Generative framework for simulation workflow

Abstract

A method for using generative artificial intelligence (AI) to produce a framework for a simulation workflow includes receiving a process flow diagram for equipment at a facility. The method also includes receiving first data related to the equipment from one or more sensors. The method also includes determining parameters for the equipment based upon the process flow diagram and the first data. The method also includes receiving second data from the one or more sensors. The method also includes calibrating a subset of models based upon the parameters, the first data, and the second data to produce calibrated models. The method also includes performing a facility simulation using the calibrated models based upon the second data to produce an output.

Description

Attorney Docket No.: IS23.0563-WO-PCTGENERATIVE FRAMEWORK FOR SIMULATION WORKFLOWCross-Reference to Related Applications

[0001] This application claims priority to U.S. Provisional Patent Application No. 63 / 691,420, filed on September 6, 2024, which is incorporated by reference herein.Background

[0002] Simulation workflows are domain-intensive and depend upon vast experience to determine a useful simulation or representation of a system. A conventional simulation workflow includes multiple coordinated steps such as (1) setting up a project, (2) defining inputs and outputs of a simulation, and (3) building models. Building models involves creating a process flow diagram (PFD) and invoking equipment, processes, and components, which are also referred to as unit operations.

[0003] Once this is complete, a user may input or configure a (e.g., thermodynamic) model, input conditions, design parameters, etc. before running the simulation. The simulation workflow is again iterative, and human expert intelligence is used to analyze each step before optimization. This coordinated task involves an understanding of the facility, equipment, sizing, determination of process conditions, and analysis of the impact of these conditions on the process.Summary

[0004] A method for using generative artificial intelligence (Al) to produce a framework for a simulation workflow is disclosed. The method includes receiving a process flow diagram for equipment at a facility. The method also includes receiving first data related to the equipment from one or more sensors. The method also includes determining parameters for the equipment based upon the process flow diagram and the first data. The method also includes receiving second data from the one or more sensors. The method also includes calibrating a subset of models based upon the parameters, the first data, and the second data to produce calibrated models. The method also includes performing a facility simulation using the calibrated models based upon the second data to produce an output.

[0005] A computing system is also disclosed. The computing system includes one or more processors and a memory system. The memory system includes one or more non-transitoryAttorney Docket No.: IS23.0563-WO-PCT computer-readable media storing instructions that, when executed by at least one of the one or more processors, cause the computing system to perform operations. The operations include receiving a process flow diagram for equipment at a facility. The operations also include receiving first data related to the equipment from one or more sensors. The operations also include determining parameters for the equipment based upon the process flow diagram and the first data. The operations also include receiving second data from the one or more sensors. The second data is measured after the first data. The operations also include calibrating a subset of models based upon the parameters, the first data, and the second data to produce calibrated models. The operations also include performing a facility simulation using the calibrated models based upon the second data to produce an output. The operations also include generating a recommendation based upon the output.

[0006] A non-transitory computer-readable medium is also disclosed. The medium includes instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations. The operations include receiving a process flow diagram for equipment at a facility. The operations also include receiving first data related to the equipment from one or more sensors. The operations also include determining parameters for the equipment based upon the process flow diagram and the first data. The operations also include receiving second data from the one or more sensors. The operations also include calibrating a subset of models based upon the parameters, the first data, and the second data to produce calibrated models. The operations also include performing a facility simulation in sequential tasks to produce an aggregated output. The facility simulation is performed based upon the second data using the calibrated models.

[0007] It will be appreciated that this summary is intended merely to introduce some aspects of the present methods, systems, and media, which are more fully described and / or claimed below. Accordingly, this summary is not intended to be limiting.Brief Description of the Drawings

[0008] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the present teachings and together with the description, serve to explain the principles of the present teachings. In the figures:Attorney Docket No.: IS23.0563-WO-PCT

[0009] Figure 1 illustrates an example of a system that includes various management components to manage various aspects of a geologic environment, according to an embodiment.

[0010] Figure 2 illustrates a schematic view of a system for using generative artificial intelligence (Al) to produce a framework for a simulation workflow, according to an embodiment.

[0011] Figure 3 illustrates a schematic view of a large language model (LLM) agent that may be used in the system, according to an embodiment.

[0012] Figure 4 illustrates a single branch simulation performed by the system, according to an embodiment.

[0013] Figure 5 illustrates a flowchart of a method for using generative artificial intelligence (Al) to produce a framework for a simulation workflow, according to an embodiment.

[0014] Figures 6A-6F illustrate a flowchart of an operation performed by a (e.g., midstream) simulation agent, according to an embodiment.

[0015] Figures 7A and 7B illustrate tool calls examples performed by the simulation agent, according to an embodiment.

[0016] Figures 8 and 9 illustrate examples of instructions being received by the simulation agent and responses being generated by the simulation agent, according to an embodiment.

[0017] Figure 10 illustrates a schematic view of a computing system for performing at least a portion of the method(s) described herein, according to an embodiment.Detailed Description

[0018] Reference will now be made in detail to embodiments, examples of which are illustrated in the accompanying drawings and figures. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure. However, it will be apparent to one of ordinary skill in the art that the present disclosure may be practiced without these specific details. In other instances, well-known methods, procedures, components, circuits, and networks have not been described in detail so as not to unnecessarily obscure aspects of the embodiments.

[0019] It will also be understood that, although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first object or step could be termed a second object or step, and, similarly, a second object or step could be termed a firstAttorney Docket No.: IS23.0563-WO-PCT object or step, without departing from the scope of the present disclosure. The first object or step, and the second object or step, are both, objects or steps, respectively, but they are not to be considered the same object or step.

[0020] The terminology used in the description herein is for the purpose of describing particular embodiments and is not intended to be limiting. As used in this description and the appended claims, the singular forms “a,” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term “and / or” as used herein refers to and encompasses any possible combinations of one or more of the associated listed items. It will be further understood that the terms “includes,” “including,” “comprises” and / or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. Further, as used herein, the term “if’ may be construed to mean “when” or “upon” or “in response to determining” or “in response to detecting,” depending on the context.

[0021] Attention is now directed to processing procedures, methods, techniques, and workflows that are in accordance with some embodiments. Some operations in the processing procedures, methods, techniques, and workflows disclosed herein may be combined and / or the order of some operations may be changed.System Overview

[0022] Figure 1 illustrates an example of a system 100 that includes various management components 110 to manage various aspects of a geologic environment 150 (e.g., an environment that includes a sedimentary basin, a reservoir 151, one or more faults 153-1, one or more geobodies 153-2, etc.). For example, the management components 110 may allow for direct or indirect management of sensing, drilling, injecting, extracting, etc., with respect to the geologic environment 150. In turn, further information about the geologic environment 150 may become available as feedback 160 (e.g., optionally as input to one or more of the management components 110).

[0023] In the example of Figure 1, the management components 110 include a seismic data component 112, an additional information component 114 (e.g., well / logging data), a processing component 116, a simulation component 120, an attribute component 130, anAttorney Docket No.: IS23.0563-WO-PCT analysis / visualization component 142 and a workflow component 144. In operation, seismic data and other information provided per the components 112 and 114 may be input to the simulation component 120.

[0024] In an example embodiment, the simulation component 120 may rely on entities 122. Entities 122 may include earth entities or geological objects such as wells, surfaces, bodies, reservoirs, etc. In the system 100, the entities 122 may include virtual representations of actual physical entities that are reconstructed for purposes of simulation. The entities 122 may include entities based on data acquired via sensing, observation, etc. (e.g., the seismic data 112 and other information 114). 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 porosity property). Such properties may represent one or more measurements (e.g., acquired data), calculations, etc.

[0025] In an example embodiment, the simulation component 120 may operate in conjunction with a software framework such as an object -based framework. In such a framework, entities may include entities based on pre-defined classes to facilitate modeling and simulation. A commercially available example of an object-based framework is the MICROSOFT® .NET® framework (Redmond, Washington), which provides a set of extensible object classes. In the .NET® framework, an object class encapsulates a module of reusable code and associated data structures. Object classes may be used to instantiate object instances for use in by a program, script, etc. For example, borehole classes may define objects for representing boreholes based on well data.

[0026] In the example of Figure 1, the simulation component 120 may process information to conform to one or more attributes specified by the attribute component 130, which may include a library of attributes. Such processing may occur prior to input to the simulation component 120 (e.g., consider the processing component 116). As an example, the simulation component 120 may perform operations on input information based on one or more attributes specified by the attribute component 130. In an example embodiment, the simulation component 120 may construct one or more models of the geologic environment 150, which may be relied on to simulate behavior of the geologic environment 150 (e.g., responsive to one or more acts, whether natural or artificial). In the example of Figure 1, the analysis / visualization component 142 may allow for interaction with a model or model-based results (e.g., simulation results, etc.). As an example,Attorney Docket No.: IS23.0563-WO-PCT output from the simulation component 120 may be input to one or more other workflows, as indicated by a workflow component 144.

[0027] As an example, the simulation component 120 may include one or more features of a simulator such as the ECLIPSE1Mreservoir simulator (SLB, Houston Texas), the INTERSECT™ reservoir simulator (SLB, Houston Texas), etc. As an example, a simulation component, a simulator, etc. may include features to implement one or more meshless techniques (e.g., to solve one or more equations, etc.). 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 SAGD, etc ).

[0028] As an example, the simulation component 120 may include one or more features of a simulator such as SYMMETRY™ software (SLB, Houston, Texas). More particularly, SYMMETRY™ may process workflows in a single integrated environment with accurate thermodynamic fluid representation and consistent modeling across multiple disciplines including process, production, and HSE. The simulator integrates steady-state and transient (e.g., dynamic) analyses that may be tailored for each domain. This approach enables users to optimize processes in upstream, midstream, and downstream sectors while maximizing profits and minimizing capital expenditures. It may also help reduce emissions, energy consumption, and waste.

[0029] As an example, the simulation component 120 may include one or more features of a simulator such as PIPESIM™ (SLB, Houston, Texas). More particularly, PIPESIM™ is steadystate multiphase flow simulator that incorporates the three areas of flow modeling: multiphase flow, heat transfer and fluid behavior.

[0030] As an example, the simulation component 120 may include one or more features of a simulator such as OLGA™ (SLB, Houston, Texas). More particularly, OLGA™ is a dynamic multiphase flow simulator that models transient flow (e.g., time-dependent behaviors) to maximize production potential. Transient modeling is a component for feasibility studies and field development design. Dynamic simulation is useful in deep water and is used in both offshore and onshore developments to investigate transient behavior in pipelines and wellbores. Transient simulation with the OLGA™ simulator provides an added dimension to steady-state analysis by predicting system dynamics, such as time-varying changes in flow rates, fluid compositions, temperature, solids deposition, and operational changes.Attorney Docket No.: IS23.0563-WO-PCT

[0031] In an example embodiment, the management components 110 may include features of a commercially available framework such as the PETREL® seismic to simulation software framework (SLB, Houston, Texas). The PETREL® framework provides components that allow for optimization of exploration and development operations. The PETREL® framework includes seismic to simulation software components that may 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) may develop collaborative workflows and integrate operations to streamline processes. Such a framework may be considered an application and may be considered a data-driven application (e.g., where data is input for purposes of modeling, simulating, etc.).

[0032] In an example embodiment, various aspects of the management components 110 may include add-ons or plug-ins that operate according to specifications of a framework environment. For example, a commercially available framework environment marketed as the OCEAN® framework environment (SLB, Houston, Texas) allows for integration of add-ons (or plug-ins) into a PETREL® framework workflow. The OCEAN® framework environment leverages .NET® tools (Microsoft Corporation, Redmond, Washington) and offers stable, user-friendly interfaces for efficient development. In an example embodiment, various components may be implemented as add-ons (or plug-ins) that conform to and operate according to specifications of a framework environment (e.g., according to application programming interface (API) specifications, etc.).

[0033] Figure 1 also shows an example of a framework 170 that includes a model simulation layer 180 along with a framework services layer 190, a framework core layer 195 and a modules layer 175. The framework 170 may include the commercially available OCEAN® framework where the model simulation layer 180 is the commercially available PETREL® model -centric software package that hosts OCEAN® framework applications. In an example embodiment, the PETREL® software may be considered a data-driven application. The PETREL® software may include a framework for model building and visualization.

[0034] As an example, a framework may include features for implementing one or more mesh generation techniques. For example, a framework may include an input component for receipt of information from interpretation of seismic data, one or more attributes based at least in part on seismic data, log data, image data, etc. Such a framework may include a mesh generationAttorney Docket No.: IS23.0563-WO-PCT component that processes input information, optionally in conjunction with other information, to generate a mesh.

[0035] In the example of Figure 1, the model simulation layer 180 may provide domain objects 182, act as a data source 184, provide for rendering 186 and provide for various user interfaces 188. Rendering 186 may provide a graphical environment in which applications may display their data while the user interfaces 188 may provide a common look and feel for application user interface components.

[0036] As an example, the domain objects 182 may include entity objects, property objects and optionally other objects. Entity objects may be used to geometrically represent wells, surfaces, bodies, reservoirs, etc., while property objects may be used to provide property values as well as data versions and display parameters. For example, an entity object may represent a well where a property object provides log information as well as version information and display information (e.g., to display the well as part of a model).

[0037] In the example of Figure 1, data may be stored in one or more data sources (or data stores, generally physical data storage devices), which may be at the same or different physical sites and accessible via one or more networks. The model simulation layer 180 may be configured to model projects. As such, a particular project may be stored where stored project information may include inputs, models, results and cases. Thus, upon completion of a modeling session, a user may store a project. At a later time, the proj ect may be accessed and restored using the model simulation layer 180, which may recreate instances of the relevant domain objects.

[0038] In the example of Figure 1, the geologic environment 150 may include layers (e.g., stratification) that include a reservoir 151 and one or more other features such as the fault 153-1, the geobody 153-2, etc. As an example, the geologic environment 150 may be outfitted with any of 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 well site 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, Figure 1 shows a satellite inAttorney Docket No.: IS23.0563-WO-PCT communication with the network 155 that may be configured for communications, noting that the satellite may additionally or instead include circuitry for imagery (e.g., spatial, spectral, temporal, radiometric, etc.).

[0039] Figure 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.

[0040] As mentioned, the system 100 may be used to perform one or more workflows. A workflow may be a process that includes a number of worksteps. A workstep may operate on data, for example, to create new data, to update existing data, etc. As an example, a may operate on one or more inputs and create one or more results, for example, based on one or more algorithms. As an example, a system may include a workflow editor for creation, editing, executing, etc. of a workflow. In such an example, the workflow editor may provide for selection of one or more predefined worksteps, one or more customized worksteps, etc. As an example, a workflow may be a workflow implementable in the PETREL® software, for example, that operates on seismic data, seismic attribute(s), etc. As an example, a workflow may be a process implementable in the OCEAN® framework. As an example, a workflow may include one or more worksteps that access a module such as a plug-in (e g., external executable code, etc.).Generative Framework for Simulation Workflow

[0041] The present disclosure includes a generative framework, which involves a large language model (LLM) that may be trained on pertinent data. The LLM may then act as a brain of the system. The system may orchestrate the workflow by learning the sequence of the workflow. This may be accomplished by training the models with various relevant documents and / or multimodalAttorney Docket No.: IS23.0563-WO-PCT data. In another embodiment, the model may be grounded for a specific workflow by providing instructions and fine-tuning data.

[0042] In another embodiment, the brain may be further optimized by providing feedback on its performance. More particularly, the model may be designed to perform a sequence of hierarchical tasks which satisfy conditions. The execution of subtasks to satisfy the conditions may be thought through by the brain model. Once the model finishes one of the tasks, it proceeds to the next task and again divides it into multiple sub-tasks and achieves the objective. This workflow may continue until the bigger objective is achieved.

[0043] The generative model and / or the brain may have access to real-time process and operations data, relevant documents, configuration files, simulation engines, or a combination thereof. In another embodiment, the generative model may have access to other generative models to coordinate the larger workflow and run practical scenario analysis.

[0044] The framework may assist a subject matter expert (SME) or domain expert with determining a streamlined solution of points, which may be further analyzed by the SME. In another embodiment, the framework may be defined as an optimization problem with an objective to achieve. In yet another embodiment, the framework may solve the exact problem in hand, providing the final solution. In each of the above scenarios, the framework involves multiple interacting generative models, cooperating together to complete a task. The models may be provided access to the data, simulators, optimizers, and any other tool to complete the job.

[0045] Figure 2 illustrates a schematic view of a system 200 for using generative artificial intelligence (Al) to produce a framework for a simulation workflow, according to an embodiment. The system 200 may include one or more software platforms (three are shown: 210, 220, 230). The first software platform 210 may be used for designing, deploying, and / or managing data analytics applications and predictive machine learning (ML) models. In an example, the first software platform 210 may be DATAIKU™. The first software platform 210 may include or be configured to run a production assistant 211 and one or more agents (five are shown: 212-216).

[0046] In an example, the first agent 212 may be used to model a process workflow in one environment, integrating facilities and process units with pipelines, networks and flare, and safety systems models, while ensuring consistent thermodynamics and fluid characterization across the full system. In an example, the first agent 212 may be SYMMETRY™. The second agent 213 may be a multi-phase flow simulator. In an example, the second agent may be PIPESIM™. TheAttorney Docket No.: IS23.0563-WO-PCT third agent 214 may be a physics-informed Al model builder for the oil and gas industry. Tn an example, the third agent 214 may be GEMINUS™. The fourth agent 215 may be a data agent 215, and the fifth agent 216 may be an equipment agent.

[0047] The second software platform 220 may be used for artificial intelligence (Al), data management, and / or physics-based science for oil and gas exploration, development, drilling, production, and / or energy transition. In an example, the second software platform 220 may be Delfi™. The second software platform 220 may include a backend 221 that is configured to interact with the first agent 212. The second software platform 220 may also include a FA workspace 222 that is configured to interact with the agents 212-214. The second software platform 220 may also include a model operation module 223 that is configured to interact with the equipment agent 216.

[0048] The third software platform 230 may be used to solve production and asset performance challenges in the energy domain. It may also or instead be used to integrate data from reservoirs, wells, and / or facilities, using a single, open data foundation. In an example, the third software platform 230 may be COGNITE™. The third software platform 230 may include or be configured to build or run an asset data model 231, which may interact with the backend 221. The third software platform 230 may also include or be configured to build or run a production data model (PDM) 232 that is configured to interact with the FA workspace 222. The third software platform 230 may also include or be configured to build or run an Al module 233. In an example, the Al module 233 may be ATLAS™ Al.

[0049] Figure 3 illustrates a schematic view of a large language model (LLM) agent 300 that may be used in the system 200, according to an embodiment. In an example, the task 310 encodes the user goal (e.g., “estimate compressor power at 85% motor efficiency”) into a structured plan with sub-tasks such as asset lookup, model selection, variable mapping, simulation, and reporting. The LLM 320 may be or include a tool-using large language model that decomposes the task, selects tools, forms API calls, and reasons over results. The LLM 320 maintains memory of plant context and constraints (e g., HAZOP limits) while orchestrating steps. The tools / equipment 330 may include external capabilities callable by the agent, including model repositories, flowsheet solvers (e.g., steady-state and transient), data services (e.g., tags, historians), and optimization / calibration routines. The environment / facility 340 may be or include the physicalAttorney Docket No.: IS23.0563-WO-PCT plant and its digital twins (e.g., asset hierarchy, process units, and sensors). The agent grounds decisions in live sensor data and model states for that facility.

[0050] Figure 4 illustrates a single branch simulation performed by the system 200, according to an embodiment. More particularly, Figure 4 shows a single-branch flow: the agent (1) interprets the user request, (2) finds the target asset, (3) determines simulation type (e.g., steady-state vs. transient; unit vs. facility), (4) fetches input data and maps plant tags to model variables, (5) runs simulation via a tool call, (6) parses results, and (7) displays outcomes and recommendations

[0051] Figure 5 illustrates a flowchart of a method for using generative artificial intelligence (Al) to produce a framework for a simulation workflow, according to an embodiment. An illustrative order of the method 500 is provided below; however, one or more portions of the method 500 may be performed in a different order, simultaneously, repeated, or omitted. At least a portion of the method 500 may be performed by a computing system.

[0052] The method 500 may include receiving a process flow diagram for equipment at a facility, as at 505. In an example, the process flow diagram may show a three-phase separator (SEP-101) receiving a well stream feed; a gas path through a compressor (K-411 A) and air cooler (AC-201) to export; a liquids path through a heat exchanger (E-301) and pump (P-201) to storage; control valves (e.g., CV-101), flare network connectivity, recycle / bypass lines, and instrumentation tags (PT-101, TT-101, FT-101) indicating measurement points. The facility may be used to process oil and / or gas. The facility may be a new or existing facility. In an example, the equipment may be or include a pump and / or a heat exchanger.

[0053] The method 500 may also include receiving first data from one or more sensors at the facility, as at 510. The one or more sensors may be coupled to the equipment. In an example, the first data may include temperature (TT-), pressure (PT-), differential pressure (DP-), flow (FT-), level (LT-*), vibration spectra (accelerometers on K-411 A), electrical power and current (e.g., kW / A from VFDs), valve position (% open), ambient weather (e.g., dry-bulb, wind), composition (e.g., GC for gas stream), density (e.g., API / gravity meters), and energy source metadata (e.g., grid vs. gas-turbine).

[0054] The method 500 may also include determining parameters for the equipment based upon the process flow diagram and the first data, as at 515. The parameters may include input parameters, internal parameters, output parameters, design parameters, a physics-based model, or a combination thereof. Examples of the input parameters may include feed flow / composition, inletAttorney Docket No.: IS23.0563-WO-PCTP / T, ambient conditions, control setpoints, utility prices, and current variable frequency drive (VFD) frequency. Examples of the internal parameters may include separator droplet cut size and residence time, compressor polytropic efficiency and map coefficients, heat-exchanger overall U and fouling factor, valve Cv, and pipe roughness / friction factors. Examples of the output parameters may include unit outlet P / T, phase split, component flow rates, power consumption, thermal duty, CO2 emissions, and equipment health score. Examples of the design parameters may include vessel diameter / length / intemals, number of compressor stages and impeller diameter, heatexchanger area / passes, pump impeller trim, and line sizes. The physics-based model may be a thermodynamic model. For example, the physics-based model may include a thermodynamic package and correlations consistent across units (e.g., used by the flowsheet).

[0055] The method 500 may also include selecting a subset of a plurality of models based upon the process flow diagram, as at 520. The models may be generative and interact with one another. Each model corresponds to a different piece of the equipment or a process performed at least partly by the equipment. In an example, the models may include a separator hydraulics model, a compressor performance map model, a heat-exchanger energy balance model, a pipeline hydraulics model, and an emissions estimator, and the subset may include the separator, the compressor, and the air-cooler models.

[0056] The method 500 may also include receiving second data from the one or more sensors, as at 525. The second data may be measured after the first data.

[0057] The method 500 may also include calibrating the subset of models based upon the parameters, the first data, and / or the second data to produce calibrated models, as at 530. The calibration may use a cost function. In one embodiment, calibration minimizes a weighted sum of squared errors between simulated outputs and the corresponding measurements across time and tags. Each error term may be multiplied by a weight that is inversely related to the sensor’s estimated variance (e.g., from a UQ engine), with a small floor so near-zero variances do not dominate. The objective also includes a regularization term that keeps the tuned parameters close to engineering priors. Tunable parameters may include, for example, heat-transfer coefficients, compressor efficiency / map terms, valve Cv, and pipe roughness. Optionally, a sparsity term discourages changing many parameters at once, and a robust loss (e.g., Huber) may be used instead of pure squared error to reduce sensitivity to outliers. The models may be at a facility-based level. The models may be calibrated iteratively.Attorney Docket No.: IS23.0563-WO-PCT

[0058] The method 500 may also include performing a facility simulation using the calibrated models to produce an output, as at 535. The facility simulation may be performed based upon the second data. The facility simulation may include forward-simulating the output, optimizing the output, forecasting the output, or a combination thereof. The facility simulation may be performed in sequential tasks, which are then aggregated to produce an aggregated output. In an example, the sequential tasks may include separator hydraulics —> compressor power estimation cooler duty —> flare load check emissions calculation —> setpoint optimization. Equipment-level results may be aggregated to a facility output (e g., throughput, energy, CO2).

[0059] The method 500 may also include generating a recommendation based upon the output, as at 540. In an example, the recommendation may include repairing and / or replacing the equipment. More particularly, the recommendation may include (i) reduce K-411A VFD frequency from 52.5 Hz to 49.8 Hz to maintain outlet pressure while cutting power -20%; (ii) schedule chemical cleaning or retube E-301 when inferred fouling factor exceeds a threshold; and / or (iii) lower separator temperature setpoint by 3 °C to increase condensate recovery with negligible backpressure impact.

[0060] The method 500 may also include displaying the output and / or the recommendation, as at 545.

[0061] The method 500 may also include performing a facility action based upon and / or in response to the output and / or the recommendation, as at 550. The facility action may be or include generating or transmitting a signal that instructs or causes an automated action to implement the recommendation. The facility action may also or instead include physically implementing the recommendation.

[0062] In an embodiment, the method 500 may also include generating, by a large-language-model (LLM)-based generator, a human-readable set of operating procedures aligned with the recommendation. The operating procedures may be automatically updated in near-real time as third data from the one or more sensors is acquired. The third data may be measured after the second data.

[0063] In an embodiment, the calibrated models may be refined via a federated-learning scheme executed across a plurality of geographically-separated facilities, such that only model parameters or gradients are exchanged between the geographically-separated facilities and raw sensor data remains on-premises to preserve data privacy and comply with data-sovereignty regulations.Attorney Docket No.: IS23.0563-WO-PCT

[0064] In an embodiment, the recommendation may be generated by a reinforcement-learning (RL) agent constrained by a safety envelope derived from hazard-and-operability (HAZOP) studies. In this embodiment, the signal may adjust one or more control setpoints of the equipment in accordance with an RL policy that maximizes a reward function combining production efficiency and safety metrics.

[0065] In one embodiment, the RL agent maximizes a step-by-step reward that:• increases when normalized throughput goes up;• decreases when normalized energy use (kWh) and CO2 emissions go up;• adds a penalty whenever product quality falls below its specification;• discourages abrupt changes in control setpoints and key process variables; and• applies safety penalties that grow as operating conditions approach or cross HAZOP - derived limits, with hard trips ending the episode. The terms may be normalized to plant baselines so the reward is unit-consistent across different equipment and sites.

[0066] In another embodiment, the agent starts from the same base reward and subtracts linear and quadratic penalties for any safety -constraint violation. The penalty multipliers may be updated (e.g., online) so the policy steadily tightens compliance with the HAZOP safety envelope while still optimizing production, energy and emissions.

[0067] In an embodiment, the facility simulation may include co-simulating a subsurface reservoir model and / or a surface-facility digital twin so that optimization of the output simultaneously (i) maximizes hydrocarbon recovery and (ii) minimizes facility energy consumption and associated CO2 emissions.

[0068] In an embodiment, the cost function used for calibrating the subset of models may be dynamically re-weighted by an uncertainty-quantification engine that assigns confidence intervals to sensor signals from each of the one or more sensors and / or adjusts calibration weights according to an estimated measurement uncertainty of the sensor signals.

[0069] In an embodiment, the method 500 may also include detecting a divergence between the aggregated output and the third data from the one or more sensors. The divergence being greater than a predetermined threshold may automatically trigger (i) a root-cause-analysis module to queries a knowledge graph of failure modes for the equipment and / or (ii) generation of a maintenance work order.Attorney Docket No.: IS23.0563-WO-PCT

[0070] In an embodiment, the method 500 may also include synthetically augmenting historical data by sampling from the subset of models to create simulated operating scenarios. The synthetically augmented historical data may be incorporated into subsequent calibration cycles to improve a robustness of the subset of models when true operating data is sparser than a predetermined threshold.

[0071] In an embodiment, the signal may instruct an autonomous robotic actuator to execute at least one maintenance or process-adjustment task identified in the recommendation, thereby reducing a mean time to repair (MTTR) and unplanned downtime of the equipment.

[0072] In an embodiment, a system for performing the method 500 may include (a) a sensor network configured to capture real-time facility data; (b) a data-acquisition and preprocessing layer; (c) a generative-AI engine; and (d) an edge-computing module configured to execute the calibrated models locally with a processing latency not exceeding a predefined threshold, thereby enabling closed-loop control of the equipment.

[0073] Figures 6A-6F illustrate a flowchart of an operation performed by a (e.g., midstream) simulation agent, according to an embodiment. More particularly, Figure 6A shows assets-with- workflows. The agent queries an asset service to list facilities bound to simulation workflows, and it uses these IDs to scope subsequent API calls. Figure 6B shows an asset hierarchy. It retrieves the facility tree and identifies target equipment instances (e.g., “Separator- 101”), preserving instance type and IDs for mapping. Figure 6C shows models. The agent enumerates available models and associated workflows to find a compatible flowsheet for the selected asset. Figure 6D shows model files. It inspects model structure (e.g., Process Equipment. Separator at “ / Separator”) to learn variable paths. Figure 6E shows variable definitions. It pulls canonical input / output variable definitions and tag suggestions to auto-build an IO map. Figure 6F shows matching. It matches plant equipment to model nodes (e.g., substring, fuzzy, or ontology) and records mapping metadata used in later simulations.

[0074] Figures 7A and 7B illustrate tool calls examples performed by the simulation agent, according to an embodiment. More particularly, Figure 7A shows a get equipment inputs tool. The tool returns model-aligned input variables for a given equipment ID, including variable paths and tag associations. Figure 7B shows a request simulation tool. The agent supplies inputs, requests outputs, and receives solver results with values and units. The call is replayable for audit.Attorney Docket No.: IS23.0563-WO-PCT

[0075] Figures 8 and 9 illustrate examples of instructions being received by the simulation agent and responses being generated by the simulation agent, according to an embodiment. More particularly, Figure 8 shows an ESP power what-if. A natural -language request triggers a parameterized simulation; the agent converts “-5% frequency” into VFD Hz, executes a profile, and returns power impact. Figure 9 shows compressor emissions. The agent pulls equipment, accepts motor efficiency and energy source, runs energy / emissions models, and returns annualized CO? with assumptions.Exemplary Computing System

[0076] In some embodiments, the methods of the present disclosure may be executed by a computing system. Figure 10 illustrates an example of such a computing system 1000, in accordance with some embodiments. The computing system 1000 may include a computer or computer system 1001 A, which may be an individual computer system 1001 A or an arrangement of distributed computer systems. The computer system 1001A includes one or more analysis modules 1002 that are configured to perform various tasks according to some embodiments, such as one or more methods disclosed herein. To perform these various tasks, the analysis module 1002 executes independently, or in coordination with, one or more processors 1004, which is (or are) connected to one or more storage media 1006. The processor(s) 1004 is (or are) also connected to a network interface 1007 to allow the computer system 1001 A to communicate over a data network 1009 with one or more additional computer systems and / or computing systems, such as 1001B, 1001C, and / or 1001D (note that computer systems 1001B, 1001C and / or 1001D may or may not share the same architecture as computer system 1001 A, and may be located in different physical locations, e.g., computer systems 1001A and 1001B may be located in a processing facility, while in communication with one or more computer systems such as 1001C and / or 100 ID that are located in one or more data centers, and / or located in varying countries on different continents).

[0077] A processor may include a microprocessor, microcontroller, processor module or subsystem, programmable integrated circuit, programmable gate array, or another control or computing device.

[0078] The storage media 1006 may be implemented as one or more computer-readable or machine-readable storage media. Note that while in the example embodiment of Figure 10 storageAttorney Docket No.: IS23.0563-WO-PCT media 1006 is depicted as within computer system 1001 A, in some embodiments, storage media 1006 may be distributed within and / or across multiple internal and / or external enclosures of computing system 1001A and / or additional computing systems. Storage media 1006 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), BLURAY® disks, or other types of optical storage, or other types of storage devices. Note that the instructions discussed above may be provided on one computer-readable or machine-readable storage medium, or may be provided on multiple computer-readable or machine-readable storage media distributed in a large system having possibly plural nodes. Such computer-readable or machine-readable storage medium or media is (are) considered to be part of an article (or article of manufacture). An article or article of manufacture may refer to any manufactured single component or multiple components. The storage medium or media may be located either in the machine running the machine-readable instructions, or located at a remote site from which machine-readable instructions may be downloaded over a network for execution.

[0079] In some embodiments, computing system 1000 contains one or more method execution module(s) 1008. In the example of computing system 1000, computer system 1001A includes the method execution module 1008. In some embodiments, a single method execution module may be used to perform some aspects of one or more embodiments of the methods disclosed herein. In other embodiments, a plurality of method execution modules may be used to perform some aspects of methods herein.

[0080] It should be appreciated that computing system 1000 is merely one example of a computing system, and that computing system 1000 may have more or fewer components than shown, may combine additional components not depicted in the example embodiment of Figure 10, and / or computing system 1000 may have a different configuration or arrangement of the components depicted in Figure 10. The various components shown in Figure 10 may be implemented in hardware, software, or a combination of both hardware and software, including one or more signal processing and / or application specific integrated circuits.Attorney Docket No.: IS23.0563-WO-PCT

[0081] Further, the steps in the processing methods described herein may be implemented by running one or more functional modules in information processing apparatus such as general purpose processors or application specific chips, such as ASICs, FPGAs, PLDs, or other appropriate devices. These modules, combinations of these modules, and / or their combination with general hardware are included within the scope of the present disclosure.

[0082] Computational interpretations, models, and / or other interpretation aids may be refined in an iterative fashion; this concept is applicable to the methods discussed herein. This may include use of feedback loops executed on an algorithmic basis, such as at a computing device (e.g., computing system 1000, Figure 10), and / or through manual control by a user who may make determinations regarding whether a given step, action, template, model, or set of curves has become sufficiently accurate for the evaluation of the subsurface three-dimensional geologic formation under consideration.

[0083] The foregoing description, for purposes of explanation, has been described with reference to specific embodiments. However, the illustrative discussions above are not intended to be exhaustive or limiting to the precise forms disclosed. Many modifications and variations are possible in view of the above teachings. Moreover, the order in which the elements of the methods described herein are illustrated and described may be re-arranged, and / or two or more elements may occur simultaneously. The embodiments were chosen and described in order to best explain the principles of the disclosure and its practical applications, to thereby enable others skilled in the art to best utilize the disclosed embodiments and various embodiments with various modifications as are suited to the particular use contemplated.

Claims

Attorney Docket No.: 1S23.0563-WO-PCTCLAIMSWhat is claimed is:

1. A method for using generative artificial intelligence (Al) to produce a framework for a simulation workflow, the method comprising: receiving a process flow diagram for equipment at a facility; receiving first data related to the equipment from one or more sensors; determining parameters for the equipment based upon the process flow diagram and the first data; receiving second data from the one or more sensors; calibrating a subset of models based upon the parameters, the first data, and the second data to produce calibrated models; and performing a facility simulation using the calibrated models based upon the second data to produce an output.

2. The method of claim 1, wherein the facility is used to process oil and / or gas, wherein the facility is a new facility, and wherein the equipment comprises a pump, a heat exchanger, or both.

3. The method of claim 1, wherein the parameters comprise input parameters, internal parameters, output parameters, design parameters, and a physics-based model, and wherein the physics-based model comprises a thermodynamic model.

4. The method of claim 1, further comprising selecting the subset of the models from a plurality of models based upon the process flow diagram, wherein the models are generative and interact with one another, and wherein each model corresponds to a different piece of the equipment or a process performed at least partly by the equipment.

5. The method of claim 1, wherein the calibration uses a cost function, wherein the models are at a facility -based level, and wherein the models are calibrated iteratively.Attorney Docket No.: IS23.0563-WO-PCT6. The method of claim 1 , wherein the facility simulation is performed in sequential tasks, which are then aggregated to produce an aggregated output.

7. The method of claim 1, further comprising generating a recommendation based upon the output.

8. The method of claim 7, wherein the recommendation is to repair or replace the equipment.

9. The method of claim 8, further comprising displaying the output and the recommendation.

10. The method of claim 8, further comprising performing an action to implement the recommendation.

11. A computing system, comprising: one or more processors; and a memory system comprising one or more non-transitory computer-readable media storing instructions that, when executed by at least one of the one or more processors, cause the computing system to perform operations, the operations comprising: receiving a process flow diagram for equipment at a facility; receiving first data related to the equipment from one or more sensors; determining parameters for the equipment based upon the process flow diagram and the first data; receiving second data from the one or more sensors, wherein the second data is measured after the first data; calibrating a subset of models based upon the parameters, the first data, and the second data to produce calibrated models; performing a facility simulation using the calibrated models based upon the second data to produce an output; and generating a recommendation based upon the output.Attorney Docket No.: IS23.0563-WO-PCT12. The computing system of claim 11 , wherein the operations further comprise generating, by a large-language-model (LLM)-based generator, a human-readable set of operating procedures aligned with the recommendation, wherein the operating procedures are automatically updated in near-real time as third data from the one or more sensors is acquired, and wherein the third data is measured after the second data.

13. The computing system of claim 11, wherein the calibrated models are refined via a federated-learning scheme executed across a plurality of geographically-separated facilities, such that only model parameters or gradients are exchanged between the geographically-separated facilities and raw sensor data remains on-premises to preserve data privacy and comply with data-sovereignty regulations.

14. The computing system of claim 11, wherein the recommendation is produced by a reinforcement-learning (RL) agent constrained by a safety envelope derived from hazard-and-operability (HAZOP) studies, and wherein the recommendation is to adjust one or more control setpoints of the equipment in accordance with an RL policy that maximizes a reward function combining production efficiency and safety metrics.

15. The computing system of claim 11, wherein performing the facility simulation comprises co-simulating a subsurface reservoir model and a surface-facility digital twin so that optimization of the output simultaneously (i) maximizes hydrocarbon recovery and (ii) minimizes facility energy consumption and associated CO2 emissions.

16. A non-transitory computer-readable medium storing instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations, the operations comprising: receiving a process flow diagram for equipment at a facility; receiving first data related to the equipment from one or more sensors; determining parameters for the equipment based upon the process flow diagram and the first data; receiving second data from the one or more sensors;Attorney Docket No.: IS23.0563-WO-PCT calibrating a subset of models based upon the parameters, the first data, and the second data to produce calibrated models; and performing a facility simulation in sequential tasks to produce an aggregated output, wherein the facility simulation is performed based upon the second data using the calibrated models.

17. The non-transitory computer-readable medium of claim 16, wherein the calibration uses a cost function that is dynamically re-weighted by an uncertainty-quantification engine that assigns confidence intervals to sensor signals from each of the one or more sensors and adjusts calibration weights according to an estimated measurement uncertainty of the sensor signals.

18. The non-transitory computer-readable medium of claim 16, wherein the operations further comprise detecting a divergence between the aggregated output and third data from the one or more sensors, wherein the divergence being greater than a predetermined threshold automatically triggers (i) a root-cause-analysis module to queries a knowledge graph of failure modes for the equipment and (ii) generation of a maintenance work order.

19. The non-transitory computer-readable medium of claim 16, wherein the operations further comprise synthetically augmenting historical data by sampling from the subset of models to create simulated operating scenarios, wherein the synthetically augmented historical data is incorporated into subsequent calibration cycles to improve a robustness of the subset of models when true operating data is sparser than a predetermined threshold.

20. The non-transitory computer-readable medium of claim 16, wherein the recommendation instructs an autonomous robotic actuator to execute at least one maintenance or process-adjustment task, thereby reducing a mean time to repair (MTTR) and unplanned downtime of the equipment.

Images