Multispectral rock characterization system

Abstract

A system may include a white light source; an ultraviolet light source; the digital machine vision camera is used for capturing an image of the rock drilling cutting sample irradiated by the white light source and the ultraviolet light source; and circuitry operable to generate a calibration image of the rock cuttings sample, the calibration image having a contrast between the hydrocarbon-containing rock cuttings sample and the hydrocarbon-free rock cuttings sample.

Description

[0001] Related applications

[0002] This application claims priority to and the benefit of U.S. Provisional Application Serial No. 63 / 562,864, filed on March 8, 2024, the entire contents of which are incorporated herein by reference. Background Art

[0003] A resource field can be an accumulation, pool, or group of pools of one or more resources (e.g., oil, gas, oil and gas) in a subsurface environment. A resource field can include at least one reservoir. The reservoir can be shaped in a manner that can capture hydrocarbons and can be covered by impermeable or sealing rock. A borehole can be drilled into the environment, wherein the borehole can be used to form a well that can be used to produce hydrocarbons from the reservoir.

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

[0005] Oilfield planning can occur in one or more phases, which may include an exploration phase aimed at identifying and evaluating environments (e.g., prospects, plays, etc.), which may include drilling one or more boreholes (e.g., one or more exploratory wells, etc.). Other phases may include evaluation, development, and production phases.

[0006] In various situations, materials from a wellbore can be evaluated, for example, to characterize a formation. For example, consider evaluating drill cuttings, which may be broken rock fragments of a formation that can be transported from downhole to the surface via the circulation of drilling fluid. This evaluation can rely on human observation of the drill cuttings, which can be subjective and inconsistent. To the extent that characterization based on drill cuttings can be improved, drilling can be improved. Summary of the Invention

[0007] A system may include a white light source; an ultraviolet light source; a digital machine vision camera for capturing images of a rock drill cutting sample illuminated by the white light source and the ultraviolet light source; and circuitry operable to generate a calibration image of the rock drill cutting sample, the calibration image having a contrast between a rock drill cutting sample containing hydrocarbons and a rock drill cutting sample not containing hydrocarbons. A method may include illuminating a rock drill cutting sample with white light and ultraviolet light; capturing an image of the rock drill cutting sample; and characterizing the rock drill cutting sample based at least in part on physical properties derived from the image and at least in part on fluorescence emissions derived from the image. One or more computer-readable storage media may include computer-executable instructions executable to instruct a computing system to: illuminate the rock drill cutting sample with white light and ultraviolet light; capture an image of the rock drill cutting sample; and characterize the rock drill cutting sample based at least in part on physical properties derived from the image and at least in part on fluorescence emissions derived from the image. Various other apparatuses, systems, methods, etc. are also disclosed.

[0008] This Summary is provided to introduce a selection of concepts that are further described below in the Detailed Description. This Summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used to help limit the scope of the claimed subject matter. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The features and advantages of the described embodiments may be more readily understood by referring to the following description taken in conjunction with the accompanying drawings.

[0010] Figure 1 An example of a device in a geological environment is shown;

[0011] Figure 2 Examples of devices and examples of hole types are shown;

[0012] Figure 3 An example of a system is shown;

[0013] Figure 4 An example of a workflow is shown;

[0014] Figure 5 An example of a system is shown;

[0015] Figure 6 An example of a human vision fluoroscope is shown;

[0016] Figure 7 An example of a drawing is shown;

[0017] Figure 8 An example of a machine vision camera is shown;

[0018] Figure 9Examples of lenses and examples of light phenomena are shown;

[0019] Figure 10 An example of a system is shown;

[0020] Figure 11 An example of an image is shown;

[0021] Figure 12 shows an example of an image; and

[0022] Figure 13 An example of a method and an example of a system are shown; and

[0023] Figure 14 An example of a computing system is shown. DETAILED DESCRIPTION

[0024] The following description includes the best mode currently contemplated for practicing the described embodiments. This description should not be considered limiting, but is made merely for the purpose of describing the general principles of the embodiments. Reference should be made to the issued claims to determine the scope of the described embodiments.

[0025] Figure 1 An example of a geological environment 120 is shown. Figure 1 In , the geological environment 120 can be a sedimentary basin that includes layers (e.g., strata) that include a reservoir 121 and that can, for example, be intersected by a fault 123 (e.g., or multiple faults). As an example, the geological environment 120 can be equipped with various sensors, detectors, actuators, etc. For example, equipment 122 can include communication circuits for receiving and sending information with respect to one or more networks 125. Such information can include information associated with downhole devices 124, which can be devices that obtain information, assist in resource recovery, etc. Other equipment 126 can be located remotely from the well site and include sensing, detection, transmission, or other circuits. Such equipment can include storage and communication circuits to store and transmit data, instructions, etc. As an example, one or more pieces of equipment can provide measurement, collection, communication, storage, analysis, etc. of data (e.g., for one or more produced resources, etc.). As an example, one or more satellites can be provided for purposes of communication, data acquisition, etc. For example, Figure 1 A satellite is shown in communication with network 125, which may be configured for communication, noting that the satellite may additionally or alternatively include circuitry for imaging (e.g., spatial, spectral, temporal, radiometric, etc.).

[0026] Figure 1The geological environment 120 is also shown as optionally including equipment 127 and 128 associated with a well, the well including a substantially horizontal portion that may intersect one or more fractures 129. For example, consider a well in a shale formation, which may include natural fractures, artificial fractures (e.g., hydraulic fractures), or a combination of natural and artificial fractures. As an example, a well may be drilled for a laterally extending reservoir. In such an example, there may be lateral variations in properties, stresses, etc., wherein assessment of such variations may assist in planning, operations, etc. to develop the reservoir (e.g., via fracturing, injection, extraction, etc.). As an example, equipment 127 and / or 128 may include components, a system, multiple systems, etc. for fracturing, seismic sensing, analysis of seismic data, assessment of one or more fractures, injection, production, etc. As an example, equipment 127 and / or 128 may provide for measurement, collection, communication, storage, analysis, etc. of data, such as production data (e.g., resources used for one or more productions). As an example, one or more satellites may be provided for purposes of communication, data acquisition, etc.

[0027] Figure 1 Also shown are an example of apparatus 170 and an example of apparatus 180. Such apparatus, which may be a system of components, may be suitable for use in geological environment 120. While apparatus 170 and 180 are shown as land-based, various components may be suitable for offshore systems.

[0028] Equipment 170 includes a platform 171, a derrick 172, a crown block 173, a rope 174, a traveling block assembly 175, a winch 176, and a docking station 177 (e.g., a second-level station). For example, rope 174 can be controlled, at least in part, via winch 176, such that traveling block assembly 175 travels vertically relative to platform 171. For example, by pulling rope 174 in, winch 176 can thread rope 174 through crown block 173 and lift traveling block assembly 175 upward, away from platform 171. However, by allowing rope 174 to be released, winch 176 can thread rope 174 through crown block 173 and lower traveling block assembly 175 toward platform 171. If traveling block assembly 175 is carrying a pipe (e.g., casing, etc.), tracking the movement of traveling block 175 can provide an indication of how much pipe has been deployed.

[0029] A derrick may be a structure used to support a crown block and a traveling block, the traveling block being operably coupled to the crown block at least in part via ropes. The derrick may be pyramid-shaped and provide a suitable strength-to-weight ratio. The derrick may be movable as a unit or piece-by-piece (e.g., to be assembled and disassembled).

[0030] As an example, a winch may include a spool, a brake, a power source, and various auxiliary devices. The winch can controllably pay out and reel in a rope. The rope can be wound around a crown block and coupled to a traveling block to gain mechanical advantage in a "block and tackle" or "pulley" fashion. Paying out and reeling in the rope may cause the traveling block (e.g., and anything that may be suspended below it) to descend into or rise from the borehole. Paying out the rope may be powered by gravity, or by a motor, engine, or the like (e.g., an electric motor, a diesel engine, or the like).

[0031] As an example, a crown block can include a set of pulleys (e.g., sheaves) that can be located at or near the top of a derrick or mast, through which a rope passes. A traveling block can include a set of sheaves that can be moved up and down in the derrick or mast by passing a rope through the set of sheaves of the traveling block and the set of sheaves of the crown block. The crown block, the traveling block, and the ropes can form a pulley system for the derrick or mast that can enable heavy loads (e.g., drill strings, pipes, casing, liners, etc.) to be lifted out of or lowered into a borehole. As an example, the diameter of the rope can be about 1 cm to about 5 cm, such as a steel cable. By using a set of sheaves, such a rope can carry a heavier load than a rope that can support as a single strand.

[0032] As an example, a derrickman may be a member of a drilling rig crew who works on a platform attached to a derrick or mast. The derrick may include a docking station on which the derrickman may stand. As an example, such a docking station may be about 10 meters or more above the drill floor. In an operation known as pulling out of the hole (TOH), the derrickman may wear a safety harness that enables him to reach out from a working docking station (e.g., a second-story platform) to reach a pipe located at or near the center of the derrick or mast and throw a line around the pipe and pull it back to its storage location (e.g., a fingerboard), for example, until it is desired to return the pipe to the borehole. As an example, a drilling rig may include automated pipe handling equipment so that the derrickman controls the machinery rather than physically handling the pipe.

[0033] As an example, tripping a drill bit may refer to the act of pulling equipment out of a borehole and / or placing equipment into a borehole. As an example, the equipment may include a drill string, which may be pulled out of a hole and / or placed or replaced in a hole. As an example, tripping a drill bit may be performed when the drill bit has become dull or has otherwise ceased to effectively drill a well and is to be replaced.

[0034] Figure 2An example of a wellsite system 200 is shown (e.g., at a wellsite that may be onshore or offshore). As shown, the wellsite system 200 may include a mud tank 201 for holding mud and other materials (e.g., where the mud may be a drilling fluid); a suction line 203 that serves as an inlet to a mud pump 204 for pumping mud from the mud tank 201 so that the mud flows to a vibrating hose 206; a drawworks 207 for wind-in one or more drilling lines 212; a riser 208 that receives mud from the vibrating hose 206; a kelly hose 209 that receives mud from the riser 208; one or more goosenecks 210; a traveling block 211; and a crown block 213 for carrying the traveling block 211 via the one or more drilling lines 212 (e.g., see FIG. 1 ). Figure 1 Crane 173); derrick 214 (see e.g. Figure 1 201; a kelly 218 or top drive 240; a kelly drive bushing 219; a rotary table 220; a drill floor 221; a bellhos 222; one or more blowout preventers (BOPs) 223; a drill string 225; a drill bit 226; a casing head 227; and a flow tube 228 for conveying mud and other materials to, for example, a mud tank 201.

[0035] exist Figure 2 In the exemplary system of FIG. , a borehole 232 is formed in a subsurface formation 230 by rotary drilling; note that various exemplary embodiments may also use directional drilling.

[0036] like Figure 2 As shown in the example of FIG, a drill string 225 is suspended within the borehole 232 and has a drill string assembly 250 including a drill bit 226 at its lower end. As an example, the drill string assembly 250 may be a bottom hole assembly (BHA).

[0037] Wellsite system 200 can provide for the operation of drill string 225 and other operations. As shown, wellsite system 200 includes platform 211 and derrick 214 positioned above borehole 232. As described above, wellsite system 200 can include rotary table 220, with drill string 225 passing through an opening in rotary table 220.

[0038] like Figure 2As shown in the example of , the wellsite system 200 may include a kelly 218 and associated components, or a top drive 240 and associated components. Regarding the kelly example, the kelly 218 may be a square or hexagonal metal / alloy rod with a hole drilled therein to serve as a mud flow path. The kelly 218 may be used to transmit rotational motion from a rotary table 220 to a drill string 225 via a kelly drive bushing 219, while allowing the drill string 225 to be lowered or raised during rotation. The kelly 218 may pass through the kelly drive bushing 219, which may be driven by the rotary table 220. As an example, the rotary table 220 may include a main bushing operably coupled to the kelly drive bushing 219, such that rotation of the rotary table 220 rotates the kelly drive bushing 219 and, thereby, rotates the kelly 218. The kelly drive bushing 219 may include an interior profile that matches the exterior profile of the kelly 218 (eg, square, hexagonal, etc.); however, with slightly larger dimensions so that the kelly 218 can move freely up and down inside the kelly drive bushing 219 .

[0039] Regarding the top drive example, the top drive 240 can provide the functions performed by the kelly and rotary table. The top drive 240 can rotate the drill string 225. As an example, the top drive 240 can include one or more motors (e.g., electric motors and / or hydraulic motors) connected to a short pipe section called a casing shaft through an appropriate transmission, which in turn can be screwed into a saver sub or the drill string 225 itself. The top drive 240 can be suspended from the traveling block 211 so that the rotating mechanism can freely travel up and down the derrick 214. As an example, the top drive 240 can allow drilling to be performed using more joint columns than the kelly / rotary table method.

[0040] exist Figure 2 In the example of , mud tank 201 can hold mud, which can be one or more types of drilling fluids. As an example, a wellbore can be drilled to produce fluids, inject fluids, or both (e.g., hydrocarbons, minerals, water, etc.).

[0041] exist Figure 2In the example of FIG. 2 , a drill string 225 (e.g., including one or more downhole tools) can be composed of a series of pipes threaded together to form a long tube with a drill bit 226 located at its lower end. As the drill string 225 is advanced into the wellbore for drilling, mud can be pumped from a mud tank 201 (e.g., or other source) by a pump 204 via lines 206, 208, and 209 to ports of a kelly 218, or, for example, to ports of a top drive 240, at some point prior to or concurrently with drilling. The mud can then flow through a channel (e.g., or multiple channels) in the drill string 225 and out of a port located on the drill bit 226 (see, e.g., directional arrows). When the mud exits the drill string 225 via the port in the drill bit 226, it can then circulate upward through the annular region between the outer surface of the drill string 225 and the surrounding wall (e.g., an open borehole, casing, etc.), as indicated by the directional arrows. In this manner, the mud lubricates the drill bit 226 and carries heat energy (e.g., friction or other energy) and formation cuttings to the surface, where the mud (e.g., and cuttings) can be returned to the mud tank 201, e.g., for recirculation (e.g., by processing to remove cuttings, etc.).

[0042] The mud pumped into the drill string 225 by the pump 204 can form a mud cake that lines the wellbore after leaving the drill string 225. Among other functions, the mud cake can reduce the friction between the drill string 225 and the surrounding wall (e.g., borehole, casing, etc.). The reduction in friction can facilitate the advancement or retraction of the drill string 225. During the drilling operation, the entire drill string 225 can be pulled out of the wellbore and optionally replaced, for example, with a new or sharpened drill bit, a smaller diameter drill string, etc. As described above, the action of pulling the drill string out of the hole or replacing the drill string in the hole is called tripping. Depending on the tripping direction, tripping can be referred to as tripping up or tripping out, or as tripping down or tripping in.

[0043] As an example, consider drilling down, where, when 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 for drilling to enlarge the wellbore. As described above, the mud can be pumped by the pump 204 into the channel of the drill string 225, and when filling the channel, the mud can be used as a transmission medium to transmit energy, for example, energy that can encode information as in mud pulse telemetry.

[0044] As an example, a mud pulse telemetry device may include a downhole device configured to implement pressure changes in the mud to generate one or more acoustic waves that can modulate information. In such an example, information from the downhole device (e.g., one or more modules of the drill string 225) can be transmitted uphole to the uphole device, which can relay such information to other equipment for processing, control, etc.

[0045] As an example, the telemetry equipment may operate via energy transmission via the drill string 225 itself. For example, consider a signal generator that transmits a coded energy signal to the drill string 225 and a repeater that can receive this energy and repeat it to further transmit the coded energy signal (e.g., information, etc.).

[0046] As an example, the drill string 225 may be equipped with a telemetry device 252, the telemetry device 252 including a rotatable drive shaft, a turbine wheel, a modulator rotor, a modulator stator, and a controllable brake, wherein the turbine wheel is mechanically coupled to the drive shaft such that mud can cause the turbine wheel to rotate, the modulator rotor is mechanically coupled to the drive shaft such that rotation of the turbine wheel causes the modulator rotor to rotate, the modulator stator is mounted adjacent to or proximate the modulator rotor such that rotation of the modulator rotor relative to the modulator stator generates pressure pulses in the mud, and the controllable brake is configured to selectively brake rotation of the modulator rotor to modulate the pressure pulses. In such an example, an alternator may be coupled to the drive shaft, wherein the alternator includes at least one stator winding electrically coupled to a control circuit for selectively short-circuiting the at least one stator winding to electromagnetically brake the alternator, thereby selectively braking rotation of the modulator rotor to modulate the pressure pulses in the mud.

[0047] exist Figure 2 In an example, the uphole control and / or data acquisition system 262 may include circuitry for sensing pressure pulses generated by the telemetry device 252 and transmitting the sensed pressure pulses or information derived therefrom for processing, control, etc., for example.

[0048] The assembly 250 of the illustrated example includes a logging while drilling (LWD) module 254 (e.g., an LWD tool), a measurement while drilling (MWD) module 256 (e.g., an MWD tool), optional modules 258, a rotary steerable system (RSS) and / or motor 260, and a drill bit 226. Such components or modules may be referred to as tools, where a drill string may include multiple tools.

[0049] As for RSS, it relates to techniques used for directional drilling. Directional drilling involves drilling into the earth to form a deviated borehole so that the trajectory of the borehole is not vertical; instead, the trajectory deviates from the vertical along one or more portions of the borehole. As an example, consider a target located at a lateral distance from a surface location where a drilling rig can be parked. In such an example, the borehole can be started from the vertical portion and then deviated from the vertical portion so that the borehole is aimed at the target and ultimately reaches the target. Directional drilling can be implemented where the target may not be accessible from a vertical position at the earth's surface, where there are materials in the earth that may hinder drilling or are otherwise harmful (e.g., consider salt domes, etc.), where the formations extend laterally (e.g., consider relatively thin but laterally extending reservoirs), where multiple boreholes are to be drilled from a single surface borehole, where relief wells are required, etc.

[0050] One method of directional drilling involves a mud motor; however, mud motors can present challenges depending on factors such as rate of penetration (ROP), weight transfer to the drill bit due to friction (e.g., weight on bit, WOB), etc. The mud motor can be a positive displacement motor (PDM), which operates to drive the drill bit (e.g., during directional drilling, etc.). The PDM operates when drilling fluid is pumped through the PDM, where the PDM converts the hydraulic power of the drilling fluid into mechanical power to rotate the drill bit.

[0051] As an example, the PDM may be operated in a combined rotation mode, wherein surface equipment is used to rotate the drill bit of the drill string by rotating the entire drill string (e.g., a rotary table, a top drive, etc.), and wherein drilling fluid is used to rotate the drill bit of the drill string. In such an example, the surface RPM (SRPM) may be determined using the surface equipment, and the downhole RPM of the mud motor may be determined using various factors related to the flow of drilling fluid, the type of mud motor, etc. As an example, in the combined rotation mode, assuming that the SRPM and the mud motor RPM are in the same direction, the drill bit RPM may be determined or estimated as the sum of the SRPM and the mud motor RPM.

[0052] For example, when the drill string is not rotating from the surface to drive the drill bit in a specific cutting direction, the PDM mud motor can operate in a so-called sliding mode. In such an example, the drill bit RPM can be determined or estimated based on the RPM of the mud motor. For example, during sliding mode, oscillation of the drill string can be provided by surface equipment, for example, to cause the drill string to oscillate in clockwise and counterclockwise directions, which can, for example, help reduce the risk of stuck pipe.

[0053] An RSS can be used for directional drilling, where there is continuous rotation from surface equipment, which can mitigate slippage of a steerable motor (e.g., a PDM). An RSS can be deployed when directional drilling (e.g., deviated, horizontal, or extended reach). An RSS can be designed to minimize interaction with the borehole wall, which can help maintain borehole quality. An RSS can be designed to apply a relatively consistent lateral force similar to a stabilizer that rotates with the drill string or orients the drill bit in the desired direction while continuously rotating at the same RPM as the drill string.

[0054] The LWD module 254 can be housed in a suitable type of drill collar and can include one or more selected types of logging tools. It will also be understood that more than one LWD and / or MWD module can be employed. Where reference is made to the location of a module, this may refer to a module at the location of the LWD module 254, the MWD module 256, and so forth, as examples. The LWD module may include capabilities for measuring, processing, and storing information, as well as for communicating with surface equipment. In the example shown, the LWD module 254 may include a seismic measurement device.

[0055] The MWD module 256 can be housed in a suitable type of drill collar and can include one or more devices for measuring characteristics of the drill string 225 and the drill bit 226. By way of example, the MWD module 256 can include a device for generating electrical power, e.g., to power various components of the drill string 225. By way of example, the MWD module 256 can include telemetry equipment 252, e.g., where a turbine wheel can generate electrical power from the flow of mud; it will be appreciated that other power sources and / or battery systems can be employed to power the various components. By way of example, the MWD module 256 can include one or more of the following types of measurement devices: a weight-on-bit measurement device, a torque measurement device, a vibration measurement device, a shock measurement device, a stick-slip measurement device, a direction measurement device, and an inclination measurement device.

[0056] Figure 2 Also shown are some examples of the types of holes that can be drilled. For example, consider an angled hole 272, an S-shaped hole 274, a deep angled hole 276, and a horizontal hole 278.

[0057] As an example, the drilling operation may include directional drilling, where, for example, at least a portion of the well includes a curved axis. For example, consider a radius defining a curvature, where the inclination relative to the vertical may vary until reaching an angle between about 30 degrees and about 60 degrees, or, for example, up to about 90 degrees or possibly greater than about 90 degrees.

[0058] As an example, a directional well can include several shapes, each of which can be designed to meet specific operational requirements. As an example, once the information is relayed to the drilling engineer, the drilling process can be performed based on the information. As an example, the inclination and / or direction can be modified based on the information received during the drilling process.

[0059] As an example, deviation of the borehole may be achieved in part by using one or more of an RSS, a downhole motor, and / or a turbine.With respect to motors, for example, the drill string may include a positive displacement motor (PDM).

[0060] As an example, the system can be a steerable system and include equipment for performing methods such as geosteering. As an example, the steerable system can include a PDM or a turbine on the lower portion of the drill string, and a bent sub can be installed just above the drill bit. As an example, above the PDM, a MWD device and / or a LWD device can be installed, the MWD device providing real-time or near-real-time data of interest (e.g., inclination, direction, pressure, temperature, actual bit weight, torque stress, etc.). With respect to 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.).

[0061] The coupling of sensors that provide real-time or near real-time information about the progress of the wellbore trajectory with one or more well logs that, for example, characterize the formation from a geological perspective, can enable geosteering methods. Such methods can include navigating a subsurface environment, for example, to follow a desired route to reach one or more desired targets.

[0062] As an example, a drill string may include an azimuthal density neutron (ADN) tool for measuring density and porosity; an MWD tool for measuring inclination, azimuth, and shock; a compensated dual resistivity (CDR) tool for measuring resistivity and gamma-ray related phenomena; one or more variable gauge stabilizers; one or more bend joints; and a geosteering tool, which may include a motor and, optionally, equipment for measuring and / or responding to one or more of inclination, resistivity, and gamma-ray related phenomena.

[0063] As an example, geosteering may include intentionally directionally controlling a wellbore based on results of downhole geological logging measurements in a manner intended to maintain the directional wellbore within a desired area, zone (e.g., a pay zone), etc. As an example, geosteering may include directing the wellbore to maintain the wellbore in a specific section of a reservoir, e.g., to minimize gas and / or water breakthrough, and e.g., to maximize economic production from a well including the wellbore.

[0064] Reference again Figure 2, the wellsite system 200 may include one or more sensors 264 operably coupled to the control and / or data acquisition system 262. As an example, the one or more sensors may be at a surface location. As an example, the one or more sensors may be at a downhole location. As an example, the one or more sensors may be located at one or more remote locations that are not within a distance of about one hundred meters from the wellsite system 200. As an example, the one or more sensors may be at an offset wellsite in a common field (e.g., an oil field and / or a gas field) between the wellsite system 200 and the offset wellsite.

[0065] As an example, one or more of sensors 264 may be provided for tracking pipes, tracking movement of at least a portion of a drill string, etc.

[0066] As an example, system 200 may include one or more sensors 266 that can sense signals and / or transmit signals to a fluid conduit, such as a drilling fluid conduit (e.g., a drilling mud conduit). For example, in system 200, one or more sensors 266 may be operably connected to a portion of riser 208 through which mud flows. As an example, a downhole tool may generate pulses that travel through the mud and are sensed by one or more of the one or more sensors 266. In such an example, the downhole tool may include associated circuitry, such as, for example, an encoding circuit that can encode the signal, for example, to reduce the need for transmission. As an example, the circuitry at the surface may include a decoding circuit to decode encoded information transmitted at least in part via mud pulse telemetry. As an example, the circuitry at the surface may include an encoder circuit and / or a decoder circuit, and the downhole circuitry may include an encoder circuit and / or a decoder circuit. As an example, system 200 may include a transmitter that can generate a signal that can be transmitted downhole via mud (e.g., drilling fluid) as a transmission medium.

[0067] As an example, one or more portions of the drill string may be stuck. The term stuck may refer to varying degrees of inability to move the drill string or remove one or more of the drill string from the borehole. As an example, in a stuck condition, the pipe may be rotated or returned to the borehole, or, for example, in a stuck condition, the drill string may not be able to be moved axially in the borehole, although some rotation may be possible. As an example, in a stuck condition, at least a portion of the drill string may not be able to be moved axially and rotationally.

[0068] Regarding the term "stuck pipe," the term can refer to a portion of a drill string that is unable to rotate or move axially. By way of example, a condition known as "differential pressure sticking" can be a condition in which the drill string is unable to move (e.g., rotate or reciprocate) along the axis of the borehole. Differential pressure sticking can occur when high contact forces, caused by low reservoir pressure, high wellbore pressure, or both, are applied to a sufficiently large area of ​​the drill string. Differential pressure sticking can have both time and financial costs.

[0069] As an example, the sticking force can be the product of the pressure differential between the wellbore and the reservoir and the area over which the pressure differential acts. This means that a relatively low pressure differential (ΔP) applied over a large working area can be just as effective in sticking pipe as a high pressure differential applied over a small area.

[0070] As an example, a condition referred to as "mechanical sticking" may be a condition that occurs by a mechanism other than differential pressure sticking that restricts or prevents movement of the drill string. Mechanical sticking may be caused by, for example, one or more of trash in the hole, abnormal wellbore geometry, cement, key seat, or accumulation of drill cuttings in the annulus.

[0071] Various types of data associated with oilfield operations can be 1-D series data. For example, consider data regarding one or more of drilling systems, downhole conditions, formation properties, and surface mechanics measured as single-channel or multi-channel time series data.

[0072] Figure 3 An example of a drilling fluid system 300 is shown that may be intended to provide various operations, which may include one or more of the following: removing drill cuttings from a well, controlling formation pressure, pausing and releasing drill cuttings, sealing permeable formations, maintaining wellbore stability, minimizing formation damage, cooling, lubricating, and supporting the drill bit and drilling components, transmitting hydraulic energy to one or more downhole tools and / or the drill bit, ensuring adequate formation evaluation, controlling corrosion, facilitating cementing and completions, preventing gas hydrate formation, and minimizing environmental impact.

[0073] like Figure 3 As shown in the example of FIG, system 300 may include a return line 310 and a discharge line 390 (see also, e.g., Figure 2 Pipelines, tubes, hoses, etc. 206, 208, 209, 210 and 228). Figure 3In an example, the system 300 may include a shaker 322, a desander 324, a desilter 326, and a degasser 328 associated with various mud pits 320 (e.g., mud tanks). The mud pits 320 may receive drilling fluid via return lines 310 and output processed drilling fluid to active pits 332. The active pits 332 may be in fluid communication with a suction pit 334 and a standby pit 336. The suction pit 334 may be in fluid communication with a pump 350 that may pump the drilling fluid to a discharge line 390. As an example, one or more mixing units 342 may be included, for example, to add one or more materials to the drilling fluid before it is pumped to the discharge line 390.

[0074] As an example, the system 300 can be used for one or more types of operations, which may include drilling, wireline, completion, blowout control, etc. With respect to completion, as an example, cementing operations may include pumping and / or receiving drilling fluid, where cement may be positioned between the casing and the borehole wall.

[0075] As an example, one could use Figure 2 System 200, Figure 3 One or more of the components of the system 300, etc., retrieve drill cuttings at the surface. Drill cuttings can be generated when rock is broken by a drill bit advancing through an underground environment. As explained, the drill cuttings can be carried to the surface by a drilling fluid (e.g., mud) circulated from one or more openings in the tool string (e.g., openings in the drill bit of the drill string). The drill cuttings can be separated from the fluid using one or more types of equipment (such as, for example, shale shakers, centrifuges, cyclones, etc.). In wireline tool drilling, the drill cuttings can be periodically fished out from the bottom of the borehole. In auger drilling, the drill cuttings can be transported to the surface on the auger spiral.

[0076] As explained, during drilling activities, a particular type of fluid may be injected from the surface through the drill pipe to the bottom of the borehole, where the fluid circulates back to the surface, as may be driven by injection pressure (e.g., a mud pump, etc.). While there may be situations involving lost circulation, where a portion or all of the drilling fluid may be adversely lost to the formation (e.g., via fractures, faults, etc.), during normal drilling, some smaller amounts of drilling fluid may be lost through filtration along with some suspended matter, which may form a cake (e.g., filter cake) along the borehole wall. Filter cake may be the residue that is deposited on a permeable medium when a slurry (e.g., drilling fluid) is forced against the medium under pressure. Filtrate may refer to the liquid that passes through the medium, leaving a filter cake on the medium. Drilling fluids may be tested to determine filtration rate and filter cake properties. Filter cake properties (such as filter cake thickness, toughness, smoothness, and permeability) may be relevant because filter cake formed on permeable areas in the borehole may lead to stuck pipe and / or one or more other types of drilling problems. Some degree of filter cake accumulation may be desirable to isolate the formation from the drilling fluid. In open hole completions in high angle or horizontal wells, the formation of an external filter cake may be more beneficial than a filter cake that forms partially within the formation, as the latter may have a higher potential for formation damage.

[0077] In contrast, lost circulation generally refers to a reduction or complete absence of fluid flow through the annulus as fluid is pumped through a tool string (e.g., drill pipe, etc.). Although definitions may vary among operators, a reduction in flow may be classified as a seepage (e.g., less than 20 bbl / hr or 3 m3 / s). 3 / hr), return of some losses (for example, greater than 20bbl / hr or 3m 3 / hr, but still some return) and total loss of return (e.g., no fluid coming out of the annulus). In the latter severe case, the hole may not fill with fluid even if the pump is turned off. If the hole does not remain full of fluid, the vertical height of the fluid column can be reduced, and the pressure exerted on the open formation can be reduced. In turn, this can lead to another area flowing into the wellbore while the lost circulation area is receiving mud, or even a catastrophic loss of well control. Even in the two less severe forms, the loss of fluid to the formation represents a loss of hazardous material with associated risks.

[0078] Figure 4 An example of a workflow 400 related to drill cuttings is shown. Figure 4In the example of , workflow 400 includes various actions such as, for example, sample collection 410, sample preparation 420, photograph acquisition 440, compression and transport 450, and photograph analysis 460. As explained, during normal operation, rock crushed by a rotating drill bit can be transported to the surface, for example, to a shale shaker. The drill cuttings can be separated by the shale shaker so that liquids and other components can be reused (e.g., circulated downhole). The drill cuttings, such as rock particles, can be analyzed by a mud logging instrument operating in a mud logging unit. Such analysis tends to rely on having one or more people in the loop (HITL). As an example, the system can provide automation that can reduce the need to include one or more people on site in the logging unit. For example, the system can provide automation of the workflow for drill cuttings analysis.

[0079] As an example, a workflow can include sample collection, where drill cuttings (e.g., rock particles) are collected from a vibrator, and sample preparation, where the rock particles can be dried in an oven for, for example, analysis, or using other drying techniques. As an example, the rock particles can be screened using one or more screens to select particles that fall within a specific range or multiple ranges. In various cases, the screened rock particles can be specifically referred to as drill cuttings. As an example, the size of the one or more grids can be approximately 0.25 mm to approximately 3 mm for the lower and upper limits, respectively. As an example, the drill cuttings (e.g., screened particles) can be placed in a tray. In various cases, the tray can be prepared by a person, where the distribution of the particles can be effectively random; for example, the particles can be touching or piled up in some areas of the tray and can be sparsely distributed in other areas. With respect to photography, the tray can be placed in front of a camera lens, where photo acquisition can be performed using visible white light and UV lighting (e.g., UV lamp, UV LED, etc.). As an example, to improve differentiation, the acquisition phase of UV irradiation can include more than one captured image, for example, at one or more UV wavelengths (e.g., short UV light, long UV light, etc.) that are known to produce fluorescence, which can be associated with the presence of hydrocarbons and / or the presence of certain minerals. As an example, photography can be performed at an oil field site, where digital images (whether raw and / or processed) can be sent to one or more destinations that may be remote from the oil field site. As an example, the digital images can be compressed using one or more compression techniques (e.g., lossless, lossy, etc.), which can facilitate transmission, particularly where transmission can be via a satellite network (e.g., considering remote locations, offshore drilling rigs, etc.), which can have low and / or expensive bandwidth. As an example, a geologist can be present at a location, whether local and / or remote, for analysis purposes. As an example, the analysis can be aimed at extracting geologically meaningful information from the drill cuttings images.

[0080] As an example, the system may be a multispectral imaging system for rock characterization. For example, consider a dual-spectral imaging system that includes at least one emission source in the ultraviolet (UV) spectrum. In such an example, the other emission source may be in the visible spectrum. As an example, the system may be a dual-spectral imaging system for rock characterization. As an example, the workflow may include performing one or more actions for calibrating the multispectral imaging system for rock characterization.

[0081] As an example, the system can be an advanced imaging system that includes components for automating one or more aspects of a rock characterization workflow for applications such as environmental applications, industrial applications, and the like. As an example, such a system can include multiple emission sources for implementing multispectral techniques. For example, consider a dual-spectral technique that can include direct absorption of white light for color and texture analysis and UV-induced fluorescence for hydrocarbon identification; note that UV-induced fluorescence can also provide characterization of one or more types of minerals.

[0082] As an example, so-called cut fluorescence can be performed. In such an example, cut can refer to the oil released from the drill cuttings when a solvent is added. Common solvents for inducing cuts can be vinyl chloride (e.g., 1,1,1-trichloroethane); note that others can include acetone, petroleum ether, alcohol, hot water, and acids. Various solvents are flammable, so care needs to be taken to handle the material safely. As an example, cutting can be performed while observing the rock sample under both normal light and UV light. Solvent cuts can allow deductions of phenomena such as, for example, oil mobility and reservoir permeability. As an example, cuts can be described based on their natural color, fluorescent color, "release" rate and intensity, and residue. Cut fluorescence of suspected hydrocarbon-bearing intervals can be analyzed; it should be noted that in various examples, there may be a positive cut fluorescence test when other hydrocarbon detection methods have failed.

[0083] As an example, fluorescence scanning can provide non-destructive, qualitative and quantitative results, which can be obtained from drill cuttings and / or cores. As an example, steady-state fluorescence spectroscopy can be used to determine the polycyclic aromatic hydrocarbon (PAH) content and / or other hydrocarbon content of oil. With respect to PAH content, due to their relatively high boiling points, PAHs tend to reside in rocks for several years, such that air exposure under standard conditions may not have a substantial impact on the ability to detect the presence of PAHs.

[0084] As explained, hydrocarbons can fluoresce when exposed to UV radiation. Aromatic hydrocarbons (AH), due to their aromatic structure and conjugated double bonds, exhibit intrinsic fluorescence in the ultraviolet-visible (UV-vis) region. Therefore, various hydrocarbon types, either on their own or in organic solvents, emit light at wavelengths longer than the excitation light. Furthermore, AH is often a prominent fluorescent component in petroleum and, depending on the environment, can dominate the fluorescence spectrum. Hydrocarbon fluids containing different AH groups can exhibit different fluorescence characteristics.

[0085] As an example, the multispectral system can be applied to the analysis of drill cuttings and / or one or more other types of samples. For example, consider core analysis, water-hydrocarbon fluid analysis, drilling fluid analysis, etc.

[0086] As an example, to meet the requirements of multispectral applications, the system can be an integrated optical system that achieves wide field of view and ultra-high resolution imaging. Such a system can be optimized to enhance image sharpness and color accuracy for white light imaging and provide high contrast for ultraviolet fluorescence imaging with relatively short exposure times.

[0087] As examples, the system may provide high-resolution imaging, UV fluorescence, machine vision, rock description generation, and oil-indicative identification of drill cuttings (eg, wellbore cuttings).

[0088] As explained, a mud logging tool can perform mud logging, which involves collecting fragments of drilled rock, known as drill cuttings, during drilling operations, which can then be prepared (e.g., rinsed and dried) and examined under a binocular microscope. Such detailed inspection involves the mud logging tool describing characteristics such as lithology, texture, color, grain size, and other relevant physical properties. However, even under a microscope, identifying the presence of hydrocarbons within the pores of drill cuttings can pose substantial challenges.

[0089] As explained, hydrocarbons can fluoresce in response to exposure to UV radiation. As an example, a system can provide improved mud logging by exposing drill cuttings to UV radiation and capturing images that can include fluorescent markers. As an example, a system can provide for examining drill cuttings (e.g., a sample or a sample of drill cuttings) under UV light and evaluating fluorescence, for example, in one or more aspects of color, intensity, and distribution. As explained, a system can provide automation, which can reduce the need for mud logging instruments to utilize conventional fluoroscopes and visually evaluate such characteristics. However, the human eye can be limited and can characterize fluorescence inconsistently. For example, for one or more reasons, one or more people may not consistently characterize the color of fluorescence. As an example, a system can provide a relatively consistent assessment of fluorescence color, which can be in a manner that provides increased automation and reduces reliance on subjective human visual observation and description.

[0090] As an example, the color of the fluorescence can provide qualitative information about the oil type (eg, hydrocarbon composition, etc.).As an example, the system can provide for the application of an advanced UV spectroscopic technique known as quantitative fluorescence technology (QFT), which enables quantitative assessment of oil measurements.

[0091] QFT provides a measurement of the fluorescence of crude oil extracted from a formation sample, where the intensity of the fluorescence is proportional to the amount of oil in the sample. An enhanced technique known as QFT2 can provide improved estimates of oil quantity and properties based on measurements made on drill cuttings or core samples. Such a technique can employ two-point fluorescence measurements that produce estimates of both quantity (weight % oil) and oil type (API gravity). As an example, the results can be combined with cable hydrocarbon porosity data to estimate the volume percent of oil in the formation, and the resulting data can be further evaluated to estimate oil mobility.

[0092] While various petrophysical analyses and well testing workflows are performed to definitively establish commercially relevant oil volumes, mud logging tools retain the responsibility of reporting and logging hydrocarbon indications early in the drilling process. For example, a system can provide advanced UV fluorescence technology that can be implemented at the wellsite, for example, as part of a dual-spectral imaging workflow. This approach can utilize advanced imaging techniques, combining direct white light absorption for color and texture analysis with UV-induced fluorescence for hydrocarbon identification. This integration of imaging technologies can be designed to overcome various challenges facing today's mud logging tools. For example, a system can provide a comprehensive and automated solution to enhance the consistency and efficiency of rock characterization during drilling operations.

[0093] As explained, a multispectral system can be a dual-spectral system for imaging samples for one or more types of geological applications. This integrated system for both white and UV imaging can reduce the need for separate setups and help ensure a seamless transition between imaging processes. For example, simultaneous data collection from both imaging techniques can be performed to produce a comprehensive dataset, ultimately improving the accuracy and uniformity of rock characterization.

[0094] As an example, the system can employ white light imaging to perform rock color and texture analysis. Sedimentary rocks tend to be the most common rock type in oil fields and are often classified largely based on their texture. As an example, the system can integrate a machine learning-driven texture recognition framework that provides enhanced reliability of the drilling cuttings characterization process at the well site. Implementing such a system on a relatively large scale requires the ability to acquire sufficiently high-resolution, consistent, and information-rich image datasets. Such datasets can be referred to as training datasets, which can, for example, be used for training and / or testing and / or tuning (e.g., hyperparameter tuning) of one or more machine learning (ML) models.

[0095] As an example, a system can include integrated components and features that prioritize simplicity, cost-effectiveness, and consistent image quality for rock texture analysis. For example, consider a system that can streamline workflow, with relatively fast setup and calibration, rapid image acquisition, and real-time high-quality image transmission. Such a system can be designed to achieve relatively high resolution and sharp focus of rock drill cuttings, for example, considering drill cuttings in a size range from about 25 microns to about 3 mm. As an example, one or more types and / or sizes of nets can be used to perform one or more processes to extract drill cuttings of a desired size or sizes from a drilling fluid. As an example, a system can be transportable and rugged to withstand wellsite deployment while remaining resilient to vibration and / or other wellsite conditions.

[0096] As an example, a system may include a digital microscope including a machine vision lens attached to a high-resolution machine vision camera connected to a portable computing device for image calibration and acquisition purposes.

[0097] Figure 5 An example of a system 500 is shown as an approximate CAD rendering. As shown, the system 500 may include a housing or casing 502, one or more handles 504, a cavity within the housing or casing 502 including a sample holder 510, an imaging unit 520, and one or more illumination sources 530 and 550. The system 500 may include a digital microscope illuminated by an LED illuminator with a temperature of 6500K.

[0098] like Figure 5 As shown, system 500 may include circuitry 580, which may include one or more interfaces, one or more processors, memory, etc. Circuitry 580 may be embedded in or operably coupled to components or assemblies within housing or casing 502. As an example, a real-time view image may be generated and presented to a display 590 (e.g., consider a 21-inch display monitor to simplify sample inspection). System 500 may be deployed at a well site to perform a drill cuttings characterization workflow at the well site. Such a system may include a high-resolution camera and multiple LED lighting, for example, for white light and UV light (e.g., consider illumination source 530 for white light and illumination source 550 for UV light). Such a system may include handles, lockable doors, etc., which may facilitate transportation of one or more individuals (e.g., for loading in a vehicle, cart, etc.). Such a system may include one or more interfaces for storage and / or transmission of digital data (e.g., digital image data) via media, networks, wires, optical fibers, etc. As an example, such a system may include one or more processors and associated memory, which may store instructions executable to perform one or more actions. As an example, such a system may include a controller, which may be processor-based.

[0099] As an example, system 500 may include a white light source (see, e.g., illumination source 530 ); an ultraviolet light source (see, e.g., illumination source 550 ); a digital machine vision camera (see, e.g., imaging unit 520 ) for capturing images of a rock drill cuttings sample illuminated by the white light source and the ultraviolet light source; and circuitry (see, e.g., circuitry 580 ) operable to generate a calibrated image of the rock drill cuttings sample, wherein a contrast is present between the rock drill cuttings sample containing hydrocarbons and the rock drill cuttings sample not containing hydrocarbons. In such an example, the image may be stored, processed, transmitted, displayed, etc. For example, consider presenting the image to display 590 , whether as raw, processed, compressed, decompressed, etc. As an example, the processing may involve the implementation of one or more machine learning models. In such an example, the results may be output and used to control one or more operations, which may include one or more field operations, such as may be associated with drilling (e.g., crushing rock with a drill bit).

[0100] As explained, the system can provide UV fluorescence imaging for oil indication identification. Even under a microscope, the presence of hydrocarbons within drill cuttings holes can present a challenge to identify (e.g., presence or absence). In addressing this challenge, one or more UV fluorescence techniques can be employed, which can be within the context of drilling operations.

[0101] At the well site, drill cuttings samples can be tested for hydrocarbons. For example, the sample can initially be examined under UV light. In such an example, the sample fluorescence can be evaluated in terms of color, intensity, and distribution. As mentioned above, this is typically a human-based process that relies on human visual observation by the mud logging tool using a conventional fluoroscope. While petrophysical analysis combined with well testing can provide a conclusive determination of the presence of commercial quantities of oil, the mud logging tool's responsibility remains to report and log hydrocarbon indications.

[0102] Figure 6 An example of a UV fluoroscope system 600 based on human observation is shown, along with image 610 of what a human would see when a sample is subjected to UV radiation. In image 610, fluorescence occurs under the UV light provided by fluoroscope system 600, with mineral fluorescence, frequently seen in rock samples, shown in the leftmost portion of the image. In the center of image 610, induced fluorescence can be observed, such as can be produced by immersing an oil-containing sample in a solvent. For example, once the solvent evaporates, the residual oil can produce a distinct fluorescent ring on the glass surface of the sample, as can be seen in the rightmost portion of image 610.

[0103] In the process of fluorescence, UV energy can be temporarily absorbed by a material and then emitted as lower energy radiation, for example, in the visible region. Figure 6 The conventional fluoroscope system shown, as commonly used in basic mud logging, provides an eyepiece window to observe the interaction of high power UV radiation and drill cuttings. Such manually operated and human observation-based fluoroscopes tend to suffer from various problems. While external cameras can be added to such fluoroscopes, the fluoroscopes themselves provide images that are typically weak in contrast, which tend to have limited utility. For example, such images may be poor candidates for use in a dataset for performing machine learning (e.g., training, testing, tuning, etc.). Various machine learning techniques can benefit from quality datasets, which can provide better trained machine learning models, whether through training, testing, tuning, etc. Poor quality data can complicate the generation of a trained machine learning model and may provide less than acceptable output.

[0104] As explained, the system may include one or more machine learning models, wherein, for example, relatively high-quality data may be used to train such one or more machine learning models (e.g., for training, testing, and / or tuning). As an example, the data may provide a reliable application of one or more machine learning tools to detect oil in drilled cuttings.

[0105] With respect to conventional UV fluoroscope systems, these may utilize one or more UV emitters that may pose one or more risks. For example, consider tube or bulb based emitters, which may require large amounts of energy, involve hazardous materials and / or generate radiation in excess of desired levels, which can sometimes be difficult to control (e.g., with respect to heat generation, radiation volume, and risk of radiation leakage, etc.). Conventional UV lamps typically use between 5 mg and 200 mg of mercury per lamp. Such UV lamps tend to require regular replacement and, at the same time, are susceptible to breakage during shipping, handling, and operation. Lamp based emitters may not be very robust to wellsite conditions and, in general, are not very robust to handling by individuals who are typically equipped with personal protective equipment, which can make handling such fragile lamp based devices challenging and fraught with risk. As explained, various lamps are mercury based, such that the mercury may escape upon rupture, which can pose a risk in either a closed or non-closed environment.

[0106] As an example, the system can include a digital imaging component that provides substantial advantages over visual inspection and recording of oil fluorescence. As an example, the system can include a UV imaging subsystem designed to overcome various aspects of traditional fluoroscopes to provide a reliable solution for oil show identification in oil fields.

[0107] As an example, the system can be one that has undergone component and component integration optimization. Addressing the dual-spectral requirements for achieving high-resolution white imaging and high-contrast UV fluorescence in high-resolution imaging involves discerning selection of components such as light sources, cameras, and associated lenses. Below, various aspects of the nuanced decision-making process underlying this selection are described, aiming to achieve seamless integration that meets the specific requirements of each of the visible and UV imaging modalities.

[0108] As explained, UV light sources tend to be lamp-based (e.g., bulbs or tubes) that rely on ionized mercury emission, with high-pressure mercury producing a primary peak at 365 nm (UVA region) and low-pressure mercury emitting primarily at 254 nm (UVC region). For UV fluorescence applications, LED technology can be an alternative, offering more compact form factors, extended lifespans (e.g., up to 20,000 hours), low power consumption, flexible operating modes (continuous or pulsed), improved thermodynamics, and the like. Regarding thermal aspects, lamp-based methods can emit thermal energy, which requires substantial consideration of how much heat is transferred to the sample. For example, the thermal energy transferred to the sample can cause a temperature increase, which can be challenging to control. In contrast, UV LEDs can be more easily controlled, for example, using digital technology, where thermal issues can be more easily addressed. For example, UV LEDs can be adjusted more quickly than UV lamps, which can require heating and / or cooling times that can stress the glass or the tube or bulb (e.g., increasing the risk of breakage).

[0109] With respect to the wavelength of UV radiation, it can be considered to be limited to a wavelength range of about 10 nm to about 400 nm, which can be divided into multiple bands, such as: UVA (e.g., about 315 nm to about 400 nm); UVB (e.g., about 280 nm to about 315 nm); and UVC (e.g., about 100 to about 280 nm). In various cases, the near-UV region, which is closest to visible light, can be defined as including wavelengths between about 200 nm and about 400 nm. The higher energy, shorter wavelength far-UV region can be defined as spanning wavelengths between about 91 nm and about 200 nm. With respect to the visible band, it can be defined as ranging from about 380 nm to about 800 nm.

[0110] As explained, fluorescence spectroscopy techniques are useful in the oil industry. When exposed to UV light, some individual components of crude oil fluoresce within a well-defined wavelength range (e.g., about 275 nm to about 550 nm); note that emission can be in both the UV and visible bands.

[0111] Fluorescence spectroscopy can involve the fluorescence of aromatic hydrocarbons when irradiated with UV light. During the irradiation, aromatic molecules absorb UV energy and immediately re-emit light at a longer wavelength, where this re-emission is called fluorescence. At the molecular level, fluorescence involves atoms and molecules changing their energy levels when excited by high-energy UV light. Electrons in molecules can exist in a specific set of energy levels. As a result of the so-called Coulomb interaction between protons and orbiting electrons, electrons can remain in their lowest-energy orbitals. When these electrons are excited by UV light, they are elevated to a higher, less stable energy level. Once elevated, the electron tends to fall back to its original, more stable energy level, releasing energy by emitting a photon. This electronic transition and emission from a higher to a lower energy state is called fluorescence emission.

[0112] As an example, the difference between excitation and emission can be noted. For example, the difference between the excitation (e.g., at 250 nm) and emission (e.g., at 275 nm to 550 nm) wavelengths can be referred to as the Stokes shift. Specific hydrocarbon compounds can be identified by the magnitude of their Stokes shift. In general, as the number of aromatic rings increases, the fluorescence response may shift to longer wavelengths. Thus, lighter compounds tend to fluoresce at shorter wavelengths, while heavier compounds fluoresce at longer wavelengths. For some examples of aromatic hydrocarbons, consider benzene, ethylbenzene, naphthalene, anthracene, chrysene, and benzo(a)pyrene; note that various other hydrocarbons may fluoresce when exposed to UV radiation.

[0113] Table 1 below shows some examples of emission intensities from various materials, including minerals (e.g., sand) and hydrocarbons. In various examples, fluorescence inspection can be applied to detect the presence of hydrocarbons that may be associated with potential spills, leaks, etc. (e.g., spills on sand, spills in water, etc.). As explained, in different contexts, fluorescence inspection can be applied to drill cuttings, for example, to determine whether the drill cuttings include hydrocarbons. In some cases, certain minerals in the drill cuttings may fluoresce, a phenomenon that may cause the minerals to glow in the visible spectrum when exposed to UV; such minerals may be referred to as fluorescent minerals. Fluorescent minerals contain particles called activators in their structure that respond to UV light by emitting a visible glow. In various examples, the system can provide a method for distinguishing mineral emissions from hydrocarbon emissions and / or otherwise explaining mineral phenomena that may be associated with exposure to UV light.

[0114] Table 1 Examples of samples and fluorescence emission

[0115]

[0116] As an example, a system can include one or more UV LEDs. In such an example, such one or more UV LEDs can be suitable for machine vision applications and can be combined with controller technology and, for example, waterproof protection or otherwise integrated. Such an approach can help ensure stable illumination in a manner that is relatively immune to external light interference, even during rapid processes. As an example, the system can employ functional accessories and advanced connectivity concepts to facilitate seamless integration of LED light sources into digital imaging platforms.

[0117] like Figure 5 As shown, the optical system design developed for lithologic characterization can have a considerable working distance (e.g., greater than 100 mm), allowing both a white light source and a UV light source to be incorporated into the optical column. Given the need for quasi-monochromatic UV light with minimal visible-range emission for UV fluorescence, the system can integrate one or more filters, such as optical bandpass filters. As an example, an optical bandpass filter can have a transmission band surrounded by two blocking bands that allow only a portion of the spectrum to pass. To absorb visible light output, UV light for machine vision can integrate a UV filter that transmits broadband UVA with a peak transmission at 365 nm.

[0118] Figure 7 An example graph 700 is shown that provides a comparison of the spectral selectivity of typical commercial UV filters. Specifically, graph 700 provides a comparison of the transmission curves of three different commercial UV filters designed to improve the spectral purity of LED UV light emitted at 365 nm. High spectral selectivity can generally be associated with a decrease in UV light intensity compared to unfiltered light. To address the requirements for spectral purity and high intensity necessary for UV fluorescence, a custom LED lamp design covering the entire imaging field of view (FOV) can be included in a system such as a Figure 5 This approach integrates high-performance LEDs with various optical systems to produce high-power irradiance precisely aligned with the target FOV.

[0119] As explained, the system can include a machine vision camera. When capturing UV-induced visible fluorescence, digital imaging provides significant advantages over visual inspection using the naked eye. The exposure time of a digital camera (e.g., in the range of a few seconds, etc.) tends to be affected by the low intensity of the visible light being imaged. However, unlike the limitations of the human eye, a digital camera provides precise control over exposure time. A digital camera provides significantly enhanced control over color accuracy. As an example, the system can provide a selection of exposure time that is carefully made to amplify image brightness while minimizing color saturation, thereby preventing loss of essential color information.

[0120] Compared to high-resolution professional photography cameras (DSLRs), machine vision cameras tend to be characterized by their compact size and cost-effectiveness, which can provide advantages. Seamless integration into a system can be facilitated by the ease of interfacing. Additionally, improved reliability (such as can be attributed to the reduced number of moving parts or the absence of moving parts) makes machine vision cameras particularly suitable for applications where robust operation is an advantage. The flexibility of machine vision cameras can include compatibility with one or more optical standards (such as, for example, C-mounts), thereby enhancing adaptability within various settings.

[0121] While modern CMOS sensors in digital cameras exhibit some inherent sensitivity to UVA, various cameras feature effective UV filtering on the sensor, which can be referred to as a Bayer filter. In various examples, the Bayer filter can be grown / deposited directly onto the sensor. While Bayer filters are mentioned, as an example, one or more Foveon sensors can be employed that can capture UV data (e.g., near-UV, etc.) as well as other data, including visible light.

[0122] Various types of digital cameras may not require additional filtering for satisfactory fluorescence photography. However, in some cases, residual leakage or insufficient UV illumination may require the use of additional camera filtering to distinguish emitted fluorescence.

[0123] Figure 8 Examples of digital machine vision cameras 810 and 820 are shown, along with their spectral responses, labeled B for blue, G for green, and R for red. Specifically, the MV18MP camera 810 exhibits superior UVA light filtering efficiency compared to the MV20MP camera 820, as shown by the camera sensor's lowest quantum efficiency value at 400 nm (i.e., the blue filter). As shown, the quantum efficiency of camera 810 at approximately 400 nm is approximately 20%, while the quantum efficiency of camera 820 at approximately 400 nm is approximately 40%. Therefore, camera 820 may be more susceptible to reflected UV light when compared to camera 810.

[0124] As an example, a system can be designed to facilitate seamless integration of UV fluorescence into a white light digital microscope. To achieve this, the system can include a machine vision camera that can provide minimal need for additional filtering. Again, Figure 8 The spectral responses of the Bayer filters from two high-resolution cameras: MV18MP camera 810 and MV20MP camera 820 are shown, where the MV18MP camera 810 has more effective UVA filtering than the MV20MP camera 820 based on the quantum efficiency value at 400 nm.

[0125] Given the selection of an appropriate machine vision camera, a suitable machine vision lens can be selected for inclusion in a bispectral imaging system.

[0126] Figure 9 Examples of machine vision lenses 910 are shown (e.g., perspective, end, and side views) along with examples of specular reflections of UV light and diffuse reflections of visible light. Lens 910 can be a CCTV-type lens that can provide control over lens zoom (iris) and focus adjustment (e.g., manually and / or by a machine). When performing rock texture analysis, optimization of optical resolution is a concern. Such optimization can involve carefully balancing lens aberrations and diffraction effects caused by the aperture. Thus, the lens numerical aperture can be configured to F / 4 to meet the criteria for white light imaging. This approach can be consistent with the primary goal of maximizing system resolution to capture subtle variations in rock texture.

[0127] For UV fluorescence applications, it may be preferable to select a higher numerical aperture (e.g., F / 8 or higher), for example, by closing the camera diaphragm to limit the impact of reflected UV light. The emitted visible fluorescence can exhibit isotropic behavior and can be approximated by Lambert's law of emission. Since the reflected UV light is governed by specular reflection rules that depend on the relative orientation of the sample surface and the UV light, strategic adjustments can involve increasing the UV light orientation angle (e.g., exceeding approximately 45° from the imaging axis) and / or simultaneously reducing the lens aperture (e.g., F / 8 or higher). This approach can effectively limit the detection of reflected UV light while facilitating the collection of a sufficient portion of the emitted UV-induced visible light.

[0128] As for aperture, it relates to the amount of light that can reach the sensor plane. In various examples, it may be desirable to collect as much light as possible, which can help reduce exposure time, which can increase throughput, reduce vibration effects, and so on. However, a larger aperture stop may also require larger diameter optics, which can be heavier and more expensive. Aperture can also affect the characteristics of an optical system. For example, the size of the aperture stop's opening is a factor influencing DOF (depth of field). A smaller aperture stop (larger f-number or F-number) produces a longer (deeper) DOF because it only allows a smaller-angle cone of light to reach the image plane (e.g., the sensor plane), thereby reducing the spread of the image of the object point. A longer (deeper) DOF allows objects at a wide range of distances from the viewpoint to be in focus simultaneously. In contrast, a larger aperture stop (smaller f-number or F-number) has a shorter (shallower) DOF. The aperture stop can also limit the effects of optical aberrations by restricting light from reaching the edges of the optics, where aberrations can be stronger than at the center. If the aperture (e.g., diameter) of the stop is too large, the image may be distorted by stronger aberrations. In various examples, the optical system may include features (e.g., hardware and / or software) that can mitigate some of the effects of aberrations (e.g., allowing for a larger aperture, and therefore greater light-gathering capability, if desired). The stop can also determine whether the image will be vignetted. A larger stop (smaller f-number or F-number) can cause the light intensity reaching the film or detector to drop off toward the edges of the image plane, particularly when, for off-axis points, a different stop becomes the aperture stop by blocking more light than an on-axis aperture stop. The stop position can also determine telecentricity. For example, if the aperture stop of a lens is located at the front focal plane of the lens, it becomes image-space telecentric, i.e., the lateral size of the image is insensitive to image plane position; however, if the stop is at the back focal plane of the lens, it becomes object-space telecentric, where the image size is insensitive to object plane position. Telecentricity facilitates accurate two-dimensional measurements, as telecentric measurement systems tend to be less sensitive to axial position errors of the sample or sensor. In various examples, a lens may have one or more field stops that can limit the FOV. For example, when the FOV is limited by a field stop in the lens (e.g., rather than at the sensor), vignetting may result, which can be problematic if the resulting field of view is smaller than desired.

[0129] As an example, one or more alternative approaches may include selecting a camera with low sensitivity to UV radiation, such as the MV18MP camera 810, while keeping the aperture open to enhance optical resolution and reduce exposure time. Such an approach may allow for a unified hardware configuration that caters to both white light and UV fluorescence applications, thereby simplifying both hardware and software setup for convenient field deployment. With respect to depth of field (DOF), as explained, the sample may be presented on a tray where the size of the individual flakes in the sample may be relatively small. For example, consider a scenario where the largest individual flake may have a size (e.g., longest dimension) of approximately 3 mm. Thus, a DOF sufficient for such a size may be related to aperture selection and, for example, the ability to achieve acceptable focus. As explained, the aperture may be selected with respect to exposure time, which may be shortened where the aperture is selected to allow more light to pass to the sensor of the digital machine vision camera.

[0130] As explained, machine vision lenses can be selected that include aperture control. As explained, the comparison between UV light excitation controlled by specular reflectance and visible fluorescence emission controlled by diffuse reflectance can facilitate selecting the incident light direction and lens aperture in a manner that allows fluorescence to be preferentially emitted over UV light excitation, optionally in conjunction with employing spectral filtering techniques.

[0131] Figure 10 An example system 1000 including selected components for white light and UV light is shown, wherein the system 1000 is used to perform verification testing regarding UV image quality. As shown, the system 1000 can include a sample tray or holder 1010, an imaging unit 1020, a white light illumination source 1030, a UV light illumination source 1050, and a column or stage 1040, which can include a base 1041, an upright portion 1042, and a cross member 1044. In such an example, various components of the column or stage 1040 can be movable or adjustable, which can be done manually and / or by one or more motors, pneumatics, hydraulics, etc. As mentioned, the system can include a controller that can provide control of one or more components, which can be used for operational and / or spatial control.

[0132] like Figure 10As shown in the example of , system 1000 may include circuitry that may include one or more processors, memory, etc. As an example, system 1000 may include battery 1085 as a power source. For example, consider one or more types of chemical batteries (e.g., lead (Pb), lithium ion, etc.). As an example, an interface of system 1000 may provide for the reception of electrical power (e.g., electric power). As an example, the system may include solar cells so that it can be powered by the sun. As an example, the system may include solar cells within a chamber (e.g., a cavity) that may be capable of recapture energy that may be emitted by one or more illumination sources.

[0133] As explained, suitable UV image quality can enhance the application of one or more machine learning techniques or processes. As an example, the system can include one or more computing frameworks for executing instructions, which can involve machine learning, implementation of trained machine learning models, etc. As an example, one or more models can provide image classification and / or image segmentation and / or one or more other functions. As an example, one or more models can provide processing of images captured using one or more types of lighting.

[0134] As explained, system 1000 may include various components integrated therein, such as multiple white LEDs and multiple UV LEDs. System 1000 may utilize a UV LED light source with a peak wavelength centered at 365 nm and a colored glass bandpass filter centered at the same wavelength. As explained, UV radiation (excitation) interacts with drill cuttings and excites the electrons of fluorophores in crude oil, resulting in emission primarily in the visible region of the electromagnetic spectrum. The fluorescence spectrum of crude oil typically consists of a broadband in the visible region. The broadband comes from overlapping emissions of different fluorophores present in the sample. System 1000 may use a CMOS image sensor to capture visible photons from sample fluorescence (emission).

[0135] As explained, the system can include a white light digital microscope with a custom UV strip light with UV filters. Within the UV LED light source, the selected UV bandpass filter can block visible photons from the tail end of the spectrum and thus reduce the potential overlap between reflected visible light and UV-induced fluorescence and the captured fluorescence image.

[0136] As an example, a system may provide for reducing the effects of ambient light, such as by performing measurements in a dark box (eg, covering the device with an opaque optical housing, etc.).

[0137] Figure 11Example images 1110 and 1120 of white light and UV light images of a mixture of dry (oil-free) drill cuttings and oil-bearing drill cuttings using a machine vision camera are shown. Specifically, the images are of a mixture of sandstone rock under white light and UV light, with the left side of each image depicting an oil-bearing condition (e.g., with oil) and the right side showing a dry state without oil (e.g., without oil).

[0138] In images 1110 and 1120, a mixture of drill cuttings of different colors was used to test the variability of drill cutting samples on the UV fluorescence system. The UV image of pixels with dry drill cuttings, as imaged by the system, appears dark, and the rocky cuttings are invisible. In contrast, pixels with oil-bearing cuttings are bright and luminescent. Longer exposure times or higher UV powers simply saturate the detector and do not affect the contrast between oil-bearing and oil-free cuttings. The high contrast improves the ability to quickly identify oil-bearing cuttings and ensures better image quality than that of conventional camera-equipped fluoroscopes, such as those used in mud logging tool workflows.

[0139] As shown, sufficient contrast levels can be obtained, which can provide improved machine learning. As an example, contrast can also provide an assessment of intensity, where, for example, the intensity level can be used to determine one or more characteristics (e.g., concentration of hydrocarbons, type of hydrocarbons, etc.). Thus, a method such as Figure 5 The system 500 can provide for the generation of data suitable for training one or more types of machine learning models.

[0140] As an example, the system can provide UV image calibration, for example, with respect to white balance and brightness control. Currently, there is no standard white balance method, nor a practical objective procedure for achieving precise color accuracy in UV-induced fluorescence imaging. Standard white balance settings recommended by camera manufacturers for white light imaging calibration are often the initial recommendation. Final determination of color can be performed by comparing the image displayed on a profile monitor with the actual appearance of the object under UV illumination. As an example, the system can provide captured images that provide fluorescence with substantially enhanced clarity and color intensity, which also exceeds what the human eye can perceive due to observing very low-intensity fluorescence emissions.

[0141] As an example, a workflow can include a calibration process. For example, consider the following: (1) select a fine sandstone sample to limit the influence of irregular sample shape; (2) saturate approximately half of the rock sample with light oil or diesel; (3) take an image of the UV-irradiated sample with maximum intensity; (4) select two uniform regions of interest in the oil-saturated sample and the original sample; (5) calculate the average brightness value for each region; and (6) adjust the camera exposure to achieve a high brightness value (L*>20) in the oil-saturated region.

[0142] As an example, once the optimal settings are determined, the same settings can be used for the UV source and camera to standardize them for fluorescence imaging. To avoid diesel evaporation and preserve calibration samples for longer periods of time, a single standard plate can be created to serve as a quality control item for the fluorescence imaging system at the well site. As an example, the system can be used with one or more quality control items (e.g., plates, etc.).

[0143] As explained, the system was applied to evaluate both hydrocarbon-bearing and hydrocarbon-free rocks. Various aspects were considered when selecting system components, for example, based on the results of UV fluorescence imaging using various filters and cameras. This selection process provided insight into the performance of the UV fluorescence imaging subsystem and facilitated the selection of adequate optical components.

[0144] Figure 12 Example results 1200 are shown, specifically, a comparison of UV fluorescence images acquired using a UV LED lamp with two different UV filters (Filter #1 and Filter #2) and two machine vision cameras (MV18MP and MV20MP). As an example, the method can include analyzing a fluorescence contrast parameter, expressed as a ratio (R), which can be derived from the brightness (L) of the oil-containing and non-oil-containing regions of interest. * )value:

[0145]

[0146] As an example, the low ratio values ​​observed with the tested filters demonstrate the excellent fluorescence contrast achieved with customized UV LED light (e.g., UV light with filter # 2). This customized UV light provides a narrow bandpass selection around the central LED wavelength (365 nm) and minimizes the amount of emitted visible light (wavelengths above 400 nm) from the excitation source, which could otherwise degrade the UV excitation source.

[0147] Alternatively, use the selected UV illumination equipped with filter #2, such as Figure 12 The results show a comparison between two different machine vision cameras: the MV18MP and MV20MP, each associated with an optimal lens configuration for enhancing UV fluorescence contrast (R < 0.3). While the results in UV fluorescence imaging are comparable, the MV18MP camera demonstrates superior performance in white light imaging. The associated imaging system effectively optimizes image resolution and mitigates the effects of diffraction caused by the lens aperture (e.g., it can be aperture-dependent). Furthermore, the MV18MP camera outperforms the MV20MP camera in UVA filtering capabilities, making it a suitable choice for the efficient design of dual-spectral systems.

[0148] As explained, the system can be a multispectral system suitable for obtaining images for white and UV illumination. Such a system can be a UV fluorescence system for mud logging, for example, to perform UV fluorescence spectroscopy on samples that may or may not include hydrocarbons (e.g., crude oil, etc.). The difference in wavelength and direction between the emitted and excitation radiation allows for efficient design of such fluorescence systems, effectively reducing the detection of the UV incident beam (excitation) and thereby achieving increased sensitivity to the fluorescence (emission).

[0149] By employing digital imaging, substantial enhancements can be achieved compared to current oil exhibition workflows that rely on the human eye to detect UV fluorescence. Notably, careful selection of camera models, combined with Bayer filters to block residual reflected UV light and the use of UV LEDs equipped with high-efficiency UV bandpass filters to offset any remaining emitted visible light, contribute to the optimization of fluorescence contrast.

[0150] As explained, the example system demonstrates that acceptable UV fluorescence contrast can be obtained by utilizing a machine vision UV light customized to integrate a bandpass UV filter and combined with a machine vision camera with minimal sensitivity to UV light.

[0151] As an example, a dual-spectral imaging system that meets the requirements of both white light and UV fluorescence imaging may also be suitable for field deployment (eg, at a well site) for application in rock characterization workflows in the oil and gas industry.

[0152] Figure 13 An example of a method 1300 is shown, including an illumination block 1310 for illuminating a drill cuttings sample with white light and ultraviolet light; a capture block 1320 for capturing an image of the rock drill cuttings sample; and a characterization block 1330 for characterizing the rock drill cuttings sample based at least in part on physical characteristics derived from the image and at least in part on fluorescence emissions derived from the image. In such an example, the method 1300 may include a determination block 1340 for determining whether the rock drill cuttings sample contains hydrocarbons or does not contain hydrocarbons.

[0153] Figure 13 Also shown are various computer-readable media (CRM) blocks 1311, 1321, 1331, and 1341. Such blocks may include instructions that can be executed by one or more processors, which may be one or more processors of a computing framework, system, computer, etc. A computer-readable medium may be a computer-readable storage medium that is not a signal, is not a carrier wave, and is non-transitory. For example, a computer-readable medium may be a physical memory component that can store information in a digital format.

[0154] exist Figure 13In the example of , system 1390 includes one or more information storage devices 1391, one or more computers 1392, one or more networks 1395, and instructions 1396. With respect to the one or more computers 1392, each computer may include one or more processors (e.g., or processing cores) 1393 and a memory 1394 for storing instructions 1396, for example, executable by at least one of the one or more processors. As an example, a computer may include one or more network interfaces (e.g., wired or wireless), one or more graphics cards, a display interface (e.g., wired or wireless), etc. System 1390 may be specifically configured to perform Figure 13 One or more portions of method 1300.

[0155] As an example, the system can employ one or more machine learning models. For example, consider one or more trained machine learning models that can receive images of rock drill cuttings and output at least an indication of the presence or absence of hydrocarbons. In such an example, the one or more trained machine learning models can provide for outputting one or more characteristics of the rock drill cuttings, which can be physical characteristics. For example, consider one or more of rock type (e.g., with classification), color, texture (e.g., grain size, roundness, sorting), cement and / or matrix material, fossils, sedimentary structure, porosity, etc. As an example, oil indication can be considered a fluorescence-based characteristic.

[0156] As an example, the system can be operated to capture images, where a single image can provide information about physical properties and hydrocarbons. As an example, the system can be operated using one or more techniques that can provide digital control of a white light source and / or a UV light source. For example, consider pulsing, where pulses can be controlled. In various instances, separate images can be acquired, where one type of image can be without UV illumination and another type of image can be with UV illumination. As explained, the system can provide simultaneous white light and UV illumination to generate a single image of a rock cutting sample for the purpose of determining the physical properties and presence of hydrocarbons, which can include determining the type of hydrocarbons and / or the composition of the hydrocarbons.

[0157] As an example, the system can provide determinations regarding one or more of contaminants, metals, drilling additives, lost circulation materials (LCM), suspected cave material, drilled formation rock cuttings, etc. For example, consider a sample that can be prepared in one or more ways, which can be a raw sample and / or a processed sample. As explained, a machine learning-based approach can be employed to make one or more types of determinations regarding a sample collected from a drilling fluid (e.g., and / or raw drilling fluid, etc.). As an example, the output of the system can be in the form of one or more well logs, which can include an estimate of the percentage of each rock type, an interpretation of the lithology, the presence and / or type / composition of hydrocarbons, etc.

[0158] As explained, the system can provide for the generation of training data that can be used for one or more of training, testing, tuning, etc., of one or more machine learning models. As explained, the system can provide for the generation of images that can have a suitably high contrast between the absence of hydrocarbons in a sample and the presence of hydrocarbons in the sample. Such images can provide robust training to allow for the generation of trained machine learning models that can improve automation, consistency, etc.

[0159] As an example, one or more image analysis machine learning models can be employed. As an example, a U-Net-type machine learning model can be employed. U-Net is an architecture that can be used for various tasks (e.g., semantic segmentation, etc.). It can include a contracting path and an expanding path, where the contracting path follows the architecture of a convolutional network. It can provide repeated applications of two 3x3 convolutions (unpadded convolutions), each followed by a rectified linear unit (ReLU) and a 2x2 max pooling operation with stride 2 for downsampling. In such an example, the number of feature channels can be doubled at each downsampling step. As an example, each step in the expanding path can provide upsampling of the feature map, followed by a 2x2 convolution ("upconvolution") that halves the number of feature channels, concatenated with a corresponding cropped feature map from the contracting path, and two 3x3 convolutions, each followed by a ReLU. As an example, cropping can be employed due to the loss of border pixels in each convolution. As an example, at the final layer, a 1x1 convolution can be used to map each 64-component feature vector to the desired number of classes. As an example, the total network may include 23 convolutional layers. As explained, one or more models may be used for one or more tasks, which may include, for example, one or more of classification and segmentation. As an example, a model may provide feedback that can be used to instruct the system. For example, consider a model that can provide the generation of parameters for one or more settings of a system, which may include settings such as position, imaging, and lighting.

[0160] Regarding the type of machine learning model, consider one or more of a support vector machine (SVM) model, a k-nearest neighbor (KNN) model, an ensemble classifier model, a neural network (NN) model, etc. As an example, the machine learning model can be a deep learning model (e.g., a deep Boltzmann machine, a deep belief network, a convolutional neural network, a stacked autoencoder, etc.), an ensemble model (e.g., a random forest, a gradient boosting machine, bootstrap aggregation, adaptive boosting (AdaBoost), stacked generalization, a gradient boosted regression tree, etc.), a neural network model (e.g., a radial basis function network, a perceptron, backpropagation, a Hopfield network, etc.), a regularization model (e.g., a ridge regression, a least absolute shrinkage and selection operator, an elastic net, a least angle regression), a rule system model (e.g., a cubic, a one rule, a zero rule, repeated incremental pruning to produce error reduction), a regression model (e.g., a linear regression, an ordinary least squares regression, a stepwise regression, a multivariate adaptive regression spline, a local estimation scatter plot smoothing, a logistic regression, etc.) , Bayesian models (e.g., naive Bayes, average dependency estimator, Bayesian belief network, Gaussian naive Bayes, multinomial naive Bayes, Bayesian network), decision tree models (e.g., classification and regression trees, iterative bisection3, C4.5, C5.0, chi-square automatic interaction detection, decision stump, conditional decision tree, M5), dimensionality reduction models (e.g., principal component analysis, partial least squares regression, Sammon map, multidimensional scaling, projection pursuit, principal component regression, partial least squares discriminant analysis, mixture discriminant analysis, quadratic discriminant analysis, regularized discriminant analysis, flexible discriminant analysis, linear discriminant analysis, etc.), instance models (e.g., k-nearest neighbors, learning vector quantization, self-organizing map, local weighted learning, etc.), clustering models (e.g., k-means, k-median, expectation maximization, hierarchical clustering, etc.), etc.

[0161] As an example, a computing framework with libraries, toolboxes, etc. can be used to build a machine model that can be a machine learning model (ML model), such as those of 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 (SVMs), boosted and bagged decision trees, k-nearest neighbors (KNNs), k-means, k-centers, 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 to perform classification and regression on image, time series, and text data. DLT includes features for building network architectures such as generative adversarial networks (GANs) and Siamese networks using custom training loops, shared weights, and automatic differentiation. DLT provides model exchange for various other frameworks.

[0162] As an example, TENSORFLOW framework (Google LLC, Mountain View, California) can be implemented, which is an open source software library for data flow programming, which includes a symbolic math library, which can be implemented for machine learning applications that can include a neural network. As an example, CAFFE framework can be implemented, which is a DL framework developed by Berkeley AI Research (BAIR) (University of California, Berkeley). As another example, consider SCIKIT platform (e.g., scikit-learn), which utilizes PYTHON programming language. As an example, a framework such as APOLLO AI framework (APOLLO.AI GmbH, Germany) can be utilized. As an example, a framework such as PYTORCH framework (Facebook AI Research Lab (FAR), Facebook, Inc., Menlo Park, California) can be utilized.

[0163] As an example, a training method can include various actions that can be performed on a dataset to train an ML model. As an example, a dataset can be split into training data and test data, where the test data can be provided for evaluation. The method can include cross-validation of parameters and optimal parameters, which can be provided for model training.

[0164] The TENSORFLOW framework can run on multiple CPUs and GPUs (with optional CUDA (NVIDIA Corp., Santa Clara, CA) and SYCL (The Khronos Group Inc., Beaverton, OR) extensions for general-purpose computing on graphics processing units (GPUs). TENSORFLOW is available on 64-bit Linux, macOS (Apple Inc., Cupertino, CA), Windows (Microsoft Corp., Redmond, WA), and mobile computing platforms, including Android (Google LLC, Mountain View, CA) and iOS (Apple Inc.) operating system-based platforms.

[0165] Tensorflow computations can be represented as stateful data flow graphs; note that the name Tensorflow comes from the operations that this neural network performs on multidimensional arrays of data. Such arrays can be called "tensors."

[0166] As an example, the device can utilize Tensorflow Lite (TFL) or another type of lightweight framework. TFL is a set of tools that enables on-device machine learning, where models can run on mobile devices, embedded devices, and IoT devices. TFL is optimized for on-device machine learning by addressing latency (no round trip to the server), privacy (no personal data leaves the device), connectivity (requires internet connectivity), size (simplified model and binary size), and power consumption (e.g., efficient inference and lack of network connection). TFL includes support for multiple platforms, covering Android and iOS devices, embedded Linux and microcontrollers, and support for multiple languages, including Java, Swift, Objective-C, C++, and Python. TFL provides high performance with hardware acceleration and model optimization.

[0167] As an example, a system may include a white light source; an ultraviolet light source; a digital machine vision camera configured to capture images of a rock drill cutting sample illuminated by the white light source and the ultraviolet light source; and circuitry operable to generate a calibration image of the rock drill cutting sample, the calibration image having a contrast between the rock drill cutting sample containing hydrocarbons and the rock drill cutting sample not containing hydrocarbons. In such an example, the ultraviolet light source may be or include an ultraviolet LED.

[0168] As an example, an arrangement of a source and a digital machine vision camera can provide for reducing detection of an incident UV light beam from a UV light source to achieve enhanced sensitivity to fluorescent emissions of hydrocarbons from a hydrocarbon-bearing rock cuttings sample. In such an example, the arrangement can include one or more Bayer filters to block the digital machine vision camera from capturing residual reflected UV light from the incident UV light beam.

[0169] As an example, the system may include one or more UV pass filters. For example, consider one or more UV pass filters forming a UV bandpass filter.

[0170] As an example, a system can include a trained machine learning model, e.g., via circuitry operable to process an image. As an example, such an image can be a calibration image from a calibration system, which can include one or more calibration features (e.g., a source, a filter, a sensor, etc.).

[0171] As an example, the circuitry may include a processor and memory accessible to the processor and an interface for receiving digital data from a digital machine vision camera.

[0172] As an example, the system's ultraviolet light source may have an orientation angle equal to or greater than 45 degrees relative to the imaging axis of the digital machine vision camera.

[0173] As an example, a system may include a digital machine vision camera having a lens with a lens aperture size less than or equal to F / 4.

[0174] As an example, a digital machine vision camera may have a quantum efficiency of less than 50% at 400 nm. In such an example, a quantum efficiency of less than 50% at 400 nm may reduce the impact of reflected ultraviolet light on the image. As an example, a digital machine vision camera may have a quantum efficiency of less than 40% at 400 nm. In such an example, the digital machine vision camera may include a lens having a lens aperture of F / 4.

[0175] As an example, a system may include circuitry that utilizes a fluorescence contrast parameter. In such an example, the fluorescence contrast parameter may be derived from brightness values ​​of a hydrocarbon-containing rock cuttings sample and a non-hydrocarbon-containing rock cuttings sample. In such an example, the fluorescence contrast parameter may be a ratio of the brightness value of the non-hydrocarbon-containing rock cuttings sample to the brightness value of the hydrocarbon-containing rock cuttings sample.

[0176] As an example, a method may include illuminating a rock drill cuttings sample with white light and ultraviolet light; capturing an image of the rock drill cuttings sample; and characterizing the rock drill cuttings sample based at least in part on physical properties derived from the image and at least in part on fluorescence emissions derived from the image. In such an example, characterizing may include determining whether the rock drill cuttings sample contains hydrocarbons or does not contain hydrocarbons.

[0177] As an example, one or more computer-readable storage media may include computer-executable instructions that are executable to instruct a computing system to: illuminate a rock drill cuttings sample with white light and ultraviolet light; capture an image of the rock drill cuttings sample; and characterize the rock drill cuttings sample based at least in part on physical properties derived from the image and at least in part on fluorescence emissions derived from the image.

[0178] As explained, the system can include one or more machine learning models, which can reside locally and / or remotely. As an example, the system can include a lightweight machine learning framework (e.g., TFL, etc.). As an example, the method can employ one or more machine learning models.

[0179] As an example, the method may be implemented in part using a computer-readable medium (CRM), for example, as a module, block, etc., which 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 at least partially allow the execution of various actions of the method. As an example, the computer-readable medium (CRM) may be a computer-readable storage medium (e.g., a non-transitory medium) that is not a carrier wave. As an example, a computer program product may include instructions suitable for execution by one or more processors (or processor cores), wherein the instructions may be executed to implement at least a portion of one or more methods.

[0180] According to an 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 output to a sensing process, an injection process, a drilling process, an extraction process, an extrusion process, a pumping process, a heating process, etc.

[0181] In some embodiments, one or more methods may be performed by a computing system. Figure 14 An example of a system 1400 is shown that may include one or more computing systems 1401-1, 1401-2, 1401-3, and 1401-4, which may be operably coupled via one or more networks 1409, which may include wired and / or wireless networks.

[0182] By way of example, a system may comprise a single computer system or an arrangement of distributed computer systems. Figure 14 In the example of , computer system 1401-1 may include one or more modules 1402, which may be or include processor-executable instructions, eg, executable to perform various tasks (eg, receive information, request information, process information, simulate, output information, etc.).

[0183] As an example, the modules can execute independently or in coordination with one or more processors 1404, which are operatively coupled to one or more storage media 1406 (e.g., via wired, wireless, etc.). As an example, one or more of the one or more processors 1404 can be operatively coupled to at least one of the one or more network interfaces 1407. In such an example, the computer system 1401-1 can, for example, send and / or receive information via one or more networks 1409 (e.g., considering one or more of the Internet, a private network, a cellular network, a satellite network, etc.). As shown, one or more other components 1408 can be included in the computer system 1401-1.

[0184] As an example, computer system 1401-1 can receive information from and / or send information to one or more other devices, which may be or include, for example, one or more of computer system 1401-2, etc. The devices may be located at a physical location different from the physical location of computer system 1401-1. As examples, the locations may be, for example, processing facility locations, data center locations (e.g., server farms, etc.), drilling rig locations, well site locations, downhole locations, etc.

[0185] 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 another control or computing device.

[0186] As an example, storage media 1406 can be implemented as one or more computer-readable or machine-readable storage media. As an example, storage can be distributed within and / or across multiple internal and / or external enclosures of the computing system and / or additional computing systems.

[0187] As an example, the one or more storage media may include one or more different forms of memory, including semiconductor memory 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 disks, floppy disks, and removable disks), other magnetic media (including magnetic tape), optical media (such as compact disks (CDs) or digital video disks (DVDs), Blu-ray discs or other types of optical storage), or other types of storage devices.

[0188] As an example, one or more storage media may be located in the machine running the machine-readable instructions, or at a remote site from which the machine-readable instructions may be downloaded over a network for execution.

[0189] As examples, various components of a system (such as, for example, a computer system) may be implemented in hardware, software, or a combination of both hardware and software (eg, including firmware), including one or more signal processing and / or application specific integrated circuits.

[0190] As an example, a system may include a processing device that may be or include a general purpose processor or a dedicated chip (eg, or chipset) such as an ASIC, FPGA, PLD, or other suitable device that may be or include circuitry.

[0191] As an example, the device can be a mobile device that includes one or more network interfaces for information communication. For example, the mobile device may include a wireless network interface (e.g., operable via IEEE 802.11, ETSI GSM, Bluetooth, satellite, etc.). As an example, the mobile device may include components such as a main processor, memory, a display, display graphics circuitry (e.g., optionally including touch and gesture circuitry), a SIM slot, audio / video circuitry, motion processing circuitry (e.g., accelerometer, gyroscope), wireless LAN circuitry, smart card circuitry, transmitter circuitry, GPS circuitry, and a battery. As an example, the mobile device can be configured as a cellular phone, a tablet computer, etc. As an example, the method can be implemented (e.g., in whole or in part) using a mobile device. As an example, the system can include one or more mobile devices.

[0192] 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 the purpose of data storage, communication, computing, etc. As an example, a device or system can include one or more components for communicating information via one or more of the Internet (e.g., where communication occurs via one or more Internet protocols), a cellular network, a satellite network, etc. As an example, the method can be implemented in a distributed environment (e.g., in whole or in part as a cloud-based service).

[0193] As an example, information can be input from a display (e.g., consider a touch screen), output to a display, or both. As an example, information can be output to a projector, a laser device, a printer, etc. so that the information can be viewed. As an example, information can be output stereoscopically or holographically. Regarding printers, consider 2D or 3D printers. As an example, a 3D printer can include one or more substances that can be output to construct a 3D object. For example, data can be provided to a 3D printer to construct a 3D representation of an underground stratum. As an example, a layer can be constructed in 3D (e.g., a horizon, etc.), a geological body can be constructed in 3D, etc. As an example, a hole, a crack, etc. can be constructed in 3D (e.g., as a positive structure, as a negative structure, etc.).

[0194] Although only a few examples have been described in detail above, those skilled in the art will readily appreciate that many modifications may be made in the examples. It is therefore intended that all such modifications be included within the scope of the present disclosure as defined in the appended claims. In the claims, means-plus-function clauses are intended to cover structures described herein as performing the recited function and to cover not only structural equivalents but also equivalent structures. Thus, although a nail and a screw may not be structural equivalents because a nail employs a cylindrical surface to fasten wooden parts together while a screw employs a helical surface, in the context of fastening wooden parts, a nail and a screw may be equivalent structures.

[0195] References (Documents incorporated herein by reference)

[0196] [1] Riecker, RE, "Hydrocarbon fluorescence and migration of petroleum," AAPG Bulletin 46(1), 60-75(1962).

[0197] [2] Reyes, MV, "Application of fluorescence techniques for mud-logging analysis of oil drilled with oil-based muds," SPE Formation Evaluation 9(04), 300-305(1994).

[0198] [3]Delaune,P.L.,Spilker,K.K.,Hanson,S.A.,Wright,A.C.,and Quagliaroli,R.,“Enhanced Wellsite Technique for Oil Detection and Characterization,”SPEAnnual Technical Conference and Exhibition,SPE-56802-MS(1999).

[0199] [4]Di Santo,S.,Yamada,T.,Bondabou,K.,and Ammar,M.,“The digitalrevolution in mudlogging:An innovative workflow for advanced analysis andclassification of drill cuttings using computer vision and machine-learning,”in[SEG International Exposition and Annual Meeting],SEG(2022).

[0200] [5]Liu,K.,Sherwood,N.,and Zhao,M.,“Advances in fluorescencespectroscopy for petroleum geosciences,”(2014).

[0201] [6]Mullins,O.C.,The Physics of Reservoir Fluids:Discovery ThroughDownhole Fluid Analysis,Schlumberger,Houston,TX(2008).

[0202] [7]Ablard,P.,Bell,C.,Cook,D.,Fornasier,I.,Poyet,J.-P.,Sharma,S.,Fielding,K.,Lawton,L.,Haines,G.,Herkommer,M.A.,et al.,“The expanding role ofmud logging,”Oilfield Review 24(1),24-41(2012).

Claims

1. A system (500, 1000), comprising: White light source (530,1030); UV light source (550, 1050); a digital machine vision camera (520, 1020) for capturing images of the rock cuttings sample illuminated by the white light source and the ultraviolet light source; and Circuitry (580, 1080) operable to generate a calibration image of a rock drill cuttings sample, the calibration image having a contrast between a rock drill cuttings sample containing hydrocarbons and a rock drill cuttings sample not containing hydrocarbons. The system of claim 1 , wherein the UV light source comprises a UV LED.

3. The system of claim 1 or 2, wherein the arrangement of the source and the digital machine vision camera reduces detection of an incident beam of UV light from the UV light source to achieve enhanced sensitivity to fluorescent emissions of hydrocarbons from a hydrocarbon-bearing rock cuttings sample, optionally wherein the arrangement includes one or more Bayer filters to block capture by the digital machine vision camera of residual reflected UV light from the incident beam of UV light.

4. A system according to any preceding claim, comprising one or more UV pass filters, optionally wherein the one or more UV pass filters form a UV band pass filter.

5. A system according to any preceding claim, comprising a trained machine learning model operable via the circuitry to process calibrated images.

6. A system according to any preceding claim, wherein the circuitry comprises a processor and a memory accessible to the processor and an interface to receive digital data from the digital machine vision camera.

7. The system of any preceding claim, wherein the ultraviolet light source comprises an orientation angle equal to or greater than 45 degrees relative to an imaging axis of the digital machine vision camera.

8. The system of any preceding claim, wherein the lens of the digital machine vision camera has a lens aperture size less than or equal to F / 4.

9. The system of any preceding claim, wherein the digital machine vision camera comprises a quantum efficiency of less than 50% at 400 nm, optionally wherein the quantum efficiency of less than 50% at 400 nm reduces the effect of reflected ultraviolet light on the image, and / or optionally wherein the digital machine vision camera comprises a quantum efficiency of less than 40% at 400 nm.

10. A system according to any preceding claim, wherein the circuit utilizes a fluorescence contrast parameter, optionally wherein the fluorescence contrast parameter is derived from brightness values ​​of a rock drill cutting sample containing hydrocarbons and a rock drill cutting sample not containing hydrocarbons, optionally wherein the fluorescence contrast parameter is a ratio of the brightness value of the rock drill cutting sample not containing hydrocarbons to the brightness value of the rock drill cutting sample containing hydrocarbons.

Images