Digital microscopy system for 3D objects

Abstract

A method may include acquiring, using a digital camera of a digital microscopy system, a digital image of an engineered three-dimensional object positioned on a base and illuminated by a light source; acquiring, using the digital camera, a digital image of a color inspection card positioned on the base and illuminated by the light source; determining a light source criterion by evaluating a position of the light source, the evaluation based at least in part on a shadow projected by the engineered three-dimensional object in the digital image of the engineered three-dimensional object and based at least in part on color saturation in the digital image of the color check card; and calibrating the digital microscopy system using the light source criteria to generate a calibrated digital microscopy system.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to European Patent Application No. 22306204.3 filed on August 9, 2022 and European Patent Application No. 22305361.2 filed on March 24, 2022. The contents of the above applications are incorporated herein by reference in their entirety. Background Art

[0003] A reservoir may be an underground formation that can be characterized at least in part by its porosity and fluid permeability. As an example, a reservoir may be part of a basin (such as a sedimentary basin). A basin may be a depression in which sediments accumulate (e.g., caused by plate tectonic activity, sedimentation, etc.). As an example, when source rocks are combined with appropriate burial depths and durations, a petroleum system may develop within the basin, thereby forming a reservoir including hydrocarbon fluids (e.g., oil, natural gas, etc.). Various operations may be performed on site to obtain such hydrocarbon fluids and / or produce such hydrocarbon fluids. For example, consider equipment operations, in which equipment may be controlled to perform one or more operations. In such an example, the control may be based at least in part on the properties of the rock, which may exist as a three-dimensional object in a drilling fluid (e.g., mud). Summary of the invention

[0004] A method may include using a digital camera of a digital microscopy system to acquire a digital image of an engineering three-dimensional object positioned on a base and illuminated by a light source; using the digital camera to acquire a digital image of a color check card positioned on the base and illuminated by the light source; determining a light source standard by evaluating a position of the light source, the evaluation being based at least in part on a shadow cast by the engineering three-dimensional object in the digital image of the engineering three-dimensional object and at least in part on a color saturation in the digital image of the color check card; and calibrating the digital microscopy system using the light source standard to generate a calibrated digital microscopy system. A system may include a digital camera; a light source; a processor; a memory accessible to the processor; and processor-executable instructions stored in the memory, the processor-executable instructions for instructing the system to: use the digital camera to acquire a digital image of an engineering three-dimensional object positioned on a base and illuminated by the light source; use the digital camera to acquire a digital image of a color check card positioned on the base and illuminated by the light source; and use at least the processor to determine a light source standard by evaluating the position of the light source, the evaluation based at least in part on a shadow cast by the engineering three-dimensional object in the digital image of the engineering three-dimensional object and at least in part on the color saturation in the digital image of the color check card. One or more non-transitory computer-readable storage media may include processor-executable instructions for instructing a computing system to: use the digital camera to acquire a digital image of an engineering three-dimensional object positioned on a base and illuminated by the light source; use the digital camera to acquire a digital image of a color check card positioned on the base and illuminated by the light source; and use at least the processor to determine a light source standard by evaluating the position of the light source, the evaluation based at least in part on a shadow cast by the engineering three-dimensional object in the digital image of the engineering three-dimensional object and at least in part on the color saturation in the digital image of the color check card. Various other devices, systems, methods, etc. are also disclosed.

[0005] This Summary is provided to introduce a selection of concepts that are further described below in the Detailed Description. This Summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used as an aid in limiting the scope of the claimed subject matter. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] The features and advantages of the described implementations may be more readily understood by referring to the following description in conjunction with the accompanying drawings.

[0007] Figure 1 An example system including various framework components associated with one or more geological environments is illustrated;

[0008] Figure 2Figure shows an example of a system;

[0009] Figure 3 Figures show examples of drilling equipment and examples of borehole shapes;

[0010] Figure 4 illustrates an example of a digital microscopy system, an example of a digital image, and an example of a method;

[0011] Figure 5 Figure 1 shows an example of a workflow;

[0012] Figure 6 An example of a graphical user interface is shown;

[0013] Figure 7 An example of a table of values ​​and an example of a grayscale image are shown;

[0014] Figure 8 An example of a table illustrating settings and techniques;

[0015] Fig. 9 An example of the method is shown;

[0016] Fig.10 An example of the method is shown;

[0017] Fig.11 An example of a method and an example of a system are illustrated;

[0018] Fig.12 illustrates examples of computers and network equipment; and

[0019] Fig.13 The diagrams illustrate example components of systems and networked systems. DETAILED DESCRIPTION

[0020] This description is not intended to be limiting but is made for the purpose of describing the general principles of implementations. Reference should be made to the issued claims to determine the scope of the described implementations.

[0021] Figure 1 An example of a system 100 is shown that includes a workspace framework 110 that can be used for instantiation, presentation, interaction with, etc. of a graphical user interface (GUI) 120. Figure 1 In the example of , GUI 120 may include graphical controls for a computing framework (eg, application) 121 , projects 122 , visualization 123 , one or more other features 124 , data access 125 , and data storage 126 .

[0022] exist Figure 1In the example of , the workspace framework 110 may be customized for a specific geological environment (such as the example geological environment 150). For example, the geological environment 150 may include multiple layers (e.g., stratification) that include a reservoir 151 and may intersect a fault 153. As an example, the geological environment 150 may be equipped with various sensors, detectors, actuators, and the like. For example, equipment 152 may include communication circuits for receiving and transmitting information relative to one or more networks 155. Such information may include information associated with downhole equipment 154, which may be equipment for obtaining information, assisting in resource recovery, and the like. Other equipment 156 may be located at a location remote from the well site and include sensing, detection, transmission, or other circuits. Such equipment may include storage and communication circuits for storing and transmitting data, instructions, and the like. As an example, one or more satellites may be provided for purposes of communication, data acquisition, and the like. For example, Figure 1 A satellite is shown in communication with a network 155 that may be configured for communication, noting that the satellite may additionally or alternatively include circuitry for imaging (eg, spatial, spectral, temporal, radioactive, etc.).

[0023] Figure 1 The geological environment 150 is also shown as optionally including equipment 157 and 158 associated with a well, the well including a substantially horizontal portion that may intersect one or more fractures 159. For example, consider a well in a shale formation, which may include natural fractures, artificial fractures (e.g., hydraulic fractures), or a combination of natural fractures and artificial fractures. As an example, a well may be drilled into a laterally extending reservoir. In such an example, there may be lateral changes in properties, stresses, etc., where an assessment of such changes may help plan, operate, etc. to develop a laterally extending reservoir (e.g., via fracturing, injection, extraction, etc.). As an example, equipment 157 and / or 158 may include multiple components, a system or multiple systems, etc. for fracturing, seismic sensing, seismic data analysis, evaluating one or more fractures, etc.

[0024] exist Figure 1 In the example of , GUI 120 shows some examples of computational frameworks, including the DRILLPLAN framework, the PETREL framework, the TECHLOG framework, the PETROMOD framework, the ECLIPSE framework, and the INTERSECT framework (Schlumberger Limited, Houston, Texas).

[0025] The DRILLPLAN framework is used for digital well construction planning and includes multiple features for automating repetitive tasks and verification workflows, thereby enabling rapid generation of drilling programs (eg, digital drill plans, etc.) of improved quality while ensuring consistency.

[0026] The PETREL framework may be part of a cognitive exploration and production (E&P) environment (Schlumberger Limited, Houston, Texas, known as the DELFI environment), used in, for example, geoscience and geoengineering to analyze subsurface data from exploration to production of fluids from reservoirs.

[0027] One or more types of frameworks may be implemented within or operatively coupled to a DELFI environment, which is a secure, cognitive, cloud-based collaborative environment that integrates data and workflows with digital technologies such as artificial intelligence (AI) and machine learning (ML). As an example, such an environment may provide operations involving one or more frameworks. A DELFI environment may be referred to as a DELFI framework, which may be one of a plurality of frameworks. As an example, a DELFI framework may include various other frameworks, which may include, for example, one or more types of models (e.g., simulation models, etc.).

[0028] The TECHLOG framework can handle and process field and laboratory data from a variety of geological environments (e.g., deepwater exploration, shale, etc.). The TECHLOG framework can structure wellbore data for analysis, planning, etc.

[0029] The PIPESIM simulator includes a solver that can provide simulation results, such as, for example, multiphase flow results (e.g., from the reservoir to the wellhead and beyond), flowline and surface facility performance, etc. The PIPESIM simulator can be integrated, for example, with the AVOCET production operations framework (Schlumberger Limited, Houston Texas). As an example, a reservoir or multiple reservoirs can be simulated with respect to one or more enhanced recovery technologies (e.g., considering thermal processes such as steam assisted gravity drainage (SAGD), etc.). As an example, the PIPESIM simulator can be an optimizer that can optimize one or more operating scenarios at least in part by simulating physical phenomena.

[0030] The ECLIPSE framework provides numerical solutions for reservoir simulators (eg, as a computational framework) to quickly and accurately predict the dynamic behavior of various types of reservoirs and development scenarios.

[0031] The INTERSECT framework provides a high-resolution reservoir simulator for simulating detailed geological features and quantifying uncertainties, for example, by creating accurate production scenarios, and when integrating accurate models of surface facilities and field operations, the INTERSECT framework can produce reliable results that can be continuously updated through real-time data exchange (e.g., one or more types of data acquisition equipment from the field that can acquire data during one or more types of field operations, etc.). The INTERSECT framework can provide completion configurations for complex wells, where such configurations can be built in the field; can provide detailed chemical enhanced oil recovery (EOR) recipes, where such recipes can be implemented in the field; can analyze the application of steam injection and other thermal EOR technologies to implement advanced production control in terms of reservoir coupling and flexible field management in the field, and the flexibility to write customized solutions for improved modeling and field management control. As with other example frameworks, the INTERSECT framework can be used as part of the DELFI cognitive E&P environment, for example, for rapid simulation of multiple concurrent cases. For example, a workflow can utilize one or more of the DELFI on-demand reservoir simulation features.

[0032] The aforementioned DELFI environment provides various features for workflows related to subsurface analysis, planning, construction, and production, as shown, for example, in the workspace framework 110. Figure 1 As shown, the output from the workspace framework 110 can be used to guide, control, etc. one or more processes in the geological environment 150, and feedback 160 (e.g., acquired data regarding operating conditions, equipment conditions, environmental conditions, etc.) can be received via one or more interfaces in one or more forms.

[0033] As an example, the workflow may proceed to a geology and geophysics ("G&G") service provider, which may generate well trajectories, which may involve the execution of one or more G&G software packages.

[0034] exist Figure 1 In the example of , visualization features 123 may be implemented via workspace framework 110, for example, to perform tasks associated with one or more of a subsurface region, planning operations, constructing well and / or surface fluid networks, and producing from a reservoir.

[0035] As an example, the visualization process can implement one or more of the various features that can be suitable for one or more network applications. For example, the template may involve the use of JAVASCRIPT object representation format (JSON) and / or one or more other languages / formats. As an example, the framework may include one or more converters. For example, consider JSON to Python converter and / or Python to JSON converter. In this method, one or more features of a framework that can be implemented in a language may be able to be accessed via a converter. For example, consider the APACHE SPARK framework, which can include features that can be implemented in a specific language, wherein the converter can convert the code of another language into the specific language, so that one or more features in the features can be utilized. As an example, the production site may include various types of equipment, various frameworks may be used for operation, etc., wherein one or more languages ​​may be utilized. In such an example, the converter can provide feature flexibility and / or compatibility.

[0036] As an example, a visualization feature may provide visualization of various earth models, features, and the like in one or more dimensions. As an example, a visualization feature may provide a presentation of information in multiple dimensions, which may optionally include a multi-resolution presentation. In such an example, the information being presented may be associated with one or more frameworks and / or one or more data stores. As an example, a visualization feature may include one or more control features for controlling equipment, which may include, for example, field equipment that can perform one or more field operations. As an example, a workflow may utilize one or more frameworks to generate information that can be used to control one or more types of field equipment (e.g., drilling equipment, cable equipment, fracturing equipment, etc.).

[0037] With respect to reservoir models that may be suitable for use by the simulator, consider the acquisition of seismic data such as obtained via reflection seismology, which can be used in geophysics, for example, to estimate the characteristics of underground formations. As an example, reflection seismology can provide seismic data that represents elastic energy waves (e.g., as transmitted by P waves and S waves, in a frequency range of about 1 Hz to about 100 Hz). The seismic data can be processed and interpreted, for example, to better understand the composition, fluid content, range, and geometry of underground rocks. Such interpretation results can be used to plan, simulate, perform, etc., one or more operations for producing fluids from a reservoir (e.g., reservoir rock, etc.).

[0038] Field acquisition equipment can be used to acquire seismic data, which can be in the form of traces, where the traces can include values ​​organized with respect to time and / or depth (e.g., considering 1D, 2D, 3D, or 4D seismic data). For example, consider an acquisition device that acquires digital samples at a rate of one sample every about 4 ms. Given the speed of sound in one or more media, the sampling rate can be converted to an approximate distance. For example, the speed of sound in rock can be about 5 km per second. Therefore, a sampling time interval of about 4 ms will correspond to a sampling "depth" interval of about 10 meters (e.g., assuming a path length from source to boundary and boundary to sensor). As an example, the duration of a trace may be about 4 seconds; therefore, for a sampling rate of one sample per about 4 ms, such a trace will include about 1000 samples, where the samples acquired later correspond to deeper reflecting boundaries. If the 4 second trace duration of the above example is divided by two (e.g., to take into account reflections), the deepest boundary depth can be estimated to be about 10 km for a vertically aligned source and sensor (e.g., assuming a sound speed of about 5 km per second).

[0039] As an example, the model can be a simulated version of a geological environment. As an example, a simulator may include multiple features for simulating physical phenomena in a geological environment based at least in part on one or more models. A simulator such as a reservoir simulator can simulate fluid flow in a geological environment based at least in part on a model that can be generated via a framework that receives seismic data. The simulator can be a computerized system (e.g., a computing system) that can use one or more processors to execute instructions to solve a set of equations describing physical phenomena subject to various constraints. In such an example, the set of equations can be spatially defined (e.g., numerically discretized) according to a spatial model including rock layers, geological bodies, etc., which has corresponding positions that can be based on interpretations of seismic and / or other data. The spatial model can be a cell-based model in which a cell is defined by a grid (e.g., a net). A cell in a cell-based model can represent a physical region or volume in a geological environment, wherein the cell can be assigned physical properties (e.g., permeability, fluid properties, etc.) that may be closely related to one or more physical phenomena (e.g., fluid volume, fluid flow, pressure, etc.). A reservoir simulation model can be a cell-based spatial model.

[0040] The simulator can be used to simulate the exploitation of a real reservoir, for example, to examine different production scenarios to find the best scenario before production or further production occurs. Reservoir simulators do not provide an exact replication of flow in a reservoir and production from a reservoir, at least in part because the boundary conditions of the equations for the description of the reservoir and the flow in porous rocks are generally known, but with a certain amount of uncertainty. Certain types of physical phenomena occur at spatial scales that may be relatively small compared to the size of the oil field. A balance can be struck between the model scale and the computational resources that make the model unit size about a few meters; rather than a smaller size (e.g., the level of detail of the pores). The modeling and simulation workflow of multiphase flow in porous media (e.g., reservoir rocks, etc.) can include summarizing real microscale data based on macroscale observations (e.g., seismic data and well data) and scaling up the scale to a manageable scale and problem size. There may be uncertainty in the input data and the solution process, making the simulation results uncertain to some extent. The process considered to be history matching can involve comparing the simulation results with actual oil field data obtained during the production of fluids from the oil field. The information collected from history matching can provide adjustments to models, data, etc., which can help improve simulation accuracy.

[0041] As an example, a simulator may utilize various types of constructs, which may be referred to as entities. An entity may include an earth entity or geological object, such as a well, ground, reservoir, etc. An entity may include a virtual representation of an actual physical entity that may be reconstructed for simulation purposes. An entity may include an entity based on data acquired via sensing, observation, etc. (e.g., consider an entity based at least in part on seismic data and / or other information). As an example, an entity may be characterized by one or more properties (e.g., a geometric pillar grid entity of an earth model may be characterized by a porosity property, etc.). Such properties may represent one or more measurements (e.g., acquired data), calculations, etc.

[0042] As an example, the simulator may utilize an object-based software framework that may include entities based on predefined classes to facilitate modeling and simulation. As an example, an object class may encapsulate reusable code and associated data structures. An object class may be used to instantiate object instances for use by programs, scripts, and the like. For example, a wellbore class may define objects for representing wellbores based on well data. A model of a basin, reservoir, and the like may include one or more wellbores, which may be used, for example, for measurement, injection, production, and the like. As an example, a wellbore may be a wellbore of a well, which may be a completion (e.g., for producing resources from a reservoir, for injecting material, and the like).

[0043] Although in Figure 1Several simulators are illustrated in the example of , but one or more other simulators may be utilized in addition or alternatively. For example, consider the VISAGE geomechanical simulator (Schlumberger Limited, Houston Texas) or the PETROMOD simulator (Schlumberger Limited, Houston Texas). The VISAGE simulator includes a finite element numerical solver that can provide simulation results, such as, for example, compaction and settlement of the geological environment, well and completion integrity in the geological environment, cap rock and fault closure integrity in the geological environment, fracturing behavior in the geological environment, thermal recovery in the geological environment, CO2 disposal, etc. The PETROMOD framework provides petroleum system modeling capabilities that can combine one or more of earthquake, well and geological information to model the evolution of sedimentary basins. The PETROMOD framework can predict whether and how a reservoir is filled with hydrocarbons, including the source and time of hydrocarbon generation, migration routes, amount, and hydrocarbon types under underground or surface conditions. The MANGROVE simulator (Schlumberger Limited, Houston, Texas) optimizes stimulation designs (e.g., stimulation treatment operations, such as hydraulic fracturing) in a reservoir-centric environment. The MANGROVE framework can combine scientific and experimental work to predict the geomechanical propagation of hydraulic fractures, reactivation of natural fractures, etc., and production predictions within a 3D reservoir model (e.g., production from drainage areas of a reservoir, where fluids move into and / or out of a well via one or more types of fractures). The MANGROVE framework can provide results related to the heterogeneous interactions between hydraulic fracture networks and natural fracture networks, which may help optimize the number and location of fracture treatment stages (e.g., stimulation treatments), for example, to improve perforation efficiency and production.

[0044] Figure 2 An example of a system 200 is shown that can be operatively coupled to one or more databases, data streams, etc. For example, one or more field devices, laboratory devices, computing devices (e.g., local and / or remote), etc. can provide and / or generate data that can be used in the system 200.

[0045] As shown, system 200 may include a geological / geophysical data block 210, a ground model block 220 (e.g., for one or more structural models), a volume model block 230, an application block 240, a numerical processing block 250, and an operational decision block 260. Figure 2As shown in the example of , the geological / geophysical data block 210 may include data 212 from the well top or borehole, data 214 from seismic interpretation, data from outcrop interpretation, and optionally data from geological knowledge. As an example, the geological / geophysical data block 210 may include data from digital images, which may include digital images of cores, cuttings, caves, outcrops, etc. Regarding the ground model block 220, it may provide one or more ground models to be created, edited, etc. based on, for example, one or more of a fault plane 222, a ground plane 224, and an optional topological relationship 226. Regarding the volume model block 230, it may provide one or more volume models to be created, edited, etc. based on, for example, one or more of a boundary representation 232 (e.g., forming a watertight model), a structured grid 234, and an unstructured mesh 236.

[0046] like Figure 2 As shown in the example of , the system 200 may allow implementation of one or more workflows, for example, where the data of the data block 210 is used to create or edit one or more ground models of the iso-ground model block 220, and the ground models may be used to create or edit one or more volume models of the iso-volume model block 230. Figure 2 As indicated by the example of , the ground model block 220 may provide one or more structural models that may be input to the application block 240. For example, such structural models may be provided to one or more applications, optionally without performing one or more processes of the volume model block 230 (e.g., for the purpose of numerical processing by the numerical processing block 250). Thus, the system 200 may be adapted for one or more workflows for structural modeling (e.g., optionally without performing numerical processing as per the numerical processing block 250).

[0047] With respect to the application block 240, it may include a plurality of applications, such as a well prediction application 242, a reserve calculation application 244, and a well stability assessment application 246. With respect to the numerical processing block 250, it may include a seismic velocity modeling process 251 and subsequent seismic processing 252, a phase and rock physical property interpolation process 253 and subsequent flow simulation 254, and a geomechanical simulation process 255 and subsequent geochemical simulation 256. As indicated, as an example, the workflow may proceed from the volume model block 230 to the numerical processing block 250, and then to the application block 240 and / or the operational decision block 260. As another example, the workflow may proceed from the ground model block 220 to the application block 240, and then to the operational decision block 260 (e.g., considering an application that operates using a structural model).

[0048] exist Figure 2In the example of FIG. 2 , operation decision block 260 may include seismic survey design process 261, well rate adjustment process 252, well trajectory planning process 263, well completion planning process 264, and processes for one or more exploration areas, for example, to decide whether to explore, develop, abandon, etc. an exploration area.

[0049] Referring again to data block 210, well top or borehole data 212 may include the spatial location of an interface between two geological layers of a subsurface discontinuity (such as a geological fault) and, optionally, the surface dip; seismic interpretation data 214 may include a set of points, lines, or surface patches interpreted from seismic reflection data and representing an interface between a medium (e.g., geological formations with different seismic wave velocities) or a subsurface discontinuity; outcrop interpretation data 216 may include a set of lines or points, optionally associated with measured dips, representing boundaries between geological layers or geological faults interpreted on the earth's surface; and geological knowledge data 218 may include, for example, knowledge of the paleo-tectonic and sedimentary evolution of a region.

[0050] With respect to the structural model, it can be, for example, a set of grids or mesh surfaces that represent one or more interfaces between geological layers (e.g., ground planes) or subsurface mechanical discontinuities (fault planes). As an example, the structural model can include some information about one or more topological relationships between ground surfaces (e.g., fault A cuts off fault B, fault B intersects fault C, etc.).

[0051] Regarding one or more boundary representations 232, they may include a numerical representation in which the subsurface model is divided into various closed cells representing geological layers and fault blocks, where an individual cell may be defined by its boundaries and, optionally, by a set of internal boundaries (such as fault planes).

[0052] With respect to one or more structured grids 234, they may include a grid that divides the volume of interest into different elementary volumes (cells), which may be indexed, for example, according to a predefined repeating pattern. With respect to one or more unstructured grids 236, they may include a grid that divides the volume of interest into different elementary volumes, which may not be easily indexed according to a predefined repeating pattern, for example (e.g., consider a Cartesian cube with indices I, J, and K along the x-axis, y-axis, and z-axis).

[0053] With respect to seismic velocity modeling 251, it may include calculating the propagation velocity of seismic waves (e.g., seismic velocity depends on the type of seismic wave and the direction in which the wave is propagating). With respect to seismic processing 252, it may include a set of processes that allow identification of the locations of seismic reflectors in space, the physical properties of the rocks between these reflectors, etc.

[0054] Regarding facies and petrophysical property interpolation 253, this may include an assessment of rock types and their petrophysical properties (e.g., porosity, permeability), such as optionally in areas not sampled by logging or coring. As an example, such interpolation may be limited by interpretation and prior geological knowledge from log and core data.

[0055] With respect to flow simulation 254, as an example, it can include simulating the flow of subsurface hydrocarbons, for example, through geological time (e.g., in the context of petroleum systems modeling, when trying to predict the presence and quality of oil in undrilled formations) or during extraction of a hydrocarbon reservoir (e.g., when some fluid is pumped from or into a reservoir).

[0056] With respect to geomechanical simulation 255, it may include simulations of rock deformation under boundary conditions. Such simulations may be used, for example, to assess the degree of compaction of a reservoir (e.g., associated with reservoir depletion as hydrocarbons are pumped from the porous and deformable rocks that comprise the reservoir). As an example, geomechanical simulations may be used for a variety of purposes, such as, for example, predicting fracturing, reconstructing the ancient geometry of a reservoir prior to structural deformation, and the like.

[0057] With respect to geochemical modeling 256, such simulations may simulate the evolution of hydrocarbon formations and compositions over geological history (eg, to assess the likelihood of petroleum accumulation in a particular subsurface formation when exploring a new prospect).

[0058] With respect to the various applications of application block 240, a well prediction application 242 may include predicting the types and characteristics of geological formations that a drill bit may encounter, and the locations where such rock may be encountered (e.g., prior to drilling a well); a reserve calculation application 244 may include assessing the total amount of hydrocarbon or ore material present in a subsurface environment (e.g., estimating the fraction that can be recovered given a set of economic and technical constraints); and a well stability assessment application 246 may include estimating the risk of collapse or damage to a drilled or yet-to-be-drilled well due to subsurface stresses.

[0059] With respect to operational decision block 260, the seismic survey design process 261 may include deciding where to place seismic sources and receivers to optimize coverage and quality of collected seismic information while minimizing acquisition costs; the well rate adjustment process 262 may include controlling injection and production well schedules and rates (e.g., to maximize recovery and production); the well trajectory planning process 263 may include designing well trajectories to maximize potential recovery and production while minimizing drilling risks and costs; the well trajectory planning process 264 may include selecting appropriate wellbore, casing, and completions (e.g., to meet expected production or injection targets in a specified reservoir); and the exploration process 265 may include making decisions in the context of exploration to continue exploration, begin production, or abandon exploration (e.g., based on a comprehensive assessment of technical and financial risks and expected returns).

[0060] System 200 may include and / or may be operatively coupled to, for example, Figure 1 The system 100 of the system. For example, the workspace framework 110 may provide instantiation, rendering, interaction with, etc. of a graphical user interface (GUI) 120 to perform one or more actions with respect to the system 200. In such an example, access to one or more frameworks (e.g., DRILLPLAN, PETREL, TECHLOG, PIPESIM, ECLIPSE, INTERSECT, etc.) may be provided. The one or more frameworks may provide geographic data acquisition such as in block 210, structural modeling such as in block 220, volume modeling such as in block 230, application execution such as in block 240, numerical processing such as in block 250, operational decision making such as in block 260, etc.

[0061] As an example, the system 200 may provide monitoring data, which may include geographic data for each geographic data block 210. In various examples, the geographic data may be acquired during one or more operations. For example, consider acquiring geographic data via downhole equipment and / or surface equipment during a drilling operation. As an example, the operational decision block 260 may include functionality for monitoring, analyzing, and the like such data in order to make one or more operational decisions, which may include controlling equipment, modifying operations, modifying plans, and the like. In such an example, data may be fed into the system 200 at one or more points where data quality may be of particular concern. For example, data quality may be characterized by one or more metrics, wherein data quality may provide indications of confidence, probability, and the like, which may be closely related to operational decisions and / or other decisions. As an example, data quality may be improved by calibrating equipment. For example, consider the calibration of a digital microscopy system that may acquire digital images of three-dimensional objects such as cuttings, caves, and the like.

[0062] Figure 3An example of a wellsite system 300 is shown (e.g., at a wellsite that may be located onshore or offshore). As shown, the wellsite system 300 may include: a mud tank 301 for storing mud and other materials (e.g., where the mud may be drilling fluid); a suction line 303, which serves as an inlet of a mud pump 304, which is used to pump mud from the mud tank 301 so that the mud flows to a vibration hose 306; a winch 307, which is used to hoist one or more drilling wire ropes 312; a riser 308, which receives mud from the vibration hose 306; a kelly hose 309, which receives mud from the riser 308; and a kelly hose 309, which receives mud from the riser 308. slurry; a gooseneck or multiple goosenecks 310; a traveling block 311; a crown block 313, which is used to carry the traveling block 311 via one or more drilling wire lines 312; a derrick 314; a kelly 318 or a top drive 340; a kelly drive bushing 319; a rotary table 320; a drill floor 321; a bell-mouth nipple 322; one or more blowout preventers (BOPs) 323; a drill string 325; a drill bit 326; a casing head 327; and a flow tube 328, which transports mud and other materials to, for example, a mud tank 301.

[0063] exist Figure 3 In the example system, a wellbore 332 is formed in a subsurface formation 330 by rotary drilling; note that various example embodiments may also use one or more directional drilling techniques, equipment, etc.

[0064] like Figure 3 As shown in the example of FIG. 3 , a drill string 325 is suspended in a wellbore 332 and has a drill string assembly 350 including a drill bit 326 at its lower end. As an example, the drill string assembly 350 may be a bottom hole assembly (BHA).

[0065] The wellsite system 300 can provide for the operation of the drill string 325 and other operations. As shown, the wellsite system 300 includes a traveling block 311 and a derrick 314 positioned above a wellbore 332. As mentioned, the wellsite system 300 can include a rotary table 320, wherein the drill string 325 passes through an opening in the rotary table 320.

[0066] like Figure 3As shown in the example of , the wellsite system 300 may include a kelly 318 and associated components, or a top drive 340 and associated components. With respect to the kelly example, the kelly 318 may be a square or hexagonal metal / alloy rod with holes drilled therein for use as a mud flow path. The kelly 318 may be used to transfer rotational motion from the rotary table 320 to the drill string 325 via the kelly drive bushing 319 while allowing the drill string 325 to be lowered or raised during rotation. The kelly 318 may pass through the kelly drive bushing 319, which may be driven by the rotary table 320. As an example, the rotary table 320 may include a square bushing that is operatively coupled to the kelly drive bushing 319, such that rotation of the rotary table 320 may cause the kelly drive bushing 319 to rotate and thus cause the kelly 318 to rotate. The kelly drive bushing 319 may include an inner profile that matches the outer profile of the kelly 318 (e.g., square, hexagonal, etc.); however, the kelly drive bushing has a slightly larger size so that the kelly 318 can move freely up and down within the kelly drive bushing 319.

[0067] With respect to the top drive example, the top drive 340 can provide the functions performed by the kelly and rotary table. The top drive 340 can rotate the drill string 325. As an example, the top drive 340 can include one or more (e.g., electric and / or hydraulic) motors connected to a small section of pipe called a cannula using appropriate gearing, which in turn can be tightened to a saver sub or the drill string 325 itself. The top drive 340 can be suspended on the traveling block 311 so that the rotating mechanism can move freely up and down along the derrick 314. As an example, the top drive 340 can allow drilling to be performed using more single columns than the kelly / rotary table approach.

[0068] exist Figure 3 In the example of, mud tank 301 can store mud, and mud can be one or more types of drilling fluids. As an example, a wellbore can be drilled to produce fluid, inject fluid or both (e.g., hydrocarbons, minerals, water, etc.).

[0069] exist Figure 3In the example of FIG. 3 , a drill string 325 (e.g., including one or more downhole tools) can be composed of a series of tubes that are threaded together to form a long tube with a drill bit 326 at the lower end. As the drill string 325 enters the wellbore for drilling, mud can be pumped from the mud tank 301 (e.g., or other source) to the mouth of the kelly 318, or, for example, to the mouth of the top drive 340, via pipelines 306, 308, and 309 by pump 304 before or at some point coincident with drilling. The mud can then flow through a channel (e.g., or multiple channels) in the drill string 325 and out of a port located on the drill bit 326 (see, e.g., directional arrows). As the mud leaves the drill string 325 via the port in the drill bit 326, the mud can then loop back upward through the annular region between the outer surface (s) of the drill string 325 and the surrounding wall (s) (e.g., open hole, casing, etc.), as indicated by the directional arrows. In this manner, the mud lubricates the drill bit 326 and carries heat (eg, frictional or other energy) and formation cuttings to the surface, where the mud can be returned to the mud tank 301 after being processed to remove cuttings and other materials, such as for recirculation.

[0070] Rock cuttings can be defined as small pieces of rock that are dislodged by the action of the drill teeth. Characteristics of rock cuttings can include composition, size, shape, color, texture, hydrocarbon content, and other properties. Rock cuttings can be collected and evaluated as part of a mud logger system or workflow. Rock cuttings are distinct from other materials that can be carried by mud. For example, consider a collapse formed by rock fragments that have been dislodged due to wellbore instability.

[0071] Material (e.g., drilling fluid) carried to the surface by the mud may be collected for one or more purposes. With respect to the collection process, consider collecting material at a vibrator of a mud system (e.g., a mud logger system, etc.), where material (e.g., cuttings and other materials, if present) may be flushed to remove fluid, where residual fluid (e.g., mud, reservoir fluid, etc.) may be drained from a sample tray. Another technique is known as a flowline mud sample, which is a sample of mud flowing directly from the wellbore from the annulus around the drill pipe, collected prior to passing through the vibrator. The mud itself may be sampled and analyzed as a mud-out sample, which is collected after it has passed through the flowline and through a shaker to remove large cuttings. This type of mud sample has been subjected to downhole pressures, temperatures, and contamination, which can cause degradation. Such mud samples may be evaluated to determine possible treatments and compared on a lag time basis to corresponding mud-in samples (e.g., samples of mud flowing into the drill pipe and downhole for drill bit lubrication and / or mud motor rotation).

[0072] The material collected at the vibrator may be wet, but free of surrounding fluid, and the material may be analyzed while wet and / or dry. In various cases, the material may be analyzed using digital photography with the goal of capturing representative material colors with minimal interference from reflections. As an example, an image of the material may be obtained in relation to depth (e.g., measured depth, etc.), where the image may be acquired under different conditions (e.g., magnification, lighting, angle, etc.). The image may be acquired using one or more wavelengths of electromagnetic radiation. For example, consider UV, IR, and / or visible wavelengths of EM radiation.

[0073] Images may be acquired using high-resolution digital microscopy (HRDM) with appropriate color-resolution illumination and depth-of-field resolution, making it easier to identify the color, texture, and shape of the borehole lithology. Rapid image acquisition can help wellsite geologists more accurately characterize the cuttings and quickly identify cuttings that may be suitable for one or more analytical techniques (e.g., X-ray diffraction, X-ray fluorescence, total organic carbon (TOC) quantification, etc.). Digital images may be stored to one or more data stores, whether local and / or remote. The data stores may be accessed to allow geologists, petrophysicists, basin modelers, etc. to conveniently review images of the material both on-site and off-site. For example, consider a data store that is included in Figure 2 system 200 and / or operatively coupled to Figure 2 System 200. In such an example, the data store may provide one or more types of geographic data, which may include digital images, assessments based on digital images, and the like.

[0074] Reference again Figure 3 The treated mud pumped into the drill string 325 by the pump 304 can form a mud cake lining the wellbore after leaving the drill string 325, and the mud cake can reduce the friction between the drill string 325 and one (multiple) surrounding walls (e.g., wellbore, casing, etc.). The reduction in friction can promote the advancement or retraction of the drill string 325. During the drilling operation, the entire drill string 325 can be pulled out of the wellbore and optionally replaced, for example, with a new or sharp drill bit, a smaller diameter drill string, etc. As mentioned, the action of pulling out the drill string from the wellbore or replacing the drill string in the wellbore is called tripping. Depending on the tripping direction, tripping can be called tripping upward or tripping outward or tripping downward or tripping inward.

[0075] As an example, consider drilling down, where when the drill bit 326 of the drill string 325 reaches the bottom of the wellbore, the pumping of mud begins to lubricate the drill bit 326 for drilling purposes to expand the wellbore. As mentioned, the mud can be pumped into the channel of the drill string 325 by the pump 304, and when filling the channel, the mud can be used as a transmission medium for transmitting energy (e.g., energy that can encode information as in mud pulse telemetry). The characteristics of the mud can be used to determine how the pulse is transmitted (e.g., pulse shape, energy loss, transmission time, etc.).

[0076] As an example, a mud pulse telemetry device may include a downhole device configured to implement changes in mud pressure to generate an acoustic wave or multiple acoustic waves based on which information can be modulated. In such an example, information from the downhole device (e.g., one or more modules of the drill string 325) can be transmitted up the wellbore to the wellhead device, which can relay such information to other equipment for processing, control, etc.

[0077] As an example, the telemetry equipment may operate by transmitting energy through the drill string 325 itself. For example, consider a signal generator that transmits a coded energy signal to the drill string 325, and a repeater that may receive such energy and relay it for further transmission of the coded energy signal (e.g., information, etc.).

[0078] As an example, the drill string 325 may be equipped with a telemetry device 352, the telemetry device including: a rotatable drive shaft; a turbine wheel mechanically coupled to the drive shaft so that mud can cause the turbine wheel to rotate; a modulator rotor mechanically coupled to the drive shaft so that rotation of the turbine wheel causes the modulator rotor to rotate; a modulator stator mounted adjacent or proximate to the modulator rotor so that rotation of the modulator rotor relative to the modulator stator generates pressure pulses in the mud; and a controllable brake for selectively braking rotation of the modulator rotor to modulate the pressure pulses. In such an example, an alternator may be coupled to the drive shaft, wherein the alternator includes at least one stator winding electrically coupled to a control circuit to selectively short-circuit the at least one stator winding to electromagnetically brake the alternator and thereby selectively brake rotation of the modulator rotor to modulate pressure pulses in the mud.

[0079] exist Figure 3 In an example of wellhead control and / or data acquisition system 362, wellhead control and / or data acquisition system 362 may include circuitry for sensing pressure pulses generated by telemetry device 352 and, for example, transmitting the sensed pressure pulses or information derived therefrom for processing, control, etc.

[0080] The illustrated example assembly 350 includes a logging while drilling (LWD) module 354, a measurement while drilling (MWD) module 356, an optional module 358, a rotary steerable system (RSS) and / or motor 360, and a drill bit 326. Such components or modules may be referred to as tools, wherein a drill string may include multiple tools.

[0081] With respect to 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 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 may be stationary. In such an example, drilling may begin at a vertical portion and then deviate from vertical so that the borehole is aligned with the target and ultimately reaches the target. Directional drilling may be implemented in the following situations: where the target is not reachable from a vertical position on 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 are laterally extended (e.g., consider relatively thin but laterally extended reservoirs), where multiple boreholes are to be drilled from a single surface borehole, where a relief well is required, etc.

[0082] One method of directional drilling involves a mud motor; however, mud motors present some 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. A mud motor is a positive displacement motor (PDM) that can operate to drive the drill bit (e.g., during directional drilling, etc.). The PDM operates when drilling fluid is pumped through it, where the PDM converts the hydraulic power of the drilling fluid into mechanical power to rotate the drill bit.

[0083] As an example, the PDM may be operated in a combined rotation mode, in which surface equipment is used to rotate the drill bit of the drill string by rotating the entire drill string (e.g., rotary table, top drive, etc.), and 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, the drill bit RPM may be determined or estimated as the sum of the SRPM and the mud motor RPM, assuming that the SRPM and the mud motor RPM are in the same direction.

[0084] As an example, when the drill string is not rotating from the surface, the PDM mud motor can be operated in a so-called sliding mode. In such an example, the drill bit RPM can be determined or estimated based on the RPM of the mud motor.

[0085] An RSS can perform directional drilling from the place of continuous rotation of the surface equipment, which can mitigate slippage of the directional motor (e.g., PDM). An RSS can be deployed when directional drilling (e.g., deflected, horizontal, or extended reach wells). An RSS can be designed to minimize interaction with the wellbore wall, which can help maintain wellbore 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 a desired direction while continuously rotating at the same RPM as the drill string.

[0086] The LWD module 354 may be housed in a suitable type of drill collar and may include one or more selected types of logging tools. It should also be understood that more than one LWD module and / or MWD module may be employed, for example, as represented by module 356 of the drill string assembly 350. Where the location of an LWD module is mentioned, by way of example, it may refer to a module at the location of the LWD module 354, module 356, etc. The LWD module may include capabilities for measuring, processing, and storing information and communicating with surface equipment. In the example shown, the LWD module 354 may include a seismic measurement device.

[0087] The MWD module 356 may be housed in a suitable type of drill collar and may include one or more devices for measuring characteristics of the drill string 325 and the drill bit 326. As an example, the MWD tool 354 may include, for example, a device for generating electricity to power various components of the drill string 325. As an example, the MWD tool 354 may include, for example, a telemetry device 352, wherein a turbine impeller may generate electricity through the flow of mud; it will be appreciated that other power sources and / or battery systems may be employed to power the various components. As an example, the MWD module 356 may include one or more of the following types of measurement devices: a bit pressure measurement device, a torque measurement device, a vibration measurement device, an impact measurement device, a stick-slip measurement device, a direction measurement device, and an inclination measurement device.

[0088] Figure 3 Also shown are some examples of the types of wellbores that can be drilled. For example, consider a slanted straight wellbore 372, an S-shaped wellbore 374, a deeply deviated wellbore 376, and a horizontal wellbore 378.

[0089] As an example, the drilling operation may include directional drilling, wherein, for example, at least a portion of the well includes a curved axis. For example, consider a radius defining a curvature, wherein the inclination relative to the vertical may vary until reaching an angle between about 30 degrees and about 60 degrees, or, for example, reaching an angle of about 90 degrees or possibly greater than about 90 degrees.

[0090] As an example, a directional well can include several shapes, each of which can be designed to meet specific operational requirements. As an example, a drilling process can be performed based on information and when the information is passed to a drilling engineer. As an example, the inclination and / or direction can be modified based on information received during the drilling process.

[0091] As an example, deflection of the borehole may be achieved in part by using downhole motors and / or turbines.With respect to motors, for example, the drill string may include a positive displacement motor (PDM).

[0092] As an example, the system may be a steerable system and include equipment for performing methods such as geosteering. As mentioned, the steerable system may be or include an RSS. As an example, the steerable system may include a PDM or turbine located at the bottom of the drill string, the PDM or turbine just above the drill bit, where a bent joint may be installed. As an example, above the PDM, an MWD device and / or an LWD device may be installed, the MWD device providing real-time or near real-time data of interest (e.g., inclination, direction, pressure, temperature, actual weight on the drill bit, torque stress, etc.). With respect to the latter, the LWD device may send various types of data of interest to the ground, including, for example, geological data (e.g., gamma ray logging, resistivity, density, and sonic logging, etc.).

[0093] The coupling of sensors that provide information about the well trajectory route in real time or near real time with one or more well logs that characterize the formation from a geological point of view, for example, can allow for the implementation of geosteering methods. Such methods can include navigating the subsurface environment, for example, to follow a desired route to a desired target or targets.

[0094] As an example, a drill string may include: an azimuthal density neutron (AND) 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 diameter stabilizers; one or more curved 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.

[0095] As an example, geosteering may include intentional directional control of a wellbore based on 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 within a particular segment of a reservoir, such as to minimize breakthrough of gas and / or water, and, for example, to maximize economic production from a well that includes the wellbore.

[0096] Reference again Figure 3, the wellsite system 300 may include one or more sensors 364, which are operatively coupled to the control and / or data acquisition system 362. As an example, the sensor or sensors may be at a surface location. As an example, the sensor or sensors may be at a downhole location. As an example, the sensor or sensors may be at one or more remote locations that are more than about one hundred meters away from the wellsite system 300. As an example, the sensor or sensors may be at a compensation wellsite, where the wellsite system 300 and the compensation wellsite are in a common oil and gas field (e.g., an oil field and / or a gas field).

[0097] As an example, one or more sensors 364 may be provided to track drill rods, track movement of at least a portion of a drill string, etc.

[0098] As an example, the system 300 may include one or more sensors 366 that can sense signals and / or transmit signals to a fluid conduit, such as a drilling fluid conduit (e.g., a drilling mud conduit). For example, in the system 300, one or more sensors 366 may be operatively coupled to a portion of the riser 308 through which mud flows. As an example, a downhole tool may generate pulses that may pass through the mud and be sensed by one or more of the one or more sensors 366. In such an example, the downhole tool may include associated circuitry, such as, for example, an encoding circuit that may encode the signal, for example, to reduce the requirements for transmission. As an example, the circuitry at the surface may include a decoding circuit to decode the encoded information transmitted at least in part via mud pulse telemetry. As an example, the circuitry at the surface may include an encoder circuit and / or a decoder circuit, and the downhole circuitry may include an encoder circuit and / or a decoder circuit. As an example, the system 300 may include a transmitter that may generate a signal that may be transmitted downhole via mud (e.g., drilling fluid) as a transmission medium.

[0099] During drilling operations, one or more portions of the drill string may become stuck. The term "stuck" may refer to one or more varying degrees of inability to move or remove the drill string from the borehole. As an example, in a stuck condition, it may be possible to rotate the drill rod or return it to the borehole, or, for example, in a stuck condition, it may not be possible to axially move the drill string in the borehole, although some degree of rotation may be possible. As an example, in a stuck condition, it may not be possible to axially and rotationally move at least a portion of the drill string.

[0100] With respect to the term "stuck drill," this may refer to a portion of a drill string being unable to rotate or move axially. As an example, a condition known as "differential stuck drill" may be a condition in which the drill string is unable to move (e.g., rotate or reciprocate) along the axis of the borehole. Differential stuck drill may occur when high contact forces caused by low reservoir pressure, high wellbore pressure, or both, are applied over a sufficiently large area of ​​the drill string. Differential stuck drill may have both temporal and economic costs.

[0101] 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 applying a relatively low pressure differential (Δp) over a large working area can have the same effect on sticking as applying a high pressure differential over a small area.

[0102] As an example, a condition referred to as "mechanically stuck drill" may be a condition in which drill string movement is restricted or prevented by a mechanism other than differential pressure sticking. Mechanically stuck drill may be caused, for example, by one or more of trash in the wellbore, wellbore geometry anomalies, cement, keyway or cuttings accumulation, and / or collapse in the annulus.

[0103] As mentioned, digital microscopy can be used to evaluate the material carried to the surface by the mud. This material can be in the form of a three-dimensional (3D) object, which can be rock cuttings when the drill bit crushes the formation rock, or it can be a wash of the formation rock, etc. The workflow may be aimed at determining the lithology of the material, where lithology can generally be defined as the macroscopic properties of the mineral content, grain size, texture and color of the rock. In such an example, lithostratigraphy can also be determined, where lithostratigraphy can generally be defined as the study and correlation of rock formations to illustrate the history of the earth based on the properties of lithology or logging responses, the mineral content, grain size, texture and color of the rock. As explained, a wellbore can be drilled using one or more technologies and one or more techniques, where the wellbore passes through one or more layers of rock. Lithology and lithostratigraphy can assist in drilling. For example, lithology and lithostratigraphy may help in drill bit selection, drilling parameter selection, directional drilling, etc.

[0104] As explained, if accumulation occurs, then cuttings and / or collapse can cause problems such as sticking, where sticking (e.g., a stuck drill string) can result in an increase in nonproductive time (NPT). The properties of the materials in the mud can also have an impact on the energy consumption, whether moving the mud or rotating the drill bit (e.g., via drill string rotation, mud motor rotation, etc.). The properties of the mud can be determined in part based on the material properties of the material to be carried by the mud. For example, consider the mud viscosity, mud type (e.g., oil-based, water-based, etc.), etc.

[0105] In digital microscopy of 3D objects, the captured images need to be accurate in color and have appropriate clarity for the imaged 3D objects (e.g., rock cuttings, caves, and / or other objects). To ensure quality, the workflow may involve controlling the settings of the system hardware and software while minimizing human error (e.g., installation, configuration, etc.). As an example, a method may be used to generate a calibrated digital microscopy system to image a 3D object. Such a method may involve verifying and confirming acceptable image quality by applying certain setup criteria.

[0106] Figure 4 An example of a digital microscopy system 400 , an example of a method 410 , and examples of digital images 480 at different magnifications acquired using the digital microscopy system 400 , as well as an example diagram of a CIELAB color space 482 are shown.

[0107] like Figure 4 As shown, the digital microscopy system 400 includes a support 401 that can be supported by a base 402 (e.g., a platform), wherein arms 403 and 404 can extend outward from the support 401 for mounting and positioning a digital camera 405 and a light source 407. As shown, the digital camera 405 includes a lens 406 for forming a microscopic image on an image plane of the digital camera 405. Figure 4 In the example of , the digital microscopy system 400 may include circuitry 408 operatively coupled to the digital camera 405 and / or the light source 407. As shown, the digital microscopy system 400 may include a display 409 that may present one or more graphical user interfaces (GUIs) 470 and a digital image 480. As an example, the circuitry 408 may be provided for communicating signals, data, etc.

[0108] exist Figure 4 In the example of , sample 450 is positioned on sample tray 440, where sample 450 is within the field of view (FOV) of digital camera 405, so that a digital image of sample 450 can be presented on a display, for example, consider digital image 480 is of sample 450 and can be presented on display 409. With respect to magnification values, these values ​​can represent digital zoom magnification values. With respect to optical zoom, it can introduce various factors, such as, for example, a depth of field (DOF) factor. In Figure 4In the example of, the digital microscopy system 400 includes a digital zoom feature and may include an optical zoom feature. For example, the lens 406 may be a fixed focus lens or an optical zoom lens. As an example, the lens may be a fixed focal length lens. As an example, a fixed lens paired with a digital sensor may provide a particular resolution and DOF. With respect to sample 450, as explained, it is a three-dimensional sample; however, sample 450 may have a relatively small height. For example, the height of material particles and / or material agglomerates may be less than 1 cm, so that a digital imaging device with a relatively small DOF may be utilized. As explained, the digital microscopy system 400 may include a digital sensor defining a sensor plane, and another plane may be an object plane.

[0109] Figure 4 The digital microscopy system 400 may be a HRDM system. For example, consider a resolution of 2,000,000 geometric pixels, 6,000,000 color pixels, a picture size of 1,600 pixels x 1,200 pixels, a suitable image format (e.g., raw, compressed, etc.), a zoom magnification of 20x to 200x, automatic white balance calibration, a halogen lamp (yellow light, 12V, 100W) with a halogen life of 1,000 hours, and a footprint (H×L×W) of 16.5×16.5×7 inches (42×42×18 cm). Such an HRDM system may be portable and suitable for field use. For example, such an HRDM system may be placed in a briefcase, backpack, etc., so that the system may be transported to one or more sites. Although various drilling-related operations are mentioned, such an HRDM system may be suitable for other field activities, such as, for example, archaeological activities, anthropological activities, etc., where digital images of 3D objects may actually be acquired and evaluated to characterize such 3D objects.

[0110] As an example, a display may have a native resolution such as, for example, 1920 pixels by 1080 pixels (e.g., 2,073,600 pixels in total, sometimes referred to as a 2 megapixel display), with a pixel pitch of about 0.25 mm and a pixel density of about 40 pixels per centimeter. Such a display may be defined by an aspect ratio such as, for example, 16:1 and a maximum number of colors such as, for example, 1,677,216 colors (e.g., 24-bit color). As an example, consider a SAMSUNG T37F series display, such as, for example, a model F22T37 display.

[0111] In the example digital image 480, the DOF may be the same for each magnification of the original digital image (e.g., at each digital zoom level) because the DOF is determined by the device used to capture the original digital image. As an example, the digital image may be stored as digital data in a memory device, where metadata may also be stored. In such an example, the metadata may include one or more types of data regarding one or more settings, characteristics, etc., of the image acquisition (e.g., image capture), environmental conditions, device specifications, time, etc. As an example, the digital file may be stored using Figure 4 The digital microscopy system 400 generates a digital file, wherein such a digital file includes at least one spatial digital 2D image of at least one 3D object.

[0112] With respect to the characteristics of digital 2D images, a digital camera can include a sensor that provides a 4:3 aspect ratio for a given number of pixels (e.g., 18 megapixels, etc.). As explained, the display may have a different aspect ratio, such as, for example, 16:9. In such an example, the full sensor image can be cropped to provide an aspect ratio that matches the display or display standard. As an example, the digital microscopy system 400 can provide a real-time view of a sample, where the captured image can be presented to the display in real time, with appropriate cropping (e.g., to avoid distortion, etc.) as described. In this approach, depending on the FOV and the distribution of the sample on the sample tray, a mechanism can be used to move the sample tray so that multiple portions of the sample can be selected for real-time viewing.

[0113] As an example, the captured digital 2D image may be 18 megapixels, where such an image may be cropped and presented to a display (e.g., a 2 megapixel display, etc.), where circuitry allows for a 2x, 3x, etc. digital zoom. In this approach, the resolution of the cropped digital 2D image may determine the degree to which digital zoom may be performed when the cropped digital 2D image is presented to the display. In this approach, the digital microscopy system 400 may provide a realistic rendering of the sample 450 (e.g., without distortion, with appropriate colors, etc.), where at least one level of digital zoom may be defined and calibrated. This approach may achieve an accuracy of sample distance measurement that may be on the order of less than 1 mm (e.g., micrometers, etc.). As an example, a scale may be presented to a display, where the sample may be measured according to the scale, where the scale varies according to the zoom level (e.g., digital and / or optical). As an example, the file may be stored to a memory device and / or transmitted via a network along with appropriate calibration information, so that the digital 2D image of the sample may be compared, inspected, etc. at different locations, different workstations, etc.

[0114] like Figure 4As shown, method 410 includes: a height block 411 for evaluating the height of digital camera 405 (see dimension "d"); a light orientation block 412 for evaluating the orientation of light source 407 (see dimensions "a", "b", and "c"); a background color block 413 for evaluating the background color, which may be the color of base 402 or a sheet placed on base 402; a lens aperture block 414 for evaluating the aperture of lens 406; a light intensity block 415 for evaluating the light intensity of light source 407; an exposure time block 416 for evaluating the exposure time of digital camera 405; and an image compression block 417 for evaluating one or more image compression techniques optionally applied to a digital image captured by digital camera 405 (e.g., digital camera 405 and / or circuit 408). As an example, circuit 408 may be involved in performing this method with the goal of calibrating digital microscopy system 400.

[0115] As an example, Figure 4 The digital microscopy system 400 can provide aperture adjustment and / or focus fine-tuning. With respect to focus fine-tuning, it can be achieved by adjusting the distance d, for example, by moving the digital camera 405 and / or by moving the sample 450 and / or the sample tray 440 (e.g., considering raising or lowering the sample using a sample tray with a specific sample platform height). As an example, the fine-tuning can be up to a scale of about one tenth of a millimeter. As an example, the method 410 can include a focus fine-tuning block for fine-tuning the focus, which can provide an appropriate resolution (see, for example, using a card for resolution checking, etc.).

[0116] exist Figure 4 In the example of , various 3D objects 450 are shown as being present on the upper surface of the base 402 of the digital microscopy system 400. The digital image 480 may represent a 2D image of the 3D objects 450, where the 3D objects 450 are heterogeneous in that different types of 3D objects are involved; note that there may be one or more 3D objects, where multiple 3D objects may be heterogeneous and / or homogeneous.

[0117] As explained, the lithology of a rock unit can describe physical properties, which can include color, texture, grain size, and composition, where at least color, texture, and grain size can be measured using a digital microscopy system. Lithology can refer to a detailed description of these properties, or a summary of the overall physical properties of the rock. Examples of lithology in the second sense can include, for example, sandstone, slate, basalt, limestone.

[0118] like Figure 4As shown, digital image 480 can be used to evaluate the particle size after the system is calibrated. In addition, as indicated by CIE color space diagram 482, digital image 480 can be used to evaluate the color after the system is calibrated. In addition, digital image 480 can be used to evaluate texture using one or more techniques.

[0119] Colorimetric techniques (e.g., CIELAB plots) can be used to quantitatively measure absolute color and thus color differences between lithologies. Figure 4 As shown in example FIG. 482 , there may be some overlap between lithologies; therefore, color alone may be used to supplement one or more other measurements (e.g., particle size, shape, and / or texture) to distinguish lithologies. For example, in FIG. 482 , there is some overlap in the colors of shale, sand, and carbonate. In order to distinguish them, particle size and / or texture (e.g., and / or one or more other features) may be utilized. As explained, a digital microscopy system may be calibrated so that digital images of acquired 3D objects may be used to robustly and accurately classify the 3D objects. As an example, a method may be used to generate a calibrated digital microscopy system, which may be an automated method or a semi-automated method (e.g., with a certain amount of manual interaction). This method may, for example, physically change a digital microscopy system and / or change its circuitry by executing instructions through one or more integrated circuits (e.g., a controller, a processor, etc.).

[0120] As an example, a calibrated digital microscopy system may generate a digital image that may be stored in a memory device or transmitted via a network in the form of a digital file, wherein the content of the digital file regarding the imaged 3D object or objects may be evaluated, compared to the actual 3D object and / or other digital images of the actual 3D object, etc., and ensure that the compared measurements are within a certain amount of error, which may be given as an error limit or multiple error limits corresponding to a calibration method or multiple calibration methods. As an example, the comparison may utilize a specific display or multiple displays, wherein information such as metadata in the digital file may be used to determine how to display the digital image and / or how to interpret the displayed content. As explained, metadata for a digital image may include information about sensor size, aspect ratio, cropping, scale, etc., which may be utilized when displaying the digital image. As an example, the metadata may include one or more types of calibration information such that an error limit or multiple error limits for the digital image of the digital file may be known.

[0121] Figure 5An example of a workflow 500 involving processing of a digital microscopy image 510 (e.g., a digital image) is shown. As shown, the workflow 500 can include parallel processing for shape 520, texture 540, and color 560, which processes can ultimately be recombined to provide a result 580. With respect to the processing for shape 520, an evaluation can be made for size 522 and shape 524. With respect to the processing for texture 540, one or more classes 541, 542, 543, 544, and 545 can be utilized, wherein one or more of the classes provide an evaluation for heterogeneity 546, and wherein one or more of the classes provide an evaluation for particle size 548. As shown, the evaluation for heterogeneity 546 can produce a measurement 550 (e.g., along a spectrum from homogeneous to heterogeneous, etc.). As shown, the evaluation for particle size 548 can be used to make determinations regarding fine 551, medium 552, and coarse 553 content, as well as size distribution 554. With respect to the processing for color 560, it can generate an appropriate result 562. In Figure 5 In the example of 500, processing of texture 540 and color 560 may be used to generate lithology 570, which may be evaluated with respect to one or more sources of lithology data 572. In combination with size 522 and shape 524, lithology 570 may be used to generate results 580, which may include quantitative and / or qualitative information characterizing one or more 3D objects present in digital microscopy image 510. As an example, digital microscopy image 510 may be stored to a memory device and / or transmitted via a network as a digital file, wherein the digital file includes information about one or more blocks of workflow 500. In such an example, the digital file may include metadata, such as information about Figure 4 Describes one or more types of metadata.

[0122] As mentioned, the lithology of a rock unit is a description of its physical characteristics as seen in outcrops, handheld or core samples, or visible with a low-power microscope. Physical characteristics can include color, texture, grain size, and composition. Lithology can refer to a detailed description of these characteristics, or a summary of the rock's overall physical characteristics. Examples of lithology in the second sense include sandstone, slate, basalt, limestone. Figure 5 As explained in the workflow 500 , lithology 570 can be evaluated using physical properties of processing for texture 540 and processing for color 560 , where, for example, color and texture (eg, including grain size) are physical properties of lithology.

[0123] Lithological information can be found in outcrops (e.g., layers, laminae, heterogeneities, etc.), in cores depending on relative bedding angles (e.g., layers, laminae, heterogeneities, etc.), and in rock cutting samples (e.g., single grains or multiple grains, etc.). For lithological classification of rock cuttings, the smallest representative unit is a single rock cutting.

[0124] Classification of sediments and sedimentary rocks can utilize various characteristics, which can include particle size and color, among others. With respect to particle size, it can range from greater than 2 mm (e.g., fine gravel, medium gravel, and coarse gravel) to less than 0.004 mm (e.g., clay-sized particles), and can be associated with one or more types of rock (e.g., conglomerate, sandstone, siltstone, mudstone, shale claystone, etc.). In addition, sorting can be evaluated in a manner that depends on particle size (e.g., very poor sorting for heterogeneous sizes to very good sorting for uniform sizes).

[0125] With respect to color, a variety of materials are considered, such as feldspar materials, which can be gray or light brown with light red to pink grains; anorthite materials, which can be dark green-gray with transparent to opaque quartz grains and other mineral grains; shales, which can be light green-gray, light gray, gray, dark gray to black, and occasionally red; and sandstones, which can have a variety of colors.

[0126] As an example, a sample may include limestone, which is a sedimentary rock including calcium carbonate, which bubbles in the presence of an acid (e.g., acetic acid, hydrochloric acid, etc.). In some samples, parts of marine organisms may be observed, such as, for example, fossilized shells. Fossils that may be found in a sample may include brachiopods, horned clams, crinoid stems, rugose corals, bryozoans, worm shells, among others.

[0127] As an example, a sample may be a fossil that needs to be characterized by a digital microscopy system. In such an example, the fossil may be present alone or with other materials (e.g., rocks, other fossils, etc.). As an example, a sample may be an organism, which may be from a human or other animal body, a plant, etc. For example, teeth, bones, or tumors are considered as some types of organisms that can be characterized by a digital microscopy system.

[0128] In object-based image analysis (OBIA), the "image object" is a central methodological element that, as an object of study, lies somewhere between application-driven rationality and technology-driven detectability. In OBIA, methods may involve combining image segmentation with knowledge-based classification. In this approach, segmentation may produce image regions, and these regions may become image objects once they are deemed meaningful; in other words, image objects may be defined using objective and / or subjective criteria, where, for example, one or more persons may be involved in the review (e.g., by human expert referees). In a digital image of the pixels of a 3D object, a single pixel is generally not sufficient to represent a 3D object; however, multiple pixels may collectively represent a 3D object.

[0129] As an example, a workflow may involve segmenting regions and using one or more of the regions for classification; note that extracting observable lithological physical properties (eg, color, texture, and grain size) from an entire image can be quite complex.

[0130] As an example, a workflow may involve four processes that generate results: generating calibrated digital images of one or more 3D objects, 3D object segmentation, 3D object measurement, and 3D object classification.

[0131] In such examples, the workflow may include using one or more machine learning (ML) models. For example, consider a classification ML model, such as a clustering model (e.g., k-means clustering, etc.) or a neural network classification model and / or prediction model. In the field of machine learning, data quantity and data quality pose obstacles to generating robust and accurate machine learning models. Figure 5 In the workflow 500 of , the workflow 500 again starts with a digital microscopy image 510. Regardless of whether an ML model is used, the consistency and quality of the input is critical for reliable output (e.g., results).

[0132] Figure 6 Example GUIs 610 and 620 are shown regarding some examples of data that may be acquired and / or generated. As mentioned, various types of data may be acquired, which may be or may include field data, laboratory data, simulation data, etc. In GUIs 610 and 620, various types of data may be received using a framework such as a TECHLOG framework. In GUI 610, the data include well logging data such as bulk density (RHOB), gamma ray (GR), photoelectric factor (PEF), and lithology and measured depth (MD). In GUI 620, the data include RHOB, neutron porosity (BPHI), bottom bulk density (ROBB), phase shift resistivity at 2MH at 40 inch spacing (P40H ohm.m), image data (e.g., borehole image), and GR and total vertical depth (TVD) minus elevation above mean sea level (TVDSS) of the well reference point depth.

[0133] As explained, a framework such as the TECHLOG framework can dynamically incorporate data transmitted directly from the well site for real-time processing and immediate analysis while drilling, which can aid in decision making during operations. As mentioned, such a framework can also access one or more other types of data, such as laboratory data, stored data, etc.

[0134] Regarding the lithology log in GUI 610, which is shown as lithology versus measured depth (MD), such logs can be viewed using, for example, Figure 5500. For example, consider using a system such as system 400 to acquire digital images of material carried to the surface by mud, where results 580 may include lithology 570 based at least in part on a digital microscopy image of a 3D object. As shown in GUI 620, other images may include borehole images of actual images acquired downhole, which may be presented relative to a measured depth (MD). As an example, one or more control instructions may be issued using a framework such as a TECHLOG framework and / or another framework that may determine lithology. As an example, Figure 5 The workflow 500 may be part of a system integrated into and / or operatively coupled to a TECHLOG framework and may be implemented via, for example, Figure 1 100 systems of systems to access.

[0135] Reference again Figure 4 A method 410 is provided for achieving improved consistency and quality of digital microscopy images. Using this method, the acquired digital microscopy images can be used for one or more purposes, which can include evaluation (e.g., during drilling, etc.), training data for training one or more ML models, test data for testing one or more ML models, etc.

[0136] Referring again to system 400, lens 406 can be a relatively compact lens attached to a high-resolution digital camera 405 (e.g., up to 20MP or more), where circuit 408 can include a computing system, which can be a portable computing system (e.g., a laptop computer, etc.). As an example, light source 407 can be a white light LED illuminator with a calibrated color temperature (e.g., 6500K) and a relatively high color rendering index (e.g., CRI>90%). Circuit 408 can include processor-executable instructions stored in a memory device accessible to a processor, so that the processor can access and execute the instructions to command system 400 to perform one or more methods. As an example, the method can be a calibration method and / or an acquisition method. For example, consider a method that can automatically call image acquisition as part of a calibration process, where one or more conditions can be changed as part of the calibration process until image acquisition consistency and quality is achieved. Such an approach can be a human-in-the-loop (HITL) approach, for example, where interaction is via a graphical user interface presented to a display and / or via physical contact with one or more features of the system 400 (e.g., raising / lowering the digital camera 405, raising / lowering / directing the light source 407, etc.), placing / removing an engineering object (EO) on the base 402, etc.

[0137] In the system 400, the digital camera 405 and its lens 406 can have a field of view (FOV). For example, the digital camera 405 and lens 406 can be selected to provide a relatively large FOV (e.g., 50 mm×30 mm). Once these hardware components are selected, the FOV depends on the distance between the digital camera 405 and the base 402 (see dimension “d”). Whenever the camera height is adjusted, a distance calibration is performed to communicate the FOV size back to the system 400. As an example, a calibration card (e.g., a flat card with a checkerboard pattern) having a known size (e.g., a diagonal of 20.59 mm) and a chess-like pattern including a certain number of columns and rows (e.g., 10×6) can be properly positioned within the FOV so that the circuit 408 can receive digital data for detecting the pattern and calibrate the distance information (e.g., dimension “d”). Once the distance measurement value is calibrated, the digital ruler of the circuit 408 can be used to check the appropriate FOV.

[0138] As an example, another method of verifying the FOV of the system 400 is to find a calibration value for the acquired image. This value can be saved as image metadata. In such an example, the calibration value of 0.0113 corresponds to a horizontal field of view of 55 mm; because the camera pixel count is 4912 and the pixel size is 1.25 μm. Therefore, this calibration value indicates an appropriate camera position (height). As an example, a method for generating a calibrated system can set the acceptable range of images to 0.0111-0.0115 (e.g., corresponding to fields of view of 54 mm×31 mm and 56 mm×32 mm, respectively) for this calibration value to ensure that the camera height is set appropriately.

[0139] With respect to the 3D nature of 3D objects, the light source 407 can cast a shadow depending on its orientation relative to the 3D object (or multiple 3D objects). In order to optimize the lighting configuration, the system 400 can be configured so that the shadows of the 3D objects are clearly shown in the image. For calibration purposes, the method can utilize a 3D engineering object (EO). For example, consider a 3D printed cuboid of 50mm×10mm×14mm for metric control. In such an example, the EO can be appropriately placed on the base 402 to show the shadow relative to the illumination from the light source 407. In this way, the size of the shadow can be determined to be approximately 3.5mm to 4.5mm, so that when, for example, rock cuttings are imaged, their shadows are shown in the image. This particular metric is mainly affected by the orientation of the light source 407.

[0140] With respect to color calibration, it is the process of communicating the proper exposure and white balance back to the system 400. For example, consider an 18% gray card that may be placed in the field of view of the digital camera 405. In such an example, the auto white balance and auto exposure functions of the digital camera 405 and / or circuit 408 may be enabled while monitoring the color histogram. Such a process may be complete once the R, G, and B channels overlap and are in the middle of the histogram (e.g., the proper RGB values ​​for 18% gray). For the system 400, consider an R gain of 25, a G gain of 0, a B gain of 29, and an auto exposure of 16. These values ​​may vary when utilizing different imaging systems or different combinations of system components. As an example, information on the R gain, G gain, B gain, and exposure of the image may also be retrieved from metadata (e.g., the gain and / or other information may be stored as metadata to a digital file including the digital image).

[0141] Regarding image quality control specifications, color accuracy is considered a factor that controls image quality. Color accuracy defines how well an imaging system can reproduce colors according to a specific standard and the hue of the imaged object. Several factors can affect the color accuracy of a system, such as temperature and lighting intensity, lens type, camera type, etc.

[0142] In various cases, the manual method may involve utilizing a Munsell color chart. For example, a user may refer to a Munsell color chart to determine a color match between a sample and a color on the Munsell color chart, which may have a color-to-color resolution of ΔE=1, although humans may not be able to achieve such a fine level of resolution. As an example, Figure 4 The digital microscopy system 400 can automatically determine color, which can have a color resolution of less than ΔE=10, where the color can be specified, for example, on a Munsell color chart, etc. As an example, a measurement reference can be provided by an institution, scientific agency, etc. (e.g., the National Institute of Standards and Technology (NIST), etc.), as in the field of metrology.

[0143] In the case of reference color depth, one or more types of color models may be utilized. For example, 8-bit color and 24-bit color may be the same, where in the RGB color space, 8 bits refer to each R, G, and B (e.g., sub-pixel), and 24 bits are the sum of three 8-bit channels (e.g., 3×8=24). Standards may include, for example, monochrome (e.g., 1 bit) to 4K (e.g., 12-bit color providing 4096 colors), etc.

[0144] Regarding the color model, RGB can be mapped to a cube. For example, the horizontal x-axis can be a red axis (R) of red values, the y-axis can be a blue axis (B) of blue values, and the z-axis can be a green axis (G) of green values. The origin of such a cube (e.g., 0,0,0) can be black, while the opposite point can be white (e.g., 1,1,1).

[0145] Another type of color model is the Y′UV model, which defines a color space based on a luminance component (Y′) and two chrominance components called U (blue projection) and V (red projection). The Y′UV color model is used in the PAL composite color video (excluding PAL-N) standard.

[0146] Yet another type of color model is the HSV color model. While the RGB color model may define a color as a percentage of red, green, and blue hues (e.g., mixed together), the HSV color model may define a color in terms of hue (H), saturation (S), and value (V). For the HSV color model, as hue changes from 0 to 1.0, the corresponding color changes from red to yellow, green, cyan, blue, magenta, and then back to red (e.g., red values ​​exist at both 0 and 1.0); as saturation changes from 0 to 1.0, the corresponding color (hue) changes from unsaturated (e.g., a shade of gray) to fully saturated (e.g., no white component); and as value or brightness changes from 0 to 1.0, the corresponding color becomes increasingly brighter.

[0147] Saturation can be described, for example, as representing the purity of a color, where the most saturated color can have the highest value (e.g., represented as white according to saturation), and mixtures of colors are represented as shades of gray (e.g., shades of cyan, green, and yellow are mixtures of real colors). As an example, saturation can be described as representing the "colorfulness" of a stimulus relative to its own brightness; where "colorfulness" is a property of vision according to which the perceived color of an area appears to be more or less colorful, and "brightness" is a property of vision according to which an area appears to emit more or less light.

[0148] When the chroma is greater than 100%, the chroma can be defined as being enhanced. Chroma can be affected by lens quality (e.g., flare in a poor quality lens reduces chroma) and signal processing. Various digital cameras and RAW converters have adjustments to chroma, which can be labeled as saturation. During RAW conversion, chroma is severely affected by image processing, especially the color correction matrix (CCM). Chroma can be adjusted using circuits such as hardware-implemented software. In digital images for artistic purposes, digital cameras may have enhanced chroma (e.g., saturation greater than 100%) to make digital images more vivid (e.g., consider 110-120% in compact digital cameras); however, enhanced chroma can cause loss of detail in highly saturated objects. In digital photography, saturation exceeding 120% can be considered excessive. In various examples herein, saturation can exceed 100%, which can be referred to as enhanced chroma, noting that chroma is generally limited to 100% by definition. As an example, in the case where the saturation of a digital image exceeds 100%, the saturation can be referred to as oversaturation. As an example, the limits may be set such that the desired saturation level is between approximately 90% and approximately 110%.

[0149] About CIELAB color space, also known as L*a*b*, it is a color space defined by the International Commission on Illumination (abbreviated as CIE) in 1976, which expresses color as three values: L* represents perceived lightness, a* and b* represent four colors unique to human vision: red, green, blue and yellow. CIELAB is intended to be a perceptually uniform space, in which a given numerical change corresponds to a similar perceived color change. CIELAB color space is a device-independent "standard observer" color model. The colors it defines are independent of any specific device (such as a computer monitor or printer), but are related to the CIE standard observer, which is the mean of the results of color matching experiments under laboratory conditions.

[0150] The CIELAB color space is 3D and covers the entire range of human color perception or color gamut. It is based on the opponent color model of human vision, where red and green form an opponent pair, and blue and yellow form an opponent pair. The lightness value L* (also called "Lstar") defines black as 0 and white as 100. The a* axis is associated with the green-red color opponent, with green being negative and red being positive. The b* axis represents the blue-yellow opponent, with blue being negative and yellow being positive.

[0151] The a* and b* axes are not limited, and depending on the reference white, the axes can exceed ±150 to cover the human color gamut. However, for practical reasons, various implementations usually limit these values. For example, if integer math is used, a* and b* are usually limited to the range of -128 to 127. As indicated, CIELAB is calculated relative to a reference white, and the CIE recommends using the CIE standard illuminant D65. D65 is used in a variety of industries and applications.

[0152] The lightness value L* in CIELAB is calculated using the cube root of the relative brightness shifted close to black. This produces an effective power curve with an exponent of about 0.43, which represents the response of the human eye to light under daylight (photopic) conditions.

[0153] As an example, a method may include accessing one or more resources about a color model (e.g., as a plug-in, external executable code, etc.). For example, consider a method that includes instructions for accessing an algorithm of a package, a computing environment such as the MATLAB computing environment (sold by MathWorks, Inc., Natick, MA), etc. The MATLAB computing environment includes an image processing toolbox, for example, with algorithms for color space (e.g., color model) conversion, transformation, etc. As an example, the MATLAB computing environment includes functions "rgb2hsv" and "hsv2rgb" to convert an image between an RGB color space and an HSV color space, and "rgb2lab" and "lab2rgb" to convert an image between an RGB color space and a CIELAB color space.

[0154] Similarly, for the RGB color space, each color is defined by its red, green, and blue values. The most effective way to check the color accuracy of a system is to take a standard color reference chart consisting of a certain number of color patches of specific RGB values, detect the captured colors and compare them to the known RGB values ​​of the color patches on the chart. The distance between the color reproduced by the system and the reference color can be determined by the color difference equation ΔE00 (also ΔE or ΔE 00 ) to quantify. Lower ΔE00 indicates higher accuracy.

[0155] Although ΔE00 is given as an example of a metric, the difference or distance between two colors can be a metric of interest in color science, which can be determined using one or more formulas. Quantification of the difference can include formulas that utilize Euclidean distance in a device-independent color space. The CIELAB method can utilize various adjustments, such as a hue rotation term (RT) to handle the blue region (hue angle around 275°), neutral color compensation (prime value in L*C*h difference), lightness compensation (SL), chroma compensation (SC), and hue compensation (SH).

[0156] With respect to reference colorimetric charts or targets, there are various types to choose from. For example, consider the Rez Checker NanoTarget (Image Science Associates, LLC, Williamson, New York). The Rez Checker NanoTarget is a miniature target that is used to evaluate color, hue, and white balance, and is also used to measure the resolution and spatial frequency response (SFR) or modulation transfer function (MTF) of digital cameras / scanners using edge gradient analysis of ISO 12233 and ISO 16067. The Rez Checker Nano Target can have a relatively precise thickness, which, as explained, may be approximately equal to the thickness of the sample tray.

[0157] Target patches can be made with pigmented paints, with 12 spectrally neutral gray patches in the center for assessing correct exposure and white balance. Slanted edges can be used to reliably measure SFR or MTF up to 3000 dots / inch or 60 cycles / mm. A five-line visual hyperbolic wedge can also be included to aid in visual assessments limiting resolution to 850dpi.

[0158] The nubs can be mounted on aircraft grade anodized aluminum and set below the top surface to help protect them from damage. The nubs can be 1 / 8" x 1 / 8" (3.175mm x 3.175mm) in size, while the overall dimensions can be 1.0" (25.4mm) high x 7 / 8" (22.2mm) wide x 0.060" (e.g., approximately 1.5mm) thick, and can be provided with a glossy or matte center gray nub. The peripheral colored nubs are a matte finish. Because these targets are hand cut and assembled, very slight nub misalignments may occur, but they do not affect the utility of the target.

[0159] The glossy gray patch may have an extended dynamic range (density ~2.4) and may be suitable for measuring digital camera imager noise. When crossed polarizers are not used, glossy surfaces may experience specular reflections when the illumination geometry is less than 45° / 0°.

[0160] Matte gray patches may have a lower dynamic range (density ~1.6), but may be more suitable for narrow illumination geometries, such as those used for endoscopic imaging or direct camera flash setups. Because the matte surface can be interpreted as imager noise, it is not recommended to use matte gray patch targets to evaluate imager noise in high magnification applications.

[0161] A target may be selected whose size is compatible with the system FOV. As indicated, the target may include multiple color patches, such as, for example, 30 color patches. An image of the target may be analyzed to return an average ΔE00 value calculated in the CIELAB color space (L*a*b*) based on the color deviation of the 30 colors displayed by the system from the reference. The reference value may be measured using a traceable NIST measurement method or a calibrated spectrophotometer to obtain the ultimate color accuracy.

[0162] As explained, the method can include focus fine-tuning, which can be accomplished by using a card such as a resolution check card (e.g., Rez Checker Nano Target). As an example, the sample tray can include a platform height that is approximately equal to the height of a card (such as a resolution check card) so that once the card is removed and the sample tray is positioned within the FOV of the digital camera, one or more distance-dependent (see, e.g., distance d) adjustments can be maintained. As explained, one or more techniques can be used to assess resolution, which can rely on, for example, the use of a resolution check card.

[0163] In various experiments, examples of system 400 used a digital camera (based on a Bayer filter) and achieved a minimum ΔE00 value of about 5. Therefore, an acceptable range of ΔE00 can be determined to be within the range of values, for example, considering calibration based on achieving values ​​less than 5.5; note that the minimum perceptible difference roughly corresponds to ΔE00=1. As explained, information about the difference value of the calibrated digital microscopy system can be stored to a digital file of the digital image so that a user and / or machine can make an assessment, comparison, etc. As explained, a human can resort to the Munsell chart to compare with a digital image of a 3D object presented on a display, where the color of the display is calibrated and / or where color information can be presented on the display (e.g., numerical values, etc.) to assist in the comparison. In such an example, an error limit or multiple error limits can be indicated so that a human can have a certain degree of confidence in the comparison and its results.

[0164] Regarding saturation, as mentioned, it describes the color intensity and purity. Saturation can be quantified by the average camera chroma (%), calculated by dividing the average chroma of the camera color by the average chroma of the ideal color checker color. After analyzing the image of the color target, this value can be returned via appropriate image analysis software. Saturation above 120% can be considered over-enhancement, which can result in loss of detail.

[0165] To avoid oversaturation and potential loss of detail, the target average camera chroma (saturation) value to be achieved can be set to around 100%. Therefore, the acceptable range can be set within 100% ± 10% (90% - 110%).

[0166] Regarding sharpness, it indicates how well an imaging system can reproduce details of an imaged object or multiple imaged objects. Sharpness is an assessment of the overall image performance, which can include the lens (optical design), digital sensor, image processing pipeline, lens focus, etc. For example, a calibration method can check the boundaries between different color bands; the more blurred the boundaries, the lower the sharpness of the system.

[0167] To measure sharpness, the bar pattern can be used to estimate the spatial frequency (line pairs per mm) when the bar pattern is no longer clearly visible. As explained, the slanted edge method can be used to measure sharpness. For example, the aforementioned Rez CheckerNano Target includes a slanted edge region (see, e.g. Figure 7 Grayscale image 732).

[0168] As an example, analysis of slanted edge images may be performed using a computing system that can return an MTF curve. Various metrics may be derived from MTF curves such as, for example, MTF10, MTF30, and MTF50, which are spatial frequencies at which the MTF is 10%, 30%, or 50% of the zero frequency, respectively. For example, MTF50 may be used as a parameter to define the sharpness of a system. For example, a target MTF50 value of about 103 cycles / mm may be achieved using a relatively large 50mm horizontal field of view. As an example, an acceptable range may be set to 80-110 cycles / mm.

[0169] As an example, MTF50 can sometimes overestimate system resolution; note that using a resolution checker card (e.g., a resolution target) such as Figure 4 The digital microscopy system 400 can distinguish features with 34 cycles / mm (cy / mm) with reasonable contrast (e.g., C=0.2). MTF50 tends to be a suitable metric to provide an automatic assessment of sharpness without resorting to artificial human visual estimation. As an example, Figure 4 The digital microscopy system 400 can utilize MTF50 to improve system resolution in an automated manner.

[0170] Figure 7 A series of tables 710, 720, and 730 are shown of a plurality of values, including target values ​​and value ranges (eg, limits, etc.), which may be used in a calibration process to generate a calibrated device, such as, for example Figure 44. As shown, table 710 includes FOV values, table 720 includes shadow size values, and table 730 shows color error values, saturation (chroma) values, and MTF50 values. The information in tables 710, 720, and 730 can be provided in one or more data structures stored in a memory of a storage device, wherein a computing system can access one or more data structures of these values ​​to generate a calibrated digital microscopy system for imaging a 3D object.

[0171] Figure 7 Also shown is a grayscale image 732 of a Rez Checker Nano Target (referred to as a card), next to a grayscale image 734 of a U.S. penny. As explained, such a card can be used for a variety of calibration tasks. As shown in the grayscale image 732, the card includes a slanted edge region having a slanted edge in one direction and a slanted edge in another direction, a plurality of differently colored squares, and a series of squares from white to black.

[0172] As an example, various image control parameters can be calculated using a computing system and a framework or multiple frameworks. For example, consider one or more of the aforementioned MATLAB frameworks, including the Imaging Toolbox, the IMATEST framework for color and / or sharpness (Imatest LLC, Boulder, Colorado), various PYTHON color libraries, etc. For consistency, the MTF evaluation can be based on ISO Standard: 12233: Resolution and Spatial Frequency Response.

[0173] As an example, selection of a region of interest (ROI) may be performed automatically (eg, based in part on segmentation) and / or manually by an operator.

[0174] As an example, the process can be at least partially automated, where a control map (e.g., Rez Checker cards for type, orientation, and location) and imaging system parameters (e.g., FOV, WD) are systematically defined and controlled by calibrating the FOV using a checkerboard card. As an example, the base 402 of the system 400 can include defined standard marking locations for a Rez Checker card.

[0175] As about Figure 4As explained, method 410 may be implemented for calibrating digital microscopy system 400 to generate a calibrated instance of system 400. As explained, the calibrated system may output a calibrated digital image, which may be in the form of a digital file with metadata, where such metadata may include information related to the calibration (e.g., specified parameter values, limits, etc.). This method may facilitate sharing and comparing digital images (e.g., image to image, image to actual sample, image to standard, etc.). This method may be used for more robust and confident classification and decision making, and may be used to model subsurface environments, perform field operations in subsurface environments, etc.

[0176] As an example, various components of system 400 may be tested to determine if they meet standards such as Figure 7 Optimized settings of the standards in Tables 710, 720 and 730).

[0177] Referring to the camera height block 411, the camera height does not affect the color accuracy and clarity of the image; however, it changes the FOV of the system 400, which is reflected in the calibration value. When the digital camera 405 is fixed at 261mm to 266mm (see dimension "d") from the base 402, the FOV is within its acceptable range. At 266mm, the field of view reaches a 55mm x 31mm target. Therefore, the digital camera 405 can be fixed at 266mm from the base 402.

[0178] Referring to the light orientation block 412, the configuration of the light includes the arm length (see dimension "a"), the lower edge height (see dimension "b"), and the upper edge height (see dimension "c"). The orientation of the light source 407 affects the shadow quality as well as the color accuracy and saturation of the image. The ranges of these three parameters while maintaining shadow size and image quality are as follows: a = 70mm to 80mm, b = 80mm to 95mm, and c = 160mm to 180mm, respectively. For example, consider a = 75mm, b = 90mm, and c = 160mm.

[0179] With respect to background color 413, the color check card can be placed on different background colors; however, most backgrounds, except bright colors (e.g., white) and glossy surfaces, do not affect image quality, especially color accuracy ΔE00. Due to the availability of lining materials, the quality control image of the color check on base 402 (gray) was acquired using an image of the cuttings in a sample tray lined with magenta tape.

[0180] Regarding the lens aperture block 414, as mentioned, the automatic exposure level of the system 400 is 16. At this exposure level, different apertures of 1.2, 2, 4, 8, 22 were examined, with the system 400 returning acceptable ΔE00, saturation, and sharpness at an aperture of 4. At apertures below 4, the image was overexposed, while at apertures above 4, the image was underexposed. Therefore, for the test system 400, the aperture was set to 4.

[0181] Regarding the light intensity block 415, the intensity of the light source 407 is adjustable, and at the maximum intensity, the image meets the standard. At lower intensities (darker than the maximum), the image quality is degraded due to insufficient brightness.

[0182] Regarding the exposure level or exposure time block 416, when the aperture is fixed at 4, the exposure time may be 14 ms or 16 ms to obtain acceptable image quality. As an example, the exposure time may be controlled via one or more types of circuits, such as digital camera circuits and / or other circuits operatively coupled to a controller of a digital camera.

[0183] Regarding the image compression block 417, the export options for digital images include PNG, compressed PNG, JPEG, and compressed JPEG. In experiments, all four options provided acceptable quality. Note that PNG provides the largest file size. Image compression does affect the quality control process, and please note that PNG can provide suitable (lossless) image quality.

[0184] Figure 8 Example tables 810 and 820 are shown, where table 810 includes Figure 4 Optimized settings for system 400 of and wherein table 820 includes various aspects of calibration as well as methods that may be utilized and the frequency with which such methods may be performed. As shown in table 810, a profile may include gain values ​​for one color or multiple colors (e.g., R, G, B, etc.). Such information may be stored to a digital file, optionally as metadata with a digital image. As an example, the optimized settings of table 810 may be stored to a digital file, optionally as metadata with a digital image acquired using a system configured according to the settings of table 810. In Figure 8 In an example of , the light orientation is given via one or more values, which may be distances in a three-dimensional coordinate system (e.g., a Cartesian coordinate system or another type of coordinate system). These values ​​may be used to set the distance to a base (e.g., a sample tray, a card, etc.) and the plane of the light source relative to the plane of the base (e.g., a sample tray, a card, etc.).

[0185] Fig. 9An example of a method 900 is shown, which includes an installation block 914 for installing hardware and software, a calibration block 918 for calibrating distance using a calibration card, a calibration block 922 for calibrating color using a gray card to generate a profile (e.g., regarding R gain, G gain, and B gain), an adjustment block 926 for adjusting one component (or multiple components) being evaluated, a check block 930 for checking the shadow size of an engineering object (EO), a capture block 934 for acquiring an image of a color check card, a check block 938 for checking image metadata regarding calibration values, exposure, and RGB values, and an analysis block 942 for analyzing DE00, saturation, and sharpness values. Fig. 9 As shown in the example of , method 900 can iteratively return to adjustment block 926 depending on the output of analysis block 942.

[0186] As explained, Figure 4 Method 410 or Fig. 9 The method 900 of method can be used to generate a calibrated digital microscopy system for imaging a 3D object. Such an optimization procedure generates a system configuration that gives acceptable performance that meets predefined criteria. As explained, in various cases, when determining the optimal value, deviations in one or both directions result in quantifiable adverse effects. This effect can be measured (e.g., quantified) and used as part of a control scheme to manually, semi-automatically, or automatically generate a calibrated digital microscopy system for a 3D object. As an example, the relationship between the setting and the effect can be automatically determined and / or pre-programmed in the control scheme. This relationship between image quality and the modification of hardware and / or software settings can be part of a workflow in which decisions are made and one or more loops are optionally implemented to achieve an optimally calibrated digital microscopy system. For example, if the quality control criteria are not met, one or more components of the digital microscopy system for the 3D object can be adjusted for verification and modification to achieve the desired level of image quality.

[0187] Fig.10An example of a method 1000 is shown, the method including an acquisition block 1012 for acquiring an image of an engineering object (EO), a decision block 1014 for determining whether a shadow cast by the EO in the image is acceptable, a color calibration block 1018 for performing color calibration, a verification block 1019 for verifying a profile (e.g., regarding white balance, gain, etc.), an acquisition block 1020 for acquiring an image of a resolution check card (e.g., a Rez Checker card, etc.), a check block 1022 for checking image calibration values, a decision block 1024 for determining whether the image calibration values ​​are acceptable, an analysis block 1028 for analyzing a quality control image, a decision block 1030 for determining whether the quality is acceptable (e.g., MTF50, etc.), a decision block 1034 for determining whether the saturation is acceptable, a decision block 1038 for determining whether the color error is acceptable (e.g., ΔE00, etc.), and a completion block 1040 for completing the calibration of the method 1000.

[0188] The foregoing description of the method 1000 relates to decision blocks 1014, 1025, 1030, 1034, and 1038 following respective "yes" branches. For example, where each of the decision blocks 1014, 1025, 1030, 1034, and 1038 determines that a predetermined level, range, etc. is met, the method 1000 may proceed to completion block 1040. However, where one or more "no" decisions (e.g., "no" branches) are made, the method 1000 may perform one or more loops that may function to iteratively improve the calibration of the digital microscopy system of the 3D object.

[0189] like Fig.10As shown in the example of , method 1000 may include loops A, B, C, D, and E. With respect to loop A, if decision block 1014 determines that the shadows in the acquired EO image are unacceptable (e.g., in terms of size, shape, etc.), method 1000 may proceed to verification block 1016 for verifying or adjusting the light orientation (e.g., adjusting the light source, etc.) and continue to acquisition block 1012. With respect to loop B, if decision block 1024 determines that the image calibration values ​​are unacceptable, method 1000 may proceed to verification block 1026 for verifying or adjusting the camera height relative to the base or EO (e.g., adjusting the camera, etc.) and continue to acquisition block 1020. With respect to loop C, if decision block 1030 determines that the image quality is unacceptable, method 1000 may proceed to verification block 1032 for verifying or adjusting the lens aperture and / or lens focus (e.g., adjusting the camera lens, adjusting the distance, etc., which may affect the clarity) and continue to acquisition block 1020. For loop closure D, if decision block 1034 determines that the saturation is unacceptable, the method 1000 may proceed to a verification block 1036 for verifying or adjusting one or more of the exposure and light intensity and continue to acquisition block 1020. With respect to loop closure E, if decision block 1038 determines that the error (e.g., ΔE00, etc.) is unacceptable, the method 1000 may proceed to a color calibration block 1018 for performing color calibration.

[0190] As explained, metrics such as ΔE00 can be used to evaluate color. Fig.10 In the example of , method 1000 allows for the evaluation of the final color, which may depend on various other factors, such that if the color metric is not satisfied, then method 1000 may re-evaluate one or more of these factors before evaluating the color again. As explained, clarity may be affected by fewer factors than color, so clarity evaluation may be performed before color evaluation.

[0191] With respect to the light source, the method may be limited in the factors that can be adjusted. For example, the light source may have a fixed intensity and a fixed color temperature, so that adjustments are limited to spatial adjustments (e.g., distance, orientation, etc.). In this method, by limiting the factors that can be adjusted, the number of adjustable factors can be reduced, thereby providing a more robust and simplified calibration method.

[0192] As explained, loop closures A, B, C, D, and E may involve acquiring another image (e.g., according to block 1012 or 1020), which may be analyzed to determine whether one or more criteria are met. As explained, methods such as method 1000 may be performed in a manual, semi-automatic, or automated manner to generate a calibrated digital microscopy system for a 3D object.

[0193] As an example, a system such as system 400 can include one or more motors that can be used to move one or more components of system 400. For example, consider a motor that can move camera arm 403 up and down, a motor that can move light source arm 404 up and down, a motor that can move base 402 up and down, etc. As explained, camera 405 and / or lens 406 can be equipped with autofocus and / or aperture adjustment features. As an example, circuit 408 can be operably connected to one or more motors (e.g., electromagnetic motors, etc.) to adjust one or more components of system 400.

[0194] refer to Figure 8 Table 820, as mentioned, depending on the sensitivity of each parameter, certain verification actions and calibration actions can be programmed to be performed according to a specific frequency, which can be higher or lower than the frequency of one or more other parameters. As an example, the system can provide an audible indication, a visual indication, and / or an audible and visual indication of the need for parameter evaluation. For example, consider a scene scene where a user may bump into a system component, a scene scene where lighting conditions may change, a scene scene where the characteristics of a 3D object may change, or other scene scenes that may occur and thus may indicate, trigger, etc., one or more calibration processes.

[0195] As an example, a trained ML model can be a classifier that can classify data. For example, consider a classification score about acceptable or unacceptable status, which may be accompanied by a regression value, such as a quality score. In such an example, training can involve reward-based feedback of a neural network (NN) model, for example, if a given classification does not match user expectations, then retraining the NN model in a dynamic manner.

[0196] As explained, the system may implement clustering or grouping, which may be a problem of similarity identification. As an example, a combined regression (prediction) and classification ML model may be constructed. For example, consider an architecture with an input layer, multiple hidden layers, and multiple output layers. In such an example, the regression and classification output layers may be connected to the last common hidden layer of the model. Given two output layers, the model may be trained using two loss functions, for example, considering the mean squared error (MSE) loss of the regression output layer and the sparse classification cross entropy of the classification output layer. An example of a combined ML model for regression (prediction) and classification may be an ML model for determining the age of abalone based on physical details, where the number of rings predicted for abalone may be used as a proxy for the age of the abalone (e.g., age may be predicted as a numerical value (in years) or a class label (with ordinal years as classes)). In various examples, the trained ML model may output probability information. For example, consider the probability that an input belongs to a particular class.

[0197] Regarding the type of ML model, consider one or more of a support vector machine (SVM) model, a k-nearest neighbor (KNN) model, an ensemble classifier model, a neural network (NN) model, 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 (CNN), a stacked autoencoder, etc.), an ensemble model (e.g., a random forest, a gradient boosting machine, bootstrap aggregation, AdaBoost, stacked generalization, a gradient boosted regression tree, etc.), a neural network model (e.g., a radial basis function network, a perceptron, back propagation, a Hopfield network, etc.), a regularization model (e.g., a ridge regression, a least absolute shrinkage and selection operator, an elastic network, a least angle regression), a rule system model (e.g., cubism, one rule, zero rule, repeated incremental pruning to reduce error), a regression model (e.g., linear regression, ordinary least squares regression, stepwise regression, multivariate adaptive regression spline, local estimation scatter plot smoothing, logistic regression, etc.) , Bayesian models (e.g., Naive Bayes, Average Dependence Estimator, Bayesian Belief Network, Gaussian Naive Bayes, Multinomial Naive Bayes, Bayesian Network), Decision Tree Models (e.g., Classification and Regression Trees, Iterative Bisection 3, C4.5, C5.0, Chi-square Automatic Interaction Detection, Decision 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, Mixed Discriminant Analysis, Quadratic Discriminant Analysis, Regularized Discriminant Analysis, Flexible Discriminant Analysis, Linear Discriminant Analysis, etc.), Instance Models (e.g., k-Nearest Neighbors, Learning Vector Quantization, Self-Organizing Maps, Local Weighted Learning, etc.), Clustering Models (e.g., k-Means, k-Median, Expectation-Maximization, Hierarchical Clustering, etc.), etc.

[0198] For example, machine learning models can be built using a computing framework (such as, for example, a MATLAB framework) with libraries, toolboxes, etc. The MATLAB framework includes a toolbox that provides supervised and unsupervised machine learning algorithms, including support vector machines (SVMs), enhanced 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 using algorithms, pre-trained models, and applications. DLT provides convolutional neural networks (convolutional networks, CNNs) and long short-term memory (LSTM) networks to perform classification and regression on images, 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 is used to exchange models with various other frameworks.

[0199] As an example, the TENSORFLOW framework (Google LLC, Mountain View, CA) can be implemented, which is an open source software library including a symbolic math library for data flow programming, which can be implemented for machine learning applications that may include neural networks. As an example, the CAFFE framework can be implemented, which is a DL framework developed by the Berkeley Artificial Intelligence Research Center (BAIR) (University of California, Berkeley, California). As another example, consider the SCIKIT platform (e.g., scikit-learn), which utilizes the PYTHON programming language. As an example, a framework such as the APOLLO AI framework (APOLLO.AI GmbH, Germany) can be utilized. As an example, a framework such as the PYTORCH framework can be utilized (Facebook AI Research Lab (FAIR), Facebook, Inc., Menlo Park, California).

[0200] As an example, a training method may include various actions that may operate on a data set to train an ML model. As an example, a data set may be divided into training data and test data, where the test data may be used for evaluation. The method may include cross-validation parameters and optimal parameters, which may be provided for model training.

[0201] The TENSORFLOW framework can run on multiple CPUs and GPUs with optional CUDA (NVIDIA Corp., Santa Clara, California) and SYCL (The Khronos Group Inc., Beaverton, Oregon) extensions for general-purpose computing on graphics processing units (GPUs). TENSORFLOW can be used on 64-bit LINUX, MACOS (Apple Inc., Cupertino, California), WINDOWS (Microsoft Corp., Redmond, Washington) and mobile computing platforms including platforms based on ANDROID (Google LLC, Mountain View, California) and IOS (Apple Inc.) operating systems.

[0202] TENSORFLOW computations can be represented as stateful data flow graphs; note that the name TENSORFLOW derives from the operations that such neural networks perform on multidimensional arrays of data. Such arrays can be called "tensors".

[0203] As an example, a device and / or multiple distributed devices may utilize TENSORFLOW LITE (TFL) or another type of lightweight framework. TFL is a set of tools that support 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 (e.g., no round-trip servers), privacy (e.g., where sensitive data can be kept on the device), connectivity (e.g., operations without an Internet connection), size (e.g., reducing model and binary size), and power consumption (e.g., efficient computational reasoning and lack of network connectivity). TFL provides multi-platform support, covering ANDROID devices and IOS devices, embedded LINUX, and microcontrollers. TFL provides support for multiple languages, including JAVA, SWIFT, Objective-C, C++, and PYTHON support. TFL provides high performance with hardware acceleration and model optimization. Machine learning tasks may include, for example, data processing, image classification, object detection, pose estimation, question answering, text classification, etc. on multiple platforms. As an example, Figure 4 The system 400 can utilize one or more features of the TFL framework. For example, the circuit 408 can implement TFL ML model features to perform one or more tasks (e.g., learning, classification, calibration, etc.).

[0204] Fig.11 An example of method 1100 and an example of system 1190 are shown. As shown, method 1100 may include: an acquisition block 1110 for acquiring a digital image of an engineering three-dimensional object positioned on a base and illuminated by a light source using a digital camera of a digital microscopy system; an acquisition block 1120 for acquiring a digital image of a color check card positioned on the base and illuminated by the light source using the digital camera; a determination block 1130 for determining a light source standard by evaluating the position of the light source, the evaluation being based at least in part on a shadow cast by the engineering three-dimensional object in the digital image of the engineering three-dimensional object and at least in part on a color saturation in the digital image of the color check card; and a calibration block 1140 for calibrating the digital microscopy system using the light source to generate a calibrated digital microscopy system.

[0205] Method 1100 Fig.111100 is shown in association with various computer readable media (CRM) blocks 1111, 1121, 1131, and 1141. These blocks typically include instructions suitable for execution by one or more processors (or processor cores) to command a computing device or system to perform one or more actions. Although various blocks are shown, a single medium may be configured with instructions to at least partially allow the execution of various actions of method 1100. As an example, a computer readable medium (CRM) may be a non-transitory and non-carrier computer readable storage medium. As an example, one or more of blocks 1111, 1121, 1131, and 1141 may be in the form of processor executable instructions.

[0206] exist Fig.11 In the example of , system 1190 includes one or more information storage devices 1191, one or more computers 1192, one or more networks 1195, and instructions 1196. With respect to one or more computers 1192, each computer may include one or more processors (e.g., or processing cores) 1193 and a memory 1194 for storing instructions 1196, which instructions may be executed, for example, by at least one of the one or more processors 1193 (see, for example, blocks 1111, 1121, 1131, and 1141). 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), and the like.

[0207] As an example, a method may include using a digital camera of a digital microscopy system to acquire a digital image of an engineering three-dimensional object positioned on a base and illuminated by a light source of the digital microscopy system; using the digital camera to acquire a digital image of a color check card positioned on the base and illuminated by the light source; determining a light source standard by evaluating the position of the light source, the evaluation being based at least in part on a shadow cast by the engineering three-dimensional object in the digital image of the engineering three-dimensional object and at least in part on the color saturation in the digital image of the color check card; and calibrating the digital microscopy system using the light source standard to generate a calibrated digital microscopy system. In such an example, the light source standard may be a distance measured from the base to the light source or, for example, an orientation of the light source relative to the engineering three-dimensional object. As an example, calibration may be performed via a machine, for example, considering a circuit operatively coupled to a motor, the motor being actuated via one or more commands to adjust a distance with respect to one or more components of the system according to one or more standards and / or to adjust an orientation with respect to one or more components of the system according to one or more standards.

[0208] As an example, a method may include using a digital camera to acquire a digital image of a field of view card positioned on a base, and, for example, evaluating the digital image of the field of view card to determine a digital camera standard, wherein the method may include calibrating a system using the digital camera standard. In such an example, the digital camera standard may be a distance measured from the base to the digital camera.

[0209] As an example, a method may include determining an aperture standard by evaluating a color in a digital image of a color check card. In such an example, evaluating a color in the digital image of the color check card may include calculating an error value between a color component and a reference color component.

[0210] As an example, a method may include setting one or more gains that may be associated with one or more colors of a sensor or sensors of a digital camera. In such an example, a digital file may be generated that includes a digital image and information about the one or more gains (e.g., taking into account metadata specifying the one or more gains).

[0211] As an example, a color check card can be used to calibrate a system that can use a digital camera to acquire a digital image of a 3D object. In such an example, the color check card can include a slanted edge feature, wherein the circuitry of the system can be used to calculate a modulation transfer function (MTF) value versus a frequency of cycles per unit distance based on the slanted edge feature in the digital image of the color check card. In such an example, based on the MTF curve, the circuitry of the system can be used to determine a clarity criterion, wherein the clarity criterion is an aperture value of an aperture of the digital camera.

[0212] As an example, a method may include generating a calibrated digital microscopy system, and using the calibrated digital microscopy system to acquire a digital image of a natural three-dimensional object. In such an example, the method may include using the digital image of the natural three-dimensional object to characterize the natural three-dimensional object to determine lithology. As an example, a method may include processing the digital image of the natural three-dimensional object to determine the type of fossil. For example, the material may include remains, imprints, or traces of past organisms preserved from past geological times (e.g., bones, shells, exoskeletons, stone imprints of animals or microorganisms).

[0213] As an example, a digital microscopy system may include an electromagnetic motor, wherein a method may include calibrating the digital microscopy system at least in part by actuating the electromagnetic motor to adjust a position of a light source of the digital microscopy system and / or to adjust a position of a digital camera of the digital microscopy system. As an example, the position may be adjusted based on a distance, an orientation, or another aspect of the system. As an example, the adjustment may be made in response to a determination regarding one or more metrics used for calibration. For example, as part of a calibration process, a circuit may issue a command to an electromagnetic motor to actuate the electromagnetic motor to cause a change in position of one or more components.

[0214] As an example, a system may include a digital camera; a light source; a processor; a memory accessible to the processor; and processor-executable instructions stored in the memory, the processor-executable instructions for commanding the system to: use the digital camera to acquire a digital image of an engineering three-dimensional object positioned on a base and illuminated by the light source; use the digital camera to acquire a digital image of a color check card positioned on the base and illuminated by the light source; and use at least the processor to determine a light source standard by evaluating the position of the light source, the evaluation being based at least in part on a shadow cast by the engineering three-dimensional object in the digital image of the engineering three-dimensional object and at least in part on a color saturation in the digital image of the color check card. In such an example, the light source standard may be a distance measured from the base to the light source. As explained, a digital microscopy system may include an electromagnetic motor that is actuatable to adjust the position of the light source of the digital microscopy system and / or adjust the position of the digital camera of the digital microscopy system.

[0215] As an example, one or more non-transitory computer-readable storage media may include processor-executable instructions for commanding a computing system to: use a digital camera to acquire a digital image of an engineering three-dimensional object positioned on a base and illuminated by a light source; use the digital camera to acquire a digital image of a color check card positioned on the base and illuminated by the light source; and determine a light source standard via evaluating the position of the light source, the evaluation being based at least in part on a shadow cast by the engineering three-dimensional object in the digital image of the engineering three-dimensional object and at least in part on a color saturation in the digital image of the color check card. In such an example, the light source standard may be a distance measured from the base to the light source.

[0216] As an example, the thickness of the sample tray or the thickness of the card may be considered such that the sample tray or the card defines a distance from the base to the light source. For example, the distance measured from the base may be a distance measured from the upper surface of the sample tray platform or the card, either of which may be about one millimeter to several millimeters thick. As an example, the distance may be a compensation distance, for example, considering a base disposed at a position where the sample tray or the card may be positioned on the base. In such an example, the distance may be compensated based on the thickness of the sample tray or the card. In general, adjusting the distance from the base adjusts the distance from the sample tray or the card positioned on the base.

[0217] As explained, the color check card may include a slanted edge feature, wherein the processor executable instructions may include instructions for commanding the computing system to calculate a modulation transfer function (MTF) curve of a modulation transfer function (MTF) value versus a frequency in number of cycles per unit distance based on the slanted edge feature in the digital image of the color check card, and determine a clarity standard based on the MTF curve, wherein the clarity standard may be an aperture value of an aperture of a digital camera that acquires the digital image of the color check card.

[0218] As an example, a computer program product may include one or more computer-readable storage media that may include processor-executable instructions for instructing a computing system to perform one or more methods and / or one or more portions of a method.

[0219] In some embodiments, one or more methods may be performed by a computing system. Fig.12 An example of a system 1200 is shown, which may include one or more computing systems 1201-1, 1201-2, 1201-3, and 1201-4, which may be operatively coupled via one or more networks 1209, which may include wired networks and / or wireless networks. As an example, Figure 4 The digital microscopy system 400 or another digital microscopy system may include Fig.12 The various features of system 1200 and / or operatively coupled to Fig.12 One or more instances of system 1200.

[0220] By way of example, a system may include a single computer system or an arrangement of distributed computer systems. Fig.12 In the example of , computer system 1201-1 may include one or more modules 1202, which may be or may include, for example, processor-executable instructions executable to perform various tasks (e.g., receiving information, requesting information, processing information, simulating, outputting information, etc.).

[0221] As an example, the modules may execute independently or in conjunction with one or more processors 1204 that are operatively coupled (e.g., via wire, wirelessly, etc.) to one or more storage media 1206. As an example, one or more of the one or more processors 1204 may be operatively coupled to at least one of the one or more network interfaces 1207. In such an example, the computer system 1201-1 may transmit and / or receive information, for example, via one or more networks 1209 (e.g., considering one or more of the Internet, a private network, a cellular network, a satellite network, etc.).

[0222] As an example, computer system 1201-1 may receive information from and / or transmit information to one or more other devices, which may be or may include, for example, one or more of computer systems 1201-2, etc. The device may be located at a different physical location than computer system 1201-1. As an example, the location may be, for example, a processing facility location, a data center location (e.g., a server farm, etc.), a drilling rig location, a well site location, a downhole location, etc.

[0223] As an example, a processor may be or may include a microprocessor, a microcontroller, a processor module or subsystem, a programmable integrated circuit, a programmable gate array, or another control or computing device.

[0224] As an example, storage media 1206 may be implemented as one or more computer-readable or machine-readable storage media. As an example, storage may be distributed within and / or between multiple internal and / or external enclosures of the computing system and / or additional computing systems.

[0225] As an example, a storage medium or multiple 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 programmable read-only memory (EEPROM), and flash memory; 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 disks, or other types of optical storage devices; or other types of storage devices.

[0226] As an example, the storage medium or media may be located in the machine running the machine-readable instructions, or located at a remote site from which the machine-readable instructions may be downloaded over a network for execution.

[0227] 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 circuits and / or application specific integrated circuits.

[0228] As an example, a system may include a processing device, which may be or may include a general purpose processor or a dedicated chip (eg, or chipset) such as an ASIC, FPGA, PLD, or other suitable device.

[0229] Fig.13 Components of an example of a computing system 1300 and an example of a networking system 1310 with a network 1320 are shown. As an example, Figure 4 The digital microscopy system 400 or another digital microscopy system may include Fig.13 Various features of system 1300 and / or system 1310 and / or operatively coupled to Fig.13 One or more instances of system 1300 and / or system 1310.

[0230] exist Fig.13 In the example, system 1300 includes one or more processors 1302, memory and / or storage components 1304, one or more input and / or output devices 1306, and bus 1308. In an example embodiment, instructions may be stored in one or more computer-readable media (e.g., memory / storage components 1304). Such instructions may be read by one or more processors (e.g., processor 1302) via a communication bus (e.g., bus 1308), which may be wired or wireless. One or more processors may execute such instructions to implement (in whole or in part) one or more properties (e.g., as part of a method). A user may view output from a process and interact with the process via an I / O device (e.g., device 1306). In an example embodiment, a computer-readable medium may be a storage component, such as a physical memory storage device, such as a chip, a chip on a package, a memory card, etc. (e.g., a computer-readable storage medium).

[0231] In an example embodiment, the components may be distributed, such as distributed in a network system 1310. The network system 1310 includes components 1322-1, 1322-2, 1322-3, ... 1322-N. For example, component 1322-1 may include processor 1302, and component 1322-3 may include a memory accessible to processor 1302. In addition, component 1322-2 may include an I / O device for display and optionally interacting with the method. Network 1320 may be or may include the Internet, an intranet, a cellular network, a satellite network, etc.

[0232] As an example, the device may be a mobile device including one or more network interfaces for conveying information. 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 multiple components, such as a main processor, a memory, a display, a display graphics circuit (e.g., optionally including a touch and gesture circuit), a SIM slot, an audio / video circuit, a motion processing circuit (e.g., an accelerometer, a gyroscope), a wireless LAN circuit, a smart card circuit, a transmitter circuit, a GPS circuit, and a battery. As an example, the mobile device may be configured as a cellular phone, a tablet computer, etc. As an example, the method may be implemented (e.g., in whole or in part) using a mobile device. As an example, the system may include one or more mobile devices.

[0233] As an example, the system may be a distributed environment, such as a so-called "cloud" environment, in which various devices, components, etc. interact for purposes of data storage, communication, computing, etc. As an example, a device or system may include one or more components for communicating information via one or more of the Internet (e.g., where communication is performed via one or more Internet protocols), a cellular network, a satellite network, etc. As an example, a method may be implemented in a distributed environment (e.g., in whole or in part as a cloud-based service).

[0234] As an example, information may be input from a display (e.g., consider a touch screen), output to a display, or both. As an example, information may be output to a projector, a laser device, a printer, etc., so that the information can be viewed. As an example, information may be output stereoscopically or holographically. With respect to printers, consider 2D or 3D printers. As an example, a 3D printer may include one or more substances that can be output to construct a 3D object. For example, data may be provided to a 3D printer to construct a 3D representation of an underground stratum. As an example, layers (e.g., a ground plane, etc.) may be constructed in 3D, geological bodies, etc. may be constructed in 3D. As an example, wellbores, fractures, etc. may be constructed in 3D (e.g., as positive structures, as negative structures, etc.).

[0235] Although only a few example embodiments have been described in detail above, those skilled in the art will readily appreciate that many modifications may be made in the example embodiments. 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 not only structural equivalents, but also equivalent structures. Thus, while 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.

Claims

1. A method comprising: acquiring, using a digital camera of a digital microscopy system, a digital image of an engineered three-dimensional object positioned on a base and illuminated by a light source of the digital microscopy system; using the digital camera to acquire a digital image of a color inspection card positioned on the base and illuminated by the light source; determining a light source standard by evaluating a position of the light source, the evaluation based at least in part on a shadow cast by the engineering three-dimensional object in the digital image of the engineering three-dimensional object and based at least in part on a color saturation in the digital image of the color check card; as well as The digital microscopy system is calibrated using the light source standard to generate a calibrated digital microscopy system.

2. The method of claim 1, wherein the light source criteria comprises a distance measured from the base to the light source.

3. The method of claim 1, further comprising: A digital image of a field of view card positioned on the base is acquired using the digital camera.

4. The method of claim 3 further comprising evaluating the digital image of the view card to determine digital camera standards.

5. The method of claim 4, wherein the digital camera criteria comprises a distance measured from the base to the digital camera.

6. The method of claim 4, wherein the calibrating comprises using the digital camera standard.

7. The method of claim 1 further comprising determining an aperture standard by evaluating colors in the digital image of the color checker card.

8. The method of claim 7, wherein evaluating the color in the digital image of the color inspection card comprises calculating an error value between a color component and a reference color component.

9. The method of claim 1 , wherein the color check card includes a slanted edge feature, and the method further comprises calculating a modulation transfer function (MTF) curve of a frequency of a number of cycles per unit distance based on the slanted edge feature in the digital image of the color check card.

10. The method of claim 9, further comprising: A sharpness criterion is determined based on the MTF curve, wherein the sharpness criterion includes an f-stop value of an aperture of the digital camera.

11. The method of claim 1 further comprising using the calibrated digital microscopy system to acquire digital images of natural three-dimensional objects.

12. The method of claim 11, further comprising characterizing the natural three-dimensional object using the digital image of the natural three-dimensional object to determine lithology.

13. The method of claim 12, further comprising processing the digital image of the natural three-dimensional object to determine fossil type.

14. The method of claim 1, wherein the digital microscopy system further comprises an electromagnetic motor, and wherein the calibration comprises actuating the electromagnetic motor to adjust a position of the light source of the digital microscopy system or to adjust a position of the digital camera of the digital microscopy system.

15. A system comprising: Digital camera; light source; processor; a memory accessible to the processor; as well as processor-executable instructions stored in the memory, the processor-executable instructions being used to instruct the system to: using the digital camera to acquire a digital image of the engineered three-dimensional object positioned on the base and illuminated by the light source; using the digital camera to acquire a digital image of a color inspection card positioned on the base and illuminated by the light source; and A light source standard is determined using at least the processor by evaluating the position of the light source, the evaluation being based at least in part on shadows cast by the engineering three-dimensional object in the digital image of the engineering three-dimensional object and at least in part on color saturation in the digital image of the color check card.

16. The system of claim 15, wherein the light source criteria comprises a distance measured from the base to the light source.

17. The system of claim 15, further comprising an electromagnetic motor actuatable to adjust a position of the light source of the digital microscopy system or to adjust a position of the digital camera of the digital microscopy system.

18. One or more non-transitory computer-readable storage media comprising processor-executable instructions for instructing a computing system to: using a digital camera to acquire a digital image of the engineered three-dimensional object positioned on the base and illuminated by the light source; using the digital camera to acquire a digital image of a color inspection card positioned on the base and illuminated by the light source; and The light source standard is determined by evaluating the position of the light source, the evaluation being based at least in part on shadows cast by the engineering three-dimensional object in the digital image of the engineering three-dimensional object and at least in part on color saturation in the digital image of the color check card.

19. The one or more non-transitory computer-readable media of claim 18, wherein the light source criteria comprises a distance measured from the base to the light source.

20. One or more non-transitory computer-readable media as described in claim 18, wherein the color check card includes a slanted edge feature, wherein the processor executable instructions include instructions to command the computing system to perform the following operations: calculate a modulation transfer function (MTF) curve of a modulation transfer function (MTF) value versus a frequency in cycles per unit distance based on the slanted edge feature in the digital image of the color check card, and determine a clarity standard based on the MTF curve, wherein the clarity standard includes an aperture value of an aperture of the digital camera.

Images