Drilling fluid frame

Abstract

A method may include receiving real-time data related to a drilling fluid for a drilling operation that utilizes a drilling fluid system including a tank and a pump, where the drilling operation includes an operation of pumping the drilling fluid to a drill bit on a drill string that rotates to extend a borehole in a formation, the drilling fluid system including the tank and the pump, and the drilling fluid system including the tank and the pump. And wherein the drilling fluid flows to an annulus between the drill string and the formation to apply pressure to the formation; detecting a tank state from a set of tank states based at least in part on the real-time data, wherein the set of tank states includes a tank state with respect to one or more operational limits of the pump; and detecting a change in tank volume based at least in part on the tank condition as an indicator of an undesired interaction between the drilling fluid and the formation.

Description

[0001] Related Applications

[0002] This application claims the benefit and priority of U.S. Provisional Application No. 63 / 374,244, filed on September 1, 2022, the entire content of which is incorporated herein by reference. Background of the Invention

[0003] Unless otherwise indicated, this section does not describe the prior art of the claims and is not considered prior art.

[0004] Modern drilling techniques, whether for water, hydrocarbons, geothermal, or others, typically involve the use of drilling fluids (also known as drilling mud or simply mud) as part of the drilling process. Drilling fluids are typically pumped to the bottom of the hole and pick up the drill cuttings generated by the drill bit, and then they are lifted to the surface for processing. Drilling fluids typically serve a wide range of additional purposes. Solid particles in the drilling fluid can be used to coat the sides of the hole to prevent them from caving in. The composition of the mixture of drilling fluids (oil, water, gas, etc.) can vary depending on the purpose of the well or the specific section being drilled.

[0005] A rig typically includes circulation equipment for circulating and managing the drilling fluid. The circulation system typically includes mud tanks for storing the drilling fluid and mud pumps for pumping the drilling fluid. Mud tanks are also commonly referred to as mud pits. Mud tanks can include active tanks and reserve tanks for storing mixtures of drilling fluids for use at different times.

[0006] The volume of the drilling fluid can be an indicator of problems or issues during the drilling process. For example, an unexpected increase in the fluid may indicate that the fluid is leaving the formation and entering the borehole, which means a well kick may be imminent. An unexpected decrease in the fluid may indicate that the fluid is entering the formation and causing fluid loss. Given the complexity of the interaction between fluid volume, plans, and the drilling process, understanding what the fluid level in the drilling process means can be challenging. This can make it challenging to create intelligent and meaningful alerts and notifications based on the drilling fluid. Summary of the Invention

[0007] A method may include receiving real-time data related to a drilling fluid for a drilling operation that utilizes a drilling fluid system including a tank and a pump, where the drilling operation includes pumping the drilling fluid to a bit on a drill string that rotates to extend a borehole in a formation, and where the drilling fluid flows into an annulus between the drill string and the formation to apply pressure to the formation; detecting a tank state from a set of tank states based at least in part on the real-time data, where the set of tank states includes tank states defined in terms of one or more operations of the pump; and detecting a change in tank volume based at least in part on the tank state as an indicator of an undesired interaction between the drilling fluid and the formation. A system may include one or more processors; a memory accessible to at least one of the one or more processors; processor-executable instructions stored in the memory and executable to direct the system to: receive real-time data related to a drilling fluid for a drilling operation that utilizes a drilling fluid system including a tank and a pump, where the drilling operation includes pumping the drilling fluid to a bit on a drill string that rotates to extend a borehole in a formation, and where the drilling fluid flows into an annulus between the drill string and the formation to apply pressure to the formation; detect a tank state from a set of tank states based at least in part on the real-time data, where the set of tank states includes tank states defined in terms of one or more operations of the pump; and detect a change in tank volume based at least in part on the tank state as an indicator of an undesired interaction between the drilling fluid and the formation. One or more non-transitory computer-readable storage media may include processor-executable instructions to direct a computing system to: receive real-time data related to a drilling fluid for a drilling operation that utilizes a drilling fluid system including a tank and a pump, where the drilling operation includes pumping the drilling fluid to a bit on a drill string that rotates to extend a borehole in a formation, and where the drilling fluid flows into an annulus between the drill string and the formation to apply pressure to the formation; detect a tank state from a set of tank states based at least in part on the real-time data, where the set of tank states includes tank states defined in terms of one or more operations of the pump; and detect a change in tank volume based at least in part on the tank state as an indicator of an undesired interaction between the drilling fluid and the formation. Various other devices, systems, methods, etc. are also disclosed.

[0008] The present invention content is provided to introduce a selection of concepts further described below in the detailed description. The present invention content is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used to help limit the scope of the claimed subject matter. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0010] Figure 1 Shows an example of the system;

[0011] Figure 2 Shows an example of the system;

[0012] Figure 3 Shows an example of the system;

[0013] Figure 4 Shows an example of the table;

[0014] Figure 5 Shows an example of the graphical user interface;

[0015] Figure 6 Shows an example of the graphical user interface;

[0016] Figure 7 Shows an example of the graphical user interface;

[0017] Figure 8 Shows an example of the graphical user interface;

[0018] Figure 9 Shows an example of the graphical user interface;

[0019] Figure 10 Shows an example of the graphical user interface;

[0020] Figure 11 Shows an example of the graphical user interface;

[0021] Figure 12 Shows an example of the method;

[0022] Figure 13 Shows an example of the graphical user interface;

[0023] Figure 14 Shows an example of the method;

[0024] Figure 15 Shows an example of the graphical user interface;

[0025] Figure 16 Shows an example of the system; and

[0026] Figure 17 Shows an example of the method. Detailed Description

[0027] Introduction

[0028] The following detailed description refers to the accompanying drawings. Where convenient, the same reference numerals are used in the drawings and the following description to refer to the same or similar components. Although several embodiments and features of the present disclosure are described herein, modifications, adaptations, and other implementations are possible without departing from the spirit and scope of the present disclosure.

[0029] Although terms such as "first" and "second" may be used herein to describe various elements, these terms are used to distinguish one element from another. For example, without departing from the scope of the present disclosure, a first object or step may be referred to as a second object or step, and similarly, a second object or step may be referred to as a first object or step. The first object or step and the second object or step are each an object or step, but they are not considered the same object or step.

[0030] The terms used in this description are for the purpose of describing particular embodiments and are not limiting. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term "and / or" as used herein refers to and encompasses any possible combination of one or more of the associated listed items. It will be further understood that when used in this specification, the terms "includes," "including," "comprises," and / or "comprising" specify the presence of the stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. Additionally, as used herein, the term "if" may be interpreted to mean "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context.

[0031] Embodiments

[0032] This description should not be regarded as limiting, but is made only for the purpose of describing the general principles of the embodiments. The scope of the described embodiments should be determined with reference to the issued claims.

[0033] Figure 1 An example of a system 100 including a workspace frame 110 is shown, and the workspace frame 110 can provide instantiation, presentation, interaction with a graphical user interface (GUI) 120, etc. In Figure 1In the example of, the GUI 120 may include graphical controls for a computing framework (e.g., an application, etc.) 121, a project 122, visualization features 123, one or more other features 124, data access 125, and data storage 126.

[0034] In Figure 1 the example of, the workspace framework 110 may be customized for a specific geological environment (such as the exemplary geological environment 150). For example, the geological environment 150 may include layers (e.g., stratified), which include a reservoir 151 and may intersect with a fault 153. As an example, the geological environment 150 may be equipped with various sensors, detectors, actuators, etc. For example, the device 152 may include a communication circuit, which may be configured to receive and transmit information regarding one or more networks 155. Such information may include information associated with downhole equipment 154, which may be a device for acquiring information, assisting in resource recovery, etc. Other devices 156 may be located away from the well site and include sensing, detecting, transmitting, or other circuits. Such devices may include storage and communication circuits to store and transmit data, instructions, etc. As an example, one or more satellites may be provided for purposes such as communication, data acquisition, etc. For example, Figure 1 shows a satellite communicating with the network 155, which may be configured for communication, note that the satellite may additionally or alternatively include circuits for imaging (e.g., spatial, spectral, temporal, radiation, etc.).

[0035] Figure 1 The geological environment 150 is also shown as optionally including well-associated devices 157 and 158, the well including a substantially horizontal portion that may intersect with one or more fractures 159. For example, consider a well in a shale formation, which may include natural fractures, artificial fractures (e.g., hydraulic fractures), or a combination of natural and artificial fractures. As an example, a well may be drilled for a laterally extending reservoir. In such an example, there may be lateral variations in properties, stresses, etc., where the assessment of such variations may assist in planning, operations, etc. to develop a laterally extended reservoir (e.g., via fracturing, injection, extraction, etc.). As an example, the devices 157 and / or 158 may include components, a system, multiple systems, etc. for fracturing, seismic sensing, analysis of seismic data, assessment of one or more fractures, etc.

[0036] In Figure 1 the example of, the GUI 120 shows some examples of computing frameworks, including the DRILLPLAN, DRILLOPS, PETREL, TECHLOG, PETROMOD, ECLIPSE, PIPESIM, and INTERSECT frameworks (SLB, Houston, Texas).

[0037] The DRILLPLAN framework provides digital well construction plans and includes features for automating repetitive tasks and verification workflows, enabling the rapid generation of improved-quality drilling programs (e.g., digital drilling plans, etc.) while ensuring consistency.

[0038] The DRILLOPS framework can execute digital drilling plans and ensure plan compliance while providing goal-based automation. The DRILLOPS framework can automatically generate activity plans for individual operations, whether they are monitored and / or controlled on the rig or in town. Automation can utilize data analysis and learning systems to assist and optimize tasks, e.g., setting the ROP to drill a stand. A preset menu of automatable drilling tasks can be presented, and using data analysis and models, the plan can be executed in a way that achieves specified goals, where, for example, measurements can be used for calibration. The DRILLOPS framework provides the flexibility to dynamically modify and replan activities, e.g., based on a live assessment of various factors (e.g., equipment, personnel, and supplies). Well construction activities (e.g., tripping, drilling, cementing, etc.) can be continuously monitored and dynamically updated using feedback from operational activities. The DRILLOPS framework can provide various levels of automation based on planning and / or replanning (e.g., via the DRILLPLAN framework), feedback, etc.

[0039] The PETREL framework can be part of the DELFI environment for geoscience and geotechnical engineering, e.g., to analyze subsurface data from exploration to production of fluids from a reservoir. The DELFI Cognitive Exploration and Production (E&P) environment (SLB, Houston, Texas), referred to herein as the DELFI environment or DELFI framework, is a secure, cognitive, cloud-based collaborative environment that integrates data and workflows with digital technologies such as artificial intelligence and machine learning.

[0040] The PETREL framework provides components that allow for the optimization of various exploration, development, and production operations. The PETREL framework includes seismic-to-simulation software components that can output information for increasing reservoir performance, e.g., by improving the productivity of the asset team. By using such a framework, various professionals (e.g., geophysicists, geologists, and reservoir engineers) can develop collaborative workflows and integrate operations to streamline processes (e.g., regarding one or more geological settings, etc.). Such a framework can be considered an application (e.g., executable using one or more devices) and can be considered a data-driven application (e.g., where data is input for the purpose of modeling, simulation, etc.).

[0041] The TECHLOG framework can process and handle field and laboratory data for various geological environments (e.g., deepwater exploration, shale, etc.). The TECHLOG framework can structure wellbore data for analysis, planning, etc.

[0042] The PETROMOD framework provides petroleum system modeling capabilities, which can combine one or more of seismic, well, and geological information to model the evolution of sedimentary basins. The PETROMOD framework can predict whether and how reservoirs are filled with hydrocarbons, including the sources and times of hydrocarbon generation, migration routes, quantities, and hydrocarbon types under subsurface or surface conditions.

[0043] The ECLIPSE framework provides numerical solutions for reservoir simulators (e.g., as a computational framework) to rapidly and accurately predict the dynamic behavior of various types of reservoirs and development scenarios.

[0044] The INTERSECT framework provides high-resolution reservoir simulators for simulating detailed geological features and quantifying uncertainties, e.g., by creating accurate production scenarios, and by integrating precise models of surface facilities and field operations, the INTERSECT framework can produce reliable results, which can be continuously updated through real-time data exchange (e.g., data from one or more types of data acquisition devices in the field, which can collect data during one or more types of field operations, etc.). The INTERSECT framework can provide completion configurations for complex wells, which can be built in the oilfield, can provide detailed enhanced oil recovery (EOR) recipes, which can be implemented in the oilfield, can analyze the application of steam injection and other thermal EOR techniques for implementation in the oilfield, advanced production control in reservoir connectivity and flexible oilfield management, and flexibility to script customized solutions for improved modeling and oilfield management control. Like other example frameworks, the INTERSECT framework can be used as part of the DELFI environment, e.g., for rapidly simulating multiple concurrent scenarios. For example, workflows can utilize one or more of the reservoir simulation features available on demand in the DELFI environment.

[0045] The above DELFI environment provides various features for workflows related to subsurface analysis, planning, construction, and production, e.g., as shown by the workspace framework 110. As Figure 1 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 can be received via one or more interfaces in one or more forms (e.g., acquiring data regarding operating conditions, equipment conditions, environmental conditions, etc.).

[0046] As an example, the workflow can proceed to a geological and geophysical (“G&G”) service provider, which can generate well trajectories, which can involve performing one or more G&G frameworks (e.g., considering the PETREL framework, etc.).

[0047] In Figure 1 the example of, the visualization feature 123 can be implemented via the workspace framework 110, e.g., to perform tasks associated with one or more of a subsurface region, planned operations, constructing wells, and / or surface fluid networks and production from a reservoir.

[0048] As an example, the visualization feature can provide visualization of various earth models, properties, etc. in one or more dimensions. As an example, the visualization feature can provide a rendering of information in multiple dimensions, which can optionally include multi-resolution rendering. In this example, the information being rendered can be associated with one or more frameworks and / or one or more data stores. As an example, the visualization feature can include one or more control features for controlling a device, which can include, e.g., a field device that can perform one or more field operations. As an example, the workflow can utilize one or more frameworks to generate information that can be used to control one or more types of field devices (e.g., drilling equipment, cable equipment, fracturing equipment, etc.).

[0049] Regarding a reservoir model that can be suitable for utilization by a simulator, consider the acquisition of seismic data acquired via reflection seismology, which is used for geophysics, e.g., to estimate the properties of subsurface formations. As an example, reflection seismology can provide seismic data representing waves of elastic energy (e.g., as transmitted by P-waves and S-waves, in a frequency range of approximately 1 Hz to approximately 100 Hz). The seismic data can be processed and interpreted, e.g., to better understand the composition, fluid content, extent, and geometry of subsurface rocks. Such interpretation results can be used for planning, simulating, executing, etc. one or more operations for producing fluids from a reservoir (e.g., reservoir rocks, etc.).

[0050] As an example, the model can be a simulated version of a geological environment. As an example, the simulator can include features for simulating physical phenomena in a geological environment 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 execute instructions using one or more processors to solve a system of equations that describes physical phenomena subject to various constraints. In such an example, the system of equations can be defined spatially (e.g., numerically discretized) according to a spatial model that includes rock layers, geological body layers, etc., having corresponding positions that can be based on the interpretation of seismic and / or other data. The spatial model can be a cell-based model, where the cells are defined by a grid (e.g., a mesh). The cells in a cell-based model can represent physical regions or volumes in a geological environment, where the cells can be assigned physical properties (e.g., permeability, fluid properties, etc.) that can be closely related to one or more physical phenomena (e.g., fluid volume, fluid flow rate, pressure, etc.). A reservoir simulation model can be a cell-based spatial model.

[0051] Although several simulators are shown in the example of Figure 1 , additionally or alternatively, one or more other simulators can be utilized. For example, consider the VISAGE geomechanics simulator (SLB, Houston, Texas) or the PIPESIM network simulator (SLB, Houston, Texas), etc. The VISAGE simulator includes a finite element numerical solver that can provide simulation results such as regarding compaction and subsidence of a geological environment, well and wellbore integrity in a geological environment, caprock and fault seal integrity in a geological environment, fracture behavior in a geological environment, heat recovery in a geological environment, CO 2Results of treatments, etc. The PIPESIM simulator includes a solver that can provide simulation results such as multiphase flow results (e.g., from the reservoir to the wellhead and beyond the wellhead, etc.), flowline and surface facility performance, etc. The PIPESIM simulator can be integrated, for example, with the AVOCET production operations framework (SLB, Houston, Texas). As an example, one or more reservoirs can be simulated with respect to one or more enhanced recovery techniques (e.g., considering thermal processes such as steam-assisted gravity drainage (SAGD)). As an example, the PIPESIM simulator can be an optimizer that can optimize one or more operating scenarios at least in part via simulation of physical phenomena. The MANGROVE simulator (SLB, Houston, Texas) provides optimization of stimulation designs (e.g., stimulation treatment operations such as hydraulic fracturing) in a reservoir-centered environment. The MANGROVE framework can combine scientific and experimental work to predict the geomechanical propagation of hydraulic fractures, reactivation of natural fractures, etc., as well as production predictions within a 3D reservoir model (e.g., production from the oil drainage area of the reservoir where fluid moves to and / or from the well via one or more types of fractures).

[0052] As an example, a tool can be positioned to obtain information in a portion of a borehole. Analysis of such information can reveal voids, dissolution surfaces (e.g., dissolution along bedding planes), stress-related features, dip events, etc. As an example, a tool can obtain information that can help characterize a fractured reservoir, optionally where the fractures can be natural and / or man-made (e.g., hydraulic fractures). Such information can assist in well completion, stimulation treatments, etc. As an example, a framework such as the TECHLOG framework described above can be used to analyze the information obtained by the tool.

[0053] As an example, a workflow can utilize one or more types of data for one or more processes (e.g., formation modeling, basin modeling, well completion design, drilling, production, injection, etc.). As an example, one or more tools can provide data that can be used in one or more workflows that can implement one or more frameworks (e.g., PETREL, TECHLOG, PETROMOD, ECLIPSE, etc.).

[0054] In Figure 1 the example of, drilling can be performed in the geological environment 150, for example, to access the reservoir 151, which can be accessed from land or sea. In Figure 1In this case, the downhole device 154 can be part of, for example, a bottom hole assembly (BHA). The BHA can be used for drilling. The downhole device 154 can transmit information to a device at the surface. The downhole device 154 can receive instructions and information from a device at the surface. During well construction, various operations (such as cementing, wireline evaluation, testing, etc.) can be performed. In such an embodiment, data collected by tools and sensors and used for reasons such as reservoir characterization can be collected and transmitted.

[0055] The well can include a substantially horizontal portion (e.g., a lateral portion) that can intersect one or more fractures. For example, a well in a shale formation can cross natural fractures, artificial fractures (e.g., hydraulic fractures), or a combination thereof. Directional drilling techniques as described herein can be used to construct such wells. However, these same techniques can be used in combination with other types of directional wells (e.g., deviated wells, S-shaped wells, extended reach wells, etc.) and are not limited to horizontal wells.

[0056] Figure 2 An example of a wellsite system 200 is shown (e.g., at a wellsite that can be onshore or offshore). As shown, the wellsite system 200 can include a mud tank 201 for holding mud and other materials (e.g., where the mud can be drilling fluid); a pumping line 203 that serves as an inlet for a mud pump 204 for pumping mud from the mud tank 201 such that the mud flows to a vibrating hose 206; a drawworks 207 for reeling in one or more drill strings 212; a standpipe 208 that receives mud from the vibrating hose 206; a kelly 209 that receives mud from the standpipe 208; one or more gooseneck pipes 210; a traveling block 211; a crown block 213 for carrying the traveling block 211 via one or more drill strings 212; a derrick 214; a kelly 218 or a top drive 240; a kelly drive bushing 219; a rotary table 220; a drill floor 221; a bell nipple 222; one or more blowout preventers (BOPs) 223; a drill string 225; a drill bit 226; a casing head 227; and a flow line 228 for transporting mud and other materials to, for example, the mud tank 201.

[0057] In Figure 2 the example system, a borehole 232 is formed in the subterranean formation 230 by rotary drilling; note that various exemplary embodiments can also use one or more directional drilling techniques, equipment, etc.

[0058] As Figure 2 shown in the example of, the drill string 225 is suspended within the borehole 232 and has a drill string assembly 250 that includes a drill bit 226 at its lower end. As an example, the drill string assembly 250 can be a bottom hole assembly (BHA).

[0059] The wellsite system 200 can provide operations of the drill string 225 and other operations. As shown, the wellsite system 200 includes a traveling block 211 and a derrick 214 positioned above the borehole 232. As described above, the wellsite system 200 can include a rotary table 220, through which the drill string 225 passes through an opening in the rotary table 220.

[0060] As Figure 2 shown in the example of, the wellsite system 200 can include a kelly 218 and associated components, etc., or a top drive 240 and associated components. Regarding the kelly example, the kelly 218 can be a square or hexagonal metal / alloy bar with holes drilled therein for use as a mud flow path. The kelly 218 can be used to transfer rotational motion from the rotary table 220 to the drill string 225 via a kelly drive bushing 219 while allowing the drill string 225 to lower or raise during rotation. The kelly 218 can pass through the kelly drive bushing 219, and the kelly drive bushing 219 can be driven by the rotary table 220. As an example, the rotary table 220 can include a main bushing operably coupled to the kelly drive bushing 219 such that rotation of the rotary table 220 can rotate the kelly drive bushing 219 and thus rotate the kelly 218. The kelly drive bushing 219 can include an internal profile that matches the external profile (e.g., square, hexagonal, etc.) of the kelly 218; however, with a slightly larger size such that the kelly 218 can freely move up and down inside the kelly drive bushing 219.

[0061] Regarding the top drive example, the top drive 240 can provide the functions performed by the kelly and the rotary table. The top drive 240 can rotate the drill string 225. As an example, the top drive 240 can include one or more motors (e.g., electric motors and / or hydraulic motors) that are connected by appropriate gearing to a short pipe section called a quill, which in turn can be screwed into a protector sub or the drill string 225 itself. The top drive 240 can be suspended from the traveling block 211, and thus the rotary mechanism can freely travel up and down the derrick 214. As an example, the top drive 240 can allow drilling to be performed using more joint stands than the kelly / rotary table method.

[0062] In Figure 2 the example of, the mud tank 201 can hold mud, which can be one or more types of drilling fluids. As an example, a wellbore can be drilled to produce fluid, inject fluid, or both (e.g., hydrocarbons, minerals, water, etc.).

[0063] In Figure 2In the example, the drill string 225 (e.g., including one or more downhole tools) can be composed of a series of pipes that are threaded together to form a long pipe, with a drill bit 226 located at its lower end. When the drill string 225 advances into the wellbore for drilling, at some point before or simultaneous with drilling, mud can be pumped by a pump 204 from a mud tank 201 (e.g., or other source) via pipelines 206, 208, and 209 to the port of the kelly 218, or for example to the port of a top drive 240. The mud can then flow through channels (e.g., or multiple channels) in the drill string 225 and out of ports located on the drill bit 226 (see, e.g., the direction arrows). When the mud exits the drill string 225 via the ports in the drill bit 226, it can then circulate upward through the annular region between the outer surface of the drill string 225 and the surrounding wall (e.g., open borehole, casing, etc.), as indicated by the direction arrows. In this way, the mud lubricates the drill bit 226 and carries thermal energy (e.g., friction or other energy) and formation cuttings to the surface, where the mud (e.g., and cuttings) can return to the mud tank 201, for example for recirculation (e.g., by treatment to remove cuttings, etc.).

[0064] The mud pumped into the drill string 225 by the pump 204 can form a mud cake that lines the wellbore after leaving the drill string 225. Among other functions, the mud cake can reduce the friction between the drill string 225 and the surrounding wall (e.g., borehole, casing, etc.). The reduction in friction can facilitate the advancement or retraction of the drill string 225. During a drilling operation, the entire drill string 225 can be pulled out of the wellbore and optionally replaced, for example, with a new or sharp drill bit, a drill string of a smaller diameter, etc. As described above, the action of pulling the drill string out of the hole or replacing the drill string in the hole is called tripping. Depending on the tripping direction, tripping can be called pulling out or tripping out or can be called running in or tripping in.

[0065] As an example, consider running in, where when the drill bit 226 of the drill string 225 reaches the bottom of the wellbore, the pumping of mud begins to lubricate the drill bit 226 for drilling to enlarge the wellbore. As described above, the mud can be pumped by the pump 204 into the channels of the drill string 225, and when filling the channels, the mud can act as a transmission medium to transmit energy, for example, energy that can encode information as in mud pulse telemetry.

[0066] As an example, a mud pulse telemetry device can include downhole devices that are configured to effect pressure changes in the mud to generate one or more acoustic waves that can modulate information. In such an example, information from downhole equipment (e.g., one or more modules of the drill string 225) can be transmitted to surface equipment, and the surface equipment can relay such information to other equipment for processing, control, etc.

[0067] As an example, the telemetry device can be operated via energy transfer through the drill string 225 itself. For example, consider a signal generator that transmits an encoded energy signal to the drill string 225 and a repeater that can receive this energy and repeat it to further transmit the encoded energy signal (e.g., information, etc.).

[0068] As an example, the drill string 225 can be equipped with a telemetry device 252 that includes a rotatable drive shaft, a turbine impeller, a modulation rotor, a modulation stator, and a controllable brake. The turbine impeller is mechanically coupled to the drive shaft such that mud can cause the turbine impeller to rotate. The modulation rotor is mechanically coupled to the drive shaft such that rotation of the turbine impeller causes rotation of the modulation rotor. The modulation stator is mounted adjacent to or near the modulation rotor such that rotation of the modulation rotor relative to the modulation stator generates pressure pulses in the mud. The controllable brake is used to selectively brake the rotation of the modulation rotor to modulate the pressure pulses. In such an example, an alternator can be coupled to the aforementioned drive shaft, where the alternator includes at least one stator winding electrically coupled to a control circuit to selectively short-circuit at least one stator winding to electromagnetically brake the alternator, thereby selectively braking the rotation of the modulator rotor to modulate the pressure pulses in the mud.

[0069] In Figure 2 the example of, the surface control and / or data acquisition system 262 can include circuitry to sense the pressure pulses generated by the telemetry device 252 and, for example, transmit the sensed pressure pulses or information derived therefrom for processing, control, etc.

[0070] The components 250 of the illustrated example include various modules 254, 256, and 258, which can be or include logging-while-drilling (LWD) modules (e.g., LWD tools), measurement-while-drilling (MWD) modules (e.g., MWD tools), and / or one or more other modules. As an example, the module 260 can be or include a rotary steerable system (RSS) (e.g., an RSS or RSS tool) and / or a motor (e.g., a mud motor, etc.). In various examples, the drill string can include an RSS tool, a mud motor, or an RSS tool and a mud motor. As shown, the component 250 includes a drill bit 226. Such components or modules can be referred to as tools, where the drill string can include multiple tools.

[0071] As for RSS, it relates to techniques for directional drilling. Directional drilling involves drilling into the ground to form a deviated borehole such that the trajectory of the borehole is not vertical; instead, the trajectory deviates from the vertical direction along one or more portions of the borehole. As an example, consider a target located at a lateral distance from the surface location where the rig can be stationed. In such an example, the borehole can start from a vertical section and then deviate from the vertical section such that the borehole aims at and eventually reaches the target. Directional drilling can be implemented where the target may not be accessible from a vertical position at the Earth's surface, where there are substances in the Earth that may impede drilling or be otherwise detrimental (e.g., consider salt domes, etc.), where the formations extend laterally (e.g., consider relatively thin but laterally extensive reservoirs), where multiple boreholes are to be drilled from a single surface borehole, where relief wells are required, etc.

[0072] One method of directional drilling involves a mud motor; however, there can be some challenges with mud motors depending on factors such as the rate of penetration (ROP), the transfer of weight to the bit due to friction (e.g., weight on bit, WOB), etc. The mud motor can be a positive displacement motor (PDM) that operates to drive the bit (e.g., during directional drilling, etc.). The PDM operates when drilling fluid is pumped through the PDM, where the PDM converts the hydraulic power of the drilling fluid into mechanical power to rotate the bit.

[0073] As an example, a mud motor (e.g., PDM) can operate in different modes, which can include a rotary mode and a slide mode. The slide mode involves drilling with the mud motor rotating the bit downhole without rotating the drill string from the surface. This operation can be carried out when the BHA has been assembled with a bent sub or a bent housing mud motor or both for directional drilling. Sliding can be used to build and control or adjust the hole angle. In directional drilling, the orientation of the bit can be achieved through a bent sub and a measuring device for determining the offset direction, and the bent sub can have a relatively small angular offset relative to the axis of the drill string. Without rotating the drill string, the bit can rotate as the mud flows through the mud motor to drill in the direction it is pointing. With a steerable motor, when the desired wellbore direction is reached, the entire drill string can be rotated to drill straight rather than at an angle. By controlling the amount of hole drilled in the slide mode versus the rotary mode, the wellbore trajectory can be controlled quite precisely.

[0074] As an example, the PDM can operate in a combined rotation mode where surface equipment is used to rotate the bit of the drill string by rotating the entire drill string (e.g., rotary table, top drive, etc.), and where the drilling fluid is used to rotate the bit of the drill string. In such an example, the surface RPM (SRPM) can be determined by using the surface equipment, and various factors related to the flow of the drilling fluid, mud motor type, etc. can be used to determine the downhole RPM of the mud motor. As an example, in the combined rotation mode, assuming the SRPM and the mud motor RPM are in the same direction, the bit RPM can be determined or estimated as the sum of the SRPM and the mud motor RPM.

[0075] As an example, when the drill string is not rotated from the surface (e.g., as in the rotary mode), the PDM mud motor can operate in a so-called sliding mode. In such an example, the bit RPM can be determined or estimated based on the RPM of the mud motor. As an example, the drill string including the mud motor can be oscillated using surface mechanisms such as, for example, a top drive. In such an example, the top drive can oscillate the drill string clockwise and counterclockwise while the drilling fluid drives the rotation of the mud motor. In such an example, one or more techniques can be employed to control the drilling direction (e.g., bit orientation), degree of oscillation, etc. Since the oscillation involves clockwise and counterclockwise movement, this oscillation is not the rotation used in rotary drilling.

[0076] The RSS can perform directional drilling where there is continuous rotation from surface equipment, which can reduce the sliding of the steerable motor (e.g., PDM). The RSS can be deployed when performing directional drilling (e.g., deviated well, horizontal well, or extended reach well). The RSS can be aimed at minimizing interaction with the borehole wall, which can help maintain borehole quality. The RSS can be aimed at applying a relatively consistent lateral force similar to a stabilizer that rotates with the drill string or orientates the bit in a desired direction while continuously rotating at the same revolutions per minute as the drill string.

[0077] Module 254 can be an LWD module, which can be housed in a suitable type of drill collar and can contain one or more selected types of logging tools. It will also be understood that more than one LWD module and / or one MWD module can be employed, e.g., as represented by module 256 of drill string assembly 250. In the case of referring to the location of the LWD module, as an example, it can refer to the module at the location of module 254, module 256, etc. The LWD module can include the ability to measure, process, and store information and to communicate with surface equipment. In the example shown, module 254 can include a seismic measurement device.

[0078] In the case where module 256 is an MWD module (e.g., an MWD tool), it can be accommodated in a drill collar of a suitable type and can include one or more devices for measuring the characteristics of drill string 225 and bit 226. As an example, the MWD tool can include equipment for generating electricity, e.g., to power various components of drill string 225. As an example, the MWD tool can include telemetry equipment 252, e.g., where one or more turbine impellers can generate electricity through the flow of mud; it should be understood that other power sources and / or battery systems can be employed to power the various components. As an example, module 256 can include one or more of the following types of measuring devices: weight-on-bit measuring device, torque measuring device, vibration measuring device, shock measuring device, stick-slip measuring device, direction measuring device, and inclination measuring device.

[0079] Figure 2 Some examples of the types of holes that can be drilled are also shown. For example, consider inclined hole 272, S-shaped hole 274, deep inclined hole 276, and horizontal hole 278.

[0080] As an example, a drilling operation can include directional drilling, where for example at least a portion of the well includes a curved axis. For example, consider the radius defining the curvature, where the inclination relative to the vertical direction can vary until an angle between about 30 degrees and about 60 degrees is reached, or for example an angle of about 90 degrees or possibly greater than about 90 degrees is reached.

[0081] As an example, a directional well can include several shapes, where each shape can be designed to meet specific operational requirements. As an example, when information is relayed to the drilling engineer, the drilling process can be performed based on the information. As an example, the inclination and / or direction can be modified based on information received during the drilling process.

[0082] As an example, deviation of the hole can be achieved in part by using downhole motors and / or turbines. Regarding motors, for example, the drill string can include a positive displacement motor (PDM).

[0083] As an example, the system can be a steerable system and include equipment for performing methods such as geosteering. As described above, the steerable system can be an RSS or include an RSS. As an example, the steerable system can include a PDM or turbine on the lower part of the drill string, and a bent sub can be installed directly above the bit. As an example, above the PDM, an MWD device and / or an LWD device can be installed, and the MWD device provides real-time or near-real-time data of interest (e.g., inclination, direction, pressure, temperature, actual weight on the bit, torque stress, etc.). Regarding the latter, the LWD device can send various types of data of interest to the surface, including for example geological data (e.g., gamma ray logging, resistivity, density, and acoustic logging, etc.).

[0084] The coupling of sensors that provide information about the process of wellbore trajectory in real-time or near real-time with one or more well logs that characterize the formation from a geological perspective, for example, can allow for the implementation of a geosteering method. Such a method can include navigating a subterranean environment, for example, to follow a desired route to reach one or more desired targets.

[0085] As an example, a drill string can include an azimuthal density neutron (ADN) tool for measuring density and porosity; a measurement while drilling (MWD) tool for measuring inclination, azimuth, and shock; a compensated dual resistivity (CDR) tool for measuring resistivity and gamma ray related phenomena; one or more variable gauge stabilizers; one or more bent subs; and a geosteering tool, which can include a motor and optionally devices for measuring and / or responding to one or more of inclination, resistivity, and gamma ray related phenomena.

[0086] As an example, geosteering can include intentionally directing the control of a directional wellbore in a manner aimed at keeping the wellbore within a desired area, zone (e.g., an oil-producing zone), etc., based on the results of downhole geological well logging measurements. As an example, geosteering can include guiding the wellbore to keep the wellbore within a particular section of a reservoir, for example, to minimize gas and / or water breakthrough, and for example, to maximize the economic production from a well that includes the wellbore.

[0087] Referring again to Figure 2 , the wellsite system 200 can include one or more sensors 264 operatively coupled to a control and / or data acquisition system 262. As an example, one or more sensors can be at a surface location. As an example, one or more sensors can be at a downhole location. As an example, one or more sensors can be at one or more remote locations that are not within a distance on the order of about one hundred meters from the wellsite system 200. As an example, one or more sensors can be at the wellsite system 200 and at an offset wellsite in an offset wellsite in a common oilfield (e.g., an oilfield and / or gasfield).

[0088] As an example, one or more of the sensors 264 can be provided for tracking tubing, tracking the movement of at least a portion of the drill string, etc.

[0089] As an example, system 200 can include one or more sensors 266, which can sense signals and / or transmit signals to a fluid conduit, such as a drilling fluid conduit (e.g., a drilling mud conduit). For example, in system 200, one or more sensors 266 can be operatively connected to a portion of the riser 208 through which mud flows. As an example, downhole tools can generate pulses that can travel through the mud and be sensed by one or more of the one or more sensors 266. In such an example, the downhole tool can include associated circuitry, such as, for example, encoding circuitry that can encode signals to, for example, reduce the requirements regarding transmission. As an example, circuitry at the surface can include decoding circuitry to decode encoded information transmitted at least in part via mud pulse telemetry. As an example, circuitry at the surface can include encoder circuitry and / or decoder circuitry, and downhole circuitry can include encoder circuitry and / or decoder circuitry. As an example, system 200 can include a transmitter that can generate signals that can be transmitted downhole via mud (e.g., drilling fluid) as a transmission medium.

[0090] As an example, one or more portions of the drill string can become stuck. The term stuck can refer to different degrees of inability to move the drill string or remove one or more of the drill string from the borehole. As an example, in a stuck condition, the pipe can be rotated or lowered back into the borehole, or, for example, in a stuck condition, it may not be possible to axially move the drill string in the borehole, although a certain amount 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.

[0091] Regarding the term "stuck pipe", this can refer to a portion of the drill string that may not axially rotate or move. As an example, a condition known as "differential sticking" can be a condition where the drill string may not move along the axis of the hole (e.g., rotate or reciprocate). Differential sticking can occur when high contact forces caused by low reservoir pressure, high wellbore pressure, or both are applied over a large enough area of the drill string. Differential sticking can have time and financial costs.

[0092] As an example, the sticking force can be the product of the pressure differential between the wellbore and the reservoir and the area over which the pressure differential acts. This means that a relatively low pressure differential (ΔP) applied over a large working space domain can be as effective in sticking the pipe as a high pressure differential applied over a small area.

[0093] As an example, a condition known as "mechanical sticking" can be a condition that restricts or prevents the movement of the drill string through means other than differential pressure sticking. Mechanical sticking can be caused by, for example, one or more of junk in the hole, abnormal wellbore geometry, cement, keyseats, or accumulation of drill cuttings in the annulus. One or more types of sticking can introduce one or more types of risks, which can be directed at the borehole wall, equipment, mud, mud flow, etc. In various situations, sticking can introduce non-productive time (NPT), for example, depending on the degree of sticking, the frequency of sticking, one or more actions taken to reduce sticking, etc.

[0094] Figure 3 FIG. shows a schematic diagram of a computing or processor system 300 according to one embodiment. The processor system 300 may include one or more processors 302 having different core configurations (including multiple cores) and clock frequencies. One or more processors 302 may be operable to execute instructions, application logic, etc. It should be understood that these functions may be provided by multiple processors or multiple cores on a single chip operating in parallel and / or communicatively linked together. In at least one embodiment, one or more processors 302 may be or include one or more GPUs.

[0095] The processor system 300 may also include a memory system, which may be or include one or more memory devices and / or computer-readable media 304 having different physical sizes, accessibility, storage capacities, etc., such as flash drives, hard disk drives, disks, random access memories, etc., for storing data, such as images, files, and program instructions executed by the processor 302. In one embodiment, the computer-readable medium 304 may store instructions that, when executed by the processor 302, are configured to cause the processor system 300 to perform operations. For example, the execution of such instructions may cause the processor system 300 to implement one or more parts and / or embodiments of the above-described method.

[0096] The processor system 300 may also include one or more network interfaces 306. The network interface 306 may include any hardware, application, and / or other software. Thus, the network interface 306 may include an Ethernet adapter, a wireless transceiver, a PCI interface, and / or a serial network component for communicating over a wired or wireless medium using protocols such as Ethernet, wireless Ethernet, etc.

[0097] As an example, the processor system 300 can be a mobile device that includes one or more network interfaces for information communication. For example, the mobile device can include a wireless network interface (e.g., operable via one or more IEEE 802.11 protocols, ETSI GSM, Bluetooth, satellite, etc.). As an example, the mobile device can include components such as a main processor, memory, display, display graphics circuitry (e.g., optionally including touch and gesture circuitry), SIM slot, audio / video circuitry, motion processing circuitry (e.g., accelerometer, gyroscope, etc.), wireless LAN circuitry, smart card circuitry, transmitter circuitry, GPS circuitry, and a battery. As an example, the mobile device can be configured as a cellular phone, tablet, etc. As an example, the method can be implemented using a mobile device (e.g., in whole or in part). As an example, the system can include one or more mobile devices.

[0098] The processor system 300 can also include one or more peripheral interfaces 308 for communicating with a display, projector, keyboard, mouse, touchpad, sensors, other types of input and / or output peripheral devices, etc. In some embodiments, the components of the processor system 300 need not be enclosed within a single housing or even positioned in close proximity to each other, but in other implementations, the components and / or other components can be provided in a single housing. As an example, the system can be a distributed environment, e.g., a so-called "cloud" environment, where various devices, components, etc. interact for purposes of data storage, communication, computing, etc. As an example, the method can be implemented in a distributed environment (e.g., in whole or in part as a cloud-based service).

[0099] In Figure 3 the example, the memory device 304 can be physically or logically arranged or configured to store data on one or more storage devices 310. The storage devices 310 can include one or more file systems or databases in any suitable format. The storage devices 310 can also include one or more software programs 312, which can contain interpretable and / or executable instructions for performing one or more of the disclosed processes (e.g., processor-executable instructions that can be stored in the memory 304 and executed to direct the system 300 to perform one or more actions). When requested by the processor 302, one or more or a portion of the software programs 312 can be loaded from the storage device 310 into the memory device 304 for execution by the processor 302.

[0100] Those skilled in the art will understand that the above components are merely an example of a hardware configuration, as the processor system 300 may include any type of hardware components for implementing the disclosed embodiments, including any accompanying firmware or software. The processor system 300 may also be implemented in part or in whole by electronic circuit components or processors, such as application specific integrated circuits (ASICs) or field programmable gate arrays (FPGAs).

[0101] The processor system 300 may be configured to receive a directional drilling plan 320 (e.g., and / or generate a directional drilling plan). As described above, a well plan is a description of a proposed wellbore to be used by a drilling team when drilling a well. A well plan typically includes information about shape, orientation, depth, completion, and evaluation, as well as information about the equipment to be used, actions to be taken at different points during the well construction, and other information that the team planning the well believes will be relevant / helpful to the team drilling the well. A directional drilling plan may also include information on how to direct and manage the direction of the well.

[0102] The processor system 300 may be configured to receive drilling data 322. The drilling data 322 may include data collected by one or more sensors associated with surface equipment or downhole equipment. The drilling data 322 may include information such as data related to the position of the BHA (such as survey data or continuous position data), drilling parameters (such as weight on bit (WOB), rate of penetration (ROP), torque, or other parameters), text information entered by individuals working at the wellsite, or other data collected during the construction of the well.

[0103] In one embodiment, the processor system 300 is part of a rig control system (RCS) of a rig (e.g., including downhole equipment operably coupled to the rig). In another embodiment, the processor system 300 is a separately installed computing unit that includes a display installed at the rig site and receiving data from the RCS. In such an embodiment, the software on the processor system 300 may be installed on the computing unit, brought to the wellsite, and installed and communicatively connected to the rig control system to prepare to construct a well or a portion thereof.

[0104] In another embodiment, the processor system 300 may be located at a location remote from the wellsite and receive the drilling data 322 via a communication medium using protocols such as wellsite information transfer specification or standard (WITS) and markup language (WITSML). In such an embodiment, the software on the processor system 300 may be a web-native application accessed by a user using a web browser. In such an embodiment, the processor system 300 may be remote from the wellsite where the well is being constructed, and the user may be at the wellsite or at a location remote from the wellsite.

[0105] As explained, a drilling fluid (e.g., mud) can be disposed in a tank (e.g., a pit), where the drilling fluid can flow from one or more tanks to one or more other tanks, from one or more tanks to a borehole and / or from the borehole to one or more tanks (e.g., directly and / or indirectly). As an example, a function of the drilling fluid can be pressure control. For example, the drilling fluid can be within the borehole and provide pressure to control fluid behavior. Such pressure can depend on one or more properties of the drilling fluid, such as density. In various cases, the hydrostatic head equation can be used, for example, to calculate the pressure exerted by the drilling fluid. In fluid mechanics, the head can be defined as the height of a column of liquid that corresponds to a particular pressure exerted by the column of liquid on the base of its container. As an example, the head of the drilling fluid can be determined, where the pressure exerted by the drilling fluid at the bottom hole location of the borehole can be determined. In such an example, if the pressure exerted is greater than the formation pressure of the formation fluid, the formation fluid may not flow into the borehole (e.g., wellbore).

[0106] As an example, if the formation pressure increases, the mud density can be increased to balance the pressure and the wellbore can be kept stable. As an example, unbalanced formation pressure can cause an unexpected influx of formation fluid (e.g., a kick) into the wellbore. In various cases, if such an influx (e.g., a kick) is not properly addressed, the risk of a blowout can increase in the event of a blowout situation.

[0107] As an example, a method can include using the density of the drilling fluid, the true vertical depth (TVD), and the acceleration due to gravity to calculate the hydrostatic pressure. In such an example, if the hydrostatic pressure is greater than or equal to the formation pressure, the formation fluid may not flow into the wellbore.

[0108] As an example, a system can provide well control such that no uncontrollable flow of formation fluid enters the wellbore. In such an example, such a system can include one or more features associated with the drilling fluid (e.g., mud). For example, consider a system that can provide determination of one or more pit states (e.g., the tank state of a tank) of a pit that can include one or more drilling fluids. In such an example, the system can provide well control by selecting the drilling fluid, delivering the drilling fluid, regulating the drilling fluid, regulating the flow rate of one or more drilling fluids, etc. As explained, well control can depend on the drilling fluid. In various cases, the drilling fluid can be limited such that the well control can account for one or more limitations. For example, consider an offshore scenario where a limited amount of drilling fluid is available and where providing additional drilling fluid may take a significant amount of time (e.g., for transporting additional drilling fluid to an offshore site).

[0109] As an example, drilling fluids can be used for hydrostatic pressure control in a manner designed to control stresses from tectonic forces, which may cause wellbore instability even if formation fluid pressures are balanced.

[0110] As an example, where formation pressures may be below normal, air, gas, mist, hard foam, low density mud (e.g., oil-based), or a combination thereof can be utilized.

[0111] As an example, the density of the mud can be adjusted for one or more purposes. For example, consider adjusting the density of the mud to the minimum value that allows for proper well control and allows for proper wellbore stability. For the latter, if the mud density is too high, there may be a risk of fracturing the formation.

[0112] As explained, a pit state (e.g., tank state) can be defined, which can facilitate one or more operations, which can include well control. As an example, the pit state can depend on the rig state and / or can be discerned at least in part based on one or more rig states. For example, in the context of the rig state, a particular rig state can involve pumping or not pumping the mud pump. As an example, one or more pit states can be independent of one or more rig states.

[0113] As an example, the framework can be a computational framework that uses the pit state to provide well control. For example, one or more pit states and / or one or more pit state transitions can indicate one or more conditions that can be addressed by well control. For example, consider an indication of a well kick, where well control can be implemented in response to the indication of a well kick. In such an example, by properly addressing the well kick, the risk of a blowout can be reduced. In cases where the blowout risk increases, the framework can require one or more actions that may be associated with addressing the blowout. For example, consider a framework that may require preparing one or more blowout preventers (BOPs), which can include one or more types of rams, etc., which can be actuated to block the flow from the wellbore.

[0114] As an example, the framework can utilize a defined pit state associated with one or more volumes of drilling fluid (e.g., mud). As an example, the volume of the drilling fluid can increase, which can be referred to as a volume increase or simply an increase. As an example, the volume of the drilling fluid may decrease, which is referred to as a volume loss or simply a loss. Regarding an increase, it may be caused by formation fluid flowing into the wellbore. Regarding a loss, it may be caused by the drilling fluid flowing into the formation. As explained, whether formation fluid flows into the wellbore or the drilling fluid flows into the formation can be based on one or more pressures, fluid properties, formation properties, etc.

[0115] Regarding losses, if losses are not addressed in a timely manner, they can impact wellbore integrity. For example, in the case where drilling fluid flows from the wellbore (e.g., the borehole) into the formation, the flow can degrade the formation and, in turn, degrade the wall of the wellbore (e.g., the borehole wall). Regarding increases, if increases are not handled promptly, they can confound or complicate well control; note that increases can also impact wellbore integrity. As explained, if losses become significant, where the drilling fluid may be restricted (e.g., limited volume), compensating for the losses can reduce the volume of drilling fluid, such that well control is affected. In cases where it may take a significant amount of time to provide additional drilling fluid, it can impact timing, which can introduce non-productive time (NPT), other waste, and / or increased risks (e.g., regarding the ability to provide well control, etc.).

[0116] Background state of mud volume balance

[0117] In one embodiment, a computing system can be used to facilitate estimating the expected behavior of a mud pit based on an understanding of the operating context. The behavior and / or state being processed can enable the application of conditional alerts to detect unexpected drilling fluid conditions, such as increases or losses in a mud pit system.

[0118] Interpreting the mud pit correctly can involve understanding the expected state of the system and whether the actual behavior matches the expected behavior. As an example, a set of alert rules that may be appropriate in one operating context may not be an appropriate set of alerts in another context. Appropriately matching a set of alerts to the appropriate context can help ensure that the alerts will provide meaningful information to relevant personnel and systems. As explained, the framework can use one or more pit states to provide well control. In such an example, the framework can issue one or more instructions to one or more downhole devices in response to an alert to perform one or more actions, which can facilitate well control (e.g., address losses, increases, etc.).

[0119] As an example, a framework can be used to detect abnormal increases or losses in a mud pit. As an example, one method can involve defining the expected behavior of an active pit relative to changes in the mud flow rate into one or more pits. In one embodiment, a set of states can be detected based on the mud flow rate into one or more pits. In one embodiment, the method can use an active mud pit (e.g., one or more mud pits that are considered active).

[0120] Figure 4 An example of Table 400 is shown, which shows an example of a method for determining tank status (e.g., pit status). In Figure 4In it, the representation shows various pit states (descending, stable, transient, ascending, zero, unknown, unstable, downlink, etc.) and the pumping actions and expected active volume changes in each specific state. For example, the "descending" state indicates a state where the flow rate gradually decreases and the active pit is expected to change. In this specific state, the pump pumps the drilling fluid downward, and the expected active volume change increases. In the "stable" state, the flow rate is stable, and the active pit is expected to be in a stable state, where the pump pumps the drilling fluid and the expected active volume is stable. In the "ascending" state, the flow rate gradually increases, and the active pit is expected to change. In the "zero" state, the flow rate is zero because the pump can be turned off (e.g., no pumping). As explained, various tank states can be defined with respect to one or more pumping operations of one or more pumps (e.g., considering gradual decrease, gradual increase, pump on, pump off, etc.).

[0121] Figure 4 The method in the example of can estimate one or more transient periods during which the active pit is unstable. This may be due to, for example, emptying the fill line based on the level of flow rate change. The duration of the transient period can be accumulated until the line is completely emptied or reaches its expected level. The method can calculate the time to completely empty or fill the flow line and output the period during which the expected pit is in an unstable state.

[0122] A method can also detect when the flow rate changes because it affects the active pit and the outflow measurement located at the flow line. It can also calculate the periods during which the expected active pit stabilizes with and without mud flow.

[0123] Different alarm settings and / or control actions can be associated with different states. Thus, alarms that are not relevant to a specific state and may, for example, generate false alarms can be disabled for one or more states for which they are inappropriate. For example, when the expected active pit is stable, a set of alarms can be used to effectively detect Figure 4 increases and losses in state 1 (stable) or 4 (zero). This set of alarms may not be suitable for states such as 0, 2, 3, and 6 when an active pit volume change can be expected. As an example, the change in tank volume can be detected at least partially based on the tank state. For example, for the detected tank state, the expected behavior can be indicated, and computational techniques can be associated with the detected tank state considering the expected behavior.

[0124] As an example, a method can actively monitor a drilling fluid circulation system (e.g., a drilling fluid system) and associate the drilling fluid circulation system with a state based on that activity. For example, the state can be Figure 4One of the states shown in. After allocating a state to the drilling fluid circulation system (e.g., the pit state), the system can select one or more alarms and / or control actions associated with and considered valid for that state. One or more alarms and / or control actions associated with the state can then be activated. The system can also monitor changes in the state of the drilling fluid circulation system. In response to determining that the state of the drilling fluid circulation system has changed, the system can activate one or more of the different alarms associated with the new state and deactivate one or more of the alarms associated with the previous state but not associated with the new state. As explained, the framework can provide one or more well control actions, which can be prompted by issuing an alarm.

[0125] As an example, the framework can utilize a pit state-based (e.g., tank state-based) method to select one or more computational techniques for evaluating whether a loss or an increase is occurring or has occurred. For example, various pit states can be associated with one or more field operations that can cause a change in the mud volume in one or more pits. As explained, changes can be anticipated, where the type of change is associated with the pit state. In such a method, the framework can utilize a pit state-based method that selects an appropriate computational technique, which can be physics-based, machine learning-based, hybrid, etc., to evaluate whether a loss or an increase is occurring or has occurred. As an example, the framework can operate in a real-time or near-real-time manner to make a determination as to whether a loss or an increase is occurring or has occurred. Regarding the near-real-time manner, delays that may include transmission, computation, etc. times are considered. As an example, the framework can implement one or more delays that can provide enhanced determination and / or robustness. As an example, the framework can provide an output regarding an increase or a loss within a time period that can be less than a few minutes (e.g., less than five minutes). In such an example, the output can depend on the pit state and / or the pit state transition, where the pit state can involve one or more types of field operations (e.g., line discharge, line fill, mud transfer, etc.) that may take a specific amount of time.

[0126] As an example, the framework can automatically determine the pit state based on one or more inputs, which can include one or more sensor-based inputs (e.g., sensor measurements, etc.). As an example, the framework can automatically detect the pit state associated with mud flow, the active volume of mud, etc. In such an example, the inputs for detecting the pit state can include one or more hoisting system inputs (e.g., truck position and hook load over time), bit depth, flow rate, etc. For example, consider a framework that can receive the truck position and hook load, where such values are sampled approximately once every 5 seconds. Regarding the bit depth, it can provide an indication of how much mud is in the borehole (e.g., wellbore) and / or can provide an indication of the truck position relative to the stands of drill pipe. Regarding the flow rate, it can provide an indication of mud leaving and / or mud entering one or more pits. As an example, the framework can utilize one or more parameters that can be operating parameters. In various examples, the framework can include operating parameters that affect the mud volume and, for example, does not include those operating parameters that may not affect the mud volume. As for the number of pit states, the framework can utilize more than three pit states and less than approximately 15 pit states. As an example, the framework can utilize approximately four to six pit states. As an example, the framework can utilize pit states that include a stable pit state and a dynamic pit state. As an example, the framework can utilize an unknown pit state, which can provide robustness, for example, in cases where the detection of predefined states may be problematic. In such an example, the framework can issue one or more instructions, warnings, etc., where the detection results in an unknown pit state.

[0127] Figure 5 A graphical user interface (GUI) 500 showing an example of the pit state during a drilling connection is shown. In Figure 5 it, channels are shown over time, where the channels include mud flow rate (e.g., 0 to 1000 gallons per minute), the volume of the active pit (e.g., plus and minus 30 bbl), and a status channel indicating various pit states over time (e.g., a single pit state at a given time).

[0128] In Figure 5 it, the unstable state and transient correspond to the expected periods (e.g., transient periods) of draining and filling the flow line. The stable state region indicates the expected stable periods of the pit and flow rate. The falling state and rising state indicators correspond to changes in the falling and rising flow rates, respectively. As explained, states such as the pit state can be context-dependent states. As explained, the pit state can provide an assessment of gain and / or loss.

[0129] In Figure 5In an example, the volume of the active pit increases during an unstable state time period associated with line discharge, but then decreases during an unstable state time period associated with line fill. When comparing the volume of the active pit before and after the unstable state time period, it is shown that the difference is relatively small (e.g., less than a few barrels of mud). In such an example, the increase and subsequent loss are instantaneous and associated with line discharge and line fill, rather than with downhole conditions such as the influx of formation fluid or the outflow of mud. As Figure 5 shown, the line discharge and line fill operations take approximately 10 minutes to perform, and for example, the stabilization period can be of a duration of several minutes.

[0130] Figure 6 An example of a GUI 600 for state definition during a long connection is shown, which has multiple steps to incrementally increase the flow rate. Figure 6 The transient time period in shows a time period of transient behavior due to the multi-stage incremental increase with that mud flow rate. In the GUI 600, the channels include mud flow rate (e.g., 0 to 1000 gallons per minute), active pit volume (e.g., 20 bbl to 70 bbl), and status. In Figure 6 the example of, the result indicates that no increase has occurred; however, there is an indication of loss. In such an example, the loss can be determined by comparing the active pit volume during the first stabilization period and the last stabilization period in the GUI 600, which indicates a loss of approximately 5 barrels (bbl), which can be compared to a threshold, for example, to trigger the issuance of a signal (e.g., an alarm, communication, control instruction, etc.). As explained, the loss may be associated with the flow of mud from the wellbore into the formation. Additionally, Figure 6 the GUI 600 of shows how various operations can cause changes in the active pit volume (e.g., of one or more active pits), which may be difficult for a person to track and / or make one or more determinations. As explained, the automated pit state detection framework can operate to detect the pit state and select appropriate techniques to evaluate one or more characteristics of the mud operation to achieve a determination of whether the change in mud volume is expected or unexpected, and for example, if unexpected, can trigger the issuance of a signal (e.g., indicating an increase or loss).

[0131] The system can use various values to determine the rig state. In drilling, there is typically a plan specifying a particular activity at a particular depth and / or time. In one embodiment, the system can use the plan information as well as the flow rate information to determine the pit state. Additional information and sensor values can also be used to determine and define the pit state (e.g., tank state), such as Figure 4Those specified in. In addition, the status can be further decomposed. For example, although the above example uses mud flow rate as an input, more statuses can be added. For example, status 4 (zero) can be decomposed into considering whether there is pipe movement or not, and status 1 (stable) can be decomposed into whether there is cuttings return or not, etc.

[0132] As described above, the method can define a set of actions that affect the mud volume balance in one or more areas of the drilling fluid circulation system that may occur during a drilling operation, and assign these actions to one or more statuses. The method can involve associating these statuses with the expected drilling fluid volume and the expected change in the drilling fluid volume when the status is active. The method can also involve defining one or more sets of alarms and / or control conditions for the drilling fluid circulation system and associating alarm conditions and alarm triggers with different drilling fluid volume statuses. In real time, the system can monitor the status and selectively activate and deactivate alarms, control instructions, etc. based on the status. As explained, the framework can provide more information and meaningful alarms and / or controls, and for example, can reduce examples where false alarms or missed alarms may occur.

[0133] Detection of increased mud volume during circulation

[0134] As described above, it can be challenging to determine whether to issue an alarm based on changes in the drilling fluid volume and the drilling fluid circulation system. As an example, the framework can provide for determining when there is fluid loss or fluid gain in one or more pits that is worthy of generating an alarm and / or control action. In one embodiment, the method measures the total active volume of the drilling fluid and the sum of the volumes to distinguish between, for example, transfers between pits (e.g., which can be considered expected behavior and not worthy of an alarm and / or control action) and fluid gain associated with the formation (e.g., which can be considered unexpected behavior worthy of an alarm and / or control action). For example, when applied to the active volume (e.g., the combined volume of all pits pumped by the mud pump into the well) and the combined volume of all pits of the rig, the method can help distinguish fluid gain from the formation and fluid gain from mud transfer from the reserve pit to the active pit.

[0135] In one embodiment, the method can use a dynamic window method for detecting a statistically significant volume increase within a volume of interest to detect an increase in the volume of interest. In one embodiment, a method can be applied to both active volume measurements and total volume measurements. Thus, this method can help determine the origin of the increase observed in the active volume and associate it with a possible well kick or internal transfer of mud within the drilling fluid circulation system. Thus, the framework can operate to distinguish between drilling fluid system operations and drilling fluid formation interactions (e.g., increase or loss).

[0136] While the various examples are directed to solving problems such as increases due to flow from the formation and / or losses due to flow to the formation, the framework can provide for determining whether one or more drilling fluid system operations are operating properly. For example, one or more drilling fluid system operations (e.g., discharge, fill, etc.) can be specified according to one or more standard operating procedures (SOPs). In such an example, the framework can be designed to detect one or more pit states that can occur in one or more sequences and determine whether compliance with one or more SOPs has been met. In such an example, in the case of deviation from one or more SOPs, the framework can issue one or more instructions, notifications, etc. to help ensure compliance with one or more SOPs and / or awareness of the deviation. As explained, the framework can include pit states associated with expected behavior, which can depend at least in part on expected drilling fluid system operations (e.g., one or more SOPs, etc.).

[0137] In one embodiment, the increase detection can be triggered by a possible positive increase rate within a relatively short time window prior to a given time. For example, within the time window, the value of the increase rate can be calculated. In one embodiment, the time window can be relatively short (e.g., less than 10 minutes). In one embodiment, the time window can be within 2 minutes (e.g., less than or equal to 2 minutes). In one embodiment, if the increase rate is statistically significantly greater than zero within the time window, then the volume accumulation can be initiated backwards in time.

[0138] As an example, the volume accumulation can be performed on a dynamic window. In one embodiment, the dynamic window can start with a short window and then magnify towards the past until the cumulative volume within the window is statistically equal to or greater than a set threshold (e.g., considering a threshold of about 5 bbl) or a predefined maximum window size.

[0139] Figure 7 An example of the GUI 700 is shown, which shows the use of various time windows, where the channels include pit state, increase detection (e.g., alert, trigger, etc.) and the total active volume (TVA) in the barrel. In Figure 7 the example, a fitted linear regression on a dynamic backward window can be implemented to reach a threshold increase (see, e.g., ∆V), as shown (see, e.g., the black arrow pointing backwards in time), which can occur multiple times (e.g., in an iterative manner). In another embodiment, a combination of one or more stop criteria for magnifying the dynamic window can be used. For example, a trend change, such as a sharp, unexpected volume jump that may be due to an unaccounted operating procedure. In the case of a threshold, such as the 5 bbl example given above, when the threshold is reached before the predefined maximum window size is reached, the system can assume confirmation of the increase, otherwise not.

[0140] When the threshold is set to 5 bbl, the size of the dynamic window can reflect the duration when the last 5 bbl is obtained or exceeded. Dividing the increase in the cumulative volume by the duration of the dynamic window yields the average increase rate. In one embodiment, the alert and / or control action framework can also be configured according to the average increase rate and / or the magnitude of the cumulative amount. As Figure 7 shown in the example of, the increase detection channel can provide staging of one or more alerts, control actions, etc. For example, a warning can be issued or indicated in the GUI 700 before a subsequent elevated level, such as a full alert, issuing a control signal for well control, etc.

[0141] Applying the increase detection to the total active volume (TVA) during the circulation and the sum of all volumes (SumTK) can be used to generate two sets of time increase notifications. The active volume can inherently exist in the sum of the pits. If an increase exists in both the TVA and the SumTK, it can be identified as an increase from outside the measurement system, which may come from the wellbore during normal operating routines and indicates the presence of a kick (e.g., formation fluid entering the wellbore). For the case where the increase exists only in the active volume and not in the sum of all pits, it can be identified as an internal transfer of mud between the drilling circulation systems, such as a transfer from the reserve pit to the active pit. As explained, the framework can distinguish between drilling fluid system operations (e.g., as performed according to one or more operating procedures of the equipment used) and formation interactions that may cause an increase or loss.

[0142] Figure 8 An example of the GUI 800 is shown, where an increase is detected in the active pit (TVA) and the sum of all pits (SumTK), and the two indicators intersect to show an alert increase from the wellbore (the red interval on the top track). In the GUI 800, the channels include flow rate (e.g., gallons per minute), SumTK (e.g., bbl), the cumulative increase rate associated with all pits (e.g., bbl / minute), TVA (e.g., bbl), the cumulative increase rate associated with the active pit (e.g., bbl / minute), and the alert increase, which can be encoded relative to the volume (e.g., bbl). As shown, the alert increase channel indicates an alert, where the increase in volume is indicated by the channels TVA and SumTK.

[0143] Figure 9An example of the GUI 900 is shown, where an increase is detected in the active pit (TVA) and the sum of all pits (SumTK). The two indicators intersect to trigger the presentation of an increased alert from the wellbore. For example, the alert increase channel is considered to include a color-coded warning (e.g., light red), followed by a full alert (e.g., dark red), which can be associated with issuing one or more control instructions to address the increase. In such an example, the warning can be associated with the increase in TVA, and the full alert can be associated with the increase in TVA and the increase in SumTK. As shown, these increases occur during a stable pit state. As explained, alerts and / or control actions can be issued based on the detection of one or more increases. For example, one or more control actions can be issued when an increase (e.g., or loss) in one channel (e.g., TVA) is detected, and another or more control actions can be issued when increases (e.g., or losses) in two channels (e.g., TVA and SumTK) are detected. As explained, the framework can detect the pit state and behavior of multiple aspects of the drilling fluid system, which can be associated with one or more surface and / or downhole phenomena.

[0144] As an example, the GUI 900 can request the presentation of a pop-up graphic of recommended control actions that can be implemented by the drilling fluid system to address the increase. Figure 9 The GUI 900 also illustrates relatively high noise in the active pit signal (TVA); however, the SumTK channel exhibits less noise. In such an example, the framework can operate to evaluate the noise and, for example, classify the noise as being associated with a specific type of phenomenon, which can be a downhole phenomenon (e.g., formation interaction) or a surface phenomenon (e.g., drilling fluid system behavior). As an example, the framework can operate to address one or more behaviors, whether downhole or surface.

[0145] As explained, the framework can operate to detect the pit state and select one or more computational techniques to evaluate whether an increase or loss may be occurring and / or has occurred. Such a framework can operate in a rapid manner such that one or more control actions can optionally be taken automatically for the proper operation of the drilling fluid system, which can be for the purpose of addressing an increase or loss, or for example, to meet one or more SOPs, service equipment, etc.

[0146] Figure 10 An example of the GUI 1000 is illustrated, where an increase detected in the active pit (TVA) is not seen in the sum of all pits (Sum TK). In Figure 10In the example, these two indicators do not intersect. Thus, the framework can require alarms, warnings, control actions, etc. to be issued regarding the active well, which can be associated with the increase due to the transfer of drilling fluid from the reserve pit to the active pit (e.g., the reserve volume decreases while the active volume increases). As explained, such a transfer can be part of the operation process, enabling the framework to track such a process and, for example, determine whether it is carried out according to a specified protocol (e.g., SOP, etc.).

[0147] As an example, the drilling fluid system can include multiple pits, which can be more than two pits, more than four pits, more than six pits, more than ten pits, etc. For example, the rig can include twenty pits. As an example, the framework can provide an effective way to process data associated with multiple pits. For example, the framework can provide an effective way to process data associated with twenty pits. In such an example, manual human processing is impractical and will introduce delays (e.g., resolving losses, increases, etc.) that may complicate or confuse timely well control actions. Generally, as the number of pits increases, manual processing becomes more impractical.

[0148] As an example, regarding efficiency, as explained, the framework can operate to detect pit status, calculate one or more metrics for the active pit, and calculate one or more metrics for all pits. In this method, the framework can utilize one or more computing techniques to calculate such one or more metrics in a manner agnostic to the number of pits (e.g., where the number of pits exceeds two pits, etc.). In such a method, the user interface (e.g., GUI) can be similarly configured in a manner agnostic to the number of pits. As an example, in the case where the framework provides an assessment of the drilling fluid system, it can provide the identification of one or more pit-specific issues (e.g., regarding SOP, etc.). As explained, the framework can have a primary function of providing an indication of the change in the volume of the drilling fluid (e.g., mud), which indicates formation interactions that may be related to well control; note that well control issues can include one or more of increases, losses, formation damage, wellbore damage, etc.

[0149] Detection of increased mud volume using outflow measurement method

[0150] As an example, the method can provide an analysis of the outflow to detect flow problems and provide related notifications such as alarms and / or control actions. In one embodiment, the method can be used to analyze the paddle flowmeter signal to detect fluid inflow.

[0151] A paddle flowmeter can be a sensor installed onshore and offshore rigs for measuring fluid flow. Paddle flowmeters are often used to measure outflows, but tend to be noisy, provide poor accuracy, and typically require frequent calibration. Therefore, using these flowmeters to generate alerts and / or control actions can be difficult to do in an accurate and useful way. Given these conditions, one approach is to use alerts that can operate under specific conditions and operations, where one approach prioritizes a stable flow under conditions such as drilling activities and deactivates under no flow in, having a mud supply tank pump, or a change in flow.

[0152] In some embodiments, one approach can involve preprocessing sensor data. Such processing can be performed for one or more purposes, such as for example measurement calibration and / or denoising. As an example, preprocessing can occur before performing detection and estimation of the deviation of the measurement from the stationary behavior. In one embodiment, the measurement can be calibrated and mapped within a dynamic range of [0, 100]. Values outside the bounds can be considered faulty and excluded from the calculation. In some embodiments, it can be assumed that measurements are missing or corrupted such that extrapolation is not used.

[0153] Detection for change can be triggered by a possible deviation from stationarity within a time window prior to a given acquisition time. For example, given an acquisition time , a short time window of the duration prior to the acquisition time the data d(t) within is fit by linear regression:

[0154]

[0155] along with the estimated mean values of the slope and offset parameters (a, b) , the associated standard deviation is calculated . If the absolute value of the estimated mean slope deviates from a previously defined detection criterion, the method can start gradually expanding the short time window towards the past until a stop criterion is met within the expanded dynamic window. One detection criterion is to deviate within a factor k of the calculated standard deviation of the estimated slope from the minimum slope :

[0156]

[0157] The dynamic window can be initiated as a short window and magnified towards the past one time sample at a time until some stop criterion is met. One stop criterion for the dynamic window size might be the maximum window size or a target reached, which can be used for decisions to increase or decrease within the dynamic window.

[0158] As an example, let Represents ordered time samples within a long time window. For example, when at and , and represent the number of time samples within a short time window, a dynamic time window, and a long time window respectively, excluding the time sample . Among them, . For , the data within is fitted by linear regression:

[0159]

[0160] In such an example, for each time sample, for example, the framework can define the measured state through the following :

[0161]

[0162] In the above, is a predefined minimum sensitivity value. As an example, for well-calibrated effluent measurements, can be assumed to be between 5 - 10. The value shows that the absolute estimated change in the measurement signal is between and , and indicates the sign of the change, for example, positive when there is an increase and negative when there is a decrease.

[0163] To ensure the consistency and continuity of the state, one method can compare them with continuously increasing and continuously decreasing states. This can be performed by associating the vector with if the framework is to detect a consistent increase, or with if the framework is to detect a consistent decrease. In such an example, note that the minimum and maximum lengths of the vector S can be and respectively.

[0164] As an example, a method for determining the consistent behavior of a data stream can be used. As follows. For example, first note that the square of the sum of the vector norm :

[0165]

[0166] and less than , and more than Relevance:

[0167]

[0168] Thus, in such an example, consider:

[0169]

[0170] In the above, when is true, it equals 1. Thus, the following decision criteria can be used to determine increases and decreases.

[0171] As an example, let represent the decision at time . Consider the following definitions:

[0172]

[0173] As an example, in an alternative, consider:

[0174]

[0175] As an example, once the framework makes a decision on an increase or decrease, that decision can be incorporated into a larger decision workflow, e.g., for issuing alerts, warnings, control actions, etc.

[0176] As an example, the framework can use a combination of one or more stop criteria to define the expansion of a dynamic window. For example, consider one or more trend changes, such as one or more sharp unexpected volume jumps, which may be due to unaccounted operational processes. In the case of the thresholds described above, when the threshold is reached before the predefined maximum window size is reached, the framework can assume a confirmed deviation from stability, otherwise not.

[0177] The size of the dynamic window can reflect the duration when the change starts to occur. As an example, by dividing the amount of change by the duration of the dynamic window, the framework can obtain the average rate of change. As an example, alerts or control action processes can be designed based on the average increase rate and / or the magnitude of the cumulative volume.

[0178] Figure 11 An example GUI 1100 with a magnified portion is shown. In Figure 11 , the GUI 1100 shows the behavior of computing techniques and alert and / or control action generation. In the example of Figure 11 , the outflow state is combined with the behavior of the inflow to issue alerts and / or control actions. In the example GUI 1100, the alerts indicated at specific intervals represent the inflow from the wellbore, and various other intervals indicate abnormal outflows due to changes in the inflow, which do not trigger alerts. More specifically, inFigure 11 In this, an outflow alarm during a drilling operation is shown. Inflow is detected prior to the last connection (see the corresponding interval). Regarding the magnified portion of the GUI 1100, it is a magnification of the inflow, where a specific interval indicates an alarm, which can trigger one or more control actions (e.g., for well control). In Figure 11 the example of, the GUI 1100 includes various channels, which can include, for example, flow, outflow, and block position (BPOS), which can show how stands of drill pipe move into or out of the wellbore. As shown, a flow alarm and / or control action channel can be included in such a GUI.

[0179] Real-time automatic notification of abnormal increase in active pit in the background of short connection

[0180] As an example, the framework can provide for detecting an abnormal increase in an active pit or multiple pits in the context of a short connection, which can provide improved safety and integrity for one or more wellsite operations. As an example, an abnormal increase in an active pit or multiple pits can be investigated during various drilling phases, where, for example, the detection of one or more increases can trigger one or more real-time alarms and / or control actions. As an example, the framework can provide the presentation of one or more GUIs that allow an engineer to simultaneously inspect several active wells, which can, for example, reduce the probability of having a kick, which can lead to a catastrophic event at one or more rig sites.

[0181] As an example, the framework can provide for monitoring one or more active pits while drilling, such that the team can ensure that one or more actions (e.g., automatically, semi-automatically, manually, etc.) are implemented in an effort to reduce the risk of one or more catastrophic events at the rig site. As an example, the framework can provide for monitoring one or more active pits in the context of a connection, which can provide for the generation and use of a return flow fingerprint. In such an example, an individual or team can inspect the response of the active pit during the connection and compare it to one or more previous connections (e.g., or a combination thereof). However, in various situations, such a process may not be sufficient for one or more specific cases, e.g., considering one or more examples where the connection is too short to calculate a valid return flow fingerprint.

[0182] As an example, the framework can provide for the implementation of real-time automation of an abnormal increase in one or more active pits in the context of relatively short connections. In one embodiment, the start of a connection based on the flow in the signal response can be identified, a reference volume of the active pit prior to the connection can be identified, and then a check can be made, for example, by checking whether the drill is on the slips (e.g., within the slips or inside the slips), that the connection is being properly executed. Then, such a method can apply one or more conditions on the measured connection time, bit depth difference, and flow comparison to discard connections that lack coherence (e.g., do not make reasonable sense). If the difference between two connections is greater than or equal to a threshold amount (e.g., 5 bbl), then such a method can also identify the active pit volume after the connection and trigger a real-time alert and / or control action. If there is mud transfer in the active pit, then such a method can also suppress the alert and / or control action by looking at the total volume of all pits.

[0183] As an example, the method implemented by the framework can provide a solution for automatically detecting in real time an abnormal increase in one or more active pits with relatively short connections. In such an example, the framework can provide for detection of the increase when the return fingerprint is insufficient and provide an automatic calculation that gives the user a clear indication of the active pit and automatically issues an alert and / or control action (e.g., automatically, semi-automatically, etc.).

[0184] In one embodiment, the method can use one or more of the following input channels: absolute time [s]; drill state [unitless]; pit state [unitless]; mud flow rate [m 3 / s]; bit depth [m]; active pit volume [m 3 and the sum of the volumes of all pits [m 3 .

[0185] As an example, such a method can provide the following outputs:

[0186]

[0187] Such a method can detect an abnormal increase in one or more active pits in the context of short connections.

[0188] Figure 12Shows an example of method 1200 that can be implemented by a framework. As shown, method 1200 can include a series of actions represented by blocks. For example, consider block 1214 that records a 10 - second time window before a pit state transition (e.g., from 0 to 1); block 1218 that takes a first point from a TVA variable; block 1222 that records a pit state transition (e.g., from 2 to 1); block 1230 that uses the rig state to determine if there is a detection of slip between the first and second points; block 1234 that makes a determination as to whether there is less than a certain amount of time (e.g., 25 minutes, etc.) between the first and second points; block 1238 that makes a determination as to whether the bit depth is greater than a specific depth during a stand (e.g., greater than 150 feet or some other distance far enough from the ground); block 1242 that determines if the pump flow rate during the first point is actually the same as during the second point (e.g., within about 20%); block 1246 that compares the volume difference between the first and second points with a threshold (e.g., 5bbl); and block 1250 that determines if there is a transfer (e.g., TVA increases but the sum of the pits is stable), where if block 1250 determines there is a transfer, method 1200 continues according to continue block 1258 (e.g., for evaluating another connection, etc.), and where if block 1250 determines there is no transfer (e.g., does not occur), method 1200 proceeds to emit block 1254 for emitting an alarm, control instructions, etc.

[0189] As an example, in one embodiment, over time, the various blocks of method 1200 can be repeated; note that one or more parameters (e.g., time, volume, etc.) can be adjusted to be consistent with a particular drilling fluid system, operation, etc.

[0190] In one embodiment, when the pit state value transitions from stable to gradually decreasing (e.g., from 1 to 0) and the rig state has not been set to within the slips, as a possible previous (e.g., prior) reference point that may have been adopted, the values of the following variables can be captured for the first or updated "before" reference point (e.g., considering the past 10 seconds relative to the current time according to block 1214): bit depth, mud influx flow rate, active mud tank volume, and total tank volume.

[0191] As an example, if a threshold time period (e.g., more than 25 minutes) has passed since the "before" reference point, the method can discard the "before" reference point (see, e.g., block 1234).

[0192] In response to a transition of the pit state from transient to stable (e.g., from 2 to 1), the framework can provide any pit state value between transient and stable during a specific interval (e.g., considering an interval of approximately three minutes), and if the rig state has been within the slips since the "before" reference point (see, e.g., box 1230), the framework can take the following actions, labeled A, B, and C:

[0193] A. Take the following values for the "after" reference point: bit depth, mud influx flow rate, active mud tank volume, and total tank volume.

[0194] B. Calculate the outputs as shown in the output table (above).

[0195] C. Trigger an alarm and / or control action, e.g., set the output of the active pit connection alarm to 1 at the time of the "after" reference point if a set of conditions is met, e.g., where the following set of conditions is met: the duration between before the reference point and after the reference point is below a threshold (e.g., 25 minutes) (see, e.g., box 1234); the bit depth difference is below a set threshold (e.g., 150 ft) (see, e.g., box 1238); the flow rate difference in percentage is less than a threshold (e.g., 20%) (see, e.g., box 1242); the active pit volume difference is greater than a threshold (e.g., 5 bbl) (see, e.g., box 1246); and an optional input sum specifying the volume of all pits, e.g., the difference in the sum of the volumes of all pits is greater than 0.9 * the active pit volume difference (i.e., no transfer is detected).

[0196] After well completion, the framework can forget (e.g., delete, rewrite, etc.) the "before" and "after" reference points and / or the framework can store such points (e.g., the data associated with such points) to local and / or remote storage devices.

[0197] In Figure 12 example method 1200, although the boxes are shown in a specific order, method 1200 can be executed without strictly adhering to that order. For example, one or more conditional boxes for decision-making can be implemented in one or more orders different from the order shown in Figure 12 . And, as explained, the thresholds are provided as examples and can be different in implementation.

[0198] Figure 13 An example of a GUI 1300 showing the results of an embodiment of an automatic calculation method for triggering alarms, warnings, control actions, etc. (such as Figure 12 method 1200) is shown.

[0199] In Figure 13In the example, the GUI 1300 includes various channels, which may include a pit status channel, a time channel (e.g., 0 to 25 minutes), a bit depth channel (e.g., 0 to 50 meters, which may provide stand or truck position type measurements), a TVA channel (e.g., in volume), and a mud flow rate channel (e.g., in volume per unit time). As shown, the pit status indicator may extend as an overlay to the mud flow rate channel such that an operator can easily compare the mud flow rate value with the pit status.

[0200] In Figure 13 the example, the GUI 1300 includes an alert marker that indicates that the TVA has increased such that the increase is occurring or has occurred after a series of pit status transitions. In particular, from a stable state to another stable state, there is a significant increase in the TVA amount, which is associated with the bit depth channel, which, as explained, may correspond to a stand operation where a new stand starts at zero and proceeds to approximately 50 meters (e.g., or another length depending on stand length, etc.).

[0201] Automatic alarm for abnormal increase of mud supply tank during stable period

[0202] As an example, the framework can provide a mechanism that can be used to help reduce the risk of one or more types of events at the wellsite. In such an example, the framework can provide monitoring of one or more mud supply tanks during one or more stationary periods. In various cases, a flow check can be part of a well control procedure that may involve stopping all drilling, tripping, and circulation operations for a period of time to monitor the well. The mud supply tanks can be arranged and their volume changes monitored to detect the presence of a potential increase. This information can be used to prevent events such as a well kick. A method for real-time automation of abnormal increases in mud supply tanks during stationary periods is disclosed herein. In one embodiment, the method involves identifying a stationary period based on inflow and bit depth signals. The method can also involve looking for the absence of circulation and bit depth stability. Then, the method looks for volume increases in the mud supply tanks to detect which are queued. Once the queued detection is complete, the method can monitor the identified mud supply tanks to detect abnormal volume increases worthy of notification.

[0203] The method can be used to automatically detect abnormal increases in mud supply tanks in real-time during stationary periods. The automation model can allow for the detection of mud supply tank volume increases during stationary periods. The method can provide a clear indication of the mud supply tank volume to the user during stationary periods and issue an alert as needed.

[0204] In one embodiment, the method uses one or more of the following inputs: absolute time [s]; pit state [dimensionless]; bit depth [m]; flow-out blade [%]; riser pressure [Pa]; mud supply tank volume 1 [m3]; and mud supply tank volume 2 [m 3 .

[0205] As an example, the method can provide the following information:

[0206]

[0207] In one embodiment, a method can be used to detect an abnormal increase in the mud supply tank pipeline during one or more stationary periods using logic.

[0208] Figure 14 An example of method 1400 is shown, which includes various blocks that can correspond to various actions. As shown, a series of blocks 1414, 1416, 1418, and 1420 can provide conditional determinations, such as the pit state being zero or unstable, the bit depth changing steadily (e.g., less than 2 meters), the riser pressure being below a threshold (e.g., less than 100 psi), and the flow-out being stable (e.g., according to one or more criteria). As shown, the conditional determinations can indicate the presence of a stationary period according to block 1430. For the stationary period, method 1400 can determine whether there is an increase in the total tank volume (TTV) according to block 1434, determine whether the TTV is greater than a threshold (e.g., 0.7 m 3 ), implement a wait (e.g., 60 seconds, etc.) according to block 1442, and obtain a reference TTV reading according to block 1446. As Figure 14 shown in the example of, method 1400 can enter monitoring block 1450, which can utilize the reference reading of block 1446. For example, consider determining whether the TTV minus the reference TTV is greater than a threshold volume (e.g., 2 bbl), such that method 1400 proceeds to potential alert block 1454, which can introduce a wait time of, for example, 30 seconds or other appropriate amount of time before proceeding to alert block 1458, which can call one or more control actions, issue one or more recommended control actions, etc. As Figure 14 indicated in the example of, if the alert is not triggered before a certain time (e.g., 5 minutes), the monitoring can continue past block 1454 and maintain the alert or repeat the alert of block 1458.

[0209] In Figure 14 the example of, the different blocks can be implemented in a different order, where, for example, fewer or more actions can occur than those shown; note that the various limits or thresholds can be appropriately selected or adjusted according to one or more factors.

[0210] In one embodiment, the framework may implement a method for determining a stationary period involving the use of several conditions, e.g., as explained with respect to blocks 1414, 1416, 1418, and 1420. Similarly, such conditions may include one or more of the following: the pit state value is zero or unstable; the bit depth is stable or substantially stable (e.g., it may be determined that the drill string moves no more than 2 meters); the standpipe pressure (SPPA) is less than a threshold amount (e.g., 100 psi); and there is no flow instability.

[0211] As an example, a method may determine that a mud supply tank is queued in response to an input value. For example, if the mud supply tank volume is greater than a threshold amount (e.g., 4.4 barrels) and / or an increase in volume is observed during a stationary period, the mud supply tank may be declared queued.

[0212] As an example, the method may start monitoring a mud supply tank determined to be queued after a threshold period. In one embodiment, the threshold period may be 60 seconds; note that one or more other time values may be used. As an example, the threshold period may be selected to wait for the mud supply tank volume to stabilize. In one embodiment, after the threshold period has elapsed, a mud supply tank volume reference point is taken. In such an example, if the difference between the mud supply tank volume and the reference point exceeds a threshold amount, an alarm and / or a control action may be triggered. In one embodiment, such a threshold amount may be set to approximately 2 barrels. As an example, the method may also use the confirmation of a stationary period. For example, consider the confirmation of a 30 - second stationary period that may be observed. Additionally, a push may be applied to the alarm output. For example, in one embodiment, a 5 - minute push may be applied to the alarm output.

[0213] Figure 15 An example of the GUI 1500 showing example results of a method such as method 1400 is shown. As shown, the GUI 1500 includes various channels, such as a pit state channel, a bit depth channel, a mud flow - in channel, an outflow channel, an alarm channel, and one or more volume channels for one or more mud supply tanks (e.g., TTV1 and TTV2). In Figure 14 the example, the bit depth scale is shown from 0 meters to 30 meters, which may correspond to a standpipe of approximately 30 meters in length (e.g., three drill pipes each of approximately 10 meters in length joined to form a standpipe of approximately 30 meters in length). Figure 15

[0214] ​As explained, the bit depth can be monitored to determine if it is stable, because movement of the bit on the drill string (e.g., movement of the drill string) can cause some variation in the readings of the mud pit volume. As for the standpipe pressure, if it is above a certain level, there may be one or more inaccuracies in one or more mud pit volume readings. Regarding the flow out, it can be evaluated according to one or more criteria to determine if it is stable. Such conditions can provide some assurance that one or more mud pit volumes can be adequately measured.

[0215] As explained, the framework can utilize data obtained for one or more mud pits to detect increases or losses. As an example, such methods can provide detection of a stationary period or stationary state, which can be associated with one or more rig states, e.g., one or more slips-related states. As explained, one or more field operations can be performed relative to one or more mud pits of a drilling fluid system, where, for example, the framework can provide monitoring that can result in the issuance of one or more alerts and / or control actions.

[0216] Figure 16 An example of a wellsite system 1600 is shown, specifically, Figure 16 The wellsite system 1600 is shown in an approximate side view and an approximate plan view and in block diagram of the system 1670.

[0217] In Figure 16 the example, the wellsite system 1600 can include a compartment 1610, a rotary table 1622, a drawworks 1624, a mast 1626 (e.g., optionally carrying a top drive, etc.), mud pits 1630 (e.g., having one or more pumps, one or more vibrators, etc.), one or more pump buildings 1640, a boiler building 1642, an HPU building 1644 (e.g., having a rig fuel tank, etc.), a combination building 1648 (e.g., having one or more generators, etc.), a pipe rack 1662, a catwalk 1664, a bell nipple 1668, etc. Such equipment can include one or more associated functions and / or one or more associated operational risks, which can be risks regarding time, resources, and / or people.

[0218] As Figure 16As shown in the example, the wellsite system 1600 may include a system 1670 that includes one or more processors 1672, a memory 1674 operatively coupled to at least one of the one or more processors 1672, instructions 1676 that may be stored, for example, in the memory 1674, and one or more interfaces 1678. As an example, the system 1670 may include one or more processor-readable media that include processor-executable instructions executable by at least one of the one or more processors 1672 to cause the system 1670 to control one or more aspects of the wellsite system 1600. In such an example, the memory 1674 may be or include one or more processor-readable media, where the processor-executable instructions may be or include the instructions. As an example, the processor-readable media may be a computer-readable storage medium that is not a signal and not a carrier wave.

[0219] Figure 16 A battery 1680 is also shown, which may be operatively coupled to the system 1670, for example, to power the system 1670. As an example, the battery 1680 may be a backup battery that operates when another power source is not available to power the system 1670. As an example, the battery 1680 may be operatively coupled to a network, which may be a cloud network. As an example, the battery 1680 may include a smart battery circuit and may be operatively coupled to one or more devices via an SMBus or other type of bus.

[0220] In Figure 16 the example, a service 1690 is shown as being available, for example, via a cloud platform. Such a service may include a data service 1692, a query service 1694, and a drilling service 1696. As an example, the service 1690 may be part of a system, framework, etc. As an example, the service 1690 may include one or more services for directional drilling, which may include, for example, one or more steering trend services (e.g., a computational framework that may provide one or more services that utilize survey information to estimate one or more steering response parameters, etc.). As an example, the service 1690 may include one or more services associated with a drilling fluid system, which may include, for example, pumps for the mud tanks 1630 and the pump building 1640. As explained, the framework may provide detection of one or more of an increase, loss, equipment problem, program problem, etc. As explained, the framework may provide issuance of one or more alerts, control actions, etc., as may be associated with interaction with one or more types of formations (e.g., formation fluid flowing into the wellbore, drilling fluid flowing into the formation, etc.). As an example, the system 1670 may be used to detect one or more problems, which may be used, for example, to control one or more field operations.

[0221] Figure 17An example of method 1700 is shown. Method 1700 may include: a receiving block 1710 for receiving real-time data related to a drilling fluid for a drilling operation that utilizes a drilling fluid system including a tank and a pump, where the drilling operation includes an operation of pumping the drilling fluid to a drill bit on a drill string, the drill string rotates to extend a borehole in a formation, and where the drilling fluid flows into an annulus between the drill string and the formation to apply pressure to the formation; a detecting block 1720 for detecting a tank state from a set of tank states based at least in part on the real-time data, where the set of tank states includes tank states defined by one or more operations of the pump; and a detecting block 1730 for detecting a change in tank volume based at least in part on the tank state as an indicator of an undesirable interaction between the drilling fluid and the formation. As shown, method 1700 may include an emitting block 1740 for emitting an alert and / or a control action. For example, consider an alert for a well kick, a control action for resolving a well kick, an alert for formation damage, a control action for resolving formation damage, etc.

[0222] As Figure 17 shown, method 1700 may be implemented via one or more computer-readable media (CRM) in accordance with blocks 1711, 1721, 1731, and 1741, which may be implemented using, for example, a system such as a computing system (see, for example Figure 3 example system 300, Figure 16 example system 1670, etc.). Such blocks may include processor-executable instructions.

[0223] As explained, various systems, methods, etc. can implement one or more ML models. Regarding the types of ML models, consider one or more of support vector machine (SVM) models, k-nearest neighbor (KNN) models, ensemble classifier models, neural network (NN) models, incremental learning, Q-learning, etc. As an example, a machine learning model can be a deep learning model (e.g., deep Boltzmann machine, deep belief network, convolutional neural network, stacked autoencoder, etc.), an ensemble model (e.g., random forest, gradient boosting machine, bagging, adaptive boosting (AdaBoost), stacking generalization, gradient boosting regression tree, etc.), a neural network model (e.g., radial basis function network, perceptron, backpropagation, Hopfield network, etc.), a regularization model (e.g., ridge regression, least absolute shrinkage and selection operator, elastic net, least angle regression), a rule system model (e.g., cube, one rule, zero rule, repeated incremental pruning to produce error reduction), a regression model (e.g., linear regression, ordinary least squares regression, stepwise regression, multivariate adaptive regression splines, locally estimated scatterplot smoothing, logistic regression, etc.), a Bayesian model (e.g., naive Bayes, average dependence estimators, Bayesian belief network, Gaussian naive Bayes, multinomial naive Bayes, Bayesian network), a decision tree model (e.g., classification and regression tree, iterative dichotomiser 3, C4.5, C5.0, chi-squared automatic interaction detection, decision stump, conditional decision tree, M5), a dimensionality reduction model (e.g., principal component analysis, partial least squares regression, Sammon mapping, multidimensional scaling, projection pursuit, principal component regression, partial least squares discriminant analysis, mixture discriminant analysis, quadratic discriminant analysis, regularized discriminant analysis, flexible discriminant analysis, linear discriminant analysis, etc.), an instance model (e.g., k-nearest neighbor, learning vector quantization, self-organizing map, locally weighted learning, etc.), a clustering model (e.g., k-means, k-medians, expectation maximization, hierarchical clustering, etc.), etc.

[0224] As an example, the system can utilize one or more recurrent neural networks (RNNs). One type of RNN is called long short-term memory (LSTM), which can be units or components (e.g., of one or more units) in one or more layers. An LSTM component can be an artificial neural network (ANN) that is designed to identify patterns in data sequences such as time series data. When provided with time series data, the LSTM takes into account time and sequence, such that the LSTM can include a time dimension. For example, consider using one or more RNNs to process time data from one or more sources, optionally in combination with spatial data. This approach can identify time patterns, which can be used to make predictions (e.g., about one or more patterns at future times, etc.).

[0225] As an example, the TENSORFLOW framework (Google LLC, Mountain View, California) can be implemented, which is an open-source software library for dataflow programming that includes a symbolic mathematics library and can be implemented for machine learning applications that may include neural networks. As an example, the CAFFE framework can be implemented, which is a DL framework developed by Berkeley AI Research (BAIR) (University of California, Berkeley). As another example, consider the SCIKIT platform (e.g., scikit-learn), 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 mentioned above, frameworks such as the PYTORCH framework can be used.

[0226] As an example, the training method can include various actions that can operate on a dataset to train an ML model. As an example, the dataset can be split into training data and test data, where the test data can be provided for evaluation. The method can include cross-validation of parameters and optimal parameters, which can be provided for model training.

[0227] 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 for 64-bit LINUX, MACOS (Apple Inc., Cupertino, California), WINDOWS (Microsoft Corp., Redmond, Washington), and mobile computing platforms including platforms with ANDROID (Google LLC, Mountain View, California) and IOS (Apple Inc.) operating systems.

[0228] TENSORFLOW computations can be represented as stateful dataflow graphs; note that the name TENSORFLOW derives from the operations performed by such neural networks on multi-dimensional data arrays. Such arrays can be referred to as "tensors".

[0229] As an example, one or more detection techniques can implement one or more ML models. In such an example, one or more detection techniques can provide tank status detection and / or tank volume change detection.

[0230] As an example, a method may include: receiving real-time data related to a drilling fluid for a drilling operation that utilizes a drilling fluid system including a tank and a pump, where the drilling operation includes pumping the drilling fluid to a bit on a drill string that rotates to extend a borehole in a formation, and where the drilling fluid flows into an annulus between the drill string and the formation to apply pressure to the formation; detecting a tank state from a set of tank states at least partially based on the real-time data, where the set of tank states includes tank states defined in terms of one or more operations of the pump; and detecting a change in tank volume at least partially based on the tank state as an indicator of an undesirable interaction between the drilling fluid and the formation.

[0231] As an example, an undesirable interaction between the drilling fluid and the formation may include formation fluid flowing from the formation into the wellbore. In such an example, the change in tank volume may be an increase in tank volume. As an example, a method may include issuing an instruction to address a kick. For example, consider the instruction to be to address a kick to reduce the risk of a blowout. As an example, the instruction may direct the drilling fluid system to increase the pressure applied to the formation (e.g., consider adjusting the density of the drilling fluid, etc.).

[0232] As an example, an undesirable interaction between the drilling fluid and the formation may include a portion of the drilling fluid flowing from the borehole into the formation. In such an example, the change in tank volume may be a decrease in tank volume. As an example, a method may include issuing an instruction to address the risk of formation damage. For example, consider an instruction to direct the drilling fluid system to reduce the pressure applied to the formation.

[0233] As an example, one or more operations of the pump may include a pumping operation that indicates an expected increase in the tank volume of one or more tanks. As an example, one or more operations of the pump may include a pumping operation that indicates an expected decrease in the tank volume of one or more tanks.

[0234] As an example, the method may include detecting the change in tank volume by at least partially basing a selection of a computational technique on the tank state. For example, different tank states (e.g., pit states) may be associated with different computational techniques. As an example, the computational technique may consider pump operation.

[0235] As an example, the tank of the drilling fluid system may include a mud make-up tank, and for example, the method may include detecting the change in tank volume by detecting a change in volume of one or more of the mud make-up tanks. In such an example, the detection may include detecting a period of rest based on one or more conditions before detecting a change in volume of one or more of the mud make-up tanks.

[0236] As an example, real-time data can include drill bit depth data and pit volume data. For example, various GUIs illustrate data channels that can be obtained to perform one or more detection methods.

[0237] As an example, the method can include detecting a change in pit volume as an indicator of a problem in the drilling fluid system. In such an example, the problem can include one or more of equipment problems and operating procedure problems.

[0238] As an example, the system can include one or more processors; a memory accessible to at least one of the one or more processors; processor-executable instructions stored in the memory and executable to direct the system to: receive real-time data related to a drilling fluid for a drilling operation that utilizes a drilling fluid system including a pit and a pump, where the drilling operation includes pumping the drilling fluid to a drill bit on a drill string that rotates to extend a borehole in a formation, and where the drilling fluid flows into an annulus between the drill string and the formation to apply pressure to the formation; detect a pit state from a set of pit states based at least in part on the real-time data, where the set of pit states includes pit states defined by one or more operations of the pump; and detect a change in pit volume based at least in part on the pit state as an indicator of an undesired interaction between the drilling fluid and the formation.

[0239] As an example, one or more non-transitory computer-readable storage media can include processor-executable instructions to direct a computing system to: receive real-time data related to a drilling fluid for a drilling operation that utilizes a drilling fluid system including a pit and a pump, where the drilling operation includes pumping the drilling fluid to a drill bit on a drill string that rotates to extend a borehole in a formation, and where the drilling fluid flows into an annulus between the drill string and the formation to apply pressure to the formation; detect a pit state from a set of pit states based at least in part on the real-time data, where the set of pit states includes pit states defined by one or more operations of the pump; and detect a change in pit volume based at least in part on the pit state as an indicator of an undesired interaction between the drilling fluid and the formation.

[0240] As an example, a computer program product can include computer-executable instructions to direct a computing system to perform one or more methods, such as one or more of the methods described herein (e.g., partially, wholly, and / or in various combinations).

[0241] Conclusion

[0242] The embodiments disclosed in this disclosure are to help explain the concepts described herein. The description is not exhaustive and does not limit the claims to the exact embodiments disclosed. Modifications and variations from the exact embodiments in this disclosure may still fall within the scope of the claims.

[0243] Similarly, the described steps need not be performed in the same order as discussed or with the same degree of separation. Various steps may be appropriately omitted, repeated, combined, or divided. Accordingly, this disclosure is not limited to the above embodiments, but is defined by the appended claims according to the full scope of their equivalents. In the above description and the following claims, unless otherwise stated, the term "executing" and its variants will be interpreted to refer to any operation of program code or instructions on a device, whether compiled, interpreted, or run using other techniques.

[0244] The appended claims do not invoke section 112(f), unless the phrase "means for" is used expressly with the associated function.

Claims

1. A method (1700), comprising: receiving real-time data related to a drilling fluid for a drilling operation that utilizes a drilling fluid system including a tank and a pump, wherein the drilling operation includes pumping the drilling fluid to a drill bit on a drill string that rotates to extend a wellbore in a formation, and wherein the drilling fluid flows into an annulus between the drill string and the formation to apply pressure to the formation (1710); detecting a tank state from a set of tank states based at least in part on the real-time data, wherein the set of tank states includes tank states defined in terms of one or more operations of the pump (1720); and detecting a change in tank volume based at least in part on the tank state as an indicator of an undesirable interaction between the drilling fluid and the formation (1730).

2. The method according to claim 1, wherein the undesirable interaction between the drilling fluid and the formation includes formation fluid flowing from the formation into the wellbore, optionally, wherein the change in tank volume is an increase in tank volume.

3. The method according to claim 1 or 2, including issuing an instruction to address a well kick, optionally, wherein the instruction to address the well kick reduces the risk of a blowout, and optionally, wherein the instruction indicates that the drilling fluid system increases the pressure applied to the formation.

4. The method according to any one of the preceding claims, wherein the undesirable interaction between the drilling fluid and the formation includes a portion of the drilling fluid flowing from the borehole into the formation, optionally wherein the change in tank volume is a decrease in tank volume.

5. The method according to any one of the preceding claims, including issuing an instruction to address the risk of formation damage, optionally, wherein the instruction indicates that the drilling fluid system reduces the pressure applied to the formation.

6. The method according to any one of the preceding claims, wherein one or more operations of the pump include a pumping operation that indicates an expected increase in the tank volume of one or more of the tanks.

7. The method according to any one of the preceding claims, wherein one or more operations of the pump include a pumping operation that indicates an expected decrease in the tank volume of one or more of the tanks.

8. The method according to any one of the preceding claims, wherein detecting a change in tank volume includes selecting a calculation technique based at least in part on the tank state.

9. The method according to any one of the preceding claims, wherein the tank includes a mud makeup tank, and wherein detecting a change in tank volume includes detecting a change in the volume of one or more of the mud makeup tanks.

10. The method according to any one of the preceding claims, wherein the detecting includes detecting a period of rest based on one or more conditions before detecting a change in the volume of one or more of the mud makeup tanks.

11. The method according to any one of the preceding claims, wherein the real-time data includes drill bit depth data and tank volume data.

12. The method according to any one of the preceding claims, comprising detecting a change in tank volume as an indicator of a problem with the drilling fluid system.

13. The method according to any one of the preceding claims, wherein the problem includes one or more of an equipment problem and an operating procedure problem.

14. A system (1670), comprising: one or more processors (1672); a memory (1674) accessible by at least one of the one or more processors; processor-executable instructions (1676) stored in the memory and executable to direct the system to: receive real-time data related to drilling fluid for a drilling operation that utilizes a drilling fluid system including a tank and a pump, wherein the drilling operation includes pumping the drilling fluid to a bit on a drill string, the drill string rotating to extend a borehole in a formation, and wherein the drilling fluid flows into an annulus between the drill string and the formation to apply pressure to the formation (1711); detect a tank state from a set of tank states based at least in part on the real-time data, wherein the set of tank states includes tank states defined by one or more operations of the pump (1721); and detect a change in tank volume based at least in part on the tank state as an indicator of an undesirable interaction between the drilling fluid and the formation (1731).

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

Images