and missing HKLD points;

[0202] C. Discard points where RPM < 20 c / min;

[0203] D. Discard points where the drill bit is on bottom (RIG_STATE = 0 or 1);

[0204] E. Discard points where the traveling block speed > 0.1 m / s;

[0205] F. Discard points where HKLD < DrHkldMed; and

[0206] G. Determine the final HKLD_FR result value as the low median of the remaining points, where it can be assumed that taking the median is safe to view the exact selected points, since HKLD tends to have little noise during this period.

[0207] As an example, a method may include determining the torque value TQLS after a connection (e.g., post-connection) as follows:

[0208] A. Collect valid STOR data points during "after a connection";

[0209] B. Discard negative and missing STOR points;

[0210] C. Discard points where the drill bit is on bottom (RIG_STATE = 0 or 1);

[0211] D. Discard points where the rotational speed < 20 c / min or the rotational speed < 0.9*max(RPM);

[0212] E. Discard points where STOR > DrStorMed; and

[0213] F. Determine the final TQLS result value as the average of the remaining points, where it can be assumed that taking the average is safer than taking the median, since a large amount of STOR noise often occurs during the post-connection process.

[0214] By way of example, a method may include performing the following various calculations in a pre-connection:

[0215] A. Calculate HKLD_PU and HKLD_SO during the drilling stage, and collect points from the pre-connection well section into two sets—one for tripping out and one for tripping in (e.g., different directions of drill string movement in the borehole);

[0216] B. For both, first apply the HKLD<ConHkldMed*1.1 filter;

[0217] C. For both, discard rotation points based on the RIG_STATE input;

[0218] D. For tripping out, the set takes points with increasing BPOS, filters by min(BPOS)+1m<BPOS<max(BPOS)-1m, and the final HKLD_PU is taken as the high median of the set; and

[0219] E. For tripping in, the set takes points with decreasing BPOS, filters by min(BPOS)+1<BPOS<max(BPOS)-1, and the final HKLD_SO is taken as the low median of the set; note that such a method may be more efficient than calculating and comparing the trolley speed from the trolley position.

[0220] By way of example, a method may include performing various calculations for RIH and / or POOH as follows:

[0221] A. During the RIH and POOH stages, since no drilling occurs, pre-connection and post-connection are not defined;

[0222] B. During the analysis process, calculate min(BPOS) and max(BPOS), and take points from the 1 / 3 well section between min(BPOS) and max(BPOS);

[0223] C. HKLD_SO during RIH is taken as the low median point; and

[0224] HKLD_PU during POOH is taken as the high median of the points.

[0225] By way of example, a method may include performing various calculations regarding off-bottom pressure (OFBP) and / or differential pressure (DPRES), which may for example relate to the operation of a downhole motor (e.g., a mud motor, etc.) driven at least in part by fluid flow to rotate the drill bit. For example, consider a method that may provide determining off-bottom pressure (OFBP) and / or differential pressure (DPRES) through the following actions:

[0226] A. During the previous drilling string (e.g., pre-connection), learn the SPPA (riseer pressure) point and calculate DrSppaMed = median (SPPA);

[0227] B. Study the FLWI (mud flow rate) points during the previous drilling string (e.g., pre-connection) and calculate DrFlwiMed = median (FLWI);

[0228] C. During the next post-connection period (e.g., after connection), take SPPA / FLWI samples;

[0229] D. Remove the points where SPPA > DrSppaMed;

[0230] E. Remove the bottom point by setting the drilling rig status to "off-bottom";

[0231] F. Remove points where FLWI < 0.85 * DrFlwiMed;

[0232] G. Calculate the reference OFBP = the average of the remaining points (SPPA); and

[0233] H. For the next drilling point, calculate DPRES = SPPA – OFBP.

[0234] In various examples, one or more learning techniques can be used to determine one or more parameters; these techniques can be machine model-based learning techniques. As an example, data from off-wells can be analyzed. In such examples, various parameter values ​​can be tested to determine suitable parameter values ​​for one or more methods. For example, consider the various values ​​related to RPM, vehicle speed, flow rate, etc., given above; this could be part of one or more filtering processes. One or more such values ​​can be determined using off-well data, where, for example, the values ​​can be determined using a machine model that can be trained using off-well data to obtain those values. Such methods can aim to improve understanding of… Figure 12 The GUI 1200 describes the accuracy and / or applicability (e.g., robustness, etc.) of one or more techniques. For example, a set of parameter values ​​can be determined for a specific type of formation, a specific type of bottom hole assembly, a specific type of drilling fluid, etc. As an example, one or more parameter values ​​can be updated, which can be done through a background process that can operate on one or more offset well data, target well data, etc.

[0235] By way of example, a method may include performing various calculations regarding off-bottom pressure (OFBP) and / or differential pressure (DPRES), which may for example involve operation of a downhole motor (e.g., a mud motor, etc.) driven at least in part by a fluid flow to rotate a drill bit. For example, consider a method that may provide for determining off-bottom pressure (OFBP) and / or differential pressure (DPRES) via the following actions:

[0236] A. During the previous drilling stand (e.g., pre-connection), learn SPPA (standpipe pressure) points, and calculate DrSppaMed = median (SPPA);

[0237] B. During the previous drilling stand (e.g., pre-connection), learn FLWI (incoming mud flow rate) points, and calculate DrFlwiMed = median (FLWI);

[0238] C. During the next post-connection period (e.g., after a connection), take SPPA / FLWI samples;

[0239] D. Remove points where SPPA > DrSppaMed;

[0240] E. Remove on-bottom points by setting rig state = off-bottom;

[0241] F. Remove points where FLWI < 0.85*DrFlwiMed;

[0242] G. Calculate reference OFBP = average value (SPPA) of the remaining points; and

[0243] H. For the points of the next drilling run, calculate DPRES = SPPA – OFBP.

[0244] Referring again to Figure 12 the GUI 1200, some examples of parameter values may include "20c / min" (e.g., RPM < 20c / min), "0.1m / s" (e.g., trolley speed > 0.1m / s), "20c / min" or "0.9" (e.g., RPM < 20c / min or RPM < 0.9*max(RPM)), "1.1" (e.g., HKLD < ConHkldMed*1.1), "0.85" (e.g., these values may be expressed as parameters using names such as "param" (e.g., param1, param2, param3, param4, etc. As explained, a threshold may be another type of parameter, which may be dynamic, and may be expressed using names such as "thres" (e.g., thres1, thres2, thres3, etc.).

[0245] Figure 13An example of a GUI 1300 is shown, illustrating timelines with various states associated with an operation, in which associated time-series data may exist. Figure 13 In the example, GUI1300 shows a portion of the method for column #2 and drilling, where min(BPOS) and max(BPOS) are shown for detecting the pull-up (PU) and drop-down (SO) points using BPOS. As mentioned, one approach could include utilizing techniques that are statistically more efficient than calculating and comparing vehicle speeds from vehicle position.

[0246] As explained, a method can be used to calculate one or more downhole values, where, for example, one or more corresponding sensors may not be available to measure such downhole values. In such an example, surface data, such as time-series surface data, acquired by one or more surface-based sensors (e.g., well site sensors, etc.) can be utilized.

[0247] Figure 14 An example of method 1400 is shown, which includes a receiving box 1410 for receiving time-series data including downhole sensor data, wherein the time-series data may come from multiple wells (e.g., consider ten or more wells); a performance box 1420 for performing learning to generate a trained machine model; a receiving box 1430 for receiving time-series data of a single-well operation, which may or may not include one or more downhole sensors; an application box 1440 for applying the trained machine model to at least a portion of the received data of receiving box 1430 to compute one or more values; and an optional issuing box 1450 for issuing at least one control command for at least one operation using at least one of the one or more values. Figure 14 An example of a system 1490 that can be used to implement one or more parts of method 1400 is also shown.

[0248] As shown, method 1400 may include various parts, such as a training part, an execution part, and a control part. Regarding training, consider accessing time-series data from dozens of wells (e.g., 50 wells, 100 wells, etc.), where the time-series data may include data from downhole sensors. For example, for training purposes, various datasets of wells drilled using drill strings with one or more downhole sensors may be accessed. In such an example, training may train a machine model to reproduce downhole sensor-based values ​​using input values ​​(e.g., by matching the input-based output with the actual downhole sensor-based values). This training can be referred to as machine learning, which can generate a trained machine model. As an example, this machine learning may provide outputs of one or more parameter values, which can be applied to one or more filter models, which can be considered machine models.

[0249] As explained, in methods that can compute downhole values ​​not based on downhole sensor measurements, a trained machine model can be utilized. As an example, the trained machine model may include adaptive features. For instance, the trained machine model can be tuned using time-series data, which may include real-time data. As mentioned, the machine model can be used to determine one or more parameter values, which may be, for example, part of a filtering model that performs one or more filtering tasks on the time-series data, where the filtering model may include one or more thresholds. As an example, regarding... Figure 12 The methods described in GUI 1200 can be implemented using a monolithic machine model or multiple machine models that provide threshold recognition, data filtering, etc. Such one or more models can be operatively connected to one or more databases and / or real-time data sources.

[0250] As an example, a trained machine model can operate as one or more filters that can be applied to time-series data, such as based on individual drill string operations. As another example, one approach could include a decision tree structure that involves applying one or more filters to determine points that can be used to represent specific aspects of one or more operations related to the drill string.

[0251] As an example, the filter can be a "smart" filter obtained through training. For instance, a trained machine model can be a filter model that adapts to the input. As another example, a method can be implemented in a suitable programming language, such as Python, as instructions stored in a memory device operatively linked to the processor, wherein such instructions can be executed by the processor.

[0252] As an example, regarding implementation, during operation, time-series data can be acquired for a segment of the drill string (e.g., a stand, etc.), where a specific portion of the time-series data (e.g., a selected sample) can be used as input to determine (e.g., identify) one or more thresholds for subsequent segments of the drill string, for example, to calculate the pull-up (PU) point and the drop-down (SO) point.

[0253] As mentioned, the input may include (i) drilling status (e.g., according to such as Figure 8The inputs can be (i) the method of 800, (ii) BPOS, (iii) RPM, (iv) HKLD, and (v) STOR, and the outputs can include (i) HKLD_SO (the vehicle is descending), (ii) HKLD_PU (the vehicle is ascending), (iii) HKLD_FR (free rotation), (iv) DWOB (downhole value), (v) TQLS, and (vi) DTOR, which is downhole (e.g., DTOR = STOR – TQLS). In this example, the number of inputs can be selected in a restricted manner, which helps to limit the amount and / or type of noise that may exist and / or otherwise affect the output. As mentioned, torque values ​​can be used for one or more friction calculations. Friction can be wellbore friction that occurs during drill string rotation in the wellbore. As an example, the coefficient of friction can be calculated relative to the drill string and the wellbore. As explained, the inputs can include SPPA and / or FLWI, which can be alternatives to and / or supplements to one or more other inputs.

[0254] As for BPOS, it can be within a range that can be specified in meters (e.g., 0 meters to 40 meters) or feet. The sampling rate of BPOS may vary depending on the field equipment. As an example, the sampling rate of BPOS relative to time could be 1 second, 3 seconds, 5 seconds, 10 seconds, etc. As an example, robust systems can be configured to handle a variety of different sampling rates, which may be specific to the equipment type, the entity performing the drilling, etc. This time-series data can include noise. As an example, to handle noise, one approach could utilize the raw time-series data of BPOS and select data points (e.g., samples) for computation. Such an approach could involve filtering to select these data points. While BPOS is mentioned, such a approach can be applied to HKLD and STOR, which may include noise, outliers, etc., which are not visible in BPOS. For example, HKLD and / or STOR may include spikes (e.g., brief transients with relatively extreme values). As an example, one approach could be used in scenarios involving one or more downhole sensors. For example, based on the transmission of downhole sensor data to the surface location, estimates are available before receiving the actual downhole sensor values. As an example, in some scenarios, downhole sensor data can be stored in the device, making it accessible after the device is retrieved. In such examples, comparisons can be made between actual data and estimates.

[0255] As explained, a machine model can be a filter (or multiple filters) capable of manipulating inputs, which can be time-series data associated with a segment of a drill string (e.g., a drill string, etc.). Such a method can be used to determine (e.g., identify) one or more thresholds that can be used for subsequent drill strings.

[0256] As an example, one method can automatically detect torque loss, pull-up (PU), drop-down (SO), and free-rotation (FR) operations during drilling, and / or one or more pressures. Such a method can be operated on inputs that may be limited to drilling conditions, vehicle position, rotational speed, hook load, and surface torque, and / or may optionally include riser pressure and / or flow rate.

[0257] As explained, one approach could include implementing machine learning to identify appropriate filters for hook loads and surface torque by examining previous connections and previous drilling segments (e.g., stages). Such an approach could reduce manual user intervention. For example, such a approach could automatically extract thresholds from time-series data.

[0258] As an example, one approach could operate in a way that improves upon methods that utilize hook load thresholds to determine whether the drill string is within the slips. For instance, one approach could operate in a more robust manner to noise in time-series data, such as noise in HKLD.

[0259] As an example, one approach could utilize a trained machine model, take advantage of a limited number of inputs, and employ statistical and / or probabilistic methods to process data points (e.g., samples). Such an approach is robust to noise and is applicable to a wide range of devices that can provide basic types of ground sensors.

[0260] like Figure 14 As shown in method 1400, a training phase can occur to generate a trained machine model. For example, consider using time-series data from 50 or more wells, training with data from real downhole sensors. As indicated, the implementation phase can leverage the trained machine model. As an example, one approach could include reviewing previous drilling stands and sampling for a threshold for the next drilling stand. As an example, one approach could be implemented locally and / or remotely. As an example, a computational framework (e.g., a TECHLOG framework) could include components for implementing the method (e.g., ...). Figure 14 The method (1400) is a feature of one or more parts of a workflow (or multiple workflows), such as a torque and resistance workflow, a trip-in / trip-out load workflow, a stuck pipe workflow, a mud motor workflow, etc.

[0261] Figure 14Various computer-readable medium (CRM) boxes 1411, 1421, 1431, 1441, and 1451 are also shown. These boxes may include instructions executable by one or more processors, which may be one or more processors of a computing framework, system, computer, etc. The computer-readable medium may be a non-signal, non-carrier, and non-transitory computer-readable storage medium. As an example, a computer-readable medium may be a physical memory component capable of storing information in a digital format.

[0262] exist Figure 14 In this example, system 1490 includes one or more information storage devices 1491, one or more computers 1492, one or more networks 1495, and instructions 1496. Regarding the one or more computers 1492, each computer may include one or more processors (e.g., processing cores) 1493 and memory 1494 for storing, for example, instructions 1496 executable by at least one of the one or more processors. As an example, the computers may include one or more network interfaces (e.g., wired or wireless), one or more graphics cards, display interfaces (e.g., wired or wireless), etc. System 1490 may be specifically configured to perform... Figure 14 Method 1400 includes one or more parts.

[0263] Figure 15 An example of method 1500 is shown, which includes a partitioning box 1510 for partitioning time series data into RIH, Drilling, and POOH partitions; a calculation box 1520 for calculating a threshold for torque loss determination using a model that utilizes data from the drilling interval; a calculation box 1530 for calculating a filter value for weight determination using a model that utilizes data from the connected intervals; a determination box 1540 for determining a torque loss value using the threshold and data from the post-connection state; a determination box 1550 for determining a free-rotating hook load value (e.g., weight) using the model filter and data from the post-connection state; and a determination box 1560 for determining weights using the filter value, the model filter, and data from the pre-connection state, wherein the weights include one or more of hook load lifting values ​​and hook load lowering values. Figure 15 In the example, method 1500 includes an adaptive learning phase and a detection phase, wherein the detection provides a determination of a value, which may include a torque loss value that can be used to determine the downhole torque value. For example, the downhole torque value may be utilized in one or more workflows, which may include control workflows designed to reduce pipe jamming incidents, etc. As an example, method 1500 may include one or more boxes regarding pressure, such as pressure off the bottom and / or differential pressure.

[0264] As an example, the trained machine model can be based on time-series data including downhole sensor data. This trained model can be adaptive in its implementation, allowing for the appropriate determination of various parameter values, which can be filter parameters, thresholds, and / or filter values. Given such parameter values, a method can utilize the adjusted trained model to detect data points, which can be statistically processed to determine values ​​such as torque, weight, and / or pressure.

[0265] Method 1500 may be implemented using statistical approaches based on stand experience for weight, torque and / or pressure detection. As indicated, a method may partition stand types into zones (e.g., RIH, Drilling and POOH). As mentioned, during a drilling interval of a drilling stand, a method may calculate a statistical value, such as the medium-high value of surface torque (DrStorMed), which may be used as a threshold for torque loss detection. As mentioned, during a connection interval of a drilling stand, a method may calculate a minimum hook load value, which may be used as a filter value for calculating one or more weights. Such actions may be part of an adaptive process, where a model is utilized to "learn" parameter values of the model for detection purposes. For example, consider learning the parameter values of DrStorMed and / or ConHkldMin (e.g., connection hook load minimum) and / or ConHkldMed (e.g., connection hook load median) and / or DrHkldMed (e.g., drilling hook load median), and then utilizing one or more of the parameter values for detection. Other values may include DrSppaMed and / or DrFlwiMed, etc. As an example, to calculate TQLS, a method may collect valid STOR data points (e.g., those with STOR < DrStorMed) during a post-connection state. In such a method, the final TQLS value may be taken as the low median of the points. Regarding the determination of HKLD_FR, a method may collect data points during the post-connection state with valid HKLD and RPM. In such a method, a model filter may be used to filter the points (e.g., RPM < 0.7×max(RPM), where "0.7" may be a suitable parameter value). The final HKLD_FR result value may statistically be taken as the low median of the points. As for the determination of HKLD_PU and HKLD_SO values during the drilling phase, a method may collect points from the pre-connection state and classify these points into two groups, one for pick-up and the other for slack-off. As an example, for both, a method may first apply the HKLD < ConHkldMin filter (e.g., using the filter value from the adaptive part). Then the set may be filtered by a model filter (e.g., RPM > 1c / min condition, where "1" may be a suitable parameter value). Then, for the pick-up group, the method may take data points with increasing BPOS, filter them by a model filter (e.g., 1.2×min(BPOS) < BPOS < 0.8×max(BPOS), where "1.2" and "0.8" may be suitable parameter values), and the final HKLD_PU may be statistically determined, for example, taken as the high median of this group.Similarly, for the lowering group, the method may take data points with decreasing BPOS, filter them by a model filter (for example, 1.2×min(BPOS)<BPOS<0.8×max(BPOS)), and the final HKLD_SO may be statistically determined, for example, taken as the low median of this group.

[0266] With regard to the RIH and POOH phases, by way of example, the pre-connection and post-connection states may not be defined, as no drilling occurs. In this case, when max(BPOS)-2m<BPOS<max(BPOS), the HKLD_SO during RIH may be statistically determined as min(HKLD), where "2m" may be a suitable parameter value, and when min(BPOS)<BPOS<min(BPOS)+2m, the HKLD_PU during POOH may be statistically determined as max(HKLD), where "2m" may be a suitable parameter value.

[0267] As referred to in Figure 11 the explanation, a method may comprise, for example, continuing one or more detection processes after one or more various thresholds (for example, one or more of DrStorMed, DrHkldMed, ConHkldMed, DrSppaMed, DrFlwiMed, etc.) have been identified.

[0268] Figure 16 An example of a system 1600 is illustrated, which includes various example inputs 1621 to 1627 and various example outputs 1681 to 1687 for a machine learning model (ML model) 1650, which may be generated using the ML model 1650 as a trained ML model. As shown, the inputs may include rig state 1621, drilling state 1622, block position (BPOS) 1623, RPM 1624, hook load (HKLD) 1625, surface torque (STOR) 1626, and one or more other inputs 1627 (for example, considering one or more pressures (SPPA, etc.), flow rates (FLWI, etc.), etc.). As shown, the outputs may include hook load slack-off (HKLD_SO) 1681, hook load pick-up (HKLD_PU) 1682, hook load free rotate (HKLD_FR) 1683, downhole weight on bit (DWOB) 1684, torque loss (TQLS) 1685, downhole torque (DTOR), and one or more other outputs 1687 (for example, considering one or more pressures (OFBP, DPRES, etc.)).

[0269] By way of example, the system 1600 may be used in, for example, Figure 14In method 1400, the method may include various parts, such as training, implementation, and control. As an example, system 1600 may utilize one or more features of system 1490, which may be local, distributed, remote, or a combination of local and remote features. As an example, system 1600 may interact with... Figure 11 , 12 It is used in conjunction with one or more aspects explained by GUI 1100, 1200, and 1300 of version 13. As an example, a system such as system 1600 can be used to directly and / or indirectly determine one or more values ​​that can be used in one or more methods.

[0270] Figure 17 An example of a graphical user interface 1700 is shown, including a graph of system 1710, a graph of an example drilling bit (or drill bit) 1711, and a graph of trajectory 1730, wherein system 1710 can perform directional drilling to drill a borehole according to trajectory 1730. As shown, trajectory 1730 includes a substantially vertical section, a dogleg, and a substantially lateral section (e.g., a substantially horizontal section). System 1710 can operate in various operating modes, which may include, for example, rotary drilling and sliding drilling. Figure 17 In the example, the arrows show the flow of drilling fluid (e.g., mud) through the openings of drill bit 1711 (e.g., for lubrication, for bringing drill cuttings to the surface, etc.).

[0271] exist Figure 17 In one example, the longitudinal resistance along the drill string can be reduced from the surface to the maximum oscillation depth, at which friction and applied torque are balanced. As an example, drilling operations may include manipulating surface torque oscillations so that the maximum rock depth can be moved deep enough to generate a significant reduction in resistance. As an example, the reaction torque from the drill bit generates vibrations that propagate back up the well, disrupting friction and longitudinal resistance at the bottom of the drill string until an interference point is reached, where the torque is balanced by static friction. Figure 17 As the example shows, the intermediate region can remain relatively unaffected by ground sway torque or counter-torque. Figure 17 In the example, drilling operations could include monitoring torque, WOB, and ROP during slippage. As an example, such drilling operations could be designed to minimize the length of the intermediate zone, thereby reducing longitudinal resistance.

[0272] Drilling operations in slipper mode involving manual adjustments to change and / or maintain tool face orientation can be challenging. As an example, drilling operations in slipper mode can depend on the ability to transfer weight to the drill bit without stopping the mud motor, and on the ability to sufficiently reduce longitudinal resistance to achieve and maintain the desired tool face angle. As another example, drilling operations in slipper mode can be designed to achieve an acceptable ROP (Return on Exploration) while considering one or more other factors (e.g., equipment capacity, equipment condition, tripping, etc.).

[0273] As an example, in drilling operations, the amount of surface torque (e.g., STOR) provided by the top drive unit can largely determine how far downhole oscillation motion can be transmitted. As an example, the relationship between torque and oscillation depth can be modeled using a torque and resistance framework (e.g., a T&D framework). As an example, a system may include one or more T&D features.

[0274] As an example, the system can utilize inputs from surface hook loads and riser pressures, as well as the downhole MWD toolface angle. In such an example, the system can automatically determine the appropriate amount of surface torque to transfer downhole weight to the drill bit. This allows for toolface adjustments without lifting the drill bit, leading to more efficient drilling operations and reduced wear on downhole equipment. Such a system can be referred to as an automated auxiliary system.

[0275] As for the exemplary drill bit 1711, it may include various cutting structures (e.g., cutters) that may be numbered from 1 to N and represented in a cross-sectional view that shows the cutter density and associated spatial information by rotating the placement of the cutting structures on a single radial plane. Drill bit 1711 may be, for example, a polycrystalline diamond composite (PDC) drill bit, which may be a fixed-head drill bit that rotates as a whole and does not include separate moving parts.

[0276] like Figure 17 As shown, the drill bit may include inserts 1712-1, 1712-2, ... 1712-N, which may include, for example, primary inserts and secondary inserts. As an example, the inserts may be part of the drill body and therefore integral with it. As shown, the inserts may include insert tips for mounting multiple cutting structures (e.g., numbered 1 to N). As an example, a cutting structure may include a cutting face, wherein the cutting structure is mounted in a recess formed in the insert tip. The cutting structures may be arranged adjacent to each other in a radially extending row near the leading edge of the insert. As an example, the cutting face may have an outermost cutting tip that is furthest from the insert tip where the cutting structure is mounted. Figure 17As shown, the drill body may include various channels that allow drilling fluid to flow between and clean and cool the cutting blades 1712-1, 1712-2, ... 1712-N during drilling. As an example, the drill bit may be defined by a drill bit centerline and drill bit faces, with the cutting blades extending radially along the drill bit faces. Figure 17 As shown, each of the cutting blades 1712-1, 1712-2, ... 1712-N can extend outwards by a certain distance, thereby defining a channel between adjacent blades. Each blade includes a blade tip, which can be defined by a blade height parameter. As mentioned, a cutting structure can be mounted on the blades, where drilling utilizes the cutting structure to "cut" rock. As an example, the cutting structure can extend outwards beyond the tip of the blade to which it is mounted. The cutting structure (e.g., a cutting element) can be, for example, a PDC cutting structure, such that the drill bit can be referred to as a PDC drill bit. Shaping a PDC into a useful shape for a cutting structure can involve placing diamond grains together with their substrate in a pressure vessel and then sintering them under high temperature and pressure. As an example, the drill body can be considered as a carrier of the cutting structure.

[0277] As an example, the drill bit can be a matrix body (MBB) or steel body (SBB) drill bit. The matrix can be a hard but somewhat brittle composite material, which may include tungsten carbide grains metallurgically bonded with a softer, tougher metal binder. Matrix can be ideal as a drill bit material because its hardness provides wear resistance and corrosion resistance. Matrix drill bits may be able to withstand relatively high compressive loads, but may have relatively low resistance to impact loads compared to steel.

[0278] Because the matrix can be relatively heterogeneous, as it is a composite material, and because the matrix can vary (e.g., through design and environment) due to the size and location of the tungsten carbide particles, its physical properties may be less predictable than those of steel.

[0279] Matrix drill bits can be manufactured using a molding process. For example, tungsten carbide and binder material can be placed in a mold and then left in a furnace for a period of time. The mold can then be cooled and released to remove the unfinished matrix drill bit.

[0280] As for the steel body, it can withstand high impact loads, but it can be relatively soft and will quickly fail due to wear and corrosion without protective features. High-quality steel is often homogeneous, and its structural limits are often predictable. Steel bodies can be manufactured by processing steel bars according to a design.

[0281] In terms of drill body structure, different types of drill bits have different design features and manufacturing processes due to the properties of the materials used to make them. The lower impact toughness of matrix drill bits limits some characteristics, such as insert height. Conversely, steel has ductility and toughness, enabling it to withstand greater impact loads. This allows steel-bodied PDC drill bits to be relatively larger than matrix drill bits, and to incorporate greater height into features such as inserts.

[0282] Matrix PDC drill bits are often suitable for environments where matrix erosion could lead to drill bit failure. For impregnated diamond drill bits, a matrix structure can be used. The strength and ductility of steel give steel drill bit bodies high resistance to impact loads. Steel bodies are often stronger than matrix bodies. Due to the properties of steel, complex drill bit shapes and hydraulic designs can be manufactured on multi-axis CNC milling machines. Steel drill bits can be modified and rebuilt multiple times, which is beneficial for operators in low-cost drilling environments, as worn or damaged cutters can be replaced.

[0283] The cutting structure or cutter of a drill bit may be used continuously throughout the drill bit's lifespan. To function properly, the cutter obtains structural support and effective orientation from the drill bit body features. The cutter orientation can be such that the cutter is largely (e.g., primarily) loaded by compressive forces during operation. To prevent loss (e.g., detachment from the body), the cutter can be held in place, for example, by brazing material with sufficient structural capacity and which has been appropriately deposited during manufacturing.

[0284] Cutters can be appropriately positioned on the drill bit face (e.g., mounted on the blades) to strive to ensure the desired bottom hole coverage (e.g., complete bottom hole coverage). The term "cutter density" part refers to the number of cutters used in a particular drill bit design. For example, the cutter density of a PDC drill bit can be a function of the profile shape and length, as well as the cutter size, type, and number. If cutter redundancy exists, the redundancy typically increases from the center of the drill bit outwards in radius, as the demand for work increases with the radial distance from the drill bit centerline. Cutters closer to the gauge move farther, faster, and remove more rock compared to cutters closer to the centerline. Figure 17 As shown, cutter density can be represented by rotating the position of each cutter on a single radial plane. This illustration can be referred to as a planar representation of cutter density, shown as increasing with radial position.

[0285] Reducing the number of cutters on the drill bit face often results in the following: increased depth of cut (DOC); increased ROP; increased torque; and shortened drill bit life. However, increasing the cutting density often leads to: decreased ROP; reduced efficiency in cleaning the cut structure; and increased drill bit life.

[0286] exist Figure 17 In the example, for the drill bit depicted, the cutter density can be increased in the outward radial direction from the drill bit centerline, where the flat cutter impact pattern delineates the image of the drill bit outline.

[0287] As mentioned, the system can provide information about mechanical specific energy (MSE), which may or may not include downhole mechanical specific energy (DMSE).

[0288] MSE can be a measure of drilling efficiency. For example, MSE can represent the energy required to remove a unit volume of rock. As an example, to achieve optimal drilling efficiency, the system's objective could be to minimize MSE and maximize ROP. To control MSE, various techniques can be utilized, which may include adjusting one or more control parameters. For example, the driller and / or system can control WOB, torque, ROP, and bit RPM in an effort to control MSE.

[0289] Rock processing may involve breaking fragments from a solid rock face. Rock processing can involve pressing tools into the rock surface, which can be characterized by surface hardness. Because the rock processing process involves breaking rather than cutting hard rock into small fragments of various sizes, it can be considered a fracturing process. As an example, a fracturing process can be characterized by one or more energy / volume relationships. As an example, specific energy can be defined as the energy required to excavate a unit volume of rock, and it can serve as an indicator of the mechanical efficiency of the rock processing process. In various drilling processes, for rotary, percussion rotary, and roller cone bit drilling, the minimum value may be roughly related to the fracturing strength of the drilling medium.

[0290] As an example, the equation for MSE can be as follows:

[0291]

[0292]

[0293]

[0294] Where A is the cross-sectional area of ​​the well, and the unit of MSE can be psi, ft-lb*ft 3 Units such as...

[0295] As an example, the minimum MSE can be divided by the obtained MSE to determine the drill bit efficiency value. As another example, for a given rig power, MSE and ROP can be inversely proportional. In various drilling operations, breaking rock into fragments smaller than sufficient for dispersal results in greater energy consumption, while breaking rock into fragments too large to dispersal requires energy consumption for further braking (e.g., breaking it into even smaller fragments).

[0296] As an example, parameter-dependent drilling can be characterized by the depth of cut (DOC), where, for example, a small depth of cut can be associated with abrasion and high friction, which can lead to high MSE and low ROP, and where, for example, increased DOC can translate from scraping and abrasion into rock fracturing and breakage. Higher DOC, for instance, can result in the spalling and breakage of larger blocks of material, while less reduction to smaller blocks through regrinding can lead to lower MSE due to more efficient volumetric removal.

[0297] Although MSE can be a parameter used in control, as noted, the example MSE equations described above include WOB and RPM. As an example, a control process may utilize one or more of WOB and RPM, optionally in addition to one or more other parameters. As an example, a control process may include monitoring the MSE, which can be used for one or more purposes (e.g., control, diagnostics, etc.).

[0298] As an example, a well could be an extended-reach well (ERW) to be drilled using extended-reach drilling (ERD). For instance, an ERW can be drilled using directional drilling, where the total depth (TD) reached by the horizontal reach (HR) exceeds the actual vertical depth (TVD) by more than twice. ERD is challenging in directional drilling and requires specialized planning for well construction.

[0299] For example, an ERD (Extremely Distant Surface) can be defined as a deep well with a horizontal distance to depth or an H:V ratio of less than 2. As an example, ERD databases can classify wells into low, medium, large reach, and very large reach wells as well construction complexity increases. Construction complexity can depend on various factors, including water depth (for offshore wells), drilling rig capacity, geological constraints, and total TVD (total TVD). For example, a vertical well with a TVD greater than 7,620 meters (25,000 feet) can be considered a large reach well. Furthermore, depending on the conditions, drilling in deep water or salt formations may be classified as an ERD, even if the well's horizontal extent does not exceed twice its TVD. As an example, an ERD can be used to describe drilling from a location that might be more advantageous than a location vertically above the target. For example, consider drilling from an onshore location to reach a target vertically below a body of water. In various cases, drilling from an onshore location may be more desirable than drilling from an offshore location (e.g., a platform).

[0300] Figure 18Example GUI 1800 is shown, illustrating a geological environment comprising seven exploration wells and six development wells completed by nine sidetracking operations. As an example, systems such as System 1600 can be used for one or more types of operations in such an environment. As an example, consider using System 1600 to drill one or more sections of one or more wells. In such an example, various conditions may exist, occur, etc., for example, consider a 12.25-inch section (e.g., approximately 31.8 cm) where conditions are observed for a shut-off event.

[0301] As an example, regarding segments, consider a 17.5-inch segment (e.g., approximately 44.5 cm) achieving a 50-degree inclination for multiple wells, while a 12.25-inch segment (e.g., approximately 31.8 cm) would land at 90 degrees for multiple wells. As an example, an 8.5-inch segment (e.g., approximately 21.6 cm) can be drilled substantially horizontally (e.g., a transverse segment, etc.). As an example, the system could assist drilling of one or more segments experiencing one or more wellbore cleaning issues. For example, consider identifying sensitive inclinations for wellbore cleaning, which might be between approximately 30 degrees and approximately 70 degrees.

[0302] Figure 19 Example GUI 1900 is shown, illustrating the relationship between measured depth and time in days for drilling six wells. GUI 1900 provides data for understanding the performance of each well, particularly the daily progress of the 12.25-inch section of the well. As can be seen in GUI 1900, optimal performance was achieved during drilling well 15H, reaching 2600m, while wells 11H and 14H faced lower performance sections. During well 14H, it took nearly 12 hours to drill two stands (each point roughly representing one stand) at approximately 2000m. Regarding the performance of well 11H, the ROP was lower between 1400m and 1600m, but did not drop as abruptly as in well 14H.

[0303] As explained, MSE can be a parameter that can be used to characterize drilling, such as drilling efficiency. In particular, MSE can serve as a good indicator of drilling efficiency. While various equations for MSE have been given above, consider the following MSE equation as another example:

[0304] MSE = Input Power / Output ROP

[0305] When using surface data for calculations, the MSE concept is often more applicable to vertical sections. However, when using surface data in highly deviated wells, the MSE concept is less reliable, and it is recommended to use downhole parameters to eliminate wellbore energy losses. Thus, systems such as System 1600 can be used for... Figure 16The various outputs shown can be outputs of various downhole parameters. As an example, one approach could include estimating various downhole parameters, where the downhole MSE (DMSE) can be calculated. For example, consider the following example equation for DMSE:

[0306] DMSE = 480TORxTRPM / (ROPxD) 2 )+4DWOB / (πD 2 )

[0307] in:

[0308] DMSE: Downhole mechanical energy, unit: MPa

[0309] TRPM: Total revolutions per minute, unit: c / min

[0310] ROP: Drilling rate, unit is m / h

[0311] DWOB: Downhole drilling pressure, in kN.

[0312] DTOR: Downhole torque, measured in kN.m

[0313] D: Drill bit diameter, in meters (m)

[0314] Figure 20 An exemplary GUI 2000 showing various outputs from six wells is provided, in which the lifting and lowering weights obtained during connection can be compared using a broom model. Figure 20 Specific parts of GUI 2000, which serves as an example GUI 2100, are also shown (see, for example, see...). Figure 21 (An enlarged version). As an example, the system can generate a GUI that includes a multi-well broom with automatically acquired lift and lower points. As an example, such as Figure 16 The 1600 system can be used to generate outputs for one or more wells, one or more segments of one or more wells, etc.

[0315] Figure 21 The GUI 2100 is shown. Figure 20 A magnified view of the GUI 2100 marked in the middle. Figure 20 In the example GUI2000, especially Figure 21In the GUI 2100 shown, for well 14H, when the hole is observed (e.g., highlighted by a rectangular box), the coefficient of friction appears to increase slightly during depth and further increase just before the pull-out hole (POOH). During tripping, an over-pull of 30 kkgf was recorded, causing the scraper to run down to better clean the wellbore and prevent pipe jamming. As explained, jammed pipe can cause various problems, resource depletion, delays (e.g., non-productive time (NPT)), etc. As noted, completing the 12.25-inch segment (e.g., approximately 31 cm) took approximately 200 hours, with scraper tripping accounting for approximately 8% of the time spent on that stage (e.g., 16 hours).

[0316] Figure 22 A sample GUI 2200 showing the DMSE relative to the measured depth for six wells is provided, noting that the Total Vertical Depth (TVD) can be used additionally or alternatively. The DMSE was calculated for the six wells after processing the data using automated state and reference connection techniques. In GUI 2200, the results are displayed adjacent to each other along with the MSE calculated individually using surface parameters. The BHA used for each well was similar, without motors or downhole measurements. As shown in GUI 2200, the difference between DMSE and MSE is colored in green. As noted, DMSE is lower than MSE, and this difference increases with dip angle.

[0317] MSE and DMSE increase with depth, for example, as the rock becomes harder, and / or, for example, as tool wear (e.g., drill bit wear). As an example, a section of a well may be planned to be drilled using a single drill bit with sufficient characteristics for drilling that section. If drill bit wear exceeds the planned wear, it may be necessary to reconsider drilling that section. For example, control parameters may be adjusted to increase drilling effort into the section without having to pull the drill string out of the hole (POOH) to address drill bit wear, e.g., by replacing the drill bit. In such an example, one or more adjustments may come at the cost of time and / or other resources (e.g., mud resources, energy resources, etc.).

[0318] As an example, some fluctuations and / or increases in MSE / DMSE can be observed when drilling heterogeneous and / or harder formations. For instance, consider the data for well 10H before returning to a less noisy signal. On the other hand, wells 14H and 15H show relatively high variations in MSE and DMSE.

[0319] As explained, total vertical depth (TVD) may be related to rock hardness; therefore, the system can generate a GUI that includes one or more representations of TVD.

[0320] Figure 23An example of a GUI 2300 including the MSE and DMSE of TVD is shown, which can help with interpretation, monitoring, control, etc. Figure 23 In the analysis, multi-well analysis showed that four out of the six wells exhibited increased MSE / DMSE at the end of formation G. The difference was that well 14H had a long well section with a high MSE / DMSE exceeding 7 GPa at the end of formation G (see top of formation).

[0321] Multi-well plots of the entire well section drilled in TVD for a 12.25-inch segment (e.g., approximately 31 cm) provide identification of one or more anomalous increases in MSE. As an example, the area of ​​the plot can be analyzed more comprehensively, for example, by including the MSE along with the riser pressure and its model. As an example, mud logging reports can indicate the presence of cavitation in the formation (e.g., formation H) and subsequent losses. The presence of cavitation within the annulus may be a cause of higher friction around the drill pipe, which could explain a large difference between MSE and DMSE. As an example, a possible increase in SPP can also show a correlation.

[0322] As an example, in an environment of monitoring, control, etc., using real-time drilling data analysis, one approach may include generating a visualization of a broom model relative to actual measurements and presenting it to one or more displays, and for example for bottom hole drilling efficiency analysis, including one or more of bit wear prediction and ROP prediction. As an example, as explained, one or more types of MSE calculations may be provided, which may be associated with and / or indicate bit wear and / or ROP. As explained, downhole MSE may be calculated (e.g., DMSE = 480TORxTRPM / (ROPxD2) + 4DWOB / (πD2)).

[0323] As an example, a system may include one or more interfaces for receiving real-time surface data, which may be of poor quality (e.g., in a vendor-neutral environment, etc.). In such an example, the challenges may stem from relatively low-frequency data sampling (e.g., 0.1 Hz) and / or inconsistent drilling practices at connection times, rendering some calculations unavailable and impacting the confidence level in such a system.

[0324] As an example, such as Figure 16The 1600 system can provide detection of torque loss and lifting / lowering / free rotation weight (e.g., HKLD_PU, HKLD_SO, HKLD_FR, etc.); support for processing vendor-independent data (e.g., vendor-independent data, etc.); support automation when data quality may be an issue; estimate one or more operating friction factors (e.g., to facilitate jammed pipe detection workflows, etc.); help ensure the drill string remains relatively free and / or the casing can reach the total depth (e.g., the casing can be easily installed with acceptable friction to reach the desired depth, etc.); support operation of challenging ERD wells (ERW) with particularly high friction coefficients, etc.

[0325] Figure 24 An example of a GUI 2400 is shown, including input channels, drilling status, output weight, output torque, and output pressure. Various information and statuses can be encoded (e.g., colors, shadows, profile lines, etc.) for presentation to the display. See again... Figure 16 The system 1600 can include drilling rig status 1621 and drilling status 1622 as inputs.

[0326] Figure 25 Example table 2510 and example table 2530 show examples of drilling rig status and drilling status, respectively. As examples, one or more systems, subsystems, etc., can be used to determine drilling rig status, drilling status, etc.

[0327] As explained, one or more methods, systems, etc., can utilize methods that include various input channels, states, weights, etc. For example, consider utilizing... Figure 24 GUI 2400 and / or Figure 25 Methods for obtaining information as defined in one or more of Tables 2510 and 2530.

[0328] As an example, the system can provide automated calculations of drilling rig operation activities and bottom-out references, which can be combined with one or more technologies to provide real-time analysis and interpretation of drilling data. As mentioned, processing surface data with questionable quality, which may be recorded at relatively low frequencies (e.g., 0.2 Hz or higher), can be challenging when done in isolation. However, by utilizing technologies such as... Figure 16 In the case of System 1600, machine learning can provide the output of one or more well analyses that allow for improved drilling performance. This output can be used for monitoring, control, and various other purposes, and may include one or more improvements in efficiency and accuracy. As an example, systems such as System 1600 can automatically utilize machine learning for multi-well correlation, which can minimize the need for human interpretation.

[0329] As explained, such as Figure 16The System 1600 can be used for calculations such as MSE values ​​(e.g., DMSE values), which provide an indication of one or more variations in lithology during drilling. As explained, downhole pressure calculations show the primary indicators of annular cut and cavern load, which lead to increased non-productive time (NPT) and casing difficulty risk. When the system is used in drilling operations, this information can be part of a control loop, allowing automated, semi-automated, and other methods to help mitigate problems and / or reduce NPT.

[0330] As an example, the system can provide interpretations of drilling events in real time. As another example, the ML modeling approach can be extended to predict lessons learned from various types of problem events that may hinder operations, which can help free up labor to focus on other analyses and / or decision-making (e.g., where manual assessment might be required).

[0331] As explained, Figure 16 System 1600 can be used for one or more wells. As an example, the system's output can be compared with the output of one or more other systems. For example, consider a comparison between a system such as System 1600 and a non-automated calibration engine system. Such a non-automated calibration engine system may need to perform various offline (e.g., non-real-time) tasks and / or perform various recalibrations.

[0332] Figure 26 Example Tables 2610 and 2630 illustrate results from a non-automated calibration engine system (AC) and an ML model system (RC), which may include one or more ML models where various tools are provided for actual measurements using downhole measurement tools. For example, consider the OPTIDRILL system, which utilizes a downhole drilling mechanics and dynamics measurement sub (drill string assembly) for measurements that can be used to identify the type and severity of one or more types of BHA motion, for example, to calculate the coefficient of friction in continuous borehole. Consider, for example, a 19-sensor sub that provides downhole measurements (e.g., force, pressure, and temperature, rotational speed, and vibration) and information about BHA motion and its severity, where downhole data can be transmitted to the surface, integrated with surface measurements, and displayed on a well site drilling dashboard.

[0333] In example tables 2610 and 2630, various results are derived from data from 100 wells. Specifically, in table 2630, for simplicity, data examples from 6 wells out of the 100 wells are shown, labeled A1, B1, C1, D1, E1, and F1. The data in tables 2610 and 2630 correspond to the differences when summed with the actual measurements from the 100 wells. The ML model system provides better DTOR results in 70 of the 100 wells, better DWOB values ​​in 94 of the 100 wells, more TQLS points in 54 of the 100 wells, and more HKLD_FR points in 72 of the 100 wells. As mentioned, table 2630 shows data from 6 of the 100 wells for DTOR, TQLS, DWOB, and HKLD_FR. As explained, the ML model method can be fully automated. For example, Figure 16 The system 1600 can operate in a fully automatic mode.

[0334] As an example, frames such as the ROPO frame (Schlumberger Ltd., Houston, Texas) offer drilling rate optimization that can utilize calibrated engine systems, such as... Figure 26 The AC system is shown in Tables 2610 and 2630. As an example, an ML model system (e.g., a system denoted as RC, etc.) can be used as an alternative, for example, using reference connections, which can provide improved reliability. As an example, a framework such as the PTK framework (Schlumberger Ltd., Houston, Texas) can include drilling rate optimization features. In such examples, one or more ML models, ML model systems, etc., can be included, integrated, linked, etc., for the purpose of improved drilling.

[0335] As an example, ML modeling systems can provide drill bit wear and ROP predictions. For instance, one or more outputs of System 1600 can provide data for predicting drill bit wear and / or ROP. As another example, the coefficient of friction can be estimated, which can be used for the drill string, a portion of the drill string, the drill bit, etc.

[0336] As explained, one approach could include controlling the drilling to reduce the risk of sticking. As mentioned, in the event of sticking, time and resources may be spent resolving the sticking, which could lead to one or more problems, such as inability to release the drill string, damage to the borehole, etc. As an example, in areas where damage occurs, casing operations (such as well completion operations) can be more complex.

[0337] As explained regarding drill bit wear, the system can control drilling to achieve a desired drilling volume, which can be measured, for example, by measuring depth. Consider, for instance, a section of a specific diameter in which a specific drill bit would be used to drill the entire section without having to pull the drill string out of the hole (POOH).

[0338] As explained, techniques such as […] can be used during drilling. Figure 16 The system uses a 1600-level system to estimate the friction coefficient. In such an example, when the friction coefficient is not within the expected range or is below the expected value, the controller can invoke one or more operations. For example, consider adjusting one or more characteristics of the drilling mud, one or more drilling mud flow rates, utilizing a borehole reaming process, etc. As an example, a cleaning process can be performed, which aims to adjust the borehole to achieve a suitable friction coefficient. For example, a cleaning process can utilize a cleaning drill bit. As explained, the ERD of an ERW can cause friction problems due to large displacements.

[0339] As an example, an ML model can be a physics-based ML model and / or include one or more physics-based models. As another example, an ML model can be relatively lightweight, which can accelerate learning and / or reduce the computational resource requirements for generating one or more trained ML models.

[0340] Regarding the types of machine learning models, consider one or more examples, such as Support Vector Machine (SVM) models, k-Nearest Neighbor (KNN) models, ensemble classifier models, neural network (NN) models, etc. As examples, machine learning models can be deep learning models (e.g., Deep Boltzmann Machines, Deep Belief Networks, Convolutional Neural Networks, Stacked Autoencoders, etc.), ensemble models (e.g., Random Forests, Gradient Boosting Machines, Bootstrap Aggregation, Adaptive Boosting (AdaBoost), Stacked Generalization, Gradient Boosting Regression Trees, etc.), neural network models (e.g., Radial Basis Function Networks, Perceptrons, Backpropagation, Hopfield Networks, etc.), regularization models (e.g., Ridge Regression, Minimum Absolute Shrinkage and Selection Operators, Elastic Networks, Minimum Angle Regression), rule-based system models (e.g., Cubism, One-Rule, Zero-Rule, Repeated Incremental Pruning to Generate Error Reduction), regression models (e.g., Linear Regression, Ordinary Least Squares Regression, Stepwise Regression, Multivariate Adaptive Regression Splines, Local Estimation Scatter Plot Smoothing, Logistic Regression). Examples of models include: Bayesian models (e.g., Naive Bayes, Average Dependency Estimator, Bayesian Trust Network, Gaussian Naive Bayes, Multinomial Naive Bayes, Bayesian Networks), Decision Tree models (e.g., Classification and Regression Trees, Iterative Bisection 3, C4.5, C5.0, Chi-square Automatic Interaction Detection, Decision Stumps, Conditional Decision Trees, M5), Dimensionality Reduction models (e.g., Principal Component Analysis, Partial Least Squares Regression, Sammon Mapping, Multidimensional Scaling, Projective Pursuit, Principal Component Regression, Partial Least Squares Discriminant Analysis, Mixed Discriminant Analysis, Quadratic Discriminant Analysis, Regularized Discriminant Analysis, Flexible Discriminant Analysis, Linear Discriminant Analysis, etc.), Instance models (e.g., k-Nearest Neighbors, Learned Vector Quantization, Self-Organizing Map, Locally Weighted Learning, etc.), Clustering models (e.g., k-means, k-median, Expectation Maximization, Hierarchical Clustering, etc.), etc.

[0341] As an example, machine learning models can be built using computational frameworks with libraries, toolboxes, etc., such as those in the MATLAB framework (MathWorks, Inc., Natick, Massachusetts). The MATLAB framework includes a toolbox that provides supervised and unsupervised machine learning algorithms, including Support Vector Machines (SVM), boosting and packing decision trees, k-nearest neighbors (KNN), k-means, k-centroids, hierarchical clustering, Gaussian mixture models, and hidden Markov models. Another MATLAB framework toolbox is the Deep Learning Toolbox (DLT), which provides a framework for designing and implementing deep neural networks with algorithms, pre-trained models, and applications. DLT provides Convolutional Neural Networks (ConvNets, CNNs) and Long Short-Term Memory (LSTM) networks for performing classification and regression on image, time series, and text data. DLT includes the ability to build network architectures using custom training loops, shared weights, and automatic differentiation, such as Generative Adversarial Networks (GANs) and Siamese networks. DLT provides model exchange to various other frameworks.

[0342] As mentioned, an example of a machine learning model is a neural network (NN) (e.g., a neural network model), which can include neurons and connections, where each connection provides the output of one neuron as the input of another neuron. A weight representing its relative importance can be assigned to each connection. A given neuron can have multiple input and output connections. An NN can include a propagation function that computes the input of a neuron based on a weighted sum of the outputs of its predecessor neurons and their connections. As an example, a bias term can be added to the result of the propagation.

[0343] As an example, neurons can be organized into multiple layers, particularly in deep learning neural networks (NNs). As an example, the layer that receives external data can be an input layer, and the layer that produces one or more results can be an output layer. As an example, an NN can be fully connected, where each neuron in one layer is connected to every neuron in the next layer. As an example, an NN can utilize pooling, where a group of neurons in one layer is connected to a single neuron in the next layer, thereby reducing the number of neurons in that layer. As an example, an NN can include connections forming a directed acyclic graph (DAG), which can define a feedforward network. Alternatively, an NN can allow connections between neurons in the same or previous layers (e.g., recurrent networks).

[0344] As an example, a trained ML model (e.g., a training ML tool including hardware, etc.) can be used for one or more tasks. As an example, various types of data can be acquired and optionally stored, which can provide training for one or more ML models, retraining for one or more ML models, further training for one or more ML models, and / or offline analysis, etc.

[0345] As an example, the TENSORFLOW framework (Google LLC, Mountain View, California) can be implemented; it is an open-source software library for dataflow programming, including a symbolic mathematics library, and can be implemented for machine learning applications that may include neural networks. As an example, the CAFFE framework, a DL framework developed by Berkeley AI Research (BAIR) (University of California, Berkeley, California), can be implemented. As another example, consider using the SCIKIT platform (e.g., scikit-learn) with the Python programming language. As an example, frameworks such as the Apollo AI framework (Apollo.AI GmbH, Germany) can be utilized. As an example, frameworks such as the PYTORCH framework (Facebook AI Research Lab (FAIR), Facebook, Menlo Park, California) can be utilized.

[0346] As explained, such as Figure 16 The System 1600 can provide detection of lifting and / or lowering weights, downhole drilling pressure, torque, and / or pressure based on machine learning from surface sensors. Such an approach can be implemented with or without surface data. Note that time delays and / or transmission problems may occur in data communication from one or more downhole sensors to the surface, depending on depth (e.g., total depth or measurement depth). As an example, in the event that one or more downhole sensors and / or the downhole-to-surface transmission channel fails or becomes problematic, the drilling system can automatically switch to a surface sensor-based approach. The timeframe can vary from seconds to minutes depending on the specific circumstances. For example, in automated or semi-automated systems, reducing decision-making processes (e.g., control signal issuance, etc.) can help reduce time. In situations where surface operations are automated and therefore do not involve direct human labor, using surface data can help speed up these operations compared to using downhole data. Note that in various cases, downhole data can be used to examine surface data calculations and, where appropriate, to adjust one or more operations (e.g., slowing down), for example, in cases where one or more deviations exist between the outputs based on surface and downhole data, allowing the use of downhole data until such deviations are reduced. In such examples, once reduced, and once switching back to surface data, operations can be performed more quickly.

[0347] As explained, wells such as those drilled using ERD can be quite long (e.g., consider wells 10 km or longer). As drilling progresses, with the use of one or more downhole sensors, the waiting time for downhole data can be expected to increase, which in various cases can make the utilization of surface data computation more efficient.

[0348] Figure 27 An example of method 2700 is shown, which includes an identification box 2710 for identifying a threshold for determining the drill string bottom-out condition; a filtering box 2720 for filtering time-series surface data of the drill string's subsequent drilling states using the threshold to generate filtered time-series surface data; and a determination box 2730 for statistically determining the drill string bottom-out condition value using the filtered time-series surface data. Figure 27 As shown in the example, method 2700 may include a determination box 2740 for determining downhole drilling values ​​using drill string bottom-out condition values ​​(e.g., downhole torque, downhole friction coefficient, etc.). As an example, drill string bottom-out condition values ​​may be torque loss values, hook load values, or pressure values ​​(e.g., see [reference needed]). Figure 12 As an example, boxes 2720 and 2730 can be executed serially and / or in parallel. As explained, statistical determinations can utilize determinations of type "P" (e.g., P10, P50, P90, etc.). As an example, statistical determinations can utilize median determinations. Median determinations can provide more reliable values ​​than mean determinations because mean determinations can be affected by one or more outliers, etc.

[0349] Figure 27 Various computer-readable medium (CRM) boxes 2711, 2721, 2731, and 2741 are also shown. These boxes may include instructions executable by one or more processors, which may be one or more processors of a computing framework, system, computer, etc. The computer-readable medium may be a non-signal, non-carrier, and non-transitory computer-readable storage medium. For example, a computer-readable medium may be a physical memory component capable of storing information in a digital format.

[0350] As explained, the method can operate on a per-standby basis, where one or more states can be used to define the data. For example, consider states before, during, or after a connection. As an example, consider consecutive stands numbered 32 and 33. In such an example, a method could include using data acquired before the connection of stand 33 to identify a threshold for determining the drill string bottom-out condition; using threshold filtering on time-series surface data acquired after the connection of stand 33 (e.g., a post-connection state of the drill string) to generate filtered time-series surface data; and using the filtered time-series surface data (e.g., data acquired after the connection of stand 33) to statistically determine the drill string bottom-out condition value.

[0351] As explained, a method can utilize one or more types of machine models. For example, consider an example analysis of 100 wells, which can provide outputs of one or more parameter values ​​that can be used to identify thresholds. In such an example, the one or more parameter values ​​can be static or dynamic; if dynamic, they can vary at a rate less than the per-column rate. As explained, the method can be dynamic because the thresholds vary at a per-column rate. As an example, a method could include utilizing one or more machine models that can provide determinations of one or more states, outputs of one or more parameter values, and / or identification of one or more thresholds.

[0352] Figure 28 An example of system 2800 is shown, which may be a well construction ecosystem. As shown, system 2800 may include one or more instances of ML model system 1600 and may include drilling rig infrastructure 2810 and drilling planning component 2820, which may generate or otherwise transmit information associated with a plan to be performed using drilling rig infrastructure 2810, for example, via drilling operations layer 2840 including well site component 2842 and off-site component 2844. As shown, data acquired and / or generated by drilling operations layer 2840 may be transferred to data archiving component 2850, which may be used for purposes such as planning one or more operations (e.g., according to drilling planning component 2820).

[0353] As an example, the computing framework can be implemented within or operationally connected to a DELFI Cognitive Exploration and Production (E&P) environment (Schlumberger, Houston, Texas), a secure, cognitive, cloud-based collaborative environment that integrates data and workflows with digital technologies such as artificial intelligence and machine learning. As an example, such an environment can provide operations involving one or more frameworks. The DELFI environment may be referred to as a DELFI framework, and it can be a single framework among multiple frameworks. As an example, a DELFI framework can include a variety of other frameworks, which may include, for example, one or more types of models (e.g., simulation models, etc.).

[0354] As an example, such as Figure 16 The System 1600 can be used in one or more planning, execution, or other phases, which can be achieved using a framework such as the DELFI framework. For example, consider simulating drilling, where surface measurements are generated that can be used as inputs to the System 1600 to determine one or more performance aspects of the System 1600 before drilling using it. In such an example, simulation can help determine how to utilize the System 1600, e.g., which segment or segments might be suitable for using the System 1600 for one or more purposes.

[0355] As an example, the workflow could proceed to a geological and geophysical (“G&G”) service provider, which can generate well trajectories, which could involve the execution of one or more G&G software packages (see also example...). Figure 28 (System 2800, box 2820). Examples of such software packages include the PETREL framework. As an example, one or more systems may utilize frameworks such as the DELFI framework. Such frameworks can be operatively linked with various other frameworks to provide a multi-framework workspace.

[0356] As an example, one approach may include receiving a threshold for determining torque loss; concatenating surface torque time-series data of the drilling state after threshold filtering to generate filtered surface torque time-series data; and using the filtered surface torque time-series data to statistically determine the torque loss value.

[0357] As an example, one approach may include receiving a filtered value for weight determination; filtering surface hook load time series data of a pre-connected drilling state using the filtered value to generate filtered surface hook load time series data; and using the filtered surface torque time series data to statistically determine weight values.

[0358] As an example, the system may include a processor; processor-accessible memory; and processor-executable instructions stored in the memory that are executable to instruct the system to: receive a threshold for torque loss determination and a filter value for weight determination; use the threshold-filtered surface torque time-series data of the pre-connected drilling state to generate filtered surface torque time-series data; statistically determine the torque loss value using the filtered surface torque time-series data; filter the pre-connected surface hook load time-series data of the drilling state using the filter value to generate filtered surface hook load time-series data; and statistically determine the weight value using the filtered surface torque time-series data.

[0359] As an example, one or more computer-readable storage media may include processor-executable instructions to instruct a computing system to: receive a threshold for torque loss determination and a filter value for weight determination; use the threshold-filtered surface torque time-series data of a pre-connected drilling state to generate filtered surface torque time-series data; statistically determine a torque loss value using the filtered surface torque time-series data; filter surface hook load time-series data of a pre-connected drilling state using the filter value to generate filtered surface hook load time-series data; and statistically determine a weight value using the filtered surface torque time-series data.

[0360] As an example, a method may include identifying a threshold for determining drill string bottom-out conditions; filtering time-series surface data of the drill string's subsequent drilling states using the threshold to generate filtered time-series surface data; and statistically determining the drill string bottom-out condition value using the filtered time-series surface data. In such an example, the drill string bottom-out condition value may be a torque loss value, wherein, for example, the method may include determining a downhole torque value based at least in part on the torque loss value. In such an example, determining the downhole torque value may include utilizing the difference between surface torque and torque loss. As an example, the downhole torque loss value may indicate the amount of drill cuttings at least a portion of the adjacent drill string, particularly when the drill string is positioned in a deviated well.

[0361] As an example, the drill string clearance condition value can be a hook load value. For instance, consider one or more hook load free rotation weight values, hook load lifting values, or hook load lowering values. As an example, one approach may include determining downhole pressure on drill bit (PBT) based at least in part on the hook load value. In such an example, consider using the difference between the hook load value (which is a hook load free rotation value) and at least one measured hook load value to determine the PBT.

[0362] As an example, one approach could include determining the coefficient of friction based at least in part on drill string clearance conditions. In such an example, the approach could include utilizing a broom model.

[0363] As an example, the drill string bottom condition value can be a pressure value. For example, consider bottom pressure and / or pressure differential.

[0364] As an example, the drill string's distance from the bottom condition value can be a median value. For instance, in statistics and probability theory, the median is the value that separates the upper half of a data sample, population, or probability distribution from the lower half. For a dataset, the median (or middle value) can be considered the "middle" value. As an example, methods using the median can be compared or contrasted with methods using the mean (e.g., the average), where, by comparison, the median is not skewed by a small fraction of maximum or minimum values. Therefore, compared to the average, the median can better represent possible expectations, etc.

[0365] As an example, one approach may include identifying a threshold using surface data of the drill string's drilling status. As another example, one approach may include filtering surface data of the drill string's post-connection status, where such filtering may utilize one or more filter models. In such an example, the approach may include utilizing parameter values ​​of a filter model determined through offset well data, which may include comparing offset well data results with different parameter values.

[0366] As an example, one approach could include identifying thresholds by utilizing time-series ground data acquired during drill string drilling.

[0367] As an example, one approach could include filtering using a filter model that incorporates parameter values ​​determined from offset well data. In such an example, the offset well data could include data based on downhole sensors.

[0368] As an example, a method may include identifying multiple different thresholds for determining multiple different drill string bottoming conditions; filtering time-series surface data of the post-connection drilling state of the drill string using the multiple different thresholds to generate filtered time-series surface data; and statistically determining multiple different drill string bottoming condition values ​​using the filtered time-series surface data, wherein the multiple different drill string bottoming condition values ​​may include at least one member selected from a group consisting of torque values, weight values, and pressure values.

[0369] As an example, the system may include a processor; processor-accessible memory; and processor-executable instructions stored in the memory that can be executed to instruct the system to: identify a threshold for determining the drill string bottom-out condition; filter time-series surface data of the drill string's subsequent drilling states using the threshold to generate filtered time-series surface data; and statistically determine the drill string bottom-out condition value using the filtered time-series surface data.

[0370] As an example, one or more computer-readable storage media may include processor-executable instructions to instruct a computing system to: identify a threshold for determining drill string bottom-out conditions; filter time-series surface data of the drill string's subsequent drilling states using the threshold to generate filtered time-series surface data; and statistically determine drill string bottom-out condition values ​​using the filtered time-series surface data.

[0371] As an example, a method may be implemented in part using a computer-readable medium (CRM), such as a module, frame, etc. It includes information such as instructions suitable for execution by one or more processors (or processor cores) to instruct a computing device or system to perform one or more actions. As an example, a single medium may be configured with instructions to allow at least partial execution of various actions of the method. As an example, the computer-readable medium (CRM) may be a non-carrier computer-readable storage medium (e.g., a non-transitory medium).

[0372] According to one embodiment, one or more computer-readable media may include computer-executable instructions to instruct a computing system to output information for controlling a process. For example, such instructions may provide outputs for sensing processes, injection processes, drilling processes, extraction processes, extrusion processes, pumping processes, heating processes, etc.

[0373] In some embodiments, one or more methods may be performed by a computing system. Figure 29 An example of a system 2900 is shown that may include one or more computing systems 2901-1, 2901-2, 2901-3 and 2901-4, which may be operatively connected via one or more networks 2909, which may include wired and / or wireless networks.

[0374] As an example, the system may include a standalone computer system or an arrangement of distributed computer systems. Figure 29 In the example, computer system 2901-1 may include one or more modules 2902, which may be or include processor-executable instructions, for example, which are executable to perform various tasks (e.g., receiving information, requesting information, processing information, simulating, outputting information, etc.).

[0375] As an example, the module can execute independently or in cooperation with one or more processors 2904, which are operatively coupled to one or more storage media 2906 (e.g., via wired, wireless, etc.). As an example, one or more of the processors 2904 can be operatively coupled to at least one of one or more network interfaces 2907. In such an example, the computer system 2901-1 can send and / or receive information, for example, via one or more networks 2909 (e.g., consider one or more of the Internet, private networks, cellular networks, satellite networks, etc.).

[0376] As an example, computer system 2901-1 may receive information and / or send information to one or more other devices, such as or including one or more computer systems 2901-2, etc. The devices may be located in a physical location different from the physical location of computer system 2901-1. As an example, the location may be, for example, a processing facility location, a data center location (e.g., a server farm), a drilling rig location, a well site location, a downhole location, etc.

[0377] As an example, a processor may be or include a microprocessor, a microcontroller, a processor module or subsystem, a programmable integrated circuit, a programmable gate array, or other control or computing device.

[0378] As an example, storage medium 2906 can be implemented as one or more computer-readable or machine-readable storage media. As an example, storage can be distributed within and / or between multiple internal and / or external chassis of the computing system and / or additional computing systems.

[0379] As an example, one or more storage media may include one or more different forms of memory, including semiconductor storage devices such as dynamic or static random access memory (DRAM or SRAM), erasable and programmable read-only memory (EPROM), electrically erasable and programmable read-only memory (EEPROM) and flash memory, magnetic disks such as fixed, floppy and removable disks, other magnetic media including magnetic tape, optical discs (CD) or digital video discs (DVD), Blu-ray discs or other types of optical storage or other types of storage devices.

[0380] As an example, one or more storage media may be located in a machine that runs machine-readable instructions, or at a remote site from which machine-readable instructions can be downloaded over a network for execution.

[0381] As an example, various components of a system, such as a computer system, can be implemented in hardware, software, or a combination of hardware and software (e.g., including firmware), including one or more signal processing and / or application-specific integrated circuits.

[0382] As an example, the system may include a processing device that may be or include a general-purpose processor or a special-purpose chip (e.g., a chipset), such as an ASIC, FPGA, PLD, or other suitable device.

[0383] Figure 30 Components of a computing system 3000 and a networking system 3010 with a network 3020 are illustrated. System 3000 includes one or more processors 3002, memory and / or storage components 3004, one or more input and / or output devices 3006, and a bus 3008. According to one embodiment, instructions may be stored in one or more computer-readable media (e.g., memory / storage components 3004). Such instructions may be read by one or more processors (e.g., processor 3002) via a communication bus (e.g., bus 3008), which may be wired or wireless. One or more processors may execute such instructions to implement (all or part of) one or more attributes (e.g., as part of a method). A user may view and interact with the output from the process through an I / O device (e.g., device 3006). According to one embodiment, the computer-readable medium may be a storage component, such as a physical memory storage device, such as a chip, a chip on a package, a memory card, etc.

[0384] According to one embodiment, the components may be distributed, for example, in network system 3010. Network system 3010 includes components 3022-1, 3022-2, 3022-3, ... 3022-N. For example, component 3022-1 may include processor 3002, while component 3022-3 may include memory accessible by processor 3002. Furthermore, component 3022-2 may include I / O devices for display and optionally for interaction with the method. The network may be or include the Internet, intranet, cellular network, satellite network, etc.

[0385] As an example, a device can be a mobile device that includes one or more network interfaces for information communication. For example, a mobile device may include a wireless network interface (e.g., operating via IEEE 802.11, ETSI GSM, Bluetooth, satellite, etc.). As an example, a mobile device may include components such as a main processor, memory, display, display graphics circuitry (e.g., optionally including touch and gesture circuitry), SIM slot, audio / video circuitry, motion processing circuitry (e.g., accelerometer, gyroscope), wireless LAN circuitry, smart card circuitry, transmitter circuitry, GPS circuitry, and a battery. As an example, a mobile device can be configured as a mobile phone, tablet, etc. As an example, a method can be implemented (e.g., all or part) using a mobile device. As an example, a system may include one or more mobile devices.

[0386] As an example, the system can be a distributed environment, such as a so-called "cloud" environment, in which various devices, components, etc., interact for purposes such as data storage, communication, and computation. As an example, a device or system may include one or more components for communicating information via one or more of the Internet (e.g., in the case of communication via one or more Internet protocols), cellular networks, satellite networks, etc. As an example, a method can be implemented in a distributed environment (e.g., wholly or partially as a cloud-based service).

[0387] As examples, information can be input from a display (e.g., consider a touchscreen), output to a display, or both. As examples, information can be output to a projector, laser device, printer, etc., so that the information can be viewed. As examples, information can be output stereoscopically or holographically. Regarding printers, consider 2D or 3D printers. As examples, a 3D printer can include one or more materials that can be output to construct 3D objects. As examples, data can be provided to a 3D printer to construct a 3D representation of underground strata. As examples, layers can be constructed in 3D (e.g., strata, etc.), three-dimensional geological bodies, etc. As examples, pores, cracks, etc., can be constructed in 3D (e.g., as positive structures, as negative structures, etc.).

[0388] Although only a few examples have been described in detail above, those skilled in the art will readily understand that many modifications are possible in these examples. Therefore, all such modifications are intended to be included within the scope of this disclosure as defined in the following claims. In the claims, the device plus function clause is intended to cover not only structural equivalents but also equivalent structures of the structures described herein that perform the functions. Thus, although nails and screws may not be structurally equivalent, since nails use a cylindrical surface to hold wooden parts together while screws use a helical surface, in the context of fastening wooden parts, nails and screws can be equivalent structures.

Claims

1. A method for performing drilling operations using a drill string, comprising: Data acquired before the drill string is connected to the riser is used to identify thresholds for determining drill string bottom conditions; Using this threshold, time-series surface data acquired after the drill string is connected to the drilling state are filtered to generate filtered time-series surface data, which includes rig status, drilling status, vehicle position, RPM, hook load, surface torque, and at least one of one or more pressures and flow rates; and Filtered time-series surface data is used to statistically determine drill string bottom-out condition values ​​that are not based on downhole sensor measurements. The drill string off-bottom condition values ​​include at least one of the following: hook load lowering, hook load raising, hook load free rotation weight, downhole drilling pressure, torque loss, downhole torque, one or more pressure values, and intermediate values. This involves using a trained machine model to calculate downhole values ​​not based on downhole sensor measurements; and The drill string is controlled during drilling operations using statistically determined drill string bottom clearance conditions.

2. The method of claim 1, further comprising determining the downhole torque based at least in part on torque loss.

3. The method of claim 2, wherein the determination includes utilizing the difference between ground torque and torque loss.

4. The method of claim 2, wherein the torque loss represents the amount of drill cuttings adjacent to at least a portion of the drill string.

5. The method according to claim 4, wherein the drill string is disposed in an inclined well.

6. The method of claim 1, comprising determining downhole drilling pressure based at least in part on hook load values.

7. The method of claim 6, wherein determining the downhole drilling pressure includes using the difference between a hook load value as a hook load free rotation value and at least one measured hook load value.

8. The method of claim 1, comprising determining the coefficient of friction based at least in part on the drill string bottoming condition value.

9. The method of claim 8, further comprising using a broom model.

10. The method of claim 1, wherein the identification threshold includes utilizing time-series surface data acquired during drilling of the drill string.

11. The method of claim 1, wherein the filtering comprises utilizing a filter model that includes parameter values ​​determined via offset well data.

12. The method of claim 11, wherein the offset well data includes data based on downhole sensors.

13. The method of claim 1, further comprising identifying a plurality of different thresholds for determining a plurality of different drill string bottoming conditions; filtering time-series surface data of the post-connection drilling state of the drill string using the plurality of different thresholds to generate filtered time-series surface data; and using the filtered time-series surface data to statistically determine a plurality of different drill string bottoming condition values, wherein the plurality of different drill string bottoming condition values ​​include at least one member selected from the group consisting of torque values, weight values, and pressure values.

14. A system for performing drilling operations using a drill string, comprising: processor; Processor-accessible memory; The processor-executable instructions are stored in memory and are executable to instruct the system to perform the steps of the method described in any one of claims 1-13.

15. One or more computer-readable storage media, including processor-executable instructions, to instruct a computing system to perform the steps of the method of any one of claims 1-13.

Images