Flowmeter calibration

Abstract

A method may include receiving a flow estimate from a computational virtual flow meter at a wellsite; receiving a flow measurement from a physical flow meter at the wellsite; and invoking a calibration of the physical flow meter based on the flow estimate and the flow measurement.

Description

Technical Field

[0001] This application claims priority to and the benefit of U.S. Provisional Application Serial No. 63 / 395,636, filed on August 5, 2022, the entire contents of which are incorporated herein by reference. Background Art

[0002] Various types of flow meters may be used in an oil field to measure flow. For example, consider a multiphase flow meter that may measure the flow of a multiphase flow at a well site. In such an example, the multiphase flow meter may be a complex measuring instrument that is calibrated to provide reliable and accurate flow measurements. Over time, in response to various changes, the flow measurement from the flow meter may drift, which may be due to the flow meter losing its ability to provide reliable and accurate technology, which may be considered a loss of calibration or a calibration failure. When a flow meter needs calibration (e.g., recalibration), a crew may be called to the oil field to perform various tasks to calibrate the flow meter. Summary of the invention

[0003] A method may include receiving a flow estimate from a computed virtual flow meter at a wellsite; receiving a flow measurement from a physical flow meter at the wellsite; and invoking calibration of the physical flow meter based on the flow estimate and the flow measurement. 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 instruct the system to: receive a flow estimate from a computed virtual flow meter at a wellsite; receive a flow measurement from a physical flow meter at the wellsite; and request calibration of the physical flow meter based on the flow estimate and the flow measurement. One or more computer-readable storage media may include processor-executable instructions to instruct a computing system to: receive a flow estimate from a computed virtual flow meter at a wellsite; receive a flow measurement from a physical flow meter at the wellsite; and request calibration of the physical flow meter based on the flow estimate and the flow measurement. Various other devices, systems, methods, etc. are also disclosed.

[0004] This Summary is provided to introduce a selection of concepts that are further described below in the Detailed Description. This Summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used to help limit the scope of the claimed subject matter. BRIEF DESCRIPTION OF THE DRAWINGS

[0005] The features and advantages of the described embodiments may be more readily understood by referring to the following description taken in conjunction with the accompanying drawings.

[0006] Figure 1 An example of a system is shown;

[0007] Figure 2 An example of a system is shown;

[0008] Figure 3 An example of a system is shown;

[0009] Figure 4 An example of a valve is shown;

[0010] Figure 5 An example of a physical flow meter is shown;

[0011] Figure 6 An example of a system including an example of a physical flow meter is shown;

[0012] Figure 7 An example of a calibration controller is illustrated;

[0013] Figure 8 An example of a system is shown;

[0014] Fig. 9 An example of a system is shown;

[0015] Fig.10 An example of a method is shown;

[0016] Fig.11 An example of a method is shown;

[0017] Fig.12 An example of a controller is shown;

[0018] Fig.13 An example of a controller is shown;

[0019] Fig.14 shows examples of computers and network equipment; and

[0020] Fig.15 Example components of systems and networked systems are shown. DETAILED DESCRIPTION

[0021] The following description includes the best mode currently contemplated for practicing the described embodiments. This description should not be considered in a limiting sense, but is made only for the purpose of describing the general principles of the embodiments. Reference should be made to the issued claims to determine the scope of the described embodiments.

[0022] Figure 1 An example of a system 100 is shown that includes a workspace framework 110 that can provide instantiation, rendering, interaction with, etc., a graphical user interface (GUI) 120. Figure 1In the example of , GUI 120 may include graphical controls for computing framework (eg, application) 121 , project 122 , visualization 123 , one or more other features 124 , data access 125 , and data storage 126 .

[0023] exist Figure 1 In the example of , the workspace framework 110 may be customized for a particular geological environment, such as the exemplary geological environment 150. For example, the geological environment 150 may include layers (e.g., strata) that include a reservoir 151 and may intersect a fault 153. As an example, the geological environment 150 may be equipped with various sensors, detectors, predictors, actuators, and the like. For example, the device 152 may include communication circuits for receiving and sending information relative to one or more networks 155. Such information may include information associated with downhole equipment 154, which may be equipment that obtains information, assists in resource recovery, and the like. Other equipment 156 may be located away from the well site and include sensing, detection, prediction, transmission, or other circuits. Such equipment may include storage and communication circuits to store and transmit data, instructions, and the like. As an example, one or more satellites may be provided for purposes of communication, data acquisition, and the like. For example, Figure 1 A satellite is shown in communication with network 155, which may be configured for communications, noting that the satellite may additionally or alternatively include circuitry for imaging (eg, spatial, spectral, temporal, radiometric, etc.).

[0024] Figure 1 The geological environment 150 is also shown as optionally including equipment 157 and 158 associated with a well, the well including a substantially horizontal portion that may intersect one or more fractures 159. For example, consider a well in a shale formation, which may include natural fractures, artificial fractures (e.g., hydraulic fractures), or a combination of natural fractures and artificial fractures. As an example, a well may be drilled for a laterally extending reservoir. In such an example, there may be lateral variations in properties, stresses, etc., where an assessment of such variations may help plan, operate, etc. to develop a laterally extending reservoir (e.g., via fracturing, injection, extraction, etc.). As an example, equipment 157 and / or 158 may include components, a system, multiple systems, etc. for fracturing, seismic sensing, analysis of seismic data, assessment of one or more fractures, etc.

[0025] exist Figure 1 In the example of , the GUI 120 shows some examples of computational frameworks, including DRILLPLAN, PETREL, TECHLOG, PETROMOD, ECLIPSE, and INTERSECT frameworks (SLB, Houston, Texas).

[0026] The DRILLPLAN framework provides digital well construction planning and includes features for automation of repetitive tasks and validation workflows, enabling rapid generation of drilling programs (eg, digital drill plans, etc.) of improved quality while ensuring consistency.

[0027] The PETREL framework can be part of the DELFI cognitive exploration and production (E&P) environment (SLB, Houston, TX, referred to as the DELFI environment) for geoscience and geoengineering, for example, to analyze subsurface data from exploration to production of fluids from reservoirs.

[0028] One or more types of frameworks may be implemented within or operably coupled to a DELFI environment, which is a secure, cognitive, cloud-based collaborative environment that integrates data and workflows with digital technologies, such as artificial intelligence (AI) and machine learning (ML). As an example, such an environment may provide operations involving one or more frameworks. A DELFI environment may be referred to as a DELFI framework, which may be a framework of multiple frameworks. As an example, a DELFI environment may include various other frameworks, which may include, for example, one or more types of models (e.g., simulation models, etc.).

[0029] The TECHLOG framework can process and process oilfield and laboratory data from various geological environments (e.g., deepwater exploration, shale, etc.). The TECHLOG framework can structure wellbore data for analysis, planning, etc.

[0030] 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.), flow line 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), etc.). 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.

[0031] The ECLIPSE framework provides numerical solutions for reservoir simulators (eg, as a computational framework) for quickly and accurately predicting the dynamic behavior of various types of reservoirs and development scenarios.

[0032] The INTERSECT framework provides a high-resolution reservoir simulator for simulating detailed geological features and quantifying uncertainties, for example, by creating accurate production scenarios, and by integrating accurate models of surface facilities and field operations, the INTERSECT framework can produce reliable results that can be continuously updated through real-time data exchange (e.g., from one or more types of data acquisition equipment in the field, which can acquire data during one or more types of field operations, etc.). The INTERSECT framework can provide completion configurations for complex wells, where such configurations can be built in the field, can provide detailed chemical enhanced oil recovery (EOR) recipes, where such recipes can be implemented in the field, can analyze the application of steam injection and other thermal EOR technologies for implementation in the field, advanced production control in terms of reservoir connection and flexible field management, and flexibility to prepare customized solutions in advance to improve modeling and field management control. As with the other example frameworks, the INTERSECT framework can be used as part of the DELFI cognitive E&P environment, for example, for rapid simulation of multiple concurrent situations. For example, a workflow can utilize one or more of the on-demand DELFI reservoir simulation features.

[0033] The DELFI environment described above provides various features related to the workflow of subsurface analysis, planning, construction, and production, as shown, for example, in the workspace frame 110. Figure 1 As shown, output from the workspace framework 110 may be used to direct, control, etc., one or more processes in the geological environment 150, and feedback 160 may be received in one or more forms (e.g., acquired data regarding operating conditions, equipment conditions, environmental conditions, etc.) via one or more interfaces.

[0034] As an example, the workflow may proceed to a geological and geophysical ("G&G") service provider, which may generate well trajectories, which may involve executing one or more G&G software packages.

[0035] exist Figure 1 In the example of , visualization features 123 can be implemented via workspace framework 110, for example, to perform tasks associated with one or more of a subsurface region, planning operations, constructing wells and / or surface fluid networks, and producing from a reservoir.

[0036] As an example, the visualization process can implement one or more of the various features that can be suitable for one or more web applications. For example, the template can involve the use of JAVASCRIPT object notation format (JSON) and / or one or more other languages / formats. As an example, the framework can include one or more converters. For example, consider a JSON to Python converter and / or a Python to JSON converter. In such a method, one or more features of a framework that can be available in one language can be accessed via a converter. For example, consider an APACHE SPARK framework that can include features available in a specific language, where a converter can convert code available in another language to the specific language so that one or more features can be utilized. As an example, a production oil field can include various types of equipment, can operate with various frameworks, etc., where one or more languages ​​can be utilized. In such an example, a converter can provide feature flexibility and / or compatibility.

[0037] As an example, a visualization feature may provide visualizations of various earth models, attributes, and the like in one or more dimensions. As an example, a visualization feature may provide renderings of information in multiple dimensions, which may optionally include multi-resolution renderings. In this example, the information being presented may be associated with one or more frameworks and / or one or more data stores. As an example, a visualization feature may include one or more control features for controlling a device, which may include, for example, oilfield equipment that may perform one or more oilfield operations. As an example, a workflow may utilize one or more frameworks to generate information that may be used to control one or more types of oilfield equipment (e.g., drilling equipment, cable equipment, fracturing equipment, etc.).

[0038] Although in Figure 1Several simulators are shown in the examples of , but one or more other simulators may be utilized in addition or alternatively. For example, consider the VISAGE geomechanical simulator (SLB, Houston, Texas) or the PETROMOD simulator (SLB, Houston, Texas), etc. The VISAGE simulator includes a finite element numerical solver that can provide simulation results, such as compaction and settlement of geological environments, well and completion integrity in geological environments, cap rock and fault-seal integrity in geological environments, fracture behavior in geological environments, heat recovery in geological environments, CO2 processing, etc. The PETROMOD framework provides petroleum system modeling capabilities that 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 a reservoir will be filled with hydrocarbons, including the source and timing of hydrocarbon generation, migration routes, quantity, and type of hydrocarbons in underground or surface conditions. The MANGROVE simulator (SLB, Houston, Texas) provides optimization of stimulation designs (e.g., stimulation treatment operations, such as hydraulic fracturing) in a reservoir-centric environment. The MANGROVE framework can combine scientific and experimental work to predict geomechanical propagation of hydraulic fractures, reactivation of natural fractures, etc., as well as production predictions within 3D reservoir models (e.g., production from drainage zones of a reservoir where fluids move to and / or from a well via one or more types of fractures). The MANGROVE framework can provide results related to heterogeneous interactions between hydraulic fracture networks and natural fracture networks, which can help optimize the number and location of fracture treatment stages (e.g., stimulation treatments), for example to improve perforation efficiency and recovery.

[0039] Figure 2 An example of a geological environment 210 is shown, including reservoirs 211-1 and 211-2, which may be fractured due to faults 212-1 and 212-2, an example of a network of devices 230, an enlarged view of a portion of the network of devices 230, referred to as network 240, and an example of a system 250. Figure 2 Some examples of offshore equipment 214 for oil and gas operations associated with reservoir 211-2 and onshore equipment 216 for oil and gas operations associated with reservoir 211-1 are shown. Figure 2 In the example of FIG. 2 , geological environment 210 may include fluids such as oil (o), water (w), and gas (g), which may be layered in reservoirs 211 - 1 and 211 - 2 .

[0040] exist Figure 2In the example of , equipment 214 and 216 may include one or more of drilling equipment, cable equipment, production equipment, etc. For example, consider equipment 214 to include a drilling rig that can drill into the formation to reach a reservoir target where a well can be completed for hydrocarbon production. As an example, equipment 216 may include production equipment such as a wellhead, valves, pump equipment, gas processing equipment, flow meters, etc. As an example, Figure 1 One or more features of the system 100 may be used for operations in the geological environment 210. For example, consider utilizing a drilling or drilling planning framework, a drilling execution framework, a production framework, etc. to plan, execute, etc. one or more drilling operations, production operations, etc.

[0041] exist Figure 2 , network 240 may be an example of a relatively small production system network. As shown, network 240 forms a somewhat tree-like structure, where flow lines represent branches (eg, segments) and intersections represent nodes. Figure 2 As shown, network 240 provides for the transport of fluids (e.g., oil, water, and / or gas) from well locations along flow lines interconnected at junctions and ultimately at a central processing facility (CPF). In the case where the fluids include solids (e.g., sand, etc.), one or more pieces of equipment may provide for solids removal, collection, etc.

[0042] exist Figure 2 In the example of , various portions of network 240 may include pipelines. For example, consider a perspective view of a geological environment including two pipelines, which may be a pipeline of Man1 and a pipeline of Man3 in network 240, where Man1, Man2, and Man3 are manifolds.

[0043] like Figure 2As shown, the example system 250 includes one or more information storage devices 252, one or more computers 254, one or more networks 260, and instructions 270 (e.g., organized as one or more sets of instructions). With respect to the one or more computers 254, each computer may include one or more processors (e.g., or processing cores) 256 and a memory 258 for storing, for example, instructions 270 (e.g., one or more sets of instructions) that may be executed by at least one of the one or more processors. As an example, a computer may include one or more network interfaces (e.g., wired or wireless), one or more graphics cards, a display interface (e.g., wired or wireless), etc. As an example, images such as surface images (e.g., satellite, geological, geophysical, etc.) may be stored, processed, transmitted, etc. As an example, data may include SAR data, GPS data, etc., and may be stored, for example, in one or more of the storage devices 252. As an example, the information that may be stored in one or more of the storage devices 252 may include information about a device, a location of a device, an orientation of a device, fluid properties, etc.

[0044] As an example, the instructions 270 may include instructions (e.g., stored in the memory 258) executable by at least one of the one or more processors 256 to instruct the system 250 to perform various actions. As an example, the system 250 may be configured such that the instructions 270 provide for establishing, for example, a network modeling may be performed (see, e.g., Figure 1 As an example, one or more sets of instructions may be used to perform one or more methods, techniques, etc., and the one or more sets of instructions may be, for example, Figure 2 Instructions 270.

[0045] As an example, Figure 2 The various graphics in may be part of a graphical user interface (GUI) that may be generated using executable instructions that may be executed locally and / or remotely using local and / or remote display devices (eg, mobile devices, workstations, etc.).

[0046] Figure 3 An example of a portion of a geological environment 301 that may include various types of equipment is shown. Figure 3 As shown, environment 301 may include well site 302 and fluid network 344. Figure 3 In the example of FIG. 3 , wellsite 302 includes a wellbore 306 that extends into the earth when completed and ready to produce fluids from reservoir 311 .

[0047] exist Figure 3In the example of FIG. 3 , a wellbore production device 364 extends from a wellhead 366 of a well site 302 and extends to a reservoir 311 to pump fluid to the surface. As shown, the well site 302 is operably connected to a fluid network 344 via a delivery line 361. As shown by the various arrows, the fluid can flow from the reservoir 311 through the wellbore 306 and onto the fluid network 344. The fluid can then flow from the fluid network 344 to, for example, one or more fluid processing facilities.

[0048] exist Figure 3 In an example, the sensor(s) are positioned to monitor various parameters, for example, during operation. The sensor(s) may measure, for example, pressure, temperature, flow, composition, and other parameters of a reservoir, a wellbore, a gathering and transportation network, a processing facility, and / or other parts of an operation. As an example, the sensor(s) may be operably connected to a surface unit (e.g., to instruct the sensor to acquire data, to collect data from the sensor, etc.).

[0049] exist Figure 3 In an example, the ground unit may include computer facilities such as a memory device, a controller, one or more processors, and a display unit (e.g., for managing data, visualizing analysis results, etc.). As an example, data may be collected in the memory device and processed by the processor (e.g., for analysis, etc.). As an example, data may be collected from (one or more) sensors and / or from one or more other sources. For example, the data may be supplemented by historical data collected from other operations, user input, etc. As an example, the analyzed data may be used in a decision-making process.

[0050] As an example, a transceiver may be provided to allow communication between the surface unit and one or more pieces of equipment in environment 301. For example, a controller may be used to actuate a mechanism in environment 301 via the transceiver, optionally based on one or more decisions of a decision-making process. In this way, equipment in environment 301 may be selectively adjusted based at least in part on the collected data. Such adjustments may be made automatically, for example, based on a computer protocol, manually by an operator, or both. As an example, one or more drilling plans may be adjusted (e.g., to select optimal operating conditions, to avoid problems, etc.).

[0051] To facilitate data analysis, one or more simulators may be implemented (e.g., optionally via a surface unit or other unit, system, etc.). As an example, the data fed into the one or more simulators may be historical data, real-time data, or a combination thereof. As an example, simulations through the one or more simulators may be repeated or adjusted based on the received data.

[0052] exist Figure 3In the example of, the simulator may include a reservoir simulator 328, a wellbore simulator 330, a surface network simulator 332, a process simulator 334, and an economic simulator 336. As an example, the reservoir simulator 328 may be configured to solve for hydrocarbon flow through a reservoir and into one or more wellbores. As an example, the wellbore simulator 330 and the surface network simulator 332 may be configured to solve for hydrocarbon flow through a surface gathering and transportation network of wellbores and pipelines. Regarding the process simulator 334, it may be configured to model a processing plant, in which a fluid containing hydrocarbons is separated into its constituent components (e.g., methane, ethane, propane, etc.), for example, and prepared for further distribution (e.g., transportation via roads, railways, pipelines, etc.) and optionally for sale. As an example, the economic simulator 336 may be configured to model the costs associated with at least a portion of the operation. For example, consider the MERAK framework (SLB, Houston, Texas), which can provide an economic analysis.

[0053] As an example, a system may include and / or be operably coupled to Figure 3 One or more of the simulators 328, 330, 332, 334, and 336. As an example, such simulators may be associated with a framework and / or may be considered a tool (see, e.g., Figure 1 system 100, etc.). Figure 3 Various devices in the exemplary geological environment 301 may be operably coupled to one or more systems, one or more frameworks, etc. As an example, one or more of the sensor(s) may be operably coupled to one or more networks (e.g., wired and / or wireless) for transmitting data, which, as explained, may include data indicative of production. As shown, the sensor(s) may be used to acquire downhole data and / or surface data, which may include data related to production (e.g., flow rate, temperature, pressure, composition, etc.). Such data may be used in, for example, Figure 1 The system 100 is used for operational decision-making, etc.

[0054] Figure 4 An example of a throttle valve 400 is shown. One or more throttle valves may be included in the system (see, e.g. Figure 2 A choke valve may be located on or near a Christmas tree for controlling the production of production fluids from a well (e.g., consider a wellhead choke valve). The opening or closing of a choke valve may affect the rate and pressure at which production fluids proceed through a pipeline, processing facility, etc. An adjustable choke valve (e.g., an adjustable choke) may be linked to an automated control system to enable control of one or more production parameters of a well.

[0055] exist Figure 4In the example of , the throttle valve 400 includes openings 404 and 408 leading to corresponding passages, wherein the passages 404 and 408 can be fluidly connected via adjustment of a rod 410, which can be operably coupled to one or more types of mechanisms. For example, consider a cage mechanism, a needle seat mechanism, etc.

[0056] The plug-cage restrictor valve may include a plug operably coupled to a stem to move the plug relative to a cage, which may be a multi-component cage (e.g., consider an inner cage, an outer cage, etc.). In such an example, the cage may include multiple openings, which may be of one or more sizes. For example, consider a ring of smaller openings and a ring of larger openings, where the openings of different sizes may provide a finer adjustment of the flow rate. In such an example, the plug may first provide the opening of the smaller opening to provide fluid communication between the passages, and then upon further axial translation, provide the opening of the larger opening to provide a larger cross-sectional flow area for the fluid communication between the passages. As an example, the stem of the plug-cage restrictor valve may be rotatable, where the rotation causes the axial translation to position the plug relative to the cage.

[0057] The needle and seat throttle valve may include a needle portion that may be part of a stem or otherwise operably coupled to a stem, wherein the stem may be threaded such that rotation causes translation of the needle portion relative to the seat. When the needle portion initially translates an axial distance, an annular space is created that causes fluid communication between the passages. Upon further translation, the needle portion may be completely removed from the bore of the seat such that the annular opening becomes a cylindrical opening, which provides a larger cross-sectional flow area for fluid communication between the passages.

[0058] As an example, a throttle valve may include one or more sensors that may provide one or more measurements, such as one or more of position (eg, stem, needle portion, plug, etc.), flow, pressure, temperature, etc.

[0059] As an example, a throttle valve may be a one-way valve that is intended to operate with flow in a predetermined direction (eg, from a high-pressure side to a low-pressure side).

[0060] The choke valve can be selected so that fluctuations in the line pressure downstream of the choke valve have minimal effect on production rate. In operation, the flow through the choke valve can be in so-called critical flow conditions. In critical flow conditions, the flow rate is a function of the upstream pressure or the tubing pressure. For example, consider a standard where the downstream pressure is about 0.55 or less of the tubing pressure.

[0061] As an example, a multiphase throttling equation can be used to estimate the flowing wellhead pressure for a given set of well conditions and an appropriate multiphase throttling coefficient (e.g., Gilbert, Ros, Baxendell, Achong, etc.), which may include multiple coefficients (e.g., A1, A2, and A3). For example, consider the following equation with parameter values ​​inserted, as described below.

[0062] p wh = (3.86x10 -3 (400)(800) 0.546 ) / ((12 / 64) 1.89 ) = 1,405 psia

[0063] In the above equations that can be used to estimate flow rates or choke diameters, for a well producing 400 stb / D of oil, with a gas-to-liquid ratio of 800 scf / STB, and a choke size of 12 / 64 inch, the Gilbert coefficients are 3.86 × 10 -3 , 0.546, and 1.89. As shown, the estimated flowing wellhead pressure is 1,405 psia. In the example using the Ros throttling equation, an estimated flowing wellhead pressure of 1,371 psia was calculated.

[0064] Parameters that can be utilized in various calculations include discharge coefficient (Cd), pipe diameter (d), pipe length (L), specific heat ratio (k) (e.g., Cp / Cv), standard pressure (psc), wellhead pressure (pwh), gas flow rate (qg), liquid flow rate (ql), standard temperature (Tsc), wellhead temperature (Twh), ratio of downstream pressure to upstream pressure (y), gas compressibility factor (z), gas specific gravity (yg), etc.

[0065] exist Figure 4 In the example of FIG. 4 , the throttle valve 400 includes a port 430 that can be used to monitor the pressure. Figure 4 As shown, controller 450 may be used to control rod 410. For example, consider a motor that may be operably coupled to rod 410 such that the motor may be controlled to adjust rod 410 (e.g., to adjust the shape and size of one or more openings between passages 404 and 408, etc.).

[0066] As an example, the system can utilize one or more choke formulas. For example, consider a semi-analytical approach that can be used for oil and gas well rate estimation. Kargarpour's article entitled "Oil and gas well rate estimation by choke formula: semi-analytical approach", Journal of Petroleum Exploration and Production Technology (2019) 9:23 75-2386 is incorporated herein by reference.

[0067] In various cases, the lack of continuous well productivity measurements may result in untimely (e.g., delayed) detection of production delays. In addition, in the absence of real-time productivity, various workflows may not be suitable for automation. Productivity may be used for various purposes, such as gas injection, water injection, chemical injection, etc.

[0068] As an example, a method may utilize an equation that may be semi-empirical and data driven to provide flow based on real-time pressure measurements. Such an equation may be referred to as a model, however, it may lack a physical basis because it relies on one or more parameters, where the values ​​of the parameters are calibrated and can be recalibrated.

[0069] As an example, the equations may be part of a virtual flow meter (VFM) that may be adapted for a particular device such as a flow device. A flow device may be a device that can be used to control the flow of a fluid. For example, consider a throttle valve. As an example, a throttle VFM may provide an estimate of the flow through the throttling region of the flow device using an upstream pressure measurement and a downstream pressure measurement. Such a VFM may include two real-time inputs (pressures) and one or more other inputs that may be less frequently available (e.g., flow device characteristic dimensions, parameter values, etc.).

[0070] As an example, a VFM may be automatically recalibrated. For example, an autonomous process may provide automatic recalibration for changing conditions. As an example, a VFM may calculate real-time single-phase and / or multi-phase liquid flow rates (e.g., in a liquid-agnostic manner, etc.). As an example, a VFM may provide calculations of oil production stages using measured water cut (WC). As an example, a VFM may provide detection of production losses earlier than without the VFM. For example, consider detecting one or more anomalies in oil production, gas injection, water injection, chemical injection, etc. As an example, a VFM may be locally and / or remotely deployable (e.g., cloud and / or edge, etc.). As an example, a VFM or VIMS may provide outputs to one or more frameworks. For example, consider one or more frameworks available in a DELFI environment.

[0071] As an example, a system may include one or more multiphase flow meters that may be installed permanently and / or as needed. As an example, a multiphase flow meter may include one or more features of a Vx SPECTRA surface multiphase flow meter (SLB, Houston, Texas). Such a flow meter may utilize spectral analysis to accurately measure the flow of oil, gas, and water without phase separation. A multiphase flow meter may be used to measure a variety of pressures, although it may introduce a pressure drop into the system. In addition to introducing a pressure drop, such flow meters tend to be expensive and require attention. In this way, a single flow meter may be transported from one location to another to obtain various multiphase flow meter measurements. As an example, an AVOCET production operations framework may be operably coupled to a multiphase flow meter, such as a Vx SPECTRA surface multiphase flow meter. In such an example, data may be acquired by the AVOCET framework and / or one or more signals transmitted to the flow meter.

[0072] As an example, the system may include a virtual flow meter framework that can provide flow estimates without the use of a physical flow meter. As an example, the virtual flow meter can be a throttling virtual flow meter (VFM), which can optionally facilitate gas lift optimization in an automated manner. As an example, the VFM can be integrated into or operably coupled to one or more frameworks, such as the AVOCET production operations framework and / or one or more other frameworks. The AVOCET framework can acquire, store, display, etc. production operations information (e.g., surface, wellbore, wellhead and facility data, measurements such as well test data, fluid analysis, transfer tickets and tank inventory, etc.) for one or more purposes (e.g., tracking forecasts, production targets, budgets, etc.). The AVOCET framework can be used for various cross-domain workflows and can be integrated with one or more other frameworks, environments, etc. The AVOCET framework can provide processing of equipment, operations, etc., whether at a single site or at multiple sites.

[0073] As an example, the VFM may be a choke VFM, which may, for example, be used for one or more purposes. As an example, one or more instances of the choke VFM may be used in a gas lift operation, for example, to optimize gas lift. In such an example, an autonomous gas lift optimization system may be implemented that may provide for optimizing injection of lift gas and increasing production from one or more wells.

[0074] As an example, a VFM can be used for one or more types of equipment where there can be restrictions, such as adjustable restrictions. For example, a valve can include an adjustable restrictor that can adjust the flow rate. Such a valve can be a water valve, an oil valve, a valve for a composition, etc. As an example, a water valve can be involved in one or more water-related operations, such as water injection. In various examples, a VFM can be utilized instead of a physical flow meter or in addition to a physical flow meter. As an example, a VFM can be a backup for a physical flow meter, and a physical flow meter can provide calibration for one or more VFMs, etc.

[0075] U.S. Provisional Application Serial No. 63 / 279,832, filed on November 16, 2021, and entitled “Calibrated Virtual Flow Meter,” is incorporated herein by reference in its entirety. The '832 application provides various examples of VFMs and other devices and various examples of techniques.

[0076] Figure 5 An example of a flow meter 500 is shown including a circuit 510 and a U-sensor tube assembly 520. As shown, the U-sensor tube assembly 520 includes a pair of U-sensor tubes 521 and 523 and various driver components 524 and 525 and various sensor components 526, 527, 528, and 529.

[0077] As described above, the system may include one or more types of flow meters. A flow meter may be a type of instrument that can measure fluid flow and may optionally measure one or more other types of physical properties and / or phenomena (e.g., pressure, temperature, density, vibration, orientation, etc.).

[0078] like Figure 5As shown, the flow meter 500 may include one or more sensor tubes (e.g., U sensor tubes, etc.) 521 and 523. For example, consider that the flow meter 600 includes a pair of U sensor tubes 521 and 523, which may be provided with a split of the incoming flow, wherein the U sensor tubes 521 and 523 oscillate at a natural resonant frequency via driver components 524 and 525. In such an example, the flow meter 500 may include sensor components 526, 527, 528, and 529 as magnet and coil assembly sensitive elements, which may measure voltage amplitude (e.g., sine wave, etc.) relative to time. When the fluid flows in the pair of U sensor tubes 521 and 523, the Coriolis force causes each of the U sensor tubes 521 and 523 to twist oppositely to each other, which results in a phase shift in the voltage amplitude relative to time (e.g., a phase-shifted sine wave), which is shown in graphs 532 and 534. In such an example, the time delay between phases may be measured in microseconds, where the time delay is proportional to the mass flow rate (e.g., a greater time delay may correspond to a greater mass flow rate). In such an example, the frequency may be measured, where the frequency may provide an indication of the density. For example, consider Hooke's law, where a tube may be a spring, and the mass of the tube and the fluid therein may be considered to be coupled to the mass of the spring. In such an example, the density may be estimated to be proportional to the inverse of the square of the frequency. As an example, the volume flow rate may be determined from the mass flow rate and the density (e.g., volume flow rate = mass flow rate / density).

[0079] The flow meter may be characterized by a flow turndown ratio (e.g., up to 100:1 or greater, etc.). The flow meter may be rated for temperature and may include one or more temperature sensors. As an example, the flow meter may be adapted to operate within a temperature range of from negative 200 degrees Celsius to positive 350 degrees Celsius. The flow meter may include one or more types of interfaces, buses, etc.

[0080] As an example, a flow meter may include circuitry that can measure flow within a range of flow rates. For example, consider a range where the lower limit may be as low as zero and the upper limit may be as high as, for example, 400,000 barrels per day (BPD) or more.

[0081] As an example, a flow meter can be rated with uncertainty. For example, consider a flow uncertainty of approximately + / - 0.1% on a liquid (e.g., + / - zero stability error). With respect to density, consider a density uncertainty of approximately + / - 0.0005 g / ml, for example.

[0082] As an example, a flow meter may be constructed of a variety of different materials, one or more of which may be exposed to the fluid and considered to be fluid wetted. As an example, a flow meter may include one or more fluid wetted materials, such as, for example, one or more of stainless steel and alloys (e.g., consider 316 / 316L SST or Alloy C22).

[0083] As an example, the flow meter may be suitable for use in one or more types of hazardous areas, where hazardous areas may be characterized according to one or more standards (e.g., CSA, ATEX / IECEx). In North America, hazardous locations may be defined by a combination of classes and divisions or zones, for example, as follows: Class I (locations made hazardous by the presence of flammable gases or vapors that may be present in the air in quantities sufficient to produce an explosive or ignitable mixture); Class II (locations made hazardous by the presence of flammable or conductive dusts); Class III (locations made hazardous by the presence of fibers or flyings in the air that may ignite easily, but are unlikely to be suspended in quantities sufficient to produce an ignitable mixture); Division 1 (locations where classified hazards exist or may exist under normal conditions); Division 2 (locations where classified hazards are not normally present but may occur under abnormal conditions); Zone 0 (areas where an explosive gas atmosphere is present continuously for an extended period of time); Zone 1 (areas where an explosive atmosphere may occur during normal operation); Zone 2 (areas where an explosive gas atmosphere is not normally present); and so on.

[0084] As an example, the flow meter may include circuitry that may perform I / O counting, for example, considering one or more of dual independent pulse outputs, dual independent analog outputs, status input, and status output.

[0085] Figure 6 An example of a system 600 is shown that includes a multiphase flow meter (MPFM) 610 as a physical flow meter. As an example, the physical flow meter can be a multiphase flow meter. For example, consider the Vx SPECTRA surface multiphase flow meter (SLB, Houston, Texas). The Vx SPECTRA flow meter includes a venturi section and multivariable transmitter for measuring total flow; nuclear sources and detectors to obtain oil, gas, and water holdup; and a compact flow computer that performs calculations and converts flow measurements from line conditions to standard conditions. The Vx SPECTRA flow meter uses full gamma spectroscopy to accurately capture multiphase flow dynamics for real-time monitoring and analysis.

[0086] The Vx SPECTRA flow meter may include an embedded computer running a real-time operating system that can process data from the flow meter's instruments. The embedded computer can run interpretation models and handle external communications. The embedded computer can provide for adjusting one or more parameters that can be calibration parameters. As an example, calibration can include adjusting one or more physical components of the flow meter.

[0087] The flow meter may include a radioactive source, e.g. 133 Ba radioactive source. This flow meter may include a pressure barrier made of extremely hard ceramic to support the line pressure but also to protect the 133 The source box can be mounted in a source holder with a tungsten shield, which can be an external source shield made of tungsten, where the stainless steel source holder contains 133 A small box of Ba. may include a gamma detector that generates high voltage internally at low amperage (700 volts initially, up to 1,800 volts DC); note that there may be a shock hazard. Because the flow meter may include radioactive materials and high voltage circuits, servicing may be limited to trained and licensed individuals.

[0088] As explained, the flow meter may include various components, which may be physical hardware components, circuit components, radioactive components, etc. As an example, the flow meter may include one or more models, which may include model parameters. As an example, for the purpose of calibration of the flow meter, one or more types of parameters (e.g., physical, electrical, firmware, software, etc.) may be adjustable.

[0089] like Figure 6 As shown, MPFM 610 can be mounted on a portable carriage 601 that can facilitate delivery and removal. System 600 can include various conduits, including inlets, outlets, valves, sampling ports, flow connectors, line connectors, etc. For example, system 600 can include inlet port 602, outlet port 604, valves 621, 622 and 623, flow connectors 642 and 644, and fluid sampling ports 652 and 654. Figure 6 As shown, one or more connections 662 may be made to the MPFM 610, which may include connections for one or more of power and data (see, eg, dashed lines).

[0090] As an example, an oil field may include multiple sites with multiple MPFMs installed. For example, consider an oil field with more than 60 MPFMs. In this example, a crew of two to five people may be responsible for traveling to the sites to repair the MPFMs according to a schedule. For example, consider a 60-day schedule such that each of the 60 MPFMs may be repaired every 60 days. As an example, repairs may include calibration. For example, a crew may perform various tests to measure flow and compare to the flow measured by the MPFM so that the MPFM and / or its measurements can be subsequently calibrated. In some cases, a crew may visit and find that the MPFM is properly calibrated, and therefore, the crew visit may be considered non-productive time (NPT).

[0091] As an example, a method may include utilizing a virtual flow meter (VFM) to trigger a calibration request for a flow meter (e.g., an MPFM or other type of flow meter). In such an example, personnel may respond to a calibration request rather than operating according to a schedule or responding to a request while on a relaxed schedule.

[0092] As an example, a method may include executing an edge application for one or more flow meters (eg, MPFM, etc.) to perform operational optimization. Such a method may address one or more operational inefficiencies associated with flow metering in an oil field.

[0093] As explained, an operator may install a permanent MPFM to obtain continuous and reliable flow rates from a well or manifold (connected to multiple wells). MPFMs tend to be sensitive measuring instruments that require recalibration as operating parameters and composition of the production fluid change. As an example, an operator may be provided with a predefined calibration program that has a fixed calibration operation frequency (e.g., 2 months to 4 months) for each MPFM. At each site, the MPFMs may not be connected to a digital infrastructure, such that the operator of the well relies on maintenance personnel to provide regularly updated reports (e.g., daily) from each MPFM.

[0094] A well operator, which may operate multiple wells in an oil field, may contract with a service provider where the well operator may pay for calibration of some MPFMs that do not require calibration and other MPFMs that do require calibration but may continue to operate and provide inaccurate flow rates.

[0095] In a medium sized oil field with a production of about 150K BOPD, there may be about 35 MPFM in operation. The service provider may charge over $100,000 per month in reporting and calibration costs, which is an annual cost of $1,200,000. Methods that can help optimize the calibration schedule can result in a 20% or more cost reduction. In addition, such methods can improve data, reduce energy expenditures, decision making, and control. For example, the method may include predicting calibration time based at least in part on the output of a virtual flow meter (VFM) and a physical flow meter (PFM). For example, data from the VFM and from the PIM may be compared and analyzed, for example to determine trends that may utilize one or more thresholds to trigger the scheduling of calibration of the PIM.

[0096] As an example, data from an oil field may be acquired and processed using one or more machine learning models (ML models), which may include one or more regression models that may make predictions about when a PFM will deviate from calibration to the point where recalibration is required. In this approach, a schedule may be generated that may extend over days or months. Given such a schedule, resources may be provisioned, which may be in a just-in-time (JIT) manner or in another manner that may be consistent with LEAN practices.

[0097] With respect to one or more thresholds that may be used to trigger a calibration (e.g., recalibration) call, consideration may be given to thresholds that may depend on whether the PFM is at a well or at a manifold. As an example, a PFM for a well that produces fluid flowing to a manifold may be used to determine whether the PFM at the manifold is properly calibrated. As an example, a VFM for a well that produces fluid flowing to a manifold may be used to determine whether the PFM at the manifold is properly calibrated, noting that a VFM may be established for the manifold.

[0098] As an example, a method may employ at least two independent flow estimation solutions, wherein such method may improve the operational efficiency of a multiphase flow measurement operation. For example, the method may provide identification and prioritization of MPFMs that may benefit from calibration. As an example, the method may utilize a system including one or more edge-based virtual flow meters (VFMs) that may provide measurements at a well site that may be compared to MPFM flow rates in real time. In such an example, a real-time threshold ratio between the MPFM rate and the VFM rate may be established to continuously provide feedback on the quality of the MPFM measurements. In such a method, when a set threshold is violated, the system may issue a notification (e.g., a flag, a trigger, etc.) indicating that the MPFM needs to be calibrated.

[0099] As an example, the system may provide real-time data transmission for VFM and MPFM, which may be via satellite connection and / or SCADA; note that historical data analysis and trends of VFM and MPFM flow and operating parameters may be stored locally and / or remotely to memory.

[0100] As mentioned, one or more techniques may be employed to predict the estimated time until the next MPFM calibration. For example, historical threshold data may be used to train one or more ML models that may predict when one would expect the MPFM to breach a threshold. Such an approach may allow an operator to plan operations more efficiently.

[0101] As an example, a method may provide automatic calibration of an MPFM using an edge application. For example, an MPFM or other PFM may be remotely calibrated by remotely loading calibration parameters via an edge gateway. In such an approach, an automatic MPFM calibration application may be hosted on an edge gateway, which will automatically or through remote access allow calibration of the MPFM. Such an application may also work autonomously and use VFM data to calibrate an MPFM in an oil field. Additionally, the edge application may be synchronized with one or more actuated throttles and / or valves to provide multi-point calibration in real time.

[0102] As an example, a method can provide an estimate of rate uncertainty. For example, thresholds can be estimated in real time, and MPFM parameters can also be used to estimate uncertainty ranges in MPFM-derived rates. Such information can further help improve production allocation and gain a better understanding of production operations.

[0103] Figure 7An example of an oil field with various sites with one or more PFMs and one or more VFMs is shown, where the calibration controller 700 can predict the calibration time for each of the sites, which can be in days, as indicated by the circles representing different sites. In such an example, the calibration controller 700 can provide a schedule for calibration via one or more networks and / or via one or more site visits. With respect to site visits, the calibration controller 700 can use one or more techniques and / or one or more criteria to merge various sites. For example, considering time differences, sites within a span of four days can be merged. In such an example, two sites indicating 9 days and 11 days can be merged, and three sites indicating 27 days and 28 days can be merged. This approach can save energy, such as energy to transport staff to sites that can be visited within a day. As an example, a staff member may be able to serve a limited number of sites in a day, which may depend on the distance to be traveled. As an example, the calibration controller 700 can take such factors into account as criteria to optimize the use of staff. Other factors may include the PFM or type of PFM at the site. For example, the staff member may be skilled or have a contract to repair a specific type of PFM or multiple specific types of PFMs. As an example, weather conditions, including forecasts, may be considered.

[0104] exist Figure 7 In the example of , cloud services can be used to perform various tasks, where the cloud services can communicate with local services at the well site of the well. As an example, various features can be local and / or remote. For example, some features shown with respect to cloud services can be provided locally, where resources, skills, technologies, etc. are available.

[0105] As an example, the system can provide various types of simulations, such as reservoir simulations, wellbore simulations, surface network simulations, integrated simulations, etc. As an example, a well site can include sensors that can acquire measurements, where such measurements can be used locally and / or remotely. For example, consider measurements that can be obtained for derived flow rates, proxy models, simulation models, etc.

[0106] As an example, the system may include and / or utilize features of one or more cloud platforms (e.g., GOOGLE CLOUD, AMAZON WEB SERVICES CLOUD, AZURE CLOUD, etc.). As an example, the DELFI cognitive exploration and production (E&P) environment may be implemented at least in part in a cloud platform.

[0107] As explained, a choke valve (e.g., a choke) may be present in various oilfield facilities, such as at a well site, to control a well. In the presence of a downhole pump (such as, for example, an electric submersible pump (ESP)), the pump may provide features for flow control such that a choke valve is not necessary for flow control.

[0108] As explained, a throttle valve can be defined via a flow parameter such as the cross-sectional area of ​​the constriction region (e.g., the "throttle"), which can be represented by a diameter (e.g., an actual diameter or an effective diameter). In a throttle valve, a desired flow passes through the throttle valve such that the throttle valve can control the production of a fluid.

[0109] As an example, the following equation can be used for flow rate:

[0110]

[0111] In the foregoing equation, P1 and P2 may be real-time pressure measurements, d is the diameter of the choke, and GLR is the gas-to-liquid ratio (e.g., oil ratio if the water cut (WC) is zero). Various parameters A, b, c, and e may be determined and set that may characterize the behavior of the choke. For example, changes to one or more of the parameters may provide a signature for a particular choke.

[0112] The foregoing equation provides an estimated flow (e.g., flow rate) through a choke valve, which can provide optimization of injection and increase production from a well. As an example, equations such as the foregoing equation can be utilized in a simulation. For example, consider receiving trend data (e.g., real-time data) and outputting flow rates. In such an example, the output can reflect (e.g., simulate) the performance of a physical flow meter (e.g., a Vx SPECTRA flow meter, etc.) over time.

[0113] As an example, the system may operate without input (e.g., continuous input, full-time presence, etc.) from a physical flow meter (e.g., Vx SPECTRA flow meter, etc.) Such a system may help reduce various costs, losses, etc. that may be associated with the operation of a physical flow meter.

[0114] As an example, an oilfield site may include a pressure gauge. For example, consider a pressure gauge that can provide pressure measurements P1 and P2. In such an example, the pressure gauge can be electronic and provide an output of a signal indicating the measured pressure. For example, consider a digital pressure gauge and / or an analog and digital pressure gauge (e.g., including an analog-to-digital converter). As an example, an oilfield device may include a network device, such as, for example, a gateway that can receive signals from various devices that may include one or more pressure gauges. As an example, an oilfield site may include a pressure gauge that can obtain pressure measurements in real time, making real-time data available (e.g., real-time edge data, etc.).

[0115] As an example, a VFM can be implemented as an instruction set that can be operated in the oilfield at an oilfield device. For example, consider an edge application as a throttle VFM, which can operate on inputs such as, for example, pressure measurements from two pressure gauges (e.g., P1 and P2). Such pressure measurements can be real-time to provide trend data to an edge framework and / or a cloud framework, where rates (e.g., flow rates, etc.) can be output. This output can be utilized in the oilfield, whether generated at the oilfield and / or remotely generated and transmitted to the oilfield, which can be in the form of control actions, etc. Although various examples involve artificial lift (e.g., gas lift via gas injection), the VFM can be used for one or more purposes (e.g., water injection, chemical injection, etc.).

[0116] Figure 8 An example of a system 800 and an example of an architecture 801 are shown. As shown, the architecture 801 can provide one or more site injection and / or production optimization, which can be via one or more VFMs (e.g., throttle VFMs, etc.). For example, the architecture 801 can generate one or more results (e.g., control actions, etc.) that can be used to calibrate operations. In such an example, the one or more results can be generated locally and / or remotely (e.g., depending on the number of sites, resources, etc.). As shown, the architecture 801 can include one or more models. As explained, the model can include one or more driving force terms. An example of a driving force can be a pressure difference as can be represented by two pressure measurements (e.g., P1 and P2). The architecture 801 can include one or more physical models, one or more machine learning models, etc. As shown, the architecture 801 includes an interface for real-time data, optionally an interface for self-organizing data, and a calibration component. The result component can include a result interface, where the output result can be a control trigger, a control instruction, etc., which can call one or more actions of one or more pieces of equipment. As an example, the system 800 can include a controller for implementing Figure 7 Features of the calibration controller 700.

[0117] As shown, the system 800 may include a power source 802 (e.g., solar, a generator, a grid, etc.), which may provide power to an edge framework gateway 810, which may include one or more computing cores 812 and one or more media interfaces 814, which may, for example, receive a computer-readable medium 840, which may include one or more data structures, such as an image 842, a framework 844, and data 846. In such an example, the image 842 may be an operating system image that may enable one or more of the one or more cores 812 to establish an operating system environment suitable for executing one or more applications. For example, the framework 844 may be an application suitable for execution in an operating system established in the edge framework gateway 810. As an example, the framework 844 may be suitable for performing tasks associated with the architecture 801. For example, consider tasks associated with the utilization of one or more models, setting one or more parameters of calibration, generating one or more results based at least in part on one or more models, and the like.

[0118] exist Figure 8 In the example of the edge framework gateway 810 ("EF") can include one or more types of interfaces suitable for receiving and / or sending information. For example, consider one or more wireless interfaces that can provide local communications such as to one or more local devices 832, 834, and 836 at the site and / or remote communications to one or more remote sites 852 and 854. As an example, the local devices 832, 834, and 836 can include one or more pressure gauges.

[0119] As an example, EF 810 may be installed at a location some distance from a city, town, etc. In such an example, EF 810 may be accessible via a satellite communication network.

[0120] A communications satellite is an artificial satellite that relays and amplifies radio telecommunication signals via transponders. A satellite communications network may include one or more communications satellites, which may, for example, provide one or more communications channels. As of 2021, there are about 2,000 communications satellites in orbit around the Earth, some of which are geostationary above the equator, allowing a ground station's satellite dish to be permanently aimed at the satellite rather than tracking it.

[0121] High-frequency radio waves used for telecommunication links travel by line of sight, which may be blocked by the curve of the Earth. Communications satellites can relay signals around the curve of the Earth, allowing communications between widely separated geographic points. Communications satellites can use one or more frequencies (e.g., radio, microwave, etc.), where frequency bands can be regulated and allocated.

[0122] Satellite communications tend to be slower and more expensive than other types of electronic communications due to factors such as distance, equipment, deployment, and maintenance. For well sites that do not have other forms of communications, satellite communications may be limiting in one or more aspects. For example, where the controller is to operate in real-time or near real-time, a cloud-based control approach may introduce too much latency. Figure 8 As shown in the example of , EF 810 may be deployed where it may operate locally with one or more pieces of equipment 832 , 834 , 836 , etc., which may be for control purposes.

[0123] As needed, communication may occur from time to time between the EF 810 and one or more remote sites 852, 854, etc., which may be via satellite communications where latency and cost are tolerable. As an example, the CRM 840 may be a removable drive that may be brought to the site via one or more modes of transportation. For example, consider airdrops, people via helicopters, airplanes, or ships, etc.

[0124] Regarding airdrops, consider dropping an electronic device that can be locally activated once it is on the ground or when it is suspended by a parachute on the way to the ground. Such electronic devices can communicate via a local communication system (e.g., a local WiFi, Bluetooth, cellular, etc. communication system). In such an example, one or more data structures can be transmitted from the electronic device (e.g., such as including a CRM) to EF 810. Such a method can provide local control, where one or more people may or may not be present in the oil field. As an example, an autonomous and / or human-controllable vehicle at a site can help locate the electronic device and help download its payload to an EF (such as EF 810). For example, consider a local drone or land vehicle that can locate the airdropped electronic device and retrieve it, and directly and / or indirectly transmit one or more data structures from the electronic device to the EF. In such an example, the drone or land vehicle can establish communication with the electronic device and / or read data from the electronic device so that the data can be transmitted (e.g., to one or more EFs).

[0125] As an example, the system may include and / or provide access to various resources, which may be, for example, a DELFI environment (see, e.g. Figure 1 ). For example, consider the PIPESIM framework, which can be implemented locally and / or remotely (e.g., as a complete and / or customized framework). As an example, the PIPESIM framework and / or other frameworks can be used for one or more purposes, which can include calibration, generation of results, etc. As an example, a framework such as the PIPESIM framework can provide a comparison between the output of a semi-empirical model and the output of the PIPESIM framework.

[0126] As an example, the EF may include a licensing server, a semi-empirical model component, a framework simulation engine (e.g., a PIPESIM engine, etc.), and a REST API, where the REST API may receive one or more API calls, e.g., as one or more model requests, calibration requests, simulation requests, etc. As an example, the EF may respond to the API calls with outputs, where such outputs may be provided to one or more edge applications, pieces of equipment, etc. (e.g., for individual and / or coordinated control of one or more groups of equipment, etc.).

[0127] Referring again to architecture 801, as explained, one or more physics-based models can be deployed to the edge for implementation, for example, to operate in response to real-time data of one or more types of equipment control. As an example, a fluid simulation framework such as the PIPESIM framework can be implemented in an edge manner. Such a fluid simulation framework can be a multiphase flow simulation framework suitable for processing multiphase flows that may occur in one or more types of oilfield and / or gasfield operations.

[0128] As an example, one or more types of frameworks may be used for a virtual flow meter (VFM). For example, the framework may include a set of conservation equations describing mass momentum and energy for single-phase, two-phase, or three-phase flow (e.g., according to one or more of LEDAFLOW (Kongsberg Oil & Gas Technologies AS, Sandvika, Norway), OLGA model (SLB, Houston, Texas), TUFFP unified mechanical model (Tulsa University Fluid Flow Projects, Tulsa, Oklahoma), etc.). As an example, the framework may include a simulator so that flow simulations can be performed, which may be used for multiphase fluid flows.

[0129] like Figure 8As shown, EF can be executed within a gateway, such as an AGORA gateway (e.g., considering one or more processors, memories, etc., which can be deployed as a "box" that can be locally powered and can communicate locally with other devices via one or more interfaces). As an example, the gateway can include one or more features of an AGORA gateway (e.g., v.202, v.402, etc.) and / or another gateway. For example, consider an INTEL ATOM E3930 or E3950 dual-core with DRAM and eMMC and / or SSD. Such a gateway can include a trusted platform module (TPM), which can provide secure and measured boot support (e.g., via hashing, etc.). The gateway can include one or more interfaces (e.g., Ethernet, RS485 / 422, RS232, etc.). Regarding power, the gateway can consume less than about 100W (e.g., considering less than 10W or less than 20W). As an example, the gateway can include an operating system (e.g., considering LINUX DEBIAN LTS). As an example, the gateway can include a cellular interface (e.g., 4G LTE with global modem / GPS, etc.). As an example, the gateway may include a WIFI interface (e.g., 802.11 a / b / g / n). As an example, the gateway may operate using AC 100-240V, 50 / 60Hz, or 24VDC. Regarding size, consider a gateway having a protective box with dimensions of approximately 10 inches by 8 inches by 4 inches.

[0130] As an example, a gateway can be part of a drone. For example, consider a mobile gateway that can take off and land, where it can land to operably connect with a device to provide control of such device. In such an example, the device can include a landing pad. For example, the drone can be guided to the landing pad, where the drone can interact with the device to control the device. As an example, a wellhead can include a landing pad, where the wellhead can include one or more sensors (e.g., temperature and pressure), and where the mobile gateway can include features for generating fluid flow values ​​using information from the one or more sensors. In such an example, the mobile gateway can issue one or more control instructions (e.g., to a throttle valve, a pump, etc.).

[0131] As an example, a gateway may include hardware (e.g., circuitry) that may provide operation of a drone. As an example, a gateway may be a drone controller and a controller for other devices, where the drone controller may locate the gateway (e.g., via drone flight characteristics, etc.) so that the gateway may control the other devices.

[0132] As an example, a VFM may operate independently of a PFM and may provide relatively stable data indicative of flow. The output from a VFM may be less susceptible to changes in fluid properties and one or more other types of changes. In contrast, a PFM may be more sensitive to changes, such that the flow output by the PFM may vary in accuracy when one or more types of changes occur in the fluid and / or the environment (e.g., ambient conditions, such as temperature, etc.). As an example, a calibrated PFM may be accurate in terms of flow measurement, and the flow estimate from the VFM may be precise, with a stability that exceeds the stability of the PFM. Therefore, the characteristics of a PIM and a VFM may be different, wherein these differences may be used to understand when to calibrate the PIM.

[0133] As an example, a method may include acquiring data from a VFM and a PIM and plotting or otherwise analyzing the data relative to time, which may provide a difference relative to time, wherein if the difference becomes large and crosses a threshold, then this may indicate that the PIM requires calibration. As explained, when an oil field includes many sites with VFMs and PFMs, data may be acquired and analyzed for the purpose of training one or more ML models, which may include one or more of a classification model and / or a prediction model. As explained, a prediction model may be trained to predict when a PFM will require calibration. As explained with respect to Figure 7 As explained, a calibration controller may be utilized that may schedule, optimize schedules, etc., for the purpose of performing oilfield calibration of the PFM.

[0134] U.S. Provisional Application Serial No. 63 / 358,189, filed on July 4, 2022, and entitled “Field Pump Equipment System,” is incorporated herein by reference in its entirety (referred to herein as the '189 Application). The '189 Application describes various techniques for predicting equipment conditions. As explained herein, the PFM that requires calibration can be an equipment condition of the PFM. As an example, a VFM can be utilized to generate information that can be used as an input to a trained ML model as a predictor, as well as other inputs. For example, a flow estimate of the VFM can be used as an input. As an example, one or more pressures, temperatures, etc. can be utilized as inputs.

[0135] Fig. 9 An example of a system 900 is shown, which includes components for inference data acquisition 910, data preprocessing 920, optional data visualization 925, and fault prediction 930, which can be implemented using a containerized application programming interface (API) 932 for accessing a trained ML model 934. As shown, an edge application architecture can be utilized, in which one or more suitable languages ​​(e.g., JSON, etc.) can be implemented. Fig. 9In the example of , the system 900 can pre-process the data, where the API call can be in the form of a JSON request, where a JSON response can be received. Fig. 9 In the example of , system 900 may include one or more edge applications and one or more types of components (eg, containerized, etc.) that may be accessed using one or more APIs.

[0136] Fig.10 Examples of methods 1010, 1030, and 1050 are shown. As shown, method 1010 may include a data preprocessing block 1011, a drill-down event labeling block 1012 that may utilize one or more subject matter experts (SMEs), an evaluation block 1013 for evaluating event signatures, a feature engineering block 1014 for determining suitable features, a modeling block 1015 that may be iterated, a testing block 1016 for testing the trained model of the modeling block 1015, and a packaging and deployment block 1017 that may provide containerized packaging and deployment, for example, to an edge device.

[0137] As shown, the method 1030 includes a data collection block 1031 for collecting appropriate frequency time series signal data, such as pressure, temperature, flow, etc., which can come from VFM and PFM; a pre-processing block 1032 for handling outliers, inconsistencies, frequencies and other quality control issues; and a fault event marking block 1033, which can be assisted by (SME), such as allowing the data to be marked to mark the start time and end time of the fault event, where the fault event can be a fault of the PIM, which can be subject to service to calibrate the PIM. In such an example, the mark can be binary, where 0 indicates no event and 1 indicates the presence of a fault event. The fault event can be identified by an indicator signal, such as the difference between the VFM flow and the PFM flow. As shown, the method 1030 can also include an evaluation block 1034 for evaluating event signatures, a feature engineering block 1035 for feature engineering, a modeling block 1036 for model generation, a model adjustment block 1037, and a packaging and deployment block 1038.

[0138] In various regions in the data before and after the failure event, regions of abnormal behavior can be identified. As an example, the data can be divided into regions of normal behavior and abnormal behavior, where the underlying assumption is that there are no precursors to failure in regions of normal behavior. This approach provides for creating a data set suitable for ML model training and testing, so that the ML model can be trained for input of normal behavior data to replicate the normal behavior data. It can be expected that this trained ML model is able to closely replicate information about the PIM of normal performance and experience errors when attempting to replicate information about the PIM of abnormal performance, because the ML model is not trained on data representing abnormal behavior (e.g., abnormal behavior).

[0139] As an example, an autoencoder ML model including an encoder portion and a decoder portion may be utilized. An autoencoder ML model may be described in which the encoder portion maps an input to a code, and in which the decoder portion maps the code to a reconstruction of the input. The autoencoder ML model may be a feedforward non-recursive neural network (e.g., similar to a single-layer perceptron) that participates in a multilayer perceptron (MLP), for example, employing an input layer and an output layer connected by one or more hidden layers. The output layer may include the same number of nodes (neurons) as the input layer. As explained, the autoencoder ML model may reconstruct its input (e.g., by minimizing the difference between the input and the output), rather than predicting a target value Y given an input X. As an example, an autoencoder ML model may be trained using unsupervised learning. As explained, data may be acquired and processed so that the data represents normal behavior of the PFM, wherein once available, the ML model may be trained using such processed data in an unsupervised manner.

[0140] As explained, the ML model can simulate normal behavior, where the ML model is built using an autoencoder-decoder model architecture. As explained, the output of such an ML model can be expected to be the same as the input (e.g., the original high-frequency signal). Such an ML model can be used to calculate deviations in the input signal by providing more complete time series data as input. For example, consider a method that involves calculating the absolute difference between the input and output (e.g., reconstruction error).

[0141] By using the trained ML model, a reconstruction error can be generated, where a higher error can be an indicator of an input that is behaving abnormally. With respect to feature engineering, the reconstruction error can be used to generate features to build another ML model. For example, consider using a random survival forest model, which can provide predictions as a survival curve for each timestamp. Given the survival curve, the remaining useful life (RUL) of the PFM can be assessed, where the RUL is an indicator of how long it will take to calibrate.

[0142] Random Survival Forest (RSF) is an ensemble of tree-based learners. RSF ensures that individual trees are decorrelated by 1) building each tree on a different bootstrap sample of the original training data, and 2) evaluating the splitting criteria on a randomly selected subset of features and thresholds at each node. A prediction can be formed by aggregating the predictions of the individual trees in the ensemble. RSF can be built with many independent decision trees, where each decision tree can receive a subset of random samples and a subset of variables is randomly selected at each split in the tree for prediction, and where the final prediction can be the average of the predictions of each individual tree.

[0143] RSF can be used, for example, to provide predictions for diseases such as breast cancer. Consider a data set of 686 women and 8 prognostic factors: 1. age, 2. estrogen receptor (estrec), 3. whether hormone therapy was administered (horTh), 4. menopausal status (menostat), 5. number of positive lymph nodes (pnodes), 6. progesterone receptor (progrec), 7. tumor size (tsize), 8. tumor grade (T grade). In such an example, the goal may be to predict recurrence-free survival time. The method may include loading the data and converting it to numerical values, and then splitting the data 75 / 25 for training and testing. With respect to training, one or more of several splitting criteria may be utilized (e.g., log-rank test, etc.). Once trained, the RSF may be tested using test data.

[0144] As an example, a time-dependent Cox model can be used for survival purposes (e.g., RUL). The time-dependent Cox model can be a time-dependent Cox regression model (TDCM) that quantifies the effect of repeated measurements of covariates in an analysis of time-to-event data. As an example, one or more of a pooled logistic regression model (PLRM), a cross-sectional pooled model (CSPM), a Kaplan-Meier survival model, and a log-rank test model can be implemented (e.g., for output, for comparison, for additional output, etc.). As an example, a survival model that takes into account (e.g., statistically) the time at which the time-dependent covariate is measured can provide more reliable estimates compared to an unadjusted method.

[0145] With respect to making predictions, a sample can be pulled down from each tree in the forest until it reaches a terminal node. The data in each terminal node can be used to estimate survival and cumulative hazard functions nonparametrically, for example, using Kaplan-Meier and Nelson-Aalen estimators, respectively; note that one or more other methods can be implemented in addition or alternatively. As an example, a risk score can be calculated that represents the expected number of events for a particular terminal node. For example, an ensemble prediction can be generated by averaging the trees in the forest. As an example, a method can include generating a predicted survival function that can show differences over certain time periods.

[0146] Reference again Fig.10 , method 1050 includes an input channel box 1051, an autoencoder model box 1052 for health indicator (HI) modeling, an output channel box 1053, a reconstruction error box 1054, a feature generation box 1055, an RSF box 1056 for RUL modeling, and a survival probability curve box 1057.

[0147] As mentioned, one or more methods can be used for RUL modeling. As an example, the trained machine learning model can include a decision tree. For example, consider a decision tree that is part of a random survival forest (RSF or RSF model). As an example, the trained machine learning model can include a time-dependent Cox model.

[0148] exist Fig.10 In an example of , method 1050 may include iterative modeling that may be performed by hyperparameter optimization of a model for use in the case where an inference pipeline may be built. As an example, the model may be packaged as a standalone container (e.g., a Docker container from Docker Inc. of Palo Alto, California, etc.) that may reside on a physical gateway (e.g., an edge device). As described in Fig. 9 As explained in the example of , the containerized model set can provide interaction with one or more applications on the edge to provide a survival probability curve of the signal, which can be at each timestamp for each well, which can be visualized on one or more devices.

[0149] As explained, methods may include using one or more trained ML models to predict when a PFM may need calibration. Such methods may utilize VFM data and PIM data, where, for example, a combination of such data may provide differential trends that may be used to train one or more ML models to make predictions. The one or more trained ML models may receive VFM data and PIM data as input and output information about what may happen in the future with respect to one or more PIMs, particularly when one or more PIMs may be too far off in their measurements and therefore require calibration. As explained, a calibration controller (such as Figure 7 The calibration controller 700) can provide scheduling optimization so that oilfield operations can be performed in a more efficient manner. As an example, Figure 7 The calibration controller 700 may include and / or be operably coupled to one or more frames, which may be having, for example, Figure 6 and / or Fig. 9 The edge frame of the features shown in the system. As explained, Fig. 9 In, the fault prediction may be a calibrated fault prediction, where the fault may be determined relative to a threshold (eg, an error threshold when the error is intolerable due to one or more reasons).

[0150] As an example, a data science framework (e.g., Dataiku framework, Dataiku, Paris, France) and a container framework (e.g., DOCKER framework) can be implemented. In such an example, the container framework can provide the construction of a software unit that packages executable code and its dependencies so that the application can be quickly and reliably executed from one computing environment to another computing environment. As an example, a container can be an image, which is a lightweight, stand-alone executable software package that includes code, runtime, system tools, system libraries, and settings. The container image can become a "container" at runtime, for example, when running on a suitable engine (e.g., DOCKER engine for DOCKER container images). As an example, the edge implementation can utilize a framework, such as, for example, a lightweight machine learning framework, such as the TENSORFLOW LITE (TFL) framework (GOOGLE LLC, Mountain View, California).

[0151] As described above, methods may involve training one or more machine learning models (ML models), which may involve one or more types of training (e.g., supervised learning, unsupervised learning, a combination of supervised and unsupervised learning, etc.). As an example, learning (e.g., training) may involve accessing data, which may be divided into training and test data, then training one or more ML models using the training data to generate one or more trained ML models, and then testing the one or more trained ML models using the test data. In such methods, various model parameters may be set and / or various hyperparameters may be set and / or adjusted. In machine learning, model quality may depend on both model parameters and hyperparameters.

[0152] As an example, a machine learning framework may include one or more machine learning models. As an example, a multivariate linear regression model (MLR model) may be a machine learning model (ML model). As an example, an artificial neural network (ANN) model may be a machine learning model (ML model). As an example, a trained ML model may be implemented for one or more purposes.

[0153] As an example, the ML model can be a non-physics-based ML model, a physics-based ML model, and / or include one or more physics-based models. As an example, the ML model can be relatively lightweight, which can speed up learning and / or reduce computing resource requirements to generate one or more trained ML models.

[0154] Regarding the type of machine learning model, consider one or more examples such as a support vector machine (SVM) model, a k-nearest neighbor (KNN) model, an ensemble classifier model, a neural network (NN) model, etc. As an example, the machine learning model can be a deep learning model (e.g., a deep Boltzmann machine, a deep belief network, a convolutional neural network (CNN), a stacked autoencoder, etc.), an ensemble model (e.g., a random forest, a gradient boosting machine, bootstrap aggregation, adaptive boosting (AdaBoost), stacked generalization, a gradient boosted regression tree, etc.), a neural network model (e.g., a radial basis function network, a perceptron, back propagation, a Hopfield network, etc.), a regularization model (e.g., a ridge regression, a least absolute shrinkage and selection operator, an elastic net, a least angle regression), a rule system model (e.g., a cubic, a one rule, a zero rule, repeated incremental pruning to produce error reduction), a regression model (e.g., a linear regression, an ordinary least squares regression, a stepwise regression, a multivariate adaptive regression spline, a local estimation scatter plot smoothing, a logistic regression, etc.), a neural network model (e.g., a radial basis function network, a perceptron, a ... neural network model (e.g., a radial basis function network, a regression, etc.), Bayesian models (e.g., naive Bayes, average dependency estimator, Bayesian belief network, Gaussian naive Bayes, multinomial naive Bayes, Bayesian network), decision tree models (e.g., classification and regression trees, iterative bisection3, C4.5, C5.0, chi-square automatic interaction detection, decision stump, conditional decision tree, M5), dimensionality reduction models (e.g., principal component analysis, partial least squares regression, Sammon map, multidimensional scaling, projection pursuit, principal component regression, partial least squares discriminant analysis, mixture discriminant analysis, quadratic discriminant analysis, regularized discriminant analysis, flexible discriminant analysis, linear discriminant analysis, etc.), instance models (e.g., k-nearest neighbor, learning vector quantization, self-organizing map, local weighted learning, etc.), clustering models (e.g., k-means, k-median, expectation maximization, hierarchical clustering, etc.), etc.

[0155] As an example, a computing framework with libraries, toolboxes, etc. can be used to build machine models that can be machine learning models, such as those of the MATLAB framework (MathWorks, Inc., Natick, Massachusetts). The MATLAB framework includes toolboxes that provide supervised and unsupervised machine learning algorithms, including support vector machines (SVMs), boosted and bagged decision trees, k-nearest neighbors (KNNs), k-means, k-centers, hierarchical clustering, Gaussian mixture models, and hidden Markov models. Another MATLAB framework toolbox is the Deep Learning Toolbox (DLT), which provides a framework for designing and implementing deep neural networks with algorithms, pre-trained models, and applications. DLT provides convolutional neural networks (ConvNet, CNN) and long short-term memory (LSTM) networks to perform classification and regression on images, time series, and text data. DLT includes features for building network architectures such as generative adversarial networks (GANs) and Siamese networks using custom training loops, shared weights, and automatic differentiation. DLT provides model exchanges for various other frameworks.

[0156] As an example, the TENSORFLOW framework (Google LLC, Mountain View, California) can be implemented, which is an open source software library for data flow programming, which includes a symbolic mathematics library, which can be implemented for machine learning applications that may include neural networks. As an example, the CAFFE framework can be implemented, which is a DL framework developed by Berkeley AI Research (BAIR) (University of California, Berkeley). As another example, consider the scikit platform (e.g., scikit-learn), which utilizes the PYTHON programming language. As an example, a framework such as the APOLLO AI framework can be utilized (APOLLO.AI GmbH, Germany). As an example, a framework such as the PYTORCH framework can be utilized (Facebook AI Research Lab (FAAR), Facebook, Inc., Menlo Park, California).

[0157] As an example, a training method may include various actions that may be performed on a dataset to train an ML model. As an example, a dataset may be split into training data and test data, where the test data may be provided for evaluation. The method may include cross-validation of parameters and optimal parameters, which may be provided for model training.

[0158] The TENSORFLOW framework is scalable for general-purpose computing on multiple CPUs and GPUs with optional CUDA (NVIDIA Corp., Santa Clara, CA) and SYCL (The Khronos Group Inc., Beaverton, OR) graphics processing units (GPUs). TENSORFLOW is available for 64-bit LINUX, MACOS (Apple Inc., Cupertino, CA), WINDOWS (Microsoft Corp., Redmond, WA), and mobile computing platforms including ANDROID (Google LLC, Mountain View, CA) and IOS (Apple Inc.) operating systems.

[0159] TENSORFLOW computations can be represented as stateful data flow graphs; note that the name TENSORFLOW derives from the operations that this neural network performs on multidimensional arrays of data. Such arrays can be called "tensors".

[0160] As an example, the device and / or distributed device may utilize TENSORFLOW LITE (TFL) or another type of lightweight framework. For example, one or more pieces of equipment at the well site may include and / or utilize a lightweight framework suitable for executing machine learning models (e.g., trained ML models, etc.). TFL includes a set of tools to implement machine learning on the device, where the model can run on mobile devices, embedded devices, and IoT devices. TFL is optimized for on-device machine learning by addressing latency (no round trip to the server), privacy (no personal data leaves the device), connectivity (internet connectivity is required), size (simplified model and binary size), and power consumption (e.g., effective inference and lack of network connection). TFL has multi-platform support, covering ANDROID and iOS devices, embedded LINUX, and microcontrollers. TFL has different language support, including JAVA, SWIFT, Objective-C, C++, and PYTHON. TFL provides high performance with hardware acceleration and model optimization. TFL can be used to perform a variety of machine learning tasks, which may include, for example, data processing, image classification, object detection, pose estimation, question answering, text classification, etc. on multiple platforms.

[0161] Fig.11An example of a method 1100 is shown, the method 1100 including a receiving block 1110 for receiving a flow estimate from a computed virtual flow meter at a wellsite; a receiving block 1120 for receiving a flow measurement from a physical flow meter at the wellsite; a calling block 1130 for calling calibration of the physical flow meter based on the flow estimate and the flow measurement; and a calibration block 1140 for calibrating the physical flow meter. As an example, one or more computer-readable storage media including processor-executable instructions can be utilized, which when executed by a processor of a computing system can provide one or more actions of the method 1100, which computing system can be a computing system having local components and / or remote components. For example, consider an edge device local to a wellsite, where the edge device can be operably coupled to a remote device via a network connection.

[0162] exist Fig.11 1, method 1100 is shown with various computer readable media blocks 1111, 1121, 1131, and 1141 (e.g., CRM blocks). Such blocks may be used to perform one or more actions of method 1100. For example, consider a computing system in which instructions may include instructions of one or more of CRM blocks 1111, 1121, 1131, and 1141.

[0163] Fig.12 An example of a controller 1210 is shown with respect to an oil field 1200, which includes a well (W), a VFM (V), a PFM (P), and a gas supply 1220. As shown, the controller 1210 can issue instructions to the oil field 1200 so that gas from the gas supply 1220 can be controlled at the manifold and / or locally (e.g., well by well, etc.). As an example, a wired and / or wireless network can be utilized to control and / or receive output from the VIMS (V). Fig.12 In a process, a VFM may be used for one or more purposes. For example, some sites do not include a PFM, such that a VFM may be used as a substitute. In situations where a site does include a PFM and a VFM, the VFM may be used to determine when the PFM needs calibration. As an example, during a calibration period or other downtime for the PFM, the VFM may be automatically used for flow estimates and optionally control. In this example, once the PFM is calibrated or otherwise returned online, flow measurements from the PFM may be utilized, such as for tracking production, control, etc. As an example, a site may use a combination of VFM estimates and PFM measurements for one or more purposes. As an example, Fig.12 The controller 1210 may include Figure 7 Various features of the calibration controller 700.

[0164] Fig.13 An example of a controller 1300 is shown, which may be implemented as Fig.12 The controller 1210. Fig.13 In the example of FIG. 1 , the controller 1300 may include one or more components, such as one or more of a gas lift component 1310, an electric submersible pump component 1320, a processing component 1330, a service component 1340, a valve selection component 1350, a well selection component 1360, and one or more other components 1370. As explained, information collected via control, such as according to one or more methods, may be utilized to determine one or more actions, which may be directed to improving production, improving operation of equipment (e.g., valves, flow meters, etc.), improving utilization of one or more resources (e.g., gas, electricity, chemical injection for ESP, etc.).

[0165] As an example, a method may include receiving a flow estimate from a computed virtual flow meter at a wellsite; receiving a flow measurement from a physical flow meter at the wellsite; and invoking calibration of the physical flow meter based on the flow estimate and the flow measurement. In such an example, the method may include calibrating the physical flow meter. For example, consider calibrating the physical flow meter by performing a manual task at the wellsite and / or calibrating the physical flow meter by performing a task at the wellsite in response to receiving a command via a network interface at the wellsite.

[0166] As an example, a method may include tracking differences between flow estimates and flow measurements with respect to time. In such an example, the flow estimate may exhibit greater stability than the flow measurement. As an example, a method may include invoking calibration of the physical flow meter in response to at least one difference exceeding a threshold.

[0167] As an example, a method may include using a trained machine learning model to predict a time for calibration. In such an example, a method may include optimizing a schedule for calibration of a plurality of physical flow meters based at least in part on time. In such an example, the optimization may include utilizing one or more criteria, where, for example, the one or more criteria may include a distance criterion between different well sites, a time span criterion, and / or one or more other criteria.

[0168] As an example, the method may include invoking calibration of a physical flow meter in a manner that occurs in response to a time on a schedule. In such an example, the schedule may include times for calibrating other physical flow meters, which may be at the same site or at a different site.

[0169] As an example, the physical flow meter may be at a manifold, where, for example, one or more physical flow meters may be upstream of the manifold. In such an example, each of the physical flow meters upstream of the manifold may have a corresponding calculated virtual flow meter.

[0170] As an example, 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 instruct the system to: receive a flow estimate from a computed virtual flow meter at a wellsite; receive a flow measurement from a physical flow meter at the wellsite; and require calibration of the physical flow meter based on the flow estimate and the flow measurement.

[0171] As an example, one or more computer-readable storage media may include processor-executable instructions to instruct a computing system to: receive a flow estimate from a computed virtual flow meter at a wellsite; receive a flow measurement from a physical flow meter at the wellsite; and request calibration of the physical flow meter based on the flow estimate and the flow measurement.

[0172] As an example, a computer program product may include one or more computer-readable storage media, which may include processor-executable instructions to instruct a computing system to perform one or more methods and / or one or more portions of a method.

[0173] In some embodiments, one or more methods may be performed by a computing system. Fig.14 An example of a system 1400 is shown that may include one or more computing systems 1401-1, 1401-2, 1401-3, and 1401-4, which may be operably coupled via one or more networks 1409, which may include wired and / or wireless networks.

[0174] By way of example, a system may include a single computer system or an arrangement of distributed computer systems. Fig.14 In the example of , computer system 1401-1 may include one or more modules 1402, which may be or include processor executable instructions, for example, executable to perform various tasks (e.g., receive information, request information, process information, simulate, output information, etc.). For example, one or more modules 1402 may include Fig.11 Instructions of one or more of CRM boxes 1111, 1121, 1131 and 1141.

[0175] As an example, the modules may be executed independently or in coordination with one or more processors 1404, which are operably coupled to one or more storage media 1406 (e.g., via wire, wireless, etc.). As an example, one or more of the one or more processors 1404 may be operably coupled to at least one of the one or more network interfaces 1407; note that one or more other components 1408 may also be included. In such an example, the computer system 1401-1 may, for example, send and / or receive information via one or more networks 1409 (e.g., consider one or more of the Internet, a private network, a cellular network, a satellite network, etc.).

[0176] As an example, computer system 1401-1 can receive information from and / or send information to one or more other devices, which can be or include, for example, one or more of computer system 1401-2, etc. The devices can be located in a physical location different from the physical location of computer system 1401-1. As an example, the location can be, for example, a processing facility location, a data center location (e.g., a server farm, etc.), a drilling rig location, a well site location, a downhole location, etc.

[0177] As an example, a processor may be or include a microprocessor, a microcontroller, a processor module or subsystem, a programmable integrated circuit, a programmable gate array, or another control or computing device.

[0178] As an example, storage media 1406 can be implemented as one or more computer-readable or machine-readable storage media. As an example, storage can be distributed within and / or across multiple internal and / or external enclosures of the computing system and / or additional computing systems.

[0179] As examples, the one or more storage media may include one or more different forms of memory, including semiconductor memory devices such as dynamic or static random access memory (DRAM or SRAM), erasable and programmable read-only memory (EPROM), electrically erasable and programmable read-only memory (EEPROM) and flash memory, magnetic disks such as fixed disks, floppy disks and removable disks, other magnetic media including magnetic tapes, optical media such as compact disks (CDs) or digital video disks (DVDs), Blu-ray discs or other types of optical storage, or other types of storage devices.

[0180] As an example, one or more storage media may be located in the machine running the machine-readable instructions, or at a remote site from which the machine-readable instructions may be downloaded over a network for execution.

[0181] As an example, various components of a system (such as, for example, a computer system) may be implemented in hardware, software, or a combination of both hardware and software (eg, including firmware), including one or more signal processing and / or application specific integrated circuits.

[0182] As an example, a system may include a processing device, which may be or include a general purpose processor or a dedicated chip (eg, or chipset) such as an ASIC, FPGA, PLD, or other suitable device.

[0183] Fig.15 Components of an example of a computing system 1500 and an example of a networked system 1510 with a network 1520 are shown. System 1500 includes one or more processors 1502, memory and / or storage components 1504, one or more input and / or output devices 1506, and a bus 1508. In an example embodiment, instructions may be stored in one or more computer-readable media (e.g., memory / storage components 1504). Such instructions may be read by one or more processors (e.g., processor 1502) via a communication bus (e.g., bus 1508), which may be wired or wireless. The one or more processors may execute such instructions to implement (completely or partially) one or more properties (e.g., as part of a method). A user may view output from a process and interact with the process via an I / O device (e.g., device 1506). In an example embodiment, a computer-readable medium may be a storage component, such as a physical memory storage device, e.g., a chip, a chip on a package, a memory card, etc. (e.g., a computer-readable storage medium).

[0184] In an example embodiment, the components may be distributed in, for example, a network system 1510. The network system 1510 includes components 1522-1, 1522-2, 1522-3, ..., 1522-N. For example, component 1522-1 may include (multiple) processors 1502, and (multiple) components 1522-3 may include a memory accessible by (multiple) processors 1502. In addition, (multiple) components 1522-2 may include an I / O device for display and optionally interacting with the method. The network 1520 may be or include the Internet, an intranet, a cellular network, a satellite network, etc.

[0185] As an example, the device can be a mobile device including one or more network interfaces for information communication. For example, the mobile device may include a wireless network interface (e.g., operable via IEEE 802.11, ETSI GSM, Bluetooth, satellite, etc.). As an example, the mobile device may include components such as a main processor, a memory, a display, a display graphics circuit (e.g., optionally including touch and gesture circuits), a SIM slot, an audio / video circuit, a motion processing circuit (e.g., an accelerometer, a gyroscope), a wireless LAN circuit, a smart card circuit, a transmitter circuit, a GPS circuit, and a battery. As an example, the mobile device can be configured as a cellular phone, a tablet computer, 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.

[0186] As an example, the system may be a distributed environment, such as a so-called "cloud" environment, where various devices, components, etc. interact for the purpose of data storage, communication, computing, etc. As an example, a device or system may include one or more components for communicating information via one or more of the Internet (e.g., where communication occurs via one or more Internet protocols), a cellular network, a satellite network, etc. As an example, the method may be implemented in a distributed environment (e.g., in whole or in part as a cloud-based service).

[0187] As an example, information can be input from a display (e.g., consider a touch screen), output to a display, or both. As an example, information can be output to a projector, a laser device, a printer, etc. so that the information can be viewed. As an example, information can be output stereoscopically or holographically. Regarding printers, consider 2D or 3D printers. As an example, a 3D printer can include one or more substances that can be output to construct a 3D object. For example, data can be provided to a 3D printer to construct a 3D representation of an underground stratum. As an example, a layer can be constructed in 3D (e.g., a horizon, etc.), a geological body can be constructed in 3D, etc. As an example, a hole, a crack, etc. can be constructed in 3D (e.g., as a positive structure, as a negative structure, etc.).

[0188] Although only a few example embodiments have been described in detail above, those skilled in the art will readily appreciate that many modifications may be made in the example embodiments. Therefore, all such modifications are intended to be included within the scope of the present disclosure as defined in the appended claims. In the claims, means-plus-function clauses are intended to cover structures described herein as performing the described function, and to cover not only structural equivalents, but also equivalent structures. Thus, although a nail and a screw may not be structural equivalents because a nail employs a cylindrical surface to fasten wooden parts together, while a screw employs a helical surface, in the context of fastening wooden parts, a nail and a screw may be equivalent structures.

Claims

1. A method (1100), comprising: receiving a flow estimate from a computed virtual flow meter at a well site (1110); receiving flow measurements from a physical flow meter at the wellsite (1120); and Calibration of the physical flow meter is invoked based on the flow estimate and the flow measurement (1130).

2. The method of claim 1, comprising calibrating the physical flow meter. 3 . The method of claim 1 , wherein calibrating the physical flow meter comprises performing a manual task at the wellsite.

4. The method of any preceding claim, wherein calibrating the physical flow meter comprises performing a task at the wellsite in response to receiving a command via a network interface at the wellsite.

5. A method according to any preceding claim, comprising tracking differences between the flow estimate and the flow measurement over time, optionally wherein the flow estimate exhibits greater stability than the flow measurement, and optionally comprising invoking calibration in response to at least one of the differences exceeding a threshold.

6. A method according to any preceding claim, comprising using a trained machine learning model to predict calibration times.

7. A method according to any preceding claim, comprising optimising a schedule for calibration of a plurality of physical flow meters based at least in part on the time.

8. A method according to any preceding claim, wherein optimizing comprises utilizing one or more criteria.

9. A method according to any preceding claim, wherein the one or more criteria include a distance criterion between different well sites.

10. A method according to any preceding claim, wherein the one or more criteria comprises a timespan criterion.

11. A method according to any preceding claim, wherein the one or more criteria include a distance criterion and a time span criterion between different well sites.

12. A method according to any preceding claim, wherein invoking calibration of the physical flow meter occurs in response to a time on a schedule, optionally wherein the schedule includes times for calibrating other physical flow meters.

13. A method according to any preceding claim, wherein the physical flow meter is at a manifold, optionally including one or more physical flow meters upstream of the manifold, and optionally wherein each of the physical flow meters upstream of the manifold has a corresponding calculated virtual flow meter.

14. A system (1400), comprising: one or more processors (1404); a memory (1406) accessible by at least one of the one or more processors; Processor executable instructions (1402) stored in the memory and executable to instruct the system to: Receiving a flow estimate from a calculated virtual flow meter at a well site (1111); receiving flow measurement values ​​from a physical flow meter at the well site (1121); and Calibration of the physical flow meter is invoked based on the flow estimate and the flow measurement (1131).

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

Images