Fluid production system framework

Abstract

A method can include acquiring data during operation of a fluid production system generating fluid products, where the data include pressure data, temperature data, and fluid flow data; responsive to identification of one or more fluid flow data issues, generating synthetic fluid flow data utilizing at least a portion of the pressure data and at least a portion of the temperature data as inputs to a flow meter model; controlling a remote simulation engine of a computational framework to, using at least a portion of the data, generate simulation results as to fluid composition within the fluid production system; and determining composition and volume of the fluid products based at least in part on the simulation results.

Description

FLUID PRODUCTION SYSTEM FRAMEWORKRELATED APPLICATION

[0001] This application claims priority to and the benefit of a U.S. Provisional Application having Serial No. 63 / 654,551 , filed 31 May 2024, which is incorporated by reference herein in its entirety.BACKGROUND

[0002] A reservoir can be a subsurface formation that can be characterized at least in part by its porosity and fluid permeability. As an example, a reservoir may be part of a basin such as a sedimentary basin. A basin can be a depression (e.g., caused by plate tectonic activity, subsidence, etc.) in which sediments accumulate. As an example, where hydrocarbon source rocks occur in combination with appropriate depth and duration of burial, a petroleum system may develop within a basin, which may form a reservoir that includes hydrocarbon fluids (e.g., oil, gas, etc.).

[0003] Oilfield exploration and production efforts generally include acquiring data that represent a subsurface volume of interest, and then modeling the physical characteristics of the subsurface volume based on the data. There are many sources for such data, including seismic surveys and well logs. These data permit complex models to be built, which may depict the geology of the subsurface volume, fluid migration over time in the volumes, and other aspects.

[0004] At the production stage, fluid production system operations may be monitored and controlled. A fluid production system can include various types of equipment including equipment that forms a network for fluid communication between wells and processing facilities. In various instances, control may aim to stabilize operations in the face of numerous variables (e.g., variables in reservoir-to-well flow, environmental conditions, equipment operations, physical and / or chemical process, etc.). Control may involve adjusting valves, pumping, compressing, separating, distilling, etc., where various production monitoring points may be equipped with sensors (e.g., pressure sensors, temperature sensors, flow meters, etc.) that acquire data. Well produced reservoir fluid may be considered to be a resource that may be processed to form various products where fluid composition, fluid volume, etc., maybe assessed throughout a fluid production system to help assure product quality and quantity. As such, an ability to generate results germane to operations with sufficient frequency (e.g., on a daily basis) in a manner that may keep up with acquisition of fresh data can offer opportunities to improve operation of a fluid production system and product delivery.SUMMARY

[0005] A method can include acquiring data during operation of a fluid production system generating fluid products, where the data include pressure data, temperature data, and fluid flow data; responsive to identification of one or more fluid flow data issues, generating synthetic fluid flow data utilizing at least a portion of the pressure data and at least a portion of the temperature data as inputs to a flow meter model; controlling a remote simulation engine of a computational framework to, using at least a portion of the data, generate simulation results as to fluid composition within the fluid production system; and determining composition and volume of the fluid products based at least in part on the simulation results.

[0006] A system can include a processor; a memory accessible to the processor; processor-executable instructions stored in the memory and executable by the processor to instruct the system to: acquire data during operation of a fluid production system generating fluid products, where the data include pressure data, temperature data, and fluid flow data; responsive to identification of one or more fluid flow data issues, generate synthetic fluid flow data utilizing at least a portion of the pressure data and at least a portion of the temperature data as inputs to a flow meter model; control a remote simulation engine of a computational framework to, using at least a portion of the data, generate simulation results as to fluid composition within the fluid production system; and determine composition and volume of the fluid products based at least in part on the simulation results.

[0007] One or more computer-readable media can include computerexecutable instructions executable by a system to instruct the system to: acquire data during operation of a fluid production system generating fluid products, where the data include pressure data, temperature data, and fluid flow data; responsive to identification of one or more fluid flow data issues, generate synthetic fluid flow datautilizing at least a portion of the pressure data and at least a portion of the temperature data as inputs to a flow meter model; control a remote simulation engine of a computational framework to, using at least a portion of the data, generate simulation results as to fluid composition within the fluid production system; and determine composition and volume of the fluid products based at least in part on the simulation results.

[0008] This summary is provided to introduce a selection of concepts that are further described below in the detailed description. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used as an aid in limiting the scope of the claimed subject matter.BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Features and advantages of the described implementations can be more readily understood by reference to the following description taken in conjunction with the accompanying drawings.

[0010] FIG. 1 illustrates an example system that includes various framework components associated with one or more geologic environments;

[0011] FIG. 2 illustrates examples of systems;

[0012] FIG. 3 illustrates an example of a system;

[0013] FIG. 4 illustrates an example of a framework and an example of a system;

[0014] FIG. 5 illustrates an example of a system;

[0015] FIG. 6 illustrates an example of a workflow;

[0016] FIG. 7 illustrates an example of a system;

[0017] FIG. 8 illustrates an example of a system;

[0018] FIG. 9 illustrates an example of a system;

[0019] FIG. 10 illustrates an example of a system state and an example of a plot;

[0020] FIG. 11 illustrates examples of workflows;

[0021] FIG. 12 illustrates examples of workflows;

[0022] FIG. 13 illustrates examples of workflows;

[0023] FIG. 14 illustrates examples of workflows;

[0024] FIG. 15 illustrates examples of workflows;

[0025] FIG. 16 illustrates examples of workflows;

[0026] FIG. 17 illustrates examples of workflows;

[0027] FIG. 18 illustrates examples of workflows;

[0028] FIG. 19 illustrates an example of a workflow;

[0029] FIG. 20 illustrates an example of a workflow;

[0030] FIG. 21 illustrates an example of a workflow;

[0031] FIG. 22 illustrates an example of a workflow;

[0032] FIG. 23 illustrates an example of a workflow;

[0033] FIG. 24 illustrates an example of a workflow;

[0034] FIG. 25 illustrates an example of a workflow;

[0035] FIG. 26 illustrates an example of a workflow;

[0036] FIG. 27 illustrates an example of a workflow;

[0037] FIG. 28 illustrates an example of a workflow;

[0038] FIG. 29 illustrates an example of a workflow;

[0039] FIG. 30 illustrates an example of a workflow;

[0040] FIG. 31 illustrates an example of a workflow;

[0041] FIG. 32 illustrates an example of a workflow;

[0042] FIG. 33 illustrates an example of a workflow;

[0043] FIG. 34 illustrates an example of a method and an example of a system; and

[0044] FIG. 35 illustrates examples of computer and network equipment.DETAILED DESCRIPTION

[0045] This description is not to be taken in a limiting sense, but rather is made merely for the purpose of describing the general principles of the implementations. The scope of the described implementations should be ascertained with reference to the issued claims.

[0046] FIG. 1 shows an example of a system 100 that includes a workspace framework 110 that can provide for instantiation of, rendering of, interactions with, etc., a graphical user interface (GUI) 120. In the example of FIG. 1, the GU1 120 can include graphical controls for computational frameworks (e.g., applications) 121 , projects 122,visualization 123, one or more other features 124, data access 125, and data storage 126.

[0047] In the example of FIG. 1 , the workspace framework 110 may be tailored to a particular geologic environment such as an example geologic environment 150. For example, the geologic environment 150 may include layers (e.g., stratification) that include a reservoir 151 and that may be intersected by a fault 153. As an example, the geologic environment 150 may be outfitted with a variety of sensors, detectors, actuators, etc. For example, equipment 152 may include communication circuitry to receive and to transmit information with respect to one or more networks 155. Such information may include information associated with downhole equipment 154, which may be equipment to acquire information, to assist with resource recovery, etc. Other equipment 156 may be located remote from a wellsite and include sensing, detecting, emitting or other circuitry. Such equipment may include storage and communication circuitry to store and to communicate data, instructions, etc. As an example, one or more satellites may be provided for purposes of communications, data acquisition, etc. For example, FIG. 1 shows a satellite 170 in communication with the network 155 that may be configured for communications, noting that the satellite 170 may additionally or alternatively include circuitry for imagery (e.g., spatial, spectral, temporal, radiometric, etc.).

[0048] FIG. 1 also shows the geologic environment 150 as optionally including equipment 157 and 158 associated with a well that includes a substantially horizontal portion that may intersect with one or more fractures 159. For example, consider a well in a shale formation that may include natural fractures, artificial fractures (e.g., hydraulic fractures) or a combination of natural and artificial fractures. As an example, a well may be drilled for a reservoir that is laterally extensive. In such an example, lateral variations in properties, stresses, etc. may exist where an assessment of such variations may assist with planning, operations, etc. to develop a laterally extensive reservoir (e.g., via fracturing, injecting, extracting, etc.). As an example, the equipment 157 and / or 158 may include components, a system, systems, etc. for fracturing, seismic sensing, analysis of seismic data, assessment of one or more fractures, etc.

[0049] In the example of FIG. 1 , the GUI 120 shows some examples of computational frameworks, including the DRILLPLAN, DRILLOPS, PETREL,TECHLOG, PETROMOD, ECLIPSE, INTERSECT, SYMMETRY, and PIPESIM frameworks, SLB, Houston, Texas).

[0050] The DRILLPLAN framework provides for digital well construction planning and includes features for automation of repetitive tasks and validation workflows, enabling improved quality drilling programs (e.g., digital drilling plans, etc.) to be produced quickly with assured coherency.

[0051] The DRILLOPS framework may execute a digital drilling plan and ensure plan adherence, while delivering goal-based automation. The DRILLOPS framework may generate activity plans automatically individual operations, whether they are monitored and / or controlled on the rig or in town. Automation may utilize data analysis and learning systems to assist and optimize tasks, such as, for example, setting ROP to drilling a stand. The DRILLOPS framework may provide for various levels of automation based on planning and / or re-planning (e.g., via the DRILLPLAN framework), feedback, etc.

[0052] The PETREL framework can be part of the DELFI cognitive E&P environment (SLB, Houston, Texas) for utilization in geosciences and geoengineering, for example, to analyze subsurface data from exploration to production of fluid from a reservoir. The PETREL framework provides components that allow for optimization of exploration and development operations. The PETREL framework includes seismic to simulation software components that can output information for use in increasing reservoir performance, for example, by improving asset team productivity. Through use of such a framework, various professionals (e.g., geophysicists, geologists, and reservoir engineers) can develop collaborative workflows and integrate operations to streamline processes (e.g., with respect to one or more geologic environments, etc.). Such a framework may be considered an application (e.g., executable using one or more devices) and may be considered a data-driven application (e.g., where data is input for purposes of modeling, simulating, etc.).

[0053] The TECHLOG framework can handle and process field and laboratory data for a variety of geologic environments (e.g., deepwater exploration, shale, etc.). The TECHLOG framework can structure wellbore data for analyses, planning, etc.

[0054] The PETROMOD framework provides petroleum systems modeling capabilities that can combine one or more of seismic, well, and geological informationto model the evolution of a sedimentary basin. The PETROMOD framework can predict if, and how, a reservoir has been charged with hydrocarbons, including the source and timing of hydrocarbon generation, migration routes, quantities, and hydrocarbon type in the subsurface or at surface conditions.

[0055] The ECLIPSE framework provides a reservoir simulator (e.g., as a computational framework) with numerical solutions for fast and accurate prediction of dynamic behavior for various types of reservoirs and development schemes.

[0056] The INTERSECT framework provides a high-resolution reservoir simulator for simulation of detailed geological features and quantification of uncertainties, for example, by creating accurate production scenarios and, with the integration of precise models of the surface facilities and field operations, the INTERSECT framework can produce reliable results, which may be continuously updated by real-time data exchanges (e.g., from one or more types of data acquisition equipment in the field that can acquire data during one or more types of field operations, etc.). The INTERSECT framework can provide completion configurations for complex wells where such configurations can be built in the field, can provide detailed chemical-enhanced-oil-recovery (EOR) formulations where such formulations can be implemented in the field, can analyze application of steam injection and other thermal EOR techniques for implementation in the field, advanced production controls in terms of reservoir coupling and flexible field management, and flexibility to script customized solutions for improved modeling and field management control. The INTERSECT framework, as with the other example frameworks, may be utilized as part of the DELFI cognitive E&P environment, for example, for rapid simulation of multiple concurrent cases. For example, a workflow may utilize one or more of the DELFI on demand reservoir simulation features.

[0057] The SYMMETRY framework provides for modeling process workflows, including integrating facilities, process units with pipelines, networks and flare, safety systems models, while ensuring consistent thermodynamics and fluid characterization across a system. The SYMMETRY framework includes components for optimizing processes in upstream, midstream and downstream sectors, maximizing profits and minimizing CAPEX. The SYMMETRY framework provides for oil pseudo-component characterization techniques. For example, a paraffin, isoparaffin, olefin, naphthene,aromatic (PIONA) based fluid characterization uses chemical family structures to enable accurate physical property estimation in one or more of blending, separation, and reactive systems to be more accurately simulated. Such an approach helps to ensure consistent thermodynamics and component tracking across a system. The SYMMETRY framework provides a simulation engine for performing various simulations of physical phenomena. Various frameworks can share compositional data, for example, consider sharing of data between the PIPESIM framework steadystate multiphase flow simulator and the SYMMETRY process framework. Compositional models can be integrated to evaluate and maintain fluid description fidelity and behavior, which can extend beyond capabilities of black-oil simulations. The SYMMETRY framework includes components that provide for assessments that align with the United Nations Sustainable Development Goals 12 and 13, that can optimize drilling CO2 footprint, and that can provide for emissions reductions. For example, the SYMMETRY framework can establish a baseline performance and evaluate different options for reducing emissions, including reduced routine flaring, alternatives to flaring, fuel gas minimization through energy management, and feedstock management (hydrogen or bio-feed blending). As to electrification, various scenarios can be modeled to, for example, select or optimize energy sources suitable for electrification of one or more processes, pieces of equipment, etc. As an example, simulations can be performed that aim to reduce energy consumption, optionally while considering energy sources (e.g., on-site from produced fluids, from solar, from wind, from geothermal, etc.). As an example, a workflow can include applying total site energy management models to support reduction in energy consumption in facilities at one or more scales, for example, from rotating equipment to various plants. The SYMMETRY framework can provide for simulations that aim to reduce fuel consumption, generate power from waste heat (e.g., energy integration), and optimizing applications of renewable power. The SYMMETRY framework provides for modeling of natural gas liquid (NGL) recovery optimization, sulfur plants, liquefied natural gas (LNG) train mixed refrigerant optimization, multisided heat exchangers, compressor train optimization, acid gas removal with amines, membrane separation, etc. Such features allow for modeling complex processes more effectively, predicting performance for proactive controls, and accelerating performance while maintainingtrust in rigorous modeling. As to separators, the SYMMETRY framework can enhance separation modeling capabilities; noting that performance of a separator can be one of the largest factors in overall operational performance of an asset. Components include steady state and dynamics engines, which allow for evaluation and understanding of impacts on an overall system. Separation process analysis can aim perform more accurate rating and troubleshooting of separation using steady state and / or dynamics simulations and gain a better understanding of how transient behaviors can impact a separation process.

[0058] The PIPESIM simulator includes solvers that may provide simulation results such as, for example, multiphase flow results (e.g., from a reservoir to a wellhead and beyond, etc.), flowline and surface facility performance, etc. The PIPESIM simulator may be integrated, for example, with the AVOCET production operations framework (SLB, Houston Texas). As an example, a reservoir or reservoirs may be simulated with respect to one or more enhanced recovery techniques (e.g., consider a thermal process such as steam-assisted gravity drainage (SAGD), etc.). As an example, the PIPESIM simulator may be an optimizer that can optimize one or more operational scenarios at least in part via simulation of physical phenomena.

[0059] The aforementioned DELFI environment provides various features for workflows as to subsurface analysis, planning, construction and production, for example, as illustrated in the workspace framework 110. Such an environment may be referred to as a process operations environment that can include a variety of frameworks (e.g., applications, etc.). As shown in FIG. 1 , outputs from the workspace framework 110 can be utilized for directing, controlling, etc., one or more processes in the geologic environment 150 and, feedback 160, can be received via one or more interfaces in one or more forms (e.g., acquired data as to operational conditions, equipment conditions, environment conditions, etc.).

[0060] As an example, a platform, such as, for example, the LUMI platform (SLB, Houston, Texas) may be utilized. The LUMI platform includes features that provide for artificial intelligence solutions as may be integrated with data management capabilities. The LUMI platform provides for flexible deployment options and an open, secure, and modular architecture, for example, to empower data-driven decisionmaking. The LUMI platform is operable with the DELFI environment and, hence, oneor more of various frameworks. While various platforms, environments, frameworks, libraries, etc., are mentioned, a framework may be operable in an agnostic manner, for example, to be compatible with one or more other platforms, environments, frameworks, libraries, technologies, etc.

[0061] In the example of FIG. 1 , the visualization features 123 may be implemented via the workspace framework 110, for example, to perform tasks as associated with one or more of subsurface regions, planning operations, constructing wells and / or surface fluid networks, and producing from a reservoir.

[0062] As an example, a visualization process can implement one or more of various features that can be suitable for one or more web applications. For example, a template may involve use of the JAVASCRIPT object notation format (JSON) and / or one or more other languages / formats. As an example, a framework may include one or more converters. For example, consider a JSON to PYTHON converter and / or a PYTHON to JSON converter. Such an approach can provide for compatibility of devices, frameworks, etc., with respect to one or more sets of instructions.

[0063] As an example, visualization features can provide for visualization of various earth models, properties, etc., in one or more dimensions. As an example, visualization features can provide for rendering of information in multiple dimensions, which may optionally include multiple resolution rendering. In such an example, information being rendered may be associated with one or more frameworks and / or one or more data stores. As an example, visualization features may include one or more control features for control of equipment, which can include, for example, field equipment that can perform one or more field operations. As an example, a workflow may utilize one or more frameworks to generate information that can be utilized to control one or more types of field equipment (e.g., drilling equipment, wireline equipment, fracturing equipment, etc.).

[0064] As to a reservoir model that may be suitable for utilization by a simulator, consider acquisition of seismic data as acquired via reflection seismology, which finds use in geophysics, for example, to estimate properties of subsurface formations. As an example, reflection seismology may provide seismic data representing waves of elastic energy (e.g., as transmitted by P-waves and S-waves, in a frequency range of approximately 1 Hz to approximately 100 Hz). Seismic data may be processed andinterpreted, for example, to understand better composition, fluid content, extent and geometry of subsurface rocks. Such interpretation results can be utilized to plan, simulate, perform, etc., one or more operations for production of fluid from a reservoir (e.g., reservoir rock, etc.).

[0065] Field acquisition equipment may be utilized to acquire seismic data, which may be in the form of traces where a trace can include values organized with respect to time and / or depth (e.g., consider 1 D, 2D, 3D or 4D seismic data). For example, consider acquisition equipment that acquires digital samples at a rate of one sample per approximately 4 ms. Given a speed of sound in a medium or media, a sample rate may be converted to an approximate distance. For example, the speed of sound in rock may be on the order of around 5 km per second. Thus, a sample time spacing of approximately 4 ms would correspond to a sample “depth” spacing of about 10 meters (e.g., assuming a path length from source to boundary and boundary to sensor). As an example, a trace may be about 4 seconds in duration; thus, for a sampling rate of one sample at about 4 ms intervals, such a trace would include about 1000 samples where latter acquired samples correspond to deeper reflection boundaries. If the 4 second trace duration of the foregoing example is divided by two (e.g., to account for reflection), for a vertically aligned source and sensor, a deepest boundary depth may be estimated to be about 10 km (e.g., assuming a speed of sound of about 5 km per second).

[0066] As an example, a model may be a simulated version of a geologic environment. As an example, a simulator may include features for simulating physical phenomena in a geologic environment based at least in part on a model or models. A simulator, such as a reservoir simulator, can simulate fluid flow in a geologic environment based at least in part on a model that can be generated via a framework that receives seismic data. A simulator can be a computerized system (e.g., a computing system) that can execute instructions using one or more processors to solve a system of equations that describe physical phenomena subject to various constraints. In such an example, the system of equations may be spatially defined (e.g., numerically discretized) according to a spatial model that that includes layers of rock, geobodies, etc., that have corresponding positions that can be based on interpretation of seismic and / or other data. A spatial model may be a cell-based modelwhere cells are defined by a grid (e.g., a mesh). A cell in a cell-based model can represent a physical area or volume in a geologic environment where the cell can be assigned physical properties (e.g., permeability, fluid properties, etc.) that may be germane to one or more physical phenomena (e.g., fluid volume, fluid flow, pressure, etc.). A reservoir simulation model can be a spatial model that may be cell-based.

[0067] A simulator can be utilized to simulate the exploitation of a real reservoir, for example, to examine different productions scenarios to find an optimal one before production or further production occurs. A reservoir simulator does not provide an exact replica of flow in and production from a reservoir at least in part because the description of the reservoir and the boundary conditions for the equations for flow in a porous rock are generally known with an amount of uncertainty. Certain types of physical phenomena occur at a spatial scale that can be relatively small compared to size of a field. A balance can be struck between model scale and computational resources that results in model cell sizes being of the order of meters; rather than a lesser size (e.g., a level of detail of pores). A modeling and simulation workflow for multiphase flow in porous media (e.g., reservoir rock, etc.) can include generalizing real micro-scale data from macro scale observations (e.g., seismic data and well data) and upscaling to a manageable scale and problem size. Uncertainties can exist in input data and solution procedure such that simulation results too are to some extent uncertain. A process known as history matching can involve comparing simulation results to actual field data acquired during production of fluid from a field. Information gleaned from history matching, can provide for adjustments to a model, data, etc., which can help to increase accuracy of simulation.

[0068] As an example, a simulator may utilize various types of constructs, which may be referred to as entities. Entities may include earth entities or geological objects such as wells, surfaces, reservoirs, etc. Entities can include virtual representations of actual physical entities that may be reconstructed for purposes of simulation. Entities may include entities based on data acquired via sensing, observation, etc. (e.g., consider entities based at least in part on seismic data and / or other information). As an example, an entity may be characterized by one or more properties (e.g., a geometrical pillar grid entity of an earth model may be characterized by a porosityproperty, etc.). Such properties may represent one or more measurements (e.g., acquired data), calculations, etc.

[0069] As an example, a simulator may utilize an object-based software framework, which may include entities based on pre-defined classes to facilitate modeling and simulation. As an example, an object class can encapsulate reusable code and associated data structures. Object classes can be used to instantiate object instances for use by a program, script, etc. For example, borehole classes may define objects for representing boreholes based on well data. A model of a basin, a reservoir, etc. may include one or more boreholes where a borehole may be, for example, for measurements, injection, production, etc. As an example, a borehole may be a wellbore of a well, which may be a completed well (e.g., for production of a resource from a reservoir, for injection of material, etc.).

[0070] While several simulators are illustrated in the example of FIG. 1 , one or more other simulators may be utilized, additionally or alternatively. For example, consider the VISAGE geomechanics simulator (SLB, Houston Texas), etc. As an example, the KINETIX framework (SLB Houston, Texas) may be utilized for reservoir-centric stimulation-to-production workflows that may integrate geology, petrophysics, completion engineering, reservoir engineering, and geomechanics to assist in optimization of completion and fracturing designs for a well, a pad, or a field, etc. From 1 D logs and simple geometric completions to full 3D mechanical and petrophysical models coupled with the INTERSECT simulator and the VISAGE geomechanics simulator, the KINETIX framework provides various options, including automated parallel processing (e.g., consider cloud platform computing, etc.).

[0071] As mentioned, a framework may be implemented within or in a manner operatively coupled to the LUMI platform, the DELFI environment, etc., which may include features for a secure, cognitive, cloud-based collaborative environment that integrates data and workflows with digital technologies, such as artificial intelligence and machine learning. As an example, such an environment can provide for operations that involve one or more frameworks.

[0072] As an example, data can include geochemical data. For example, consider data acquired using X-ray fluorescence (XRF) technology, Fourier transform infrared spectroscopy (FTIR) technology and / or wireline geochemical technology.

[0073] As an example, one or more probes may be deployed in a bore via a wireline or wirelines. As an example, a probe may emit energy and receive energy where such energy may be analyzed to help determine mineral composition of rock surrounding a bore. As an example, nuclear magnetic resonance may be implemented (e.g., via a wireline, downhole NMR probe, etc.), for example, to acquire data as to nuclear magnetic properties of elements in a formation (e.g., hydrogen, carbon, phosphorous, etc.).

[0074] As an example, lithology scanning technology may be employed to acquire and analyze data. For example, consider the LITHO SCANNER technology marketed by SLB (Houston, Texas). As an example, a LITHO SCANNER tool may be a gamma ray spectroscopy tool.

[0075] As an example, a tool may be positioned to acquire information in a portion of a borehole. Analysis of such information may reveal vugs, dissolution planes (e.g., dissolution along bedding planes), stress-related features, dip events, etc. As an example, a tool may acquire information that may help to characterize a fractured reservoir, optionally where fractures may be natural and / or artificial (e.g., hydraulic fractures). Such information may assist with completions, stimulation treatment, etc. As an example, information acquired by a tool may be analyzed using a framework such as the aforementioned TECHLOG framework.

[0076] As an example, a workflow may utilize one or more types of data for one or more processes (e.g., stratigraphic modeling, basin modeling, completion designs, drilling, production, injection, etc.). As an example, one or more tools may provide data that can be used in a workflow or workflows that may implement one or more frameworks (e.g., PETREL, TECHLOG, PETROMOD, ECLIPSE, SYMMETRY, etc.).

[0077] FIG. 2 shows an example of a geologic environment 210 that includes reservoirs 211 -1 and 211 -2, which may be faulted by faults 212-1 and 212-2, an example of a network of equipment 230, an enlarged view of a portion of the network of equipment 230, referred to as network 240, and an example of a system 250. FIG. 2 shows some examples of offshore equipment 214 for oil and gas operations related to the reservoir 211 -2 and onshore equipment 216 for oil and gas operations related to the reservoir 211 -1.

[0078] In the example of FIG. 2, the various equipment 214 and 216 can include drilling equipment, wireline equipment, production equipment, etc. For example, consider the equipment 214 as including a drilling rig that can drill into a formation to reach a reservoir target where a well can be completed for production of hydrocarbons. In such an example, one or more features of the system 100 of FIG. 1 may be utilized. For example, consider utilizing a drilling or well plan framework, a drilling execution framework, etc., to plan, execute, etc., one or more drilling operations.

[0079] In FIG. 2, the network 240 can be an example of a relatively small production system network. As shown, the network 240 forms somewhat of a tree like structure where flowlines represent branches (e.g., segments) and junctions represent nodes. As shown in FIG. 2, the network 240 provides for transportation of oil and gas fluids from well locations along flowlines interconnected at junctions with final delivery at a central processing facility.

[0080] In the example of FIG. 2, various portions of the network 240 may include conduit. For example, consider a perspective view of a geologic environment that includes two conduits which may be a conduit to Mani and a conduit to Man3 in the network 240.

[0081] As shown in FIG. 2, 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). As 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 the instructions 270 (e.g., one or more sets of instructions), for example, executable by at least one of the one or more processors. As an example, a computer may include one or more network interfaces (e.g., wired or wireless), one or more graphics cards, a display interface (e.g., wired or wireless), etc. As an example, imagery such as surface imagery (e.g., satellite, geological, geophysical, etc.) may be stored, processed, communicated, 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, information that may be stored in one or more of the storage devices 252 may include information about equipment, location of equipment, orientation of equipment, fluid characteristics, etc.

[0082] As an example, the instructions 270 can 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 a framework, for example, that can perform network modeling (see, e.g., the PIPESIM framework of the example of FIG. 1 , etc.). As an example, one or more methods, techniques, etc. may be performed using one or more sets of instructions, which may be, for example, the instructions 270 of FIG. 2.

[0083] FIG. 3 shows a schematic view of an example of a portion of a geologic environment 301 that can include various types of equipment. As shown in FIG. 3, the environment 301 can include a wellsite 302 and a fluid network 344. In the example of FIG. 3, the wellsite 302 includes a wellbore 306 extending into earth as completed and prepared for production of fluid from a reservoir 311 (e.g., one of the reservoirs 311 -1 or 311 -2).

[0084] In the example of FIG. 3, wellbore production equipment 364 extends from a wellhead 366 of the wellsite 302 and to the reservoir 311 to draw fluid to the surface. As shown, the wellsite 302 is operatively connected to the fluid network 344 via a transport line 361. As indicated by various arrows, fluid can flow from the reservoir 311 , through the wellbore 306 and onto the fluid network 344. Fluid can then flow from the fluid network 344, for example, to one or more fluid processing facilities.

[0085] In the example of FIG. 3, sensors (S) are located, for example, to monitor various parameters during operations. The sensors (S) may measure, for example, pressure, temperature, flowrate, composition, and other parameters of the reservoir, wellbore, gathering network, process facilities and / or other portions of an operation. As an example, the sensors (S) may be operatively connected to a surface unit (e.g., to instruct the sensors to acquire data, to collect data from the sensors, etc.).

[0086] In the example of FIG. 3, a surface unit can include computer facilities, such as a memory device, a controller, one or more processors, and a display unit (e.g., for managing data, visualizing results of an analysis, etc.). As an example, data may be collected in the memory device and processed by the processor(s) (e.g., for analysis, etc.). As an example, data may be collected from the sensors (S) and / or by one or more other sources. For example, data may be supplemented by historicaldata collected from other operations, user inputs, etc. As an example, analyzed data may be used to in a decision-making process.

[0087] As an example, a transceiver may be provided to allow communications between a surface unit and one or more pieces of equipment in the environment 301 . For example, a controller may be used to actuate mechanisms in the environment 301 via the transceiver, optionally based on one or more decisions of a decision-making process. In such a manner, equipment in the environment 301 may be selectively adjusted based at least in part on collected data. Such adjustments may be made, for example, automatically based on computer protocol, manually by an operator or both. As an example, one or more well plans may be adjusted (e.g., to select optimum operating conditions, to avoid problems, etc.).

[0088] To facilitate data analyses, one or more simulators may be implemented (e.g., optionally via the surface unit or other unit, system, etc.). As an example, data fed into one or more simulators may be historical data, real time data or combinations thereof. As an example, simulation through one or more simulators may be repeated or adjusted based on the data received.

[0089] In the example of FIG. 3, simulators can include a reservoir simulator 328, a wellbore simulator 330, a surface network simulator 332, a process simulator 334 and an economics simulator 336. As an example, the reservoir simulator 328 may be configured to solve for hydrocarbon flow rate through a reservoir and into one or more wellbores. As an example, the wellbore simulator 330 and surface network simulator 332 may be configured to solve for hydrocarbon flow rate through a wellbore and a surface gathering network of pipelines. As to the process simulator 334, it may be configured to model a processing plant where fluid containing hydrocarbons is separated into its constituent components (e.g., methane, ethane, propane, etc.), for example, and prepared for further distribution (e.g., transport via road, rail, pipe, etc.) and optionally sale. As an example, the economics simulator 336 may be configured to model costs associated with at least part of an operation. For example, consider MERAK framework (SLB, Houston, Texas), which may provide for economic analyses.

[0090] As an example, a system can include and / or be operatively coupled to one or more of the simulators 328, 330, 332, 334 and 336 of FIG. 3. As an example, such simulators may be associated with frameworks and / or may be considered tools(see, e.g., the system 100 of FIG. 1 , etc.). Various pieces of equipment in the example geologic environment 301 of FIG. 3 may be operatively coupled to one or more systems, one or more frameworks, etc. As an example, one or more of the sensors (S) may be operatively coupled to one or more networks (e.g., wired and / or wireless) for transmission of data, which, as explained, may include data indicative of production. As shown, a sensor (S) may be utilized for acquisition of downhole data and / or surface data, which can include data relevant to production (e.g., flow rate, temperature, pressure, composition, etc.). Such data may be utilized in a system such as, for example, the system 100 of FIG. 1 for operational decision making, etc.

[0091] While various examples of field equipment are illustrated for hydrocarbon related production operations, as explained, field equipment may be for one or more other types of operations where such field equipment can acquire data (e.g., field equipment data) that can be utilized for operation decision making and / or one or more other purposes. As to wind energy production equipment, data can include meteorological data associated with a site or sites, turbine blade data, turbine performance data, orientation control data, energy conversion data, etc. As to solar energy production equipment, data can include meteorological data associated with a site or sites, solar cell data, solar panel performance data, orientation control data, energy conversion data, etc.

[0092] As explained, field equipment data may be suitable for use with one or more frameworks, one or more workflows, etc. Uses of field equipment data can involve transfers such as, for example, inter-framework transfers where one or more types of data related issues may arise due to formatting, unit conversions, coordinate reference system (CRS) conversions, etc. Use of field equipment data can be enhanced through automated or semi-automated processes that can perform tasks such as identifying data (e.g., data types, etc.) and / or assessing quality of data.

[0093] FIG. 4 shows an example of a framework 400 and an example of a system 450. As shown, the framework 400 may provide for monitoring and / or control of fluid and fluid processing. For example, fluid may flow from a wellhead 410 of a well that is in fluid communication with a fluid reservoir. Such fluid may flow to a fluid gathering and compression pumping network 422 that may include one or more separation gas plants 424 (e.g., for liquid natural gas (LNG), etc.). In such an example,natural gas and / or natural gas liquids (NLGs) may be transported 432 and condensates and / or oil may be transported 442. As shown, natural gas and / or NLGs may be stored and / or distributed 436 while condensates and / or oil (e.g., crude oil, etc.) may be subjected to refining and / or petrochemical processing 444 followed by storage and / or distribution 436.

[0094] As to the system 450, it can include one or more wells (see, e.g., Well 1 , Well 2, Well 3, etc.) where fluid gathering provides for separation into various components, which may include water, shale condensate, and gas. As indicated, gas may be transported for gas processing while shale condensate may be subjected to various processes that may separate out components such as off gas, C3-C4, stabilized condensate where stabilized condensate may be further processed to separate out components such as additional C3-C4, diluent, naphtha and gas oil.

[0095] As to gas oil, that term may refer to one or more types of hydrocarbon products. For example, a so-called gas oils category may include more than 20 substances that includes four finished products (e.g., distillate fuels) and more than 20 refinery streams with similar carbon ranges. Gas oil streams may be produced either by atmospheric distillation or by secondary processing of materials, which may be, for example, derived from vacuum distillation of the residuum from atmospheric distillation of crude oil. Materials from such secondary processing may have higher aromatic and olefin contents than straight run gas oils. Distillate fuels may be straight run or a blend of various gas oil streams (e.g., both straight run and streams from secondary processing). In comparison to gas oil refinery streams that do not have product specifications, No. 2 diesel fuel and fuel oil, in the US, are to adhere to American Society for Testing Materials (ASTM) and the United States Environmental Protection Agency (EPA) specifications for commercialization. The boiling point specifications for these fuels essentially limit aromatics to 1 , 2 and 3-ring compounds with minimal 4-ring or higher polycyclic aromatic compounds (PAC). Physical properties, process history and product use specifications rather than composition may define gas oils streams and provide a rationale for composition of a gas oils category.

[0096] In the example of FIG. 4, the system 450 indicates shale as a source of hydrocarbons. For example, the wells may be drilled into a shale field. In shale fields a product that may be referred to as shale oil may be an unconventional oil producedfrom oil shale rock fragments by pyrolysis, hydrogenation, or thermal dissolution. Such processes convert organic matter within rock (e.g., kerogen) into synthetic oil and gas. The resulting oil may be used immediately as a fuel or upgraded to meet refinery feedstock specifications, for example, by adding hydrogen and removing impurities such as sulfur and nitrogen. Such refined products may be used for the same purposes as products derived from crude oil.

[0097] The term shale oil may also be used for crude oil produced from shales of other unconventional, very low permeability formations. However, to reduce risk of confusion of shale oil produced from oil shale with crude oil in oil-bearing shales, the term tight oil may be utilized for the latter. The International Energy Agency (IEA) recommends to use the term light tight oil and World Energy Resources 2013 report by the World Energy Council uses the term tight oil for crude oil in oil-bearing shales.

[0098] While shale is mentioned as an example, other types of basins, fields, reservoirs, etc., may be characterized using a framework such as, for example, the framework 400. For example, consider conventional systems (e.g., sands, etc.) or one or more other types of systems (e.g., naturally fractured carbonates, etc.). As an example, a reservoir system may be a water-hydrocarbon system contained within pores of a rock unit. In such an example, a reservoir system may include at the following components: a reservoir, an aquifer, and a transition zone (e.g., an interface) between the two. A reservoir may be considered to be a porous and permeable rock saturated with oil or gas in buoyancy pressure equilibrium with a free water level (e.g., zero buoyancy pressure) where the reservoir may include one or more containers and where the reservoir is located below a seal.

[0099] Various types of rock (e.g., igneous, sedimentary, metamorphic) may act as hydrocarbon reservoir rock where such rock can accommodate and drain hydrocarbons. Examples include sedimentary rocks, which may include clastic and non-clastic; noting that sedimentary rock may generally possess primary porosity. As to rocks that may exhibit secondary porosity, consider materials such as one or more of shale, silt stone, and limestone, which may act as a reservoir due to rock body fractures (e.g., creating secondary porosity and secondary permeability).

[0100] In the example of FIG. 4, for the example system 450, the framework 400 may utilize a consistent molecular representation of hydrocarbons across different fields and from fields to facilities.

[0101] As an example, the framework 400 may include one or more thermodynamic engines that may be utilized for fluid representation, which may be extensively validated against experimental data. As an example, the framework 400 may include a database that includes more than 20,000 chemicals, 80 thermodynamic property packages, and hundreds of unit operations, providing for model sophistication and precision.

[0102] As an example, the framework 400 may utilize a PIONA approach to model hydrocarbons, enabling accurate simulation of blending, separation, and / or reactive systems. The PIONA acronym is derived from the following molecular list: paraffins, isoparaffins, olefins, naphthenes, and aromatics; noting that an ordering of paraffins, isoparaffins, aromatics, naphthenes, and olefins may provide for an acronym PIANO. As an example, a PIONA approach may be a molecular approach that provides for accurate modeling of formation of hydrates, wax, and asphaltene and that provides for accurate simulation of hydrocarbon mixtures coming from different fields.

[0103] As an example, behavior of hydrate inhibitors may also be represented. Hydrates tend to be detrimental within a fluid network. Hydrates are compounds or complex ions that may be formed by the union of water with one or more other substances. Hydrates may form in pipelines and / or in gas gathering, compression and / or transmission facilities, for example, at reduced temperatures and high pressures. Once hydrates are formed, they may plug pipelines and affect production operations.

[0104] The framework 400 may provide features for one or more of model upstream, midstream, and downstream process workflows; dynamic optimization; identification and / or mitigation of HSE and operational risks; reduction of emissions, energy consumption, and / or waste; improved asset reliability and operational efficiency; management of CAPEX via conceptual design and FEED studies; improved compliance in meeting product specifications; optimization of compression and reduce risk of failure; improved facility performance; recognizing and mitigating flowassurance risks; evaluation of surface facilities to confirm viability of carbon capture and storage (CCS) opportunities; etc.

[0105] FIG. 5 shows an example of a downstream modeled system 500 as may be modeled using the framework 400. As shown on the left side, atmospheric distillation and vacuum distillation may be modeled as to various component streams (e.g., gas, light naphtha, heavy naphtha, diesel oil, atmospheric gas oil, light vacuum gas oil, vacuum residue, etc.). On the right side, various petrochemical products may be formed and a gasoline and gas oil blending pool may be formed; noting that gas processing of an atmospheric distillation stream may generate LPG and / or one or more other gas products (e.g., whether gas or liquified gas). As explained, various types of treatments, cracking, processing, etc., may be employed in going from reservoir fluid to desirable products. The number and / or types of processes may be manifold.

[0106] The framework 400 may provide a simulation workspace for process simulation for facilities and plants; a pipe workspace for modeling rigorous multiphase pipe networks (e.g., complex, looped, etc.); a flare workspace (e.g., consider relief system analysis with integrated platform supply vessel (PSV), network header, and stack design, etc.); and a field workspace (e.g., for integration of gas reservoir and multiphase gathering system with forecasting functionality, etc.).

[0107] The framework 400 may provide for production related modeling (e.g., inflow production relations, field forecasting, compositional reservoir modeling, etc.), network related modeling (e.g., gathering systems, pipelines, mechanistic models, flow assurance, geographic information system (GIS) inputs, pigging and slugging, etc.), process modeling (e.g., gas processing, oil and heavy oil processing, oil refining, petrochemical production and / or processing, LNG, utilities, gas-to-liquid, power generation (e.g., gas turbine, etc.), etc.), modeling of human and environmental safety (HSE) (e.g., flare systems, sizing, emissions, depressuring, blowdown studies, etc.), etc.

[0108] As an example, the framework 400 may provide for monitoring and / or control. As an example, the framework 400 may provide for optimization of one or more processes, types of equipment, etc. As an example, the framework 400 may provide for continuous improvement of operations in the field.

[0109] As an example, a framework may provide for acquisition of data from various sources, which may include sensors, equipment, operations, etc. As an example, a framework may be triggered to automatically execute one or more routines responsive to receipt of data, which may be or include sensor data. For example, consider data regarding physical conditions, compositions, etc. A composition may pertain to phase or phases (e.g., gas, liquid, solid, supercritical, etc.) and / or to molecular structure of components (e.g., chain length, aromatic, etc.). In various instances, as explained, particular products may be of concern, which may be expected to meet various criteria (e.g., volume, product rate, physical, chemical, regulatory, etc.). Data may be utilized to optimize processes, improve safety, and drive efficiency. Advanced analytics, machine learning, and Al algorithms may provide for improved predictive maintenance, real-time monitoring, decision support, control, etc., which may lead to cost savings and enhanced productivity. Cloud-based platforms may facilitate secure storage, seamless access, and collaboration across teams and geographies.

[0110] As an example, a framework may provide for integrated compositional tracking, for example, as fluid flows from one or more wells to one or more facilities. As explained, environmental and / or operational conditions may alter phase composition (e.g., gas, liquid, solid, etc.), cause reactions, demand more or lesser energy inputs (e.g., compression, pumping, etc.), result in more or lesser emissions (e.g., CO2, hydrocarbons, heat, waste, etc.), etc. As explained, a framework may provide for compositional tracking with respect to such conditions, which may provide for monitoring, control, etc., of processes for gains in efficiency, reductions in emissions, etc.

[0111] As an example, one or more processes may result in shrinkage, expansion, and flashes during one or more production pathways, which may provide for prompting the presence of one or more types of flow assurance issues that may pose a risk of causing one or more types of non-identified production losses. As an example, a framework (e.g., a rapid framework or control box) may provide for utilization of one or more loss management cells as may be associated with a particular portion or portions of a fluid production system. As an example, a frameworkmay provide for automatic loss management cell instantiation and operation for loss detection, loss control, etc.

[0112] As an example, a framework may help provide tangible context to isolated and unrelated operational data sources within the oil and gas industry. Such an approach may involve implementing a unified and standardized data interoperability layer (e.g., an operations data foundation, etc.), which may improve harmonization of cross-disciplinary engineering, production operations, hydrocarbon accounting, emissions, energy utilization, etc. As an example, a framework may provide for enhanced integration of workflows where, for example, a framework may provide an integrated asset approach that can enhance efficacy of daily operations.

[0113] FIG. 6 shows an example of an integrated compositional tracking workflow 600 that receives data from an interoperability data layer 610 for performing tasks such as deviation acceptance 620, operational flexibility 630, scenario consideration 640, molecular tracking 650, loss management 660, volumetric compensation 670, etc., where one or more of such tasks may provide for generation of visualizations and / or control 680.

[0114] FIG. 6 also shows portions of examples of a fluid production network 692 and 694. The example fluid production network (FPN) 692 shows volume in at 10 + / - 0.1 and out at 9.5 + / - 0.2; hence, losses exist. In the example FPN 692, losses may be tracked using various flow meters, for example, to identify a location of a loss, an associated operation, associated equipment, associated fluid behavior, etc. However, instrumenting an FPN with a large number of flow meters may be impractical for one or more reasons (e.g., cost, service, maintenance, calibration, etc.). As such, consider the FPN 694, which has fewer actual flow meters and additionally virtual flow meters (e.g., virtual flow sensors, etc.), which may rely on actual measurements from sensors such as pressure and / or temperature sensors as input. In such an approach, the FPN 694 may be more accurately monitored and / or controlled for losses using one or more VFMs. The example FPNs of FIG. 6 are quite simplistic; noting that an actual fluid production network may include many flowlines (e.g., hundreds, thousands, etc.). Hence, an ability to identify and / or locate losses may be quite challenging. As an example, a VFM may be implemented locally and / or remotely and may utilize one ormore models, which may include one or more physics-based model, one or more data- driven model, and / or one or more hybrid models (e.g., physics-based and data-driven).

[0115] As an example, a workflow such as the workflow 600 may be applied to a portion of an FPN and / or an entire FPN. As an example, a framework may provide for integrated compositional tracking with respect to at least a portion of an FPN using one or more VFMs and / or one or more other types of virtual sensors, virtual equipment representations, etc. As an example, a framework may provide for doing more with less in terms of actual instances of flow meters installed in an FPN. As an example, a framework may include features for rapid execution, which may provide for acquiring real-time data and accessing one or more models, which may be local and / or remote. In such an approach, the framework may provide for leveraging real-time data, for example, to improve monitoring, identification of losses, control to address losses, control to optimize performance, control to maintain performance, etc. An FPN may be operable continuously in a steady-state or close to a steady-state. Where losses exist, these may also be continuous; hence, incentives exist to identify and address losses in a timely manner, particularly where loss magnitude may be substantial.

[0116] As explained, products generated from an asset can depend on upstream processes such that a loss upstream may impact one or more products downstream. Where an aim is to consistently generate products of quality and quantity in an agreed upon manner (e.g., according to acceptable optimization of field operations), a fluid production system framework that can operate in an expeditious manner may help to meet that aim (e.g., consider a framework that can generate results on a daily basis). As an example, a framework may provide for revising agreeable quality and quantity of products dynamically responsive to real-world conditions (e.g., whether as to an asset, equipment, market demand, etc.) and may provide for harmonizing with field equipment via modeling, simulation, control, etc., to meet such quality and quantity. In such an example, one or more optimization processes may be executed, which may occur automatically, for example, responsive to one or more triggers (e.g., changes in conditions, etc.).

[0117] As an example, a framework may include a thermodynamic engine, which may provide for assessing composition through thermodynamics. As an example, a thermodynamic engine may include one or more features of theSYMMETRY THERMO engine (SLB, Houston, Texas), which provides for generation of predictions of phase equilibria and physical properties for a variety of mixtures. Such an engine may provide thermo-physical property computations with versatility to monitor well and / or other types of performance. Such an engine may provide for optimization of one or more operations such as, for example, optimization of natural gas compressors. Such an engine may provide for improvement of operations such as, for example, improved safety of relief valves, etc. As an example, an engine may include multiphase flash capabilities (e.g., using a robust material balance and phase stability algorithm). In such an example, the engine may compute a number of phases in a process at one or more locations and / or one or more points in time, whether under actual conditions and / or hypothetical conditions (e.g., scenario conditions). An engine may provide for output of composition, amount, and physical properties of materials in each phase (e.g., at thermodynamic equilibrium).

[0118] As an example, a framework may implement a modular approach that can facilitate decomposition of complex systems into more manageable, interchangeable parts, which may be referred to as cells. By segregating components into variant and common modules within a core platform, modular design simplifies customization of products and can also optimize strategic decision-making across disciplinary boundaries.

[0119] FIG. 7 shows an example of a system 700 that includes a rapid framework 710 that can provide for generation of a graphical user interface (GUI) 720 and / or one or more other interfaces for composition related tasks. As shown, the rapid framework 710 may be operatively coupled to the framework 400. As an example, the rapid framework 710 may provide for generation of results in lesser time than the framework 400 and / or for generation of results with lesser user input. For example, to operate the framework 400, a substantial level of experience may be required as options as to inputs, workflows, etc., may be extensive; whereas, to operate the rapid framework 710, one or more appropriate GUIs may be rendered to a display that can guide user input for rapid generation of results. In such an approach, the rapid framework 710 may rely on one or more types of models that may be alternatives to utilization of thermodynamic models (e.g., multiphase flash, etc.).

[0120] As shown, the rapid framework 710 may include various components such as, for example, a variable configuration component 712, a model execution component 714, and an operational variations component 716. As an example, the variable configuration component 712 may allow for a user to define from the GUI 720 which variables will be specified and sent to a computational engine of the framework 400, as well as variables that may be desired to be saved with respect to model execution. As an example, among variable configuration options, the variable configuration component 712 may provide for selecting from amongst different data sources, which may include data sources with data available at different frequencies. For example, consider data available on less than a daily basis, a daily basis, a weekly basis, a monthly basis, etc. As an example, the model execution component 714 may provide for execution of one or more models automatically, for example, according to a configuration set by a user and / or a machine. In such an approach, the rapid framework 710 may provide for generation of results without demanding that a user interact directly with an interface (e.g., a GUI) of the framework 400 (e.g., to data and obtain results manually, etc.). As an example, the operational variations component 716 may provide for visual display a network diagram of one or more models of the framework 400, which may be accessed and rendered automatically. In such an example, the rapid framework 710 may allow users to establish flow rules through intuitive controls. As an example, such rules may be integrated into various considerations transmitted to a computational engine of the framework 400 for processing.

[0121] As an example, a workflow may involve ingesting data from various sources through tailored extractors followed by an automated expert-assisted mapping process using a platform such as the COGNITE data fusion (CDF) platform (Cognite AS, Oslo, Norway), which may help to ensure accurate correspondence between entities and provide the appropriate context to a complex data environment, serving as a standardized data model.

[0122] As an example, a virtual data standard may act as a common language within a well and reservoir domain, enabling diverse systems to communicate and understand each other, thus driving efficiency, innovation, and strategic decisionmaking.

[0123] To streamline data consumption and facilitate production engineering workflows, the rapid framework 710, which may be referred to as a control box, may aid in integrated compositional tracking. The rapid framework 710 may synergize data management and engineering processes in a cohesive and integrated fashion. The rapid framework 710 may serve as a centralized platform that simplifies complex data interactions, enabling a more efficient and unified approach to engineering workflow management.

[0124] The configured development of the rapid framework 710 may provide for adapting solutions according to challenges and development focused on particular demands allowing interactions of users with real operating systems and evaluation of operating conditions of facilities.

[0125] The rapid framework 710 allow for the provision of solutions directly with one or more computational engines of various technologies, which may provide for optimization of response times to operational evaluations.

[0126] As to the framework 400, as explained, it may be a process simulatorbased framework. As explained, knowledge to operate and execution time may be impediments to utilization of the framework 400 as to real-time field operations, for example, to improve such operations (e.g., control, optimize, etc.). As an example, the rapid framework 710 may provide for optimization of solution execution time, in comparison to the framework 400; hence, the term “rapid”.

[0127] Various simulators may provide for automation for execution of one or more computation engines externally, with which it is not necessary to interact directly with the simulator interface. For example, the SYMMETRY framework includes tools available to users externally: for example, execution via COM Automation, SYMMETRY EXCEL Add-In, VMG Standalone Server and VMG Task Runner. Such tools allow the execution of a computation engine of a direct model in the SYMMETRY framework, however, given current challenges in oil / gas, CCS, chemical, etc., industries, an increasing demand exists for a more direct response time according to data generated, which may, for example, be generated on a daily basis.

[0128] In the context of production engineering, operations, and commercialization, the integration of the CDF data platform, the rapid framework 710 and the framework 400 (e.g., a computational engine, etc.), can provide for generationof a suite of automated workflows. Such an integrated approach may serve as a foundational benchmark, enhancing decision-making processes by leveraging data- driven insights to maximize value creation.

[0129] As an example, the rapid framework 710 may consume data from the CDF and utilizes a Component Object Model (COM) from the SYMMETRY framework to provide an overview of asset operations and to simplify decision-making processes (e.g., as to monitoring, control, etc.). Such an approach may provide for automating simulation while generating a comprehensible user interface to remove complexities of an engineering simulator and providing state of the art visualizations to manage simulation results. As an example, simulation results may be transmitted to the CDF to be stored and to preserve versions to validate previous models and create different operational scenarios.

[0130] An integrated compositional tracking framework can be a robust framework for operational optimization, which may enable one or more of: seamless ingesting of data from one or more extensive sensor networks, incorporating historical system states, integrating manual user inputs, and fostering a comprehensive and adaptable operational overview; conducting a systematic evaluation of operational conditions, ensuring processes are aligned and functioning at peak efficiency; performing conciliation adjustments and generate dynamic “what-if” scenarios, facilitating proactive management and strategic planning; and estimating equivalent hydrocarbon volume to account for variations in product quality and its impact in fiscal compensation.

[0131] As an example, a virtual data standard can define how data are structured, stored, and managed across various systems and processes, giving the appropriate context to data interpretation, ensuring consistency, accuracy, and the ability to share data effectively among different stakeholders, leveraging cross domain engineering solutions.

[0132] Benefits of implementing a contextualized and unified data interoperability layer for field operations can be substantial. For example, consider improvements to operational efficiency, as streamlined operations by integrating diverse data sources, which can lead to a reduction of redundant processes and revelations of hidden operational trends. Such an approach can lead to enhanceddecision-making with a centralized data platform, where information flows efficiently across operations, fostering collaboration and enhancing decision-making processes.

[0133] As an example, a framework such as a rapid framework may provide for integrity assessment of data input, which may provide a visual exploration of various principles of descriptive statistics. In such an example, the framework may provide for feature engineering and / or machine learning model development. For example, consider a framework that can facilitate engineering of relevant features for one or more machine learning models that may expedite model training and execution, along with improving accuracy of model-based results (e.g., robust results as to classification, prediction, etc.). As an example, a model may aim to generate output relevant to control of field equipment, for example, consider a model that operates as an anomaly detector such that a framework can be responsive to anomaly detection for purposes of control to help optimize or otherwise assure production targets, compliance, etc.

[0134] Once data are properly in context of facilities, a deviation acceptance module may provide an integrated view of operational movements and inventories in a single dashboard for facilities deviation per region, for example, as per setting of an allowance tolerance according to one or more goals. In such an example, data may be contextualized, which may facilitate modeling, whether as to data integrity, feature engineering, etc.

[0135] As to the term deviation, within the oil and gas industry, it refers to a permissible range of variance in a facility mass balance (e.g., physical mass balance). Such a concept facilitates managing discrepancies that arise due to measurement uncertainties, data inconsistencies, and / or operational variations. As explained, various factors can impact composition of fluid or fluids within a system that includes wells in fluid communication with one or more reservoirs and in fluid communication with one or more types of equipment (e.g., separators, compressors, etc.), which may aim to provide for generation of particular products that may be defined by their composition.

[0136] In the context of integrated compositional tracking, a deviation acceptance process may be characterized by one or more of the following aspects: automate cross domain iteration where operations and production accounting crossdomain interaction to visualize, correct and approve operation data volumes; product movements assessment for understanding how production volumes are stored, consumed, and delivered across a supply chain providing a mass balance and consistency, especially in custody transfers points; tolerance thresholds for establishing acceptable limits for deviations according to demands so that entities out of tolerance are automatically filtered; automated mass balance validation workflows such that, in case of inconsistency being reported, product movements and inventories may be assessed to take appropriate actions or further investigate considering both operation and production accounting perspectives where, in this stage, facility delivery volume options may be included such as, for example, utilization of a virtual flow meter (VFM), where operating volume and manual entry may occur to evaluate mass balance before data are passed to a subsequent; and approve data, for example, to ensure movements and inventories are within accepted levels of precision and reliability.

[0137] The acceptance of a deviation process (see, e.g., the block 620 of FIG. 6) tends to involve a balancing act between demands for precise data for production accounting and operational purposes (e.g., consider demands as to accuracy, timeliness, etc.). In various instances, control action may acceptably mitigate an issue if taken quickly, particularly where dynamics of field equipment and field operations may be uncertain or pose possibilities of conditions warranting shutdowns or other changes in operational state. For example, a complex system may demand a certain amount of time to effectuate a change in state, which may be from one steady-state to another steady-state, from a transient state to another transient state, a transient state to a steady-state, or a steady-state to a transient state. Changes in state may be accompanied by risks, which may be risks to people, equipment, an environment, product, product losses, etc. In various instances, steady-state operation may be a goal where, for example, a framework may provide for determining whether to move from one steady-state to another (e.g., as to operational criteria, production criteria, etc.). As an example, implementation of a deviation process can help to ensure robustness and reliability of integrated compositional tracking solution, providing added value such as: enhanced collaborative processes and interaction among business units for more efficient operations; more intuitive-single visualization spotsfor assessing facilities deviation; and assigning customized deviation tolerance according to desired goals.

[0138] In terms of operational flexibility (see, e.g., the block 630 of FIG. 6), a framework may provide for improvements in the ability of an organization to adapt its operations to accommodate changes in production levels, market demands, and / or one or more other external factors. Such functionality may also allow for reflecting on planned and unplanned operational events, to consider operational fluctuations without compromising the integrity and reliability common in production allocation methodologies. As an example, operational flexibility can allow for a degree of flexibility in operations to accommodate natural fluctuations without compromising integrity of an allocation process.

[0139] In integrated compositional tracking, operational changes may apply through an intuitive and guided-user-friendly interface experience where contingency projections, infrastructure arrangement updating and emerging operational requirements can be quickly considered as to whether or not they may have an impact on a thermodynamic engineering model, for example, considering appropriate operational supervision approval. As an example, a framework may provide for automated operational changes (e.g., control of field equipment, etc.), which may be performed with or without human oversight or a human-in-the-loop (HITL).

[0140] Operational flexibility can be beneficial for one or more reasons, such as, for example, one or more of: market responsiveness as operational flexibility allows entities to swiftly adjust to market fluctuations, ensuring they can respond to changes in oil prices or demand; resource optimization, which may enable efficient utilization of resources, allowing for scaling operations to match production demands without incurring substantial delays or costs; risk mitigation where flexibility helps manage risks associated with unexpected events, ensuring that operations can continue smoothly despite unforeseen challenges; competitive advantage where entities that can quickly adapt to changing market conditions are better positioned to seize new opportunities and maintain a competitive edge; sustainability commitments, for example, by adjusting production practices to meet environmental standards and societal expectations, operational flexibility contributes to the industry’s sustainability efforts; and best measurement system conditions, for example, by selecting the mostapplicable meter points according to an operations hierarchy. In various instances, emissions and / or energy consumption may be taken into account. For example, consider limits on greenhouse gas (GHG) emission, leakage of fluid to an environment, selection of energy source (e.g., grid, on-site gas turbine, solar, wind, etc.). As an example, a framework may provide for assessing energy balances and mass balances, for example, where sources of energy to power field equipment may be taken into account.

[0141] As an example, a workflow may involve assessing volumetric variations and updates in a facility’s operations philosophy, followed by activating a molecular composition analysis. For example, consider the molecular tracking block 650 of FIG. 6. In such an example, molecular tracking in the context of hydrocarbon allocation can refer to the precise monitoring and identification of different hydrocarbon molecules throughout an oil and / or gas supply chain. Such an approach helps to ensure accurate allocation of hydrocarbons from their source to the final point of sale or utilization. While hydrocarbons are mentioned, as explained, a framework may be applied additionally or alternative to one or more of a carbon focused system, which may involve carbon dioxide, a hydrogen focused system (e.g., for hydrogen production and / or storage), etc.

[0142] As explained, a thermodynamic engine may be implemented to process, identify and quantify molecular compositions of hydrocarbon fluids and combine such molecular data with production metrics to allocate hydrocarbons accurately across various stages of an oil and / or gas supply chain.

[0143] Molecular tracking may consider molecular characteristics of hydrocarbons to distribute them in a manner that reflects their origin and quality, ensuring that each stakeholder receives a proper proportion of hydrocarbons, reflecting real contribution and ownership.

[0144] As an example, once a production facility deviation has been accepted and operational change has been updated according to a last operating philosophy, a process of molecular tracking may be executed automatically considering such adjustments, proceeding with the appropriate intervention of operations and production accountings roles to validate the volumetric official closure that may bestsuit both domains. Such a level of precision can facilitate accounting, regulatory compliance, and optimizing a value chain in the oil and gas industry.

[0145] As explained, molecular tracking can enhance precision and efficiency of engineering practices, for example, by providing a deeper understanding of hydrocarbon resources and how best to manage them throughout their lifecycle. A framework may provide for molecular tracking to drive innovation and optimization in various aspects of exploration, production, and distribution. As an example, molecular tracking can generate output that includes compositional distributions from one or more exporting nodes to upstream contributors and, for example, reconciled volumetric data across a hierarchy. As explained, molecular tracking may be applied to one or more other types of molecules, which may include hydrogen and which may include carbon, either of which may not include both hydrogen (e.g., hydrogen gas) and carbon (e.g., carbon dioxide).

[0146] As an example, a workflow may involve evaluating different scenarios (see, e.g., the scenario(s) block 640 of FIG. 6), which may be implemented using a “what if?” (or what-if) functionality that provides an ability to set up changes in operational conditions such as, for example, one or more of pressures, temperatures, volumetric flows, choke openings, etc., to optimize decision-making, control, etc., through what-if-driven insights generation.

[0147] As an example, scenario testing may provide for navigating complexities of industrial operations. Such a testing process may commence with a selection of facilities, guided by a systematic hierarchy that mirrors a value chain. Such a structured approach may help to ensure that each facility is evaluated within the context of its contribution to an overall process flow and strategic objectives.

[0148] Once facilities are identified, an analysis may progress along a predetermined roadmap of scenarios, each tailored to simulate potential operational disruptions and their ripple effects across various domains. Such a roadmap can be a sequence of tests within a framework that provides for encompassing multiple perspectives, including operations, engineering, production accounting, and commercialization.

[0149] As an example, a framework such as, for example, a rapid framework, may provide for generation of insights that are deep and broad, providing a panoramicview of potential outcomes while drilling down into specifics of each scenario. Such an approach can equips decision-makers (e.g., whether human and / or machine) with foresight and agility to navigate ever-evolving challenges of an industrial landscape.

[0150] As an example, a workflow that includes insights generation may provide for one or more of: quickly identifying reasons for underperformance; sustained production enhancements and maximized asset performance; synergized alignment with operation teams; reduce commercial deviations in contrast to production plans; volumetric fluid distribution studies; chokes and pipeline optimization; development of operating procedures; evaluation of commercial plans deviation; inventory accounting; operational philosophy alignments; improvements to safety and integrity analysis; assessments of products specifications with operational alignment; appraisal of refinery internal consumption schedules; look-ahead operational scenarios; determinations as to optimum operational envelopes; etc.

[0151] As an example, integrated compositional tracking can provide for automated loss management assistance (see, e.g., the block 660 of FIG. 6). A loss management methodology in the production allocation perspective of the oil and gas industry may involve a systematic approach to identifying, quantifying, and mitigating losses throughout a production process. Such a methodology can help ensure that reported production volumes are as accurate as possible and that discrepancies are accounted for and minimized.

[0152] As to a loss management solution leveraging an integrated compositional balance consider, for example, utilization of a review meter system management index (MSMI), which may be obtained through a comprehensive audit of hydrocarbon quantity and quality measurement systems at each of a number of battery limits in a supply chain to reconcile differences that arise due to discrepancies in the measurement systems. Such an index may be a multifactorial indicator that integrates aspects related to management, compliance with standards, competence of the personnel responsible for measurement, static and dynamic measurement aspects, laboratory performance, preventive maintenance schedules, monitoring, and quality control of volumetric data. Such an index helps to implement more realistic and precise techniques for continuous monitoring of measurement systems, which may have associated hydrocarbon accounting and / or operation domains.

[0153] As to a loss management solution leveraging an integrated compositional balance consider, for example, an automated deviation identification per meter metric (e.g., a discrepancy metric). Such a metric may involve utilizing one or more analytical tools to identify patterns and / or anomalies in production data that may indicate losses using an MSMI Index, for example, to evaluate overall efficiency of various meters and accurately quantifying losses using validated models. In such an example, one or more machine learning models may be utilized.

[0154] As to a loss management solution leveraging an integrated compositional balance consider, for example, an automated loss distribution process that may adhere to one or more rules. For example, consider rules such as “if both measurement systems have a meter with an MSMI > 90%, unit with lowest MSMI owns the total loss”; “if both measurement systems have a meter with an MSMI <90%, the loss distribution is handled proportional to each by weighting the MSMI, computing a reconciled volume in the battery limits”; and “if there is not a battery limit or custody transfer, each of the units owns the loss”.

[0155] As to a loss management solution leveraging an integrated compositional balance consider, for example, conciliation pool movement. For example, when there is a battery limit or custody transfer with an MSMI < 90% the reconciled volume creates production movements from, or to, a virtual source called a “conciliation pool” which maintains a limit with a zero volumetric balance. The concept of zero volumetric balance in production allocation is a principle that aims to ensure that the measured and allocated volumes of hydrocarbons are in complete agreement, with no discrepancies. This principle may help to provide for more accurate accounting and other reporting.

[0156] As to a loss management solution leveraging an integrated compositional balance consider, for example, loss classification. Classification of losses may be performed as an aspect of production allocation, which may provide a structured approach to identifying, quantifying, and addressing diverse types of losses. Such an approach may help to ensure that production volumes are reported accurately, and that aspects of operational performance of oil and gas assets are managed effectively. Principles of loss classification may be designed to categorize and manage diverse types of losses that can occur during production processes suchas, for example, one or more of thermodynamic losses, operational losses, losses associated to meter factors and / or calibration failures, etc.

[0157] As an example, a loss management approach may be applied using integrated compositional tracking for one or more purposes. For example, consider one or more of: assessing an automated meter system audit (e.g., as to meter performance, quality, etc.); planning of mitigation strategies that may include developing and implementing strategies to reduce losses, which may include optimizing equipment performance, enhancing process controls, and improving maintenance practices; applying more realistic operational loss identification and classification; obtaining reconciled production volume by applying agreements between entities; and supervising regulatory compliance, for example, by helping to ensure that loss management practices comply with industry regulations and standards, which may dictate acceptable loss thresholds and reporting requirements.

[0158] As an example, by employing robust loss management techniques, oil and gas entities may improve their operational efficiency, reduce risks, and enhance their overall output. As explained, loss management may be an aspect of a molecular tracking workflow that supports integrity and reliability of reporting and / or other frameworks.

[0159] As explained, a framework may provide for implementing one or more volumetric compensation techniques (see, e.g., the block 670 of FIG. 6). Volumetric compensation may be part of a workflow involving integrated compositional tracking. As an example, volumetric compensation may provide for adjusting measured volumes of hydrocarbons to account for variations in product quality. Such a process may help to ensure that the allocation of hydrocarbons accurately reflects their value and not just their volume.

[0160] The quality of hydrocarbon products may be determined by various parameters such as, for example, one or more of American Petroleum Institute (API) gravity, sulfur content, and basic sediment and water (BSW). Such factors may affect market value and / or processing requirements of products. As an example, volumetric compensation may involves adjusting volumetric measurements to reflect the quality differences. For example, higher quality oil with a higher API gravity may be allocated a greater value than heavier, lower quality oil such that a workflow involving integratedcompositional tracking may apply these adjustments, helping to ensuring that each stakeholder receives a fair share of a total value, not just the volume, of the produced hydrocarbons. As explained, processing demands and / or tradeoffs may depend on volumetric compensation. For examples, one or more BSW metrics may demand processing to remove sediment, water, etc.

[0161] Volumetric compensation can impact operations of an asset, which may impact responsibilities of entities as to the asset and / or one or more other assets, projects, etc.

[0162] Volumetric compensation can be applied to production allocation in a manner that aligns measured physical volumes with energy demands, which may have associated concerns (e.g., transport, emissions, etc.). Volumetric compensation may help to provide for a more equitable and accurate distribution of hydrocarbons based on their intrinsic quality. Such an approach can depend on a deep understanding of both physical and chemical properties of hydrocarbons and demand for energy (e.g., increasing, decreasing, weather-driven, emissions concerns, etc.).

[0163] As to hydrocarbon accounting, volumetric compensation may aim to improve one or more of: validation of production forecasts against plans; evaluation of feasibility of commercial scenarios; operational planning according to commercialization agreements; volumetric and fiscal compensation at a unit level; dynamic commercial products equivalences based quality; accurate refining diet programming; assertive exporting products planning; penalties distribution; cost and tariff scenarios; product blending network assessment; fiscal inventory; assess commercial insights; compliance analysis of sale fluid specification; etc.

[0164] As explained, the SYMMETRY framework provides for tools available to users externally that allow the execution of a computation engine of a direct model in the SYMMETRY framework. However, data can be available on a relatively frequent basis such that there is an incentive to leverage such data in a timely manner, which may be challenging to perform using tools to externally access an instance of the SYMMETRY framework. As explained, a rapid framework may provide for leveraging data that may be available on a daily basis or another relatively frequent basis. As an example, a rapid framework may provide for generating results in a direct response time according to data generated on a daily basis. Given an ability to generatemeaningful results using fresh data, a system may be more readily monitored, controlled, optimized, etc.

[0165] As an example, a rapid framework can allow for generation of results based on execution of programmed tasks that may be adapted to challenges and data management paradigms (e.g., data availability, etc.). Such a framework may provide for development of programming flows and solutions for interactions of one or more external data sources. As explained, a framework may operate as a control box, which may provide for data management, for example, to acquire data that may be available from one or more sources, which may include real-time and / or historic sources. As an example, a control box may directly execute a computation engine of a framework (e.g., consider a thermodynamic engine, etc.) to generate results for a system where the control box may extract variables desired for generation of results that may adapted to operational reports, production balance systems, control, etc.

[0166] A workflow may involve configured development of a control box as a tool that allows to adapt solutions according to challenges and development as may be focused by a user. As explained, scenarios that may be identified as “what if?” scenarios may be are configured, allowing interactions between a control box and one or more real operating systems of a system of interest for evaluation of operating conditions of various facilities. A control box approach may allow for the provision of solutions directly with one or more computation engines of various technologies, providing optimization of response time to operational evaluations, which may be tailored by an entity.

[0167] As an example, a control box may be a rapid framework (e.g., processorbased) that operates as a comprehensive and accessible solution for running simulator models (e.g., SYMMETRY framework models, etc.). As explained, a control box approach may provide for generating a GUI that can be utilized by users who are not experts in process simulation development. As an example, a control box may be implemented at least in part as a desktop type of application that may be simplified in comparison to a full framework for process simulation. As explained, a control box approach may provide for speeding up execution of complex process models with reduced risks of compromising quality or accuracy of results. As explained, time can be a factor where, for example, to implement a full framework for process simulationmay take a number of days; whereas, a control box approach may take less than a day such that, for example, results may be available on a daily basis.

[0168] As an example, a control box may operate as a bridge between users and complexity of a full framework simulator (e.g., consider the thermodynamic simulator of the SYMMETRY framework). Such an approach may be achieved at least in part through particular functionalities such as an intuitive and user-friendly interface, allowing users to define and configure variables and make operational changes (e.g., flow derivation, equipment operational conditions, etc.) with minimal effort and without demand for specialized technical knowledge.

[0169] As explained with respect to the example of FIG. 7, the rapid framework 710 can include components 712, 714, and 716, which may provide functionalities to help ensure that users can make the most of the simulation results, facilitating updating of input data, its execution, analysis, presentation of results, control of field operations, etc.

[0170] As an example, the rapid framework 710 may utilize a flexible architecture that allows for configuration of multiple models and centralized management of variables and results, which may be backed by a robust relational database that guarantees integrity and accessibility of the information, allowing efficient storage of configuration and results of each of a number of computational models. As an example, collected data may be readily exploited through detailed reports and interactive dashboards.

[0171] As an example, a control box may be operatively coupled to one or more computational engines (e.g., simulation engines, etc.) via a suitable mechanism. For example, consider using the “VMGMasterlnterfaceNet” library (Virtual Materials Group), which helps to ensure interoperability between platforms and efficient data transmission. The VMGSim COM Automation engine provides a programming interface to interact directly with a process simulator without resorting to use of the SYMMETRY framework graphical user interface. VMGSim COM can be used from a COM compliant application (e.g., EXCEL, VISUAL BASIC, VISUAL C++, etc.). The COM interface to SYMMETRY may be used to interact directly with a simulator from a programming language instead of using a SYMMETRY framework GUI.

[0172] As an example, a rapid framework (e.g., a control box) may be operatively coupled with a framework to call for performance of computations, effectively embedding a computational engine, etc. The file VMGMasterlnterfaceNet.dll may be registered before using the VMG COM Automation engine from the SYMMETRY framework, which may be automatically installed and registered during installation of the SYMMETRY framework.

[0173] As an example, a computational engine (e.g., a simulation engine) may have an object-oriented design with a pre-defined hierarchy. In such an example, objects may interact with each other and be accessed through COM interfaces. A top object in a hierarchy may be referred to as the main simulation engine, which may be an object that oversees creating, storing and recalling simulation cases. As an example, an engine may interact directly with a number of different objects such as a thermodynamics manager, a root flowsheet, a units system, a case study manager, a historian, etc.

[0174] As an example, a flowsheet may include various unit operations that are connected through material ports. In such an example, the unit operations may include variables of different types, for example signal ports, energy ports and profiles. As an example, a thermodynamics manager may include a list of thermodynamic cases which can be associated with a flowsheet and / or unit operations. Such an approach can define equilibrium computations to be carried out by different unit operations.

[0175] As an example, a system, a framework, a control box, etc., may utilize one or more of multiple languages. For example, consider .NET and PYTHON. As VMGSim is .NET based, a PYTHON package such as Python.NET may be utilized to provide nearly seamless integration with the .NET Common Language Runtime (CLR) and provide an application scripting tool for .NET developers. As an example, a system may provide for execution of PYTHON code to interact with the .NET CLR, and may also be used to embed PYTHON code into a .NET application.

[0176] As an example, a rapid framework or control box may provide for execution of process simulations and an automated solutions for users for informed decision-making in an increasingly complex and dynamic operational environment.

[0177] FIG. 8 shows an example of a system 800 that includes a framework 400 (illustrated via a GUI), a rapid framework 710 (illustrated via a GUI), and a GUI 720.As shown, the GUI 720 may be utilized as part of the rapid framework 710 to drive solutions using features of the framework 400. In the example of FIG. 8, the framework 400 may provide for generation of a digital twin of a physical system where a digital twin can be a digital representation of equipment for modeling behavior of the physical system. As an example, a digital twin may be a digital representation that may be based on one or more physics-based model, one or more machine learning models, one or more hybrid models, etc. As an example, a digital twin may include one or more proxy models for physical phenomena that may otherwise be modeled using complex and resource intensive models (e.g., numerical, physics-based models, etc.).

[0178] Accurate production monitoring tends to be a challenging task. Metering flows can depend on type of sensors, which may translate to equipment and / or maintenance costs. While high fidelity meters may be available, they may be relatively prohibitive as to implementation, particularly in remote locations where servicing and / or operational conditions may present challenges (e.g., consider remote locations distant from infrastructure, roads, etc.). Systems are often designed and built according to technical and practical tradeoffs, which may be between accuracy, efficiency, and costs. With the expansion of loT and cloud computing various systems may be connected to a network, but there still may be offline meters and demands to verify in site flows and mixtures properties. In various instances, satellite communication may be available, however, it may be limited in time, bandwidth, cost, etc., which may demand appropriate scheduling, data compression, etc.

[0179] As an example, one or more types of virtual sensors may be implemented. For example, consider a virtual flow meter (VFM) that is a digital representation of flow meter, which may be, for example, a multi-phase flow meter (MPFM). An MPFM may be a relatively costly piece of equipment, which may utilize radioactive material and / or other complex technologies.

[0180] As an example, a rapid framework or control box may provide for access to one or more virtual sensors (e.g., digital twin models, etc.). Such an approach may provide for metering of flows and mixtures properties to be systematically monitored and complemented using such models. As an example, a model may complement a simulation package to emulate a thermodynamic state of a system. Such systemstend to be extremely complex and in most cases simplifications and / or approximations may be utilized to efficiently track flows in digital twin models.

[0181] Although, in principle, accurate measurements in flows and mixtures may be expected to provide certainty in production volumes, losses may also be expected in a system. Some of these losses may be identified and traceable while others may be difficult or impractical to tract. Conciliation processes of input volumes (e.g., from the well sites) and output volumes (e.g., at sell / export points) tend to rely on meters, losses, and agreements (e.g., as to limits, offsets, etc.).

[0182] In some cases, meters data may be missing (e.g., meter offline / damaged), degraded (e.g., sensor not calibrated) or non-existing as to measurements at specific points in a system network. In such cases, operators may resort to one or more approaches to complement a data point or data points. For example, consider a process that may involve one or more of averaging previous and next measurements in a line, implementing a VFM, performing a detailed thermodynamic simulation of a system state, performing data-driven machine learning regression, implementing a hybrid VFM (e.g., physics and data-driven machine learning regression), etc.

[0183] As an example, a hybrid VFM may be implemented that utilizes a comprehensive thermodynamic simulation, which may be driven, for example, by a framework such as the SYMMETRY framework. To train a robust machine learning model (ML model), data demands may be extensive. As an example, a workflow may include generating synthetic data for utilization in training of an ML model. For example, consider generation of over 40,000 scenarios per field, combining temperature, pressure, water flow, and oil flow state parameters with extensive ranges in a randomized grid. In such an example, consider created a standardized preprocessing pipeline to speed up a hybrid VFM response. In such an example, the pipeline may encode a meter name and scale a system properties state. In such an example, the preprocessing can generate output suitable for utilization by a linear regression model.

[0184] As an example, a virtual approach may utilize simulation and real data. For example, a hybrid VFM may utilize simulation results and available and validated real data from one or more real meters in one or more locations within a fluidproduction system (e.g., coupled to pipelines, etc.). As an example, a hybrid VFM may provide for implementation of a data-driven (e.g., learning from real meters, etc.) approach with data generated from a physics-guided framework engine (e.g., consider a SYMMETRY framework engine) approach that may be enriched via simulations. As an example, a framework such as a rapid framework may leverage historical data, real-time data, simulated data (e.g., synthetic data), etc. As an example, a method may include train utilizing real data (e.g., from physical meters) and synthetic data from physics-guided simulations. As an example, simulations may be utilized to increase amount of data, which may provide for extending ranges (e.g., operational, environmental, etc.), scenarios (e.g., issues, etc.), etc., which may be relevant to fluid production system operations, equipment reliability, etc. As an example, simulations may provide for filling in and / or extending limitations in real (e.g., as available from historical data from meters, etc.).

[0185] FIG. 9 shows an example of a system 900 that includes features for preprocessing and regression. As shown, ordinal encoding and / or m in-max scaling may be implemented. As to regression, consider use of one or more of a lasso technique, an XGB regressor technique, a transformed target regressor technique, etc.

[0186] As shown, a column transformer technique may be utilized. Such a technique may apply transformers to columns of an array or pandas DataFrame (e.g., multi-dimensional data structure such as two-dimensional array, or a table with rows and columns). Such an estimator may allow different columns or column subsets of input to be transformed separately where features generated by each transformer may be concatenated to form a single feature space. Such an approach may be useful for heterogeneous or columnar data, for example, to combine several feature extraction mechanisms or transformations into a single transformer.

[0187] A lasso technique may utilize a linear model trained with L1 prior as a regularizer (e.g., operating as a “lasso”). An XGBoost technique may implement an optimized distributed gradient boosting library for machine learning techniques under a gradient boosting framework. The XGBoost approach may provide for implementation of a parallel tree boosting (e.g., GBDT, GBM). Decision trees may be used for classification to predict a category, or regression to predict a numeric value.As to a transformed target regressor, it may be a meta-estimator to regress on a transformed target. Such an approach may be utilized for applying a non-linear transformation to a target y in a regression problem.

[0188] In various instances, a regression problem may be recast as a classification problem or a classification problem may be recast as a regression problem. As to regression and classification, consider a combined ML model for regression (prediction) and classification that may be for determining the age of an abalone from physical details, where predicting the number of rings of the abalone is a proxy for the age of the abalone (e.g., age can be predicted as both a numerical value (in years) or a class label (ordinal year as a class)). While the foregoing example pertains to abalone, analogous scenarios may exist within the context of field operations involving fluids.

[0189] As an example, one or more types of ML models may be utilized. For example, in the context of serialized networks, particularly those involved in fluid dynamics within pipeline systems, one or more deep learning models may be utilized. A deep learning model may provide for capturing the sequential nature and interdependencies of measurements along a pipeline or pipelines. As an example, the Long Short-Term Memory (LSTM) and / or other Recurrent Neural Network (RNN) networks may be implemented to recognize patterns in sequences of data and to capture temporal dependencies and relationships between different measurement points. For example, if meterl records the flow of crude oil, and further downstream meter2 also takes a measurement, there is a consequential dependency of the readings of meter2 on meterl , as may be due to continuous flow and potential changes in fluid properties as it travels through a pipeline.

[0190] An RNN type of architecture, with its feedback connections, can be capable of processing single data points and entire sequences of data. Such abilities may an RNN a suitable candidate for modeling flow dynamics where, in the foregoing example, the status of meter2 is a function of current flow and also of historical readings from meterl . Such a model may be trained to predict anomalies, optimize flow rates, anticipate maintenance, etc.

[0191] As an example, one or more Generative Adversarial Networks (GANs) and / or Convolutional Neural Networks (CNNs) may be implemented. GANscan include a dual-network competitive architecture that may be utilized to generate synthetic data for training and / or to model distribution of flow measurements for improved anomaly detection. As an example, one or more CNNs may be implemented in scenarios where spatial patterns across a network of sensors may be relevant, for example, consider detection of leaks or blockages where spatial configuration of a pipeline plays a role.

[0192] As explained, one or more deep learning approaches (e.g., LSTM, RNN, GAN, CNN, etc.) may be implemented to offer robust analyzing and predicting of complex interrelations within a fluid production system that may include serialized pipeline networks. Such models may provide a deeper understanding of flow dynamics and also help to enhance operational efficiency and safety of a fluid production system. As an example, a deep learning approach may provide for generation of results for multiple phases. For example, consider generation of vector output as to multiple phases rather than scalar output. In such an example, results may provide for multiphase characterizations as to composition, volume, etc., at one or more points in a fluid production system.

[0193] As an example, a library such as the scikit-learn library. The scikit-learn library utilizes the term “pipeline”, which differs from that of a physical pipeline for fluid flow. In various instances, a framework may rely on building a composite estimator where transformers may be combined with one or more other transformers and / or with classifiers or regressors. A pipeline requires all steps except the last to be a transformer where, for example, the last step may be a transformer, a classifier, a regressor, a clustering estimator, etc. A pipeline exposes methods provided by a last estimator: if the last step provides a transform method, then the pipeline would have a transform method and behave like a transformer. If the last step provides a predict method, then the pipeline would expose that method, and given a data X, use all steps except the last to transform the data, and then give that transformed data to the predict method of the last step of the pipeline. As an example, the class Pipeline may be used in combination with ColumnTransformer or FeatureUnion which concatenate the output of transformers into a composite feature space. As explained, TransformedTargetRegressor deals with transforming a target (e.g., consider a logtransform y).

[0194] As an example, a function transformer may be implemented. For example, consider the scikit-learn library FunctionTransformer, which forwards its X (and optionally y) arguments to a user-defined function or function object and returns the result of this function. Such an approach may be useful for stateless transformations such as taking the log of frequencies, performing custom scaling, etc.

[0195] As shown in the example of FIG. 9, a converter or transformer may be utilized for numpy and cupy (e.g., Num.Py to Cu.Py). CuPy is a NumPy / SciPy- compatible array library for GPU-accelerated computing with PYTHON (Py).

[0196] FIG. 10 shows an example of a system state 1010 in terms of inputs and an objective and an example plot 1020 of training and test results. As shown, the system state 1010 may include inputs (e.g., parameter inputs) such as meter name, temperature and pressure while an objective is for flow out (e.g., in terms of volume or volumetric rate).

[0197] The plot 1020 shows how predicted volume flow compares to real volume flow for training and test data for a hybrid VFM regression model; noting that a straight line at a 45-degree angle indicates perfect correspondence.

[0198] To generate thermodynamic states for different ranges, as an example, a PYTHON class may be created utilizing a win32com library to control a SYMMETRY framework engine in an analogous way as with a control box (e.g., rapid framework); however, using entirely PYTHON code. Such an approach may provide for manipulation and control of thousands of scenarios for simulation and allow for implementation of a multithreading scheme to expedite computations, for example, by managing multiple SYMMETRY framework engines at the same time (e.g., at least in part in parallel). In such an example, once simulations are performed, results may be preprocessed as a tabular scheme to prepare for machine learning model consumption.

[0199] As an example, a hybrid VFM may be called by a control box through an application programming interface (API), a software development kit (SDK) component for PYTHON, or in .NET in automatic way when a data point may be missing (e.g., or otherwise deemed unreliable, etc.) or may be toggled by a user or a machine, for example, to override a current flow and / or one or more state parameters in one or more desired points in a system network.

[0200] As an example, a VFM may be hosted in one or more manners. For example, consider a local manner (e.g., gateway, etc.), a cloud service, a server system, etc. As an example, a VFM may be implemented using a suitable execution environment (e.g., consider a PYTHON environment, etc.). As an example, a VFM may be hosted in a CDF (e.g., as a COGNITE function, etc.) and / or may be hosted as an API type of service (e.g., in DATAIKU, etc.). As an example, a VFM may be embedded within a rapid framework or control box and / or embedded in a gateway or other local computing equipment; noting that one or more remote approaches may be utilized (e.g., remote cloud service, etc.).

[0201] An article by Maheshwari et al., 2022, “Production optimization and reservoir monitoring through virtual flow metering”, in Abu Dhabi International Petroleum Exhibition and Conference, Society of Petroleum Engineers, SPE-211233- MS, is incorporated by reference herein in its entirety.

[0202] FIG. 11 shows examples of workflows 1100 that include various sections such as a data source section 1110, a data review and extraction section 1120, a data model section 1130, a facilities deviation acceptance section 1140, an operational flexibility section 1150, a molecular tracking section 1160, a scenarios section 1170, a loss management section 1180, and a volumetric compensation section 1190, together with a termination section 1195.

[0203] In FIG. 11 , the upper portion pertains to a workflow implemented using a rapid framework (e.g., a control box) and the lower portion pertains to a workflow implemented using a full-feature framework, specifically the SYMMETRY framework.

[0204] FIG. 12 shows the data source section 1110, the data review and extraction section 1120, the data model section 1130 for the workflows where the data source section 1110 includes various types of data sources such as, for example, PDMS, lab, historian, regulatory, real-time (e.g., streaming, etc.), daily reports (e.g., spreadsheets), unstructured (e.g., equipment, documents, etc.), standalone production forecast, maintenance (e.g., history, schedules, etc.), etc. In the data review and extraction section 1120, the upper workflow (e.g., the control box workflow or CBW) includes validation of operations data and extraction of data; whereas, such tasks are not present in the lower workflow (e.g., the full-feature framework workflow or FFFW). Similarly, the data model section 1130 performs tasks for the CBW and notthe FFFW. As shown, for the CBW, the data model section 1130 includes evaluation of data completeness and contextualization of data, for example, according to operations hierarchy, etc., where a virtual data standard may be created. For example, as mentioned, flow data may be unavailable and / or lacking in quality. In such an example, one or more virtual flow meters (VFMs) may be implemented to generate flow data, which may be volume data (e.g., as relevant to compositional tracking, etc.).

[0205] FIG. 13 shows the facilities deviation acceptance section 1140 of the CBW and FFFW. As shown, for the FFFW, a manual review of data sources is performed one at a time by an operator according to fluid type where operational reports are generated manually per facility (e.g., consider spreadsheets for information, audits, etc.). Additionally, for the FFFW, an internal validation process is performed between asset units, followed by non-standardized and systematic deviation recognition, which involve time consuming tasks.

[0206] In contrast to the FFFW, the CBW may involve assessment of deviation at a region level where automated decision making may be performed as to whether information adheres to operation logic as to volume flows (e.g., volumetric flows). Depending on such an assessment, the CBW may return to the operations data validation task (see, e.g., the section 1120) or, for example, may proceed to deciding whether a deviation is within a defined tolerance. As shown, if the deviation is not within the defined tolerance, the CBW may proceed to an evaluation and notification process as to this inconsistency followed by determining how to address this inconsistency, which, as shown, may be addressed in one or more manners. For example, consider operations versus accounting, conciliation, implementation of one or more VFMs, inventory adjustment, product movement, operation status, etc. Such a process may aim to address a deviation that is not within a defined tolerance, optionally iteratively using one or more techniques, to drive the CBW forward, for example, to the yes branch of the decision block as to a deviation being within a defined tolerance. Where a deviation is within a defined tolerance, an approval task may be implemented such that data are approved for furtherance of the CBW. In contrast to the FFFW tasks, the CBW provides for automated, semi-automated and / or visually guided manual processes to handle one or more deviations that may not be within one or more corresponding defined tolerances. Such an approach can expeditethe CBW in comparison to the FFFW such that fresh data may be leveraged for monitoring and / or control.

[0207] FIG. 14 shows the operational flexibility section 1150 for the CBW and FFFW. As shown, the FFFW includes human decision making as to whether or not an operational philosophy has changed where, if so, a series of tasks are performed, which may be within a loop, meaning that they may need to be performed multiple times. Such tasks can include data source adjustments, information interface adjustments, homologation of new product movement, evaluation of inconsistency procedures, etc. As shown, a decision can be made as to whether or not an inconsistency is detected, which, if so, may cause a further iteration; whereas, if no inconsistency is detected, an approval process may be performed that requires involvement of an individual or team with sufficient decision-making authority.

[0208] In contrast to the FFFW, the CBW involves setting fiscal spots and / or immobile meter systems according to an assets hierarchy followed by deciding whether a change in operational philosophy has occurred. As shown, responsive to a determined change in operational philosophy, a model or models may be updated as the realm of possible changes may be known in advance and / or otherwise readily addresses via model updates. As shown, the CBW proceeds to an update as to last operating conditions (e.g., last in terms of last time) followed by an approval, which may be optional depending on the particular scenario, asset, entities involved, consequences of output, utilization of output, etc.

[0209] FIG. 15 shows the molecular tracking section 1160 for the CBW and the FFFW where the CBW is shown to be streamlined compared to the FFFW. The CBW performs process execution, for example, considering one or more previous adjustments followed by deciding whether to officially close or not. For example, a decision not to officially close can cause the CBW to return to an operations review of data task that may be part of another section that may, for example, then proceed to the task that decides whether information is within operation logic volume flows. As shown, a decision to officially close can cause the CBW to proceed to the next section (see, e.g., the scenarios section 1170).

[0210] In contrast to the CBW, the FFFW involves specific tasks that are associated with setting up and executing a molecular tracking framework (e.g.,consider the SYMMETRY framework). As shown, for the FFFW, tasks include loading asset volumetric data, setting fiscal volume, deciding whether a zero balance exists. As shown, where a zero balance does not exist, the FFFW involves performing a hand- operated volumetric error troubleshooting tasks that may be discussed in a business unit meeting where facilities product movements legitimizing concerns may arise, which may cause the FFFW to return back to a manual review of data sources one at a time by operator and fluid type. Where a zero balance exists, an offline process may commence to execute framework features to determine a volumetric distribution. As shown, the results may be subject to validation where a lack of validation may result in performing other tasks that may cause the FFFW to return back to a manual review of data sources one at a time by operator and fluid type. If validation is successful, the FFFW may proceed to emission of a report, which may be considered to be a delayed report (e.g., due to various tasks being manual, repeated, etc.).

[0211] FIG. 16 shows the scenarios section 1170 for the CBW and the FFFW, noting that this section applies for the CBW and not the FFFW. As shown, the CBW can provide for evaluations using one or more scenarios, which may be referred to as scenario testing. If such testing is not desired, the CBW may proceed to a subsequent section. As explained, the CBW may implement a rapid framework (e.g., control box) that may provide for rapid generation of results germane to monitoring, controlling, etc., a system with respect to production of one or more products. As explained, a full-featured framework approach may be time consuming and involve various manual tasks and authorizations (e.g., due to time, results, resources, etc.). As explained, a rapid framework may operate via one or more GUIs that provide for expedited entry of parameters to be tested that may define one or more scenarios. As explained, a rapid framework may utilize one or more types of interfaces for access to one or more computational resources (e.g., compute resources, model resources, etc.).

[0212] In the example of FIG. 16, the CBW includes a region, asset, facility selection block, a set up block for setting up changes in one or more operational conditions such as pressures, temperatures, volumetric flows, choke openings, etc. In various instances, such changes may be considered to be control options for control of one or more pieces of equipment in a system. As shown, the CBW may include deciding an analysis road type and optimization of decision-making through what-if-driven insights generation (e.g., decision-making, control, etc., based at least in part on scenario results, etc.).

[0213] In the example of FIG. 16, the CBW includes a reports and dashboard visualization task, which may provide for implementation of control, changes to field equipment, etc., which may aim to reduce one or more types of issues associated with production of products from an asset.

[0214] In the example of FIG. 16, various blocks are shown as to some examples of CBW results, which may include: identification of reasons for underperformance, sustainment of production enhancements and maximized asset performance, synergized alignment with an operation team, reduce deviation according to production plans, adherence to or improvement of volumetric fluid distribution, optimization of chokes and pipeline operations, development of operating procedures, evaluation of plan deviations, inventory accounting, operational philosophy alignment, improved safety and integrity, assessment of product specifications with operational alignment, appraisal of refinery internal consumption schedules, look-ahead operational scenarios, determination of optimum operational envelopes, etc.

[0215] FIG. 17 shows the loss management section 1180 for the CBW and the FFFW. As shown, the CBW can include utilization of the MSMI, which may provide for manual, semi-automated and / or automated review. Further, the CBW can include automation of deviation identification, for example, on a per meter basis (e.g., a per flow meter basis, which may be for physical and / or virtual meters). Such an approach may help to identify one or more discrepancies that may be relevant to possible losses and / or management thereof. As shown, the CBW can provide for loss classification using one or more types of rules (e.g., decision logic, etc.) where, for example, one or more reports, visualizations, etc., may be generated. The FFFW involves various tasks, including various manual tasks. The CBW can provide for operational planning for accurate measurements, automatic meter system audits, realistic and operational loss identification and classification, loss hierarchy action identification associated with measurements (e.g., actual and / or virtual), and reconciliation amongst entities (e.g., as associated with products, product splits, etc.).

[0216] FIG. 18 shows the volumetric compensation section 1190 for the CBW and the FFFW. As shown, the CBW can provide for performing a product compensation analysis where, for example, one or more types of computational approaches may be utilized (e.g., hydrocarbon accounting, income distribution, and pipeline nomination). As explained, products can be chemical products with particular characteristics or qualities. As explained, molecular tracking can provide for assessments as to volumetric and quality, which may be on a per field basis. As an example, a system may provide for product mixture planning for distribution, which may be based at least in part on molecular tracking. As an example, a control box approach may provide for controlling and / or implementing one or more processes to arrive at desired product characteristics, qualities, volumes, fractions, etc. In contrast to the CBW, the FFFW involves various manual tasks that may depend on availability of different individuals, which can ultimately delay report generation and decisionmaking based thereon. The CBW approach provides for leveraging data in a timely manner to drive decision-making as to asset management, which can include control of field operations (e.g., dynamically on a relatively frequent basis).

[0217] FIG. 19, FIG. 20, FIG. 21 , FIG. 22, FIG. 23, FIG. 24, FIG. 25, and FIG. 26 show an example CBW 1900 where various graphical user interfaces (GUIs) are shown that may be rendered to facilitate performance of the CBW 1900 where the CBW 1900 includes a data source section 1910, a data review and extraction section 1920, a data model section 1930, a facilities deviation acceptance section 1940, an operational flexibility section 1950, a molecular tracking section 1960, a scenarios section 1970, a loss management section 1980, and a volumetric compensation section 1990, together with a termination section 1995.

[0218] FIG. 27, FIG. 28, FIG. 29, FIG. 30, FIG. 31 , FIG. 32, and FIG. 33 show an example CBW 2700 where the CBW 2700 includes a data source section 2710, a data review and extraction section 2720, a data model section 2730, a facilities deviation acceptance section 2740, an operational flexibility section 2750, a molecular tracking section 2760, a scenarios section 2770, a loss management section 2780, and a volumetric compensation section 2790, together with a termination section 2795.

[0219] As explained, a rapid framework can provide an integrated and holistic view of an asset from fluid production from one or more wells to product output, whichmay be considered an oil and gas supply chain. As explained, a rapid framework may provide ease of generation and analysis of simulation results.

[0220] As an example, a rapid framework may provide for generation of automated mass balance results considering multiple data sources, which can include real-time data (e.g., streaming data, etc.).

[0221] As an example, a rapid framework may provide for lesser downtime, losses, etc., particularly as to helping to manage and / or guarantee that products generated are properly characterized (e.g., for stakeholders, regulatory, etc.).

[0222] As an example, a rapid framework may provide for improved loss tracking and computations at one or more custody transfer points.

[0223] As an example, a rapid framework may provide for improved measurement accuracy. As explained, in various instances flow meters may be involved and, being field equipment, may be subject to noise, operational issues, etc. In various instances, one or more virtual flow meters (VFMs) may be instantiated and utilized to generate flow data (e.g., volume data, volumetric flow, etc.), which may be responsive to input of measured parameters (e.g., as may be measured using one or more field sensors). In such an approach, if flow data are missing and / or unreliable, a rapid framework may still proceed by filling in such data using one or more VFMs.

[0224] As explained, a rapid framework may integrate pipeline and facilities process simulation considering compositional tracking of fluids. Such a framework may provide for generation of one or more GUIs, which may provide for monitoring and / or controlling equipment and / or workflow performance, along with workflow results.

[0225] As explained, a rapid framework may ingest data from a number of different sources, which may be unrelated, and automatically passes such data to one or more simulation engines in a framework such as the SYMMETRY framework to evaluate a thermodynamic state of a system. As explained, one or more types of interfaces may be implemented to provide for access to a simulation engine, control of the simulation engine and receipt of simulation results. Such an approach may be performed in a remote manner, for example, using a web-interface that may be a GUI generated by a lighter-weight framework that can leverage computational features of a heavier-weight framework.

[0226] As explained, a rapid framework may provide for performing scenario evaluations, which may be expedited to generate results in a reasonable amount of time to provide for decision-making that may be on a daily basis (e.g., for purposes of control, etc.). In various instances, a system may be expected to operate in a relatively steady-state manner where the system is optimized to delivery products according to agreed upon specifications and quantities (e.g., volumes). Where the system is out of balance, product or products may be wasted in that they may not conform with agreed upon specifications. Such situations can result in re-processing, directing products elsewhere, etc. In other words, a system is generally not shut down if certain specifications are not met, rather, the system must be expeditiously tuned to bring its continuous operation into alignment. As explained, a rapid framework can help to monitor and control a system such that its continuous operation is within expectations.

[0227] As explained, a rapid framework may provide for integrated compositional analysis tied with volumetries such that data ingested demands flow data. As an example, such a rapid framework may provide for automated computations of losses using one or more flow data metrics, which may be related to one or more types of meter systems. For example, consider utilization of a Meter System Management Index (MSMI). As explained, a rapid framework may provide for utilization of one or more VFM techniques, which may be utilized for one or more purposes, which can include validation of automated measurements and points lacking measurement. As an example, a rapid framework may provide for assessing flow meter performance throughout a system and, for example, automatically substituting and / or supplementing data with VFM data where appropriate to help assure that results can be generated in a timely manner as to operation of the system and, in particular, quality and / or quantity of products generated.

[0228] As explained, a rapid framework can compute mass balance, conciliation, losses and what if scenarios on a daily basis for oil and gas production across an oil and gas supply chain. As explained, a rapid framework can validate operational conditions and volumes required to meet internal consumption or commercialization of hydrocarbons.

[0229] As explained, a rapid framework can provide for automated data loading to a model from unrelated sources, can provide a virtual data standard related withphysical assets, provide for automation of a process engineering model simulation, can provide for automated calculation of losses across an oil and gas supply chain, can integrates mass balance for pipelines and facilities process, etc.

[0230] As explained, a rapid framework may provide for generation of one or more GUIs that may be simplified compared to a GUI of a full-featured framework. Such an approach may help to manage models and automation between data ingestion and output results. As explained, time can be of the essence where a rapid framework can operate expeditiously to leverage the value of real-time data and, for example, filling in data gaps that may otherwise hinder a holistic assessment. For example, where a full-featured framework demands sensor-based data for a period of time, missing data may be filled in via interpolation such that the framework may run a simulation. In a real-time situation, such interpolation may not be appropriate, particularly where gaps in data are not double-sided gaps (e.g., consider a singlesided gap where extrapolation may be possible but not interpolation). As explained, a rapid framework may implement one or more VFMs which may be able to leverage real-time data as inputs to one or more models to generate synthetic real-time data, which may have a firmer basis in reality than an approach that relies on interpolation and / or extrapolation.

[0231] As explained, a rapid framework may provide for expediting a loss assessment process for a system, which may, in turn, provide for optimizing the system. As explained, a rapid framework can provide an integrated view of asset operations.

[0232] As an example, a rapid framework can provide for validation of product availability, which may be at a sales points based on mass balance and compositional tracking. As an example, a rapid framework can provide for dynamic management of a multi-dimensional simulation model for midstream hydrocarbon chain value to speed up and improve adjustments due to differences in production across a facilities side and reported volumes at end points.

[0233] As an example, a system may include and / or be operatively coupled to one or more gateways (e.g., gateway devices, gateway systems, etc.) such as, for example, an AGORA gateway (e.g., consider one or more processors, memory, etc., which may be deployed as a “box” that can be locally powered and that cancommunicate locally with other equipment via one or more interfaces). As an example, one or more pieces of equipment may include computational resources that can be akin to those of an AGORA gateway or more or less than those of an AGORA gateway. As an example, an AGORA gateway may be a network device.

[0234] As an example, a 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 an eMMC and / or SSD. Such a gateway may include a trusted platform module (TPM), which can provide for secure and measured boot support (e.g., via hashes, etc.). A gateway may include one or more interfaces (e.g., Ethernet, RS485 / 422, RS232, etc.). As to power, a gateway may consume less than about 100 W (e.g., consider less than 10 W or less than 20 W). As an example, a gateway may include an operating system (e.g., consider LINUX DEBIAN LTS). As an example, a gateway may include a cellular interface (e.g., 4G LTE with Global Modem I GPS, etc.). As an example, a gateway may include a WIFI interface (e.g., 802.11 a / b / g / n). As an example, a gateway may be operable using AC 100-240 V, 50 / 60 Hz or 24 VDC. As to dimensions, consider a gateway that has a protective box with dimensions of approximately 10 in x 8 in x 4 in.

[0235] As an example, a system may include one or more components, features, etc., of a SENSIA system (SENSIA LLC, Houston, Texas). As an example, a system may include one or more features of the QRATE HCC2 controller (SENSIA LLC), which may include a dedicated ARM microcontroller, embedded I / O, serial communications unit(s), Ethernet unit(s), one or more serial ports, one or more GPS units (e.g., consider a GNSS receiver for time synchronization), a video port (e.g., consider an HDMI port for edge application touch interface, etc.), one or more wireless option features, one or more modems (e.g., 5G, 4G LTE, WIFI, etc.), firmware, operating system, etc. As an example, such a controller may provide for running DOCKER containers (Docker, Inc, Palo Alto, California), etc. As an example, a system may include one or more processor-based components in the field, which may provide for framework execution. For example, consider a component that may provide for data acquisition, equipment control, interactions with one or more other components, etc. As an example, a field component may operate as an edge device, a gateway,etc., where, for example, one or more sites, wells, facilities, etc., may be operatively coupled to an edge device, a gateway, etc.

[0236] As an example, a VFM may be a field-implemented VFM. For example, consider a gateway that may host one or more VFMs where a rapid framework may access data (e.g., real or synthetic) that may be available at a gateway.

[0237] As an example, a system can be implemented at least in part using a cloud platform. As explained, a system can leverage one or more computational frameworks, which may be accessible or hosted using a framework environment (e.g., DELFI environment). As an example, a system may utilize an application programming interface (API) structure such as an open API structure to facilitate interactions.

[0238] FIG. 34 shows an example of a method 3400 and an example of a system 3490. In the example of FIG. 34, the method can an acquisition block 3410 for acquiring data during operation of a fluid production system generating fluid products, where the data include pressure data, temperature data, and fluid flow data; a generation block 3420 for, responsive to identification of one or more fluid flow data issues, generating synthetic fluid flow data utilizing at least a portion of the pressure data and at least a portion of the temperature data as inputs to a flow meter model; a control block 3430 for controlling a remote simulation engine of a computational framework to, using at least a portion of the data, generate simulation results as to fluid composition within the fluid production system; and a determination block 3440 for determining composition and volume of the fluid products based at least in part on the simulation results.

[0239] In the example of FIG. 34, the system 3490 includes one or more information storage devices 3491 , one or more computers 3492, one or more networks 3495 and instructions 3496. As to the one or more computers 3492, each computer may include one or more processors (e.g., or processing cores) 3493 and a memory 3494 for storing the instructions 3496, for example, executable by at least one of the one or more processors. As an example, a computer may include one or more network interfaces (e.g., wired or wireless), one or more graphics cards, a display interface (e.g., wired or wireless), etc.

[0240] The method 3400 is shown along with various computer-readable media blocks 3411 , 3421 , 3431 , and 3441 (e.g., CRM blocks). Such blocks may be utilized to perform one or more actions of the method 3400, the CBW 1900, etc. For example, consider the system 3490 of FIG. 34 and the instructions 3496, which may include instructions of one or more of the CRM blocks 3411 , 3421 , 3431 , and 3441 .

[0241] As an example, one or more machine learning techniques may be utilized to enhance process operations, a process operations environment, a communications framework, etc. As explained, various types of information can be generated via operations where such information may be utilized for training one or more types of machine learning models to generate one or more trained machine learning models, which may be deployed within one or more frameworks, environments, etc.

[0242] As to types of machine learning models, consider one or more of a support vector machine (SVM) model, a k-nearest neighbors (KNN) model, an ensemble classifier model, a neural network (NN) model, etc. As an example, a machine learning model can be a deep learning model (e.g., deep Boltzmann machine, deep belief network, convolutional neural network, stacked auto-encoder, etc.), an ensemble model (e.g., random forest, gradient boosting machine, bootstrapped aggregation, AdaBoost, stacked generalization, gradient boosted regression tree, etc.), a neural network model (e.g., radial basis function network, perceptron, back-propagation, Hopfield network, etc.), a regularization model (e.g., ridge regression, least absolute shrinkage and selection operator, elastic net, least angle regression), a rule system model (e.g., cubist, one rule, zero rule, repeated incremental pruning to produce error reduction), a regression model (e.g., linear regression, ordinary least squares regression, stepwise regression, multivariate adaptive regression splines, locally estimated scatterplot smoothing, logistic regression, etc.), a Bayesian model (e.g., naive Bayes, average on-dependence estimators, Bayesian belief network, Gaussian naive Bayes, multinomial naive Bayes, Bayesian network), a decision tree model (e.g., classification and regression tree, iterative dichotomiser 3, C4.5, C5.0, chi-squared automatic interaction detection, decision stump, conditional decision tree, M5), a dimensionality reduction model (e.g., principal component analysis, partial least squares regression, Sammon mapping,multidimensional scaling, projection pursuit, principal component regression, partial least squares discriminant analysis, mixture discriminant analysis, quadratic discriminant analysis, regularized discriminant analysis, flexible discriminant analysis, linear discriminant analysis, etc.), an instance model (e.g., k-nearest neighbor, learning vector quantization, self-organizing map, locally weighted learning, etc.), a clustering model (e.g., k-means, k-medians, expectation maximization, hierarchical clustering, etc.), etc.

[0243] As an example, a machine model may be built using a computational framework with a library, a toolbox, etc., such as, for example, those of the MATLAB framework (MathWorks, Inc., Natick, Massachusetts). The MATLAB framework includes a toolbox that provides supervised and unsupervised machine learning algorithms, including support vector machines (SVMs), boosted and bagged decision trees, k-nearest neighbor (KNN), k-means, k-medoids, 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, pretrained models, and apps. The DLT provides convolutional neural networks (ConvNets, CNNs) and long shortterm memory (LSTM) networks to perform classification and regression on image, time-series, and text data. The DLT includes features to build network architectures such as generative adversarial networks (GANs) and Siamese networks using custom training loops, shared weights, and automatic differentiation. The DLT provides for model exchange various other frameworks.

[0244] As an example, the TENSORFLOW framework (Google LLC, Mountain View, CA) may be implemented, which is an open-source software library for dataflow programming that includes a symbolic math library, which can be implemented for machine learning applications that can include neural networks. As an example, the CAFFE framework may be implemented, which is a DL framework developed by Berkeley Al Research (BAIR) (University of California, Berkeley, California). As another example, consider the SCIKIT platform (e.g., scikit-learn), which utilizes the PYTHON programming language. As an example, a framework such as the APOLLO Al framework may be utilized (APOLLO. Al GmbH, Germany). As an example, aframework such as the PYTORCH framework may be utilized (Facebook Al Research Lab (FAIR), Facebook, Inc., Menlo Park, California).

[0245] As an example, a training method can include various actions that can operate on a dataset to train a ML model. As an example, a dataset can be split into training data and test data where test data can provide for evaluation. A method can include cross-validation of parameters and best parameters, which can be provided for model training.

[0246] The TENSORFLOW framework can run on multiple CPUs and GPUs (with optional CUDA (NVIDIA Corp., Santa Clara, California) and SYCL (The Khronos Group Inc., Beaverton, Oregon) extensions for general-purpose computing on graphics processing units (GPUs)). TENSORFLOW is available on 64-bit LINUX, MACOS (Apple Inc., Cupertino, California), WINDOWS (Microsoft Corp., Redmond, Washington), and mobile computing platforms including ANDROID (Google LLC, Mountain View, California) and IOS (Apple Inc.) operating system-based platforms.

[0247] TENSORFLOW computations can be expressed as stateful dataflow graphs; noting that the name TENSORFLOW derives from the operations that such neural networks perform on multidimensional data arrays. Such arrays can be referred to as "tensors".

[0248] As an example, a device may utilize TENSORFLOW LITE (TFL) or another type of lightweight framework. TFL is a set of tools that enables on-device machine learning where models may run on mobile, embedded, and loT devices. TFL is optimized for on-device machine learning, by addressing latency (no round-trip to a server), privacy (no personal data leaves the device), connectivity (Internet connectivity is demanded), size (reduced model and binary size) and power consumption (e.g., efficient inference and a lack of network connections). The TFL framework provides multiple platform support, covering ANDROID and iOS devices, embedded LINUX, and microcontrollers. The TFL framework provides diverse language support, which includes JAVA, SWIFT, Objective-C, C++, and PYTHON. High performance, with hardware acceleration and model optimization. The TFL framework provides for machine learning tasks that may include, for example, image classification, object detection, pose estimation, question answering, text classification, etc., on multiple platforms.

[0249] As an example, a dynamic reservoir simulation system can be an autonomous and / or semi-autonomous integrated control system for a field (e.g., an asset) and / or be a part of an autonomous and / or semi-autonomous integrated control system for a field (e.g., operatively coupled to, etc.). Reservoir simulation can include simulation of subsurface and / or surface flows. For example, consider use of one or more types of frameworks such as one or more of the INTERSECT framework and the PIPESIM framework in an integrated control system. As explained, one or more types of frameworks, models, etc., can be implemented within a control system to improve control of one or more field operations, which, in turn, can provide for asset optimization (e.g., optimization of a field that includes one or more reservoirs and one or more wells). As explained, optimization can occur on multiple levels and can be based on field data such that control actions can be output to equipment in an effort to optimize an asset with respect to constraints and objectives.

[0250] As an example, a method can include acquiring data during operation of a fluid production system generating fluid products, where the data include pressure data, temperature data, and fluid flow data; responsive to identification of one or more fluid flow data issues, generating synthetic fluid flow data utilizing at least a portion of the pressure data and at least a portion of the temperature data as inputs to a flow meter model; controlling a remote simulation engine of a computational framework to, using at least a portion of the data, generate simulation results as to fluid composition within the fluid production system; and determining composition and volume of the fluid products based at least in part on the simulation results. In such an example, the data can include real-time data.

[0251] As an example, a method may include determining composition and volume of fluid products on at least a daily basis.

[0252] As an example, a method may include controlling that includes implementing a programming interface for direct interaction with a remote simulation engine. In such an example, controlling may occur without rendering of or interacting with a graphical user interface of a computational framework. For example, a rapid framework (e.g., a control box) may provide for interactions with a remote simulation of a computational framework without interacting directly through a native graphical user interface of the computational framework.

[0253] As an example, a remote simulation engine may be or include a thermodynamic engine.

[0254] As an example, a flow meter model may be or include a machine learning model.

[0255] As an example, a flow meter model may be or include a hybrid physicsbased and machine learning-based model.

[0256] As an example, one or more fluid flow data issues may include an absence of fluid flow data issue. For example, for one or more reasons, fluid flow data may be unable to be generated by and / or communicated by a flow meter (e.g., due to a measurement issue, a communication issue, etc.).

[0257] As an example, one or more fluid flow data issues may include a noise issue. For example, consider a noise issue that pertains to signal-to-noise ratio (SNR), where signal may be difficult to extract from noise.

[0258] As an example, one or more fluid flow data issues may indicate an issue with respect to performance of a multi-phase flow meter (MPFM) within a fluid production system.

[0259] As an example, a fluid production system can include a fluid network in fluid communication with at least one well. As an example, a fluid production system can include at least one gas and liquid separation unit. As an example, a fluid production system can include at least one distillation unit.

[0260] As an example, a method can include controlling a fluid production system based at least in part on a determined composition and volume of one or more fluid products. In such an example, controlling the fluid production system can include adjusting at least one adjustable choke of the fluid production system. For example, a well may have wellhead equipment that includes a choke where the choke may be adjustable. In various instances, a choke may be subject to wear. For example, where particulate matter such as sand is produced along with reservoir fluid (e.g., entrained in reservoir fluid). As an example, sand may erode one or more components of a valve. For example, consider an orifice formed by a component of a valve where erosion may cause an increase in cross-sectional area of the orifice over time. As explained, for one or more reasons, operation of a fluid production network may be challenging to particularly where steady-state or near-steady-state behavior isdesirable for production of products of consistent quality (e.g., composition) and quantity (e.g., volume).

[0261] As an example, a method can include controlling a remote simulation engine of a computational framework by issuing a signal responsive to interaction with a graphical user interface that is not generated by the computational framework.

[0262] As an example, a method can include identifying a loss to one or more fluid products based at least in part on simulation results. In such an example, the loss may be identified in an upstream manner or at least in part in an upstream manner. For example, one or more processes may result in shrinkage, expansion, and flashes during one or more production pathways, which may provide for prompting the presence of one or more types of flow assurance issues that may pose a risk of causing one or more types of non-identified production losses. As an example, a framework may provide for utilization of one or more loss management cells as may be associated with a particular portion or portions of a fluid production system. As an example, a framework may provide for automatic loss management cell instantiation and operation for loss detection, loss control, etc.

[0263] As an example, a system can include a processor; a memory accessible to the processor; processor-executable instructions stored in the memory and executable by the processor to instruct the system to: acquire data during operation of a fluid production system generating fluid products, where the data include pressure data, temperature data, and fluid flow data; responsive to identification of one or more fluid flow data issues, generate synthetic fluid flow data utilizing at least a portion of the pressure data and at least a portion of the temperature data as inputs to a flow meter model; control a remote simulation engine of a computational framework to, using at least a portion of the data, generate simulation results as to fluid composition within the fluid production system; and determine composition and volume of the fluid products based at least in part on the simulation results.

[0264] As an example, one or more computer-readable media can include computer-executable instructions executable by a system to instruct the system to: acquire data during operation of a fluid production system generating fluid products, where the data include pressure data, temperature data, and fluid flow data; responsive to identification of one or more fluid flow data issues, generate syntheticfluid flow data utilizing at least a portion of the pressure data and at least a portion of the temperature data as inputs to a flow meter model; control a remote simulation engine of a computational framework to, using at least a portion of the data, generate simulation results as to fluid composition within the fluid production system; and determine composition and volume of the fluid products based at least in part on the simulation results.

[0265] As an example, a computer program product can include one or more computer-readable storage media that can include processor-executable instructions to instruct a computing system to perform one or more methods and / or one or more portions of a method.

[0266] In some embodiments, a method or methods may be executed by a computing system. FIG. 35 shows an example of a system 3500 that can include one or more computing systems 3501 -1 , 3501 -2, 3501 -3 and 3501 -4, which may be operatively coupled via one or more networks 3509, which may include wired and / or wireless networks. As shown, the system 3500 may include one or more other components 3508.

[0267] As an example, a system can include an individual computer system or an arrangement of distributed computer systems. In the example of FIG. 35, the computer system 3501 -1 can include one or more modules 3502, which may be or include processor-executable instructions, for example, executable to perform various tasks (e.g., receiving information, requesting information, processing information, simulation, outputting information, etc.).

[0268] As an example, a module may be executed independently, or in coordination with, one or more processors 3504, which is (or are) operatively coupled to one or more storage media 3506 (e.g., via wire, wirelessly, etc.). As an example, one or more of the one or more processors 3504 can be operatively coupled to at least one of one or more network interface 3507. In such an example, the computer system 3501 -1 can transmit and / or receive information, for example, via the one or more networks 3509 (e.g., consider one or more of the Internet, a private network, a cellular network, a satellite network, etc.). As shown, one or more other components 3508 can be included.

[0269] As an example, the computer system 3501 -1 may receive from and / or transmit information to one or more other devices, which may be or include, for example, one or more of the computer systems 3501 -2, etc. A device may be located in a physical location that differs from that of the computer system 3501 -1. As an example, a location may be, for example, a processing facility location, a data center location (e.g., server farm, etc.), a rig location, a wellsite location, a downhole location, etc.

[0270] As an example, a processor may be or include a microprocessor, microcontroller, processor module or subsystem, programmable integrated circuit, programmable gate array, or another control or computing device.

[0271] As an example, the storage media 3506 may be implemented as one or more computer-readable or machine-readable storage media. As an example, storage may be distributed within and / or across multiple internal and / or external enclosures of a computing system and / or additional computing systems.

[0272] As an example, a storage medium or storage media may include one or more different forms of memory including semiconductor memory devices such as dynamic or static random access memories (DRAMs or SRAMs), erasable and programmable read-only memories (EPROMs), electrically erasable and programmable read-only memories (EEPROMs) and flash memories, magnetic disks such as fixed, floppy and removable disks, other magnetic media including tape, optical media such as compact disks (CDs) or digital video disks (DVDs), BLUERAY disks, or other types of optical storage, or other types of storage devices.

[0273] As an example, a storage medium or media may be located in a machine running machine-readable instructions, or located at a remote site from which machine-readable instructions may be downloaded over a network for execution.

[0274] 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 (e.g., including firmware), including one or more signal processing and / or application specific integrated circuits.

[0275] As an example, a system may include a processing apparatus that may be or include a general-purpose processors or application specific chips (e.g., or chipsets), such as ASICs, FPGAs, PLDs, or other appropriate devices.

[0276] As an example, a device may be a mobile device that includes one or more network interfaces for communication of information. For example, a mobile device may include a wireless network interface (e.g., operable via IEEE 802.11 , ETSI GSM, BLUETOOTH, satellite, etc.). As an example, a mobile device may include components such as a main processor, a memory, a display, display graphics circuitry (e.g., optionally including touch and gesture circuitry), a SIM slot, audio / video circuitry, motion processing circuitry (e.g., accelerometer, gyroscope), wireless LAN circuitry, smart card circuitry, transmitter circuitry, GPS circuitry, and a battery. As an example, a mobile device may be configured as a cell phone, a tablet, etc. As an example, a method may be implemented (e.g., wholly or in part) using a mobile device. As an example, a system may include one or more mobile devices.

[0277] As an example, a system may be a distributed environment, for example, a so-called “cloud” environment where various devices, components, etc. interact for purposes of data storage, communications, computing, etc. As an example, a device or a system may include one or more components for communication of 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, a method may be implemented in a distributed environment (e.g., wholly or in part as a cloud-based service).

[0278] As an example, information may be input from a display (e.g., consider a touchscreen), output to a display or both. As an example, information may be output to a projector, a laser device, a printer, etc. such that the information may be viewed. As an example, information may be output stereographically or holographically. As to a printer, consider 2D or a 3D printer. As an example, a 3D printer may include one or more substances that can be output to construct a 3D object. For example, data may be provided to a 3D printer to construct a 3D representation of a subterranean formation. As an example, layers may be constructed in 3D (e.g., horizons, etc.), geobodies constructed in 3D, etc. As an example, holes, fractures, etc., may be constructed in 3D (e.g., as positive structures, as negative structures, etc.).

[0279] Although only a few example embodiments have been described in detail above, those skilled in the art will readily appreciate that many modifications are possible in the example embodiments. Accordingly, all such modifications areintended to be included within the scope of this disclosure as defined in the following claims. In the claims, means-plus-function clauses are intended to cover the structures described herein as performing the recited function and not only structural equivalents, but also equivalent structures. Thus, although a nail and a screw may not be structural equivalents in that a nail employs a cylindrical surface to secure wooden parts together, whereas a screw employs a helical surface, in the environment of fastening wooden parts, a nail and a screw may be equivalent structures.

Claims

CLAIMSWhat is claimed is:1 . A method comprising: acquiring data during operation of a fluid production system generating fluid products, wherein the data comprise pressure data, temperature data, and fluid flow data; responsive to identification of one or more fluid flow data issues, generating synthetic fluid flow data utilizing at least a portion of the pressure data and at least a portion of the temperature data as inputs to a flow meter model; controlling a remote simulation engine of a computational framework to, using at least a portion of the data, generate simulation results as to fluid composition within the fluid production system; and determining composition and volume of the fluid products based at least in part on the simulation results.

2. The method of claim 1 , wherein the data comprise real-time data.

3. The method of claim 1 , wherein the determining determines the composition and volume of the fluid products on at least a daily basis.

4. The method of claim 1 , wherein the controlling comprises implementing a programming interface for direct interaction with the remote simulation engine.

5. The method of claim 4, wherein the controlling occurs without rendering of or interacting with a graphical user interface of the computational framework.

6. The method of claim 1 , wherein the remote simulation engine comprises a thermodynamic engine.

7. The method of claim 1 , wherein the flow meter model comprises a machine learning model.

8. The method of claim 1 , wherein the flow meter model comprises a hybrid physicsbased and machine learning-based model.

9. The method of claim 1 , wherein the one or more of the fluid flow data issues comprise an absence of fluid flow data issue.

10. The method of claim 1 , wherein the one or more of the fluid flow data issues comprise a noise issue.11 . The method of claim 1 , wherein the one or more of the fluid flow data issues indicate an issue with respect to performance of a multi-phase flow meter within the fluid production system.

12. The method of claim 1 , wherein the fluid production system comprises a fluid network in fluid communication with at least one well.

13. The method of claim 1 , wherein the fluid production system comprises at least one gas and liquid separation unit.

14. The method of claim 1 , wherein the fluid production system comprises at least one distillation unit.

15. The method of claim 1 , comprising controlling the fluid production system based at least in part on the determined composition and volume of the fluid products.

16. The method of claim 15, wherein the controlling the fluid production system comprises adjusting at least one adjustable choke of the fluid production system.

17. The method of claim 1 , wherein the controlling the remote simulation engine comprises issuing a signal responsive to interaction with a graphical user interface that is not generated by the computational framework.

18. The method of claim 1 , comprising identifying a loss to one or more of the fluid products based at least in part on the simulation results.

19. A system comprising: a processor; a memory accessible to the processor; processor-executable instructions stored in the memory and executable by the processor to instruct the system to: acquire data during operation of a fluid production system generating fluid products, wherein the data comprise pressure data, temperature data, and fluid flow data; responsive to identification of one or more fluid flow data issues, generate synthetic fluid flow data utilizing at least a portion of the pressure data and at least a portion of the temperature data as inputs to a flow meter model; control a remote simulation engine of a computational framework to, using at least a portion of the data, generate simulation results as to fluid composition within the fluid production system; and determine composition and volume of the fluid products based at least in part on the simulation results.

20. One or more computer-readable media comprising computer-executable instructions executable by a system to instruct the system to: acquire data during operation of a fluid production system generating fluid products, wherein the data comprise pressure data, temperature data, and fluid flow data; responsive to identification of one or more fluid flow data issues, generate synthetic fluid flow data utilizing at least a portion of the pressure data and at least a portion of the temperature data as inputs to a flow meter model;control a remote simulation engine of a computational framework to, using at least a portion of the data, generate simulation results as to fluid composition within the fluid production system; and determine composition and volume of the fluid products based at least in part on the simulation results.

Images