Machine learning approaches for descriptive, predictive, and directive equipment operation

Abstract

The digital twin of a facility defines the relationships between the different components of the facility and the facility's record system. Information from various monitoring systems of the facility is related to events by the digital twin of the facility. Use the operation history information of the facility to train a machine learning model. The trained machine learning model facilitates operations at the facility by providing descriptive information, predictive information, and / or directive information regarding the operation(s) at the facility.

Description

Technical Field

[0001] Cross - Reference to Related Applications This application claims the benefit of U.S. Provisional Application No. 63 / 338,563, filed on May 5, 2022, entitled "MACHINE LEARNING APPROACH FOR DESCRIPTIVE, PREDICTIVE, AND PRESCRIPTIVE FACILITY OPERATIONS", which is hereby incorporated by reference in its entirety.

[0002] The present disclosure generally relates to the field of using machine learning approaches to facilitate facility operations.

Background Art

[0003] Various monitoring systems can be used to monitor operations in a facility and solve problems. Data collected by different monitoring systems may be siloed in different databases, and the use of such data to facilitate facility operations is difficult and may be time - consuming.

Summary of the Invention

[0004] The present disclosure relates to facilitating facility operations. Operation history information and / or other information of the facility may be obtained. The operation history information of the facility may be obtained based on a digital twin of the facility and / or other information. The digital twin of the facility may define relationships between components of the facility. A machine learning model may be trained using the operation history information and / or other information of the facility. The trained machine learning model can facilitate one or more operations in the facility by outputting descriptive information, predictive information, prescriptive information, and / or other information regarding the operation(s) in the facility. The trained machine learning model may be stored in a storage medium.

[0005] Equipment scenario information and / or other information may be obtained. The equipment scenario information may define a scenario of a given operation on the equipment. The equipment scenario information may be input into a trained machine learning model. The trained machine learning model may output descriptive information, predictive information, directive information, and / or other information regarding a given operation on the equipment.

[0006] A system for equipment operation may comprise one or more electronic storage devices, one or more processors, and / or other components. The electronic storage device may store information related to the equipment, operation history information, information related to the operation history on the equipment, information related to the digital twin of the equipment, information related to the components of the equipment, information related to the relationships between the components of the equipment, information related to the machine learning model, information related to the training of the machine learning model, information related to the usage method of the machine learning model, and / or other information.

[0007] The processor(s) may be configured by machine-readable instructions. Execution of the machine-readable instructions may cause the processor(s) to facilitate equipment operation. The machine-readable instructions may include one or more computer program components. The computer program components may include one or more of an operation history component, a training component, a storage component, a scenario component, an equipment operation component, and / or other computer program components.

[0008] The operation history component may be configured to obtain operation history information and / or other information of the equipment. The operation history information of the equipment may be obtained based on the digital twin of the equipment and / or other information. The digital twin of the equipment may define the relationships between the components of the equipment.

[0009] In some embodiments, the digital twin may output operation history information based on the relationships between the components of the equipment and / or other information.

[0010] In some embodiments, the operation history information of the facility may include process control information, alarm information, bypass information, safety information, operator action information, and / or other information. Process control information, alarm information, bypass information, safety information, operator action information, and / or other information related to an event may be correlated for a machine learning model(s) by a digital twin.

[0011] In some embodiments, process control information, alarm information, bypass information, safety information, operator action information, and / or other information related to an event may be correlated based on a piping and instrumentation diagram, a characteristic factor diagram, and / or other information.

[0012] In some embodiments, the correlation of process control information, alarm information, bypass information, safety information, and operator action information related to an event based on a piping and instrumentation diagram may include generating a graph model of the facility based on the piping and instrumentation diagram and / or other information, and correlating process control information, alarm information, bypass information, safety information, and operator action information related to the event being executed based on the graph model of the facility.

[0013] In some embodiments, the graph model of the facility may include nodes of physical components of the facility and nodes of control components of the facility. The graph model of the facility may include different types of edges between the nodes to represent physical and logical connections between corresponding components of the facility. Physical connections between components of the facility may include process lines between components of the facility. Logical connections between components of the facility may include electrical connections and / or input / output connections between components of the facility.

[0014] The training component may be configured to train one or more machine learning models. The machine learning model(s) may be trained using operation history information of the facility and / or other information. The trained machine learning model(s) can facilitate one or more operations in the facility. The trained machine learning model(s) can facilitate the operation(s) in the facility by outputting descriptive information, predictive information, instruction information, and / or other information regarding the operation(s) in the facility.

[0015] In some embodiments, the machine learning model(s) may include one or more sequence models.

[0016] The memory component may be configured to store the trained machine learning model(s). The trained machine learning model(s) may be stored in one or more storage media.

[0017] In some embodiments, the trained machine learning model can perform one or more classification tasks.

[0018] In some embodiments, the trained machine learning model can perform one or more regression tasks.

[0019] The scenario component may be configured to obtain facility scenario information and / or other information. The facility scenario information may define a scenario of one or more operations in the facility.

[0020] The facility operation component may be configured to input the facility scenario information and / or other information into the trained machine learning model(s). The trained machine learning model(s) may output descriptive information, predictive information, and / or instruction information regarding the operation(s) in the facility. The trained machine learning model(s) may output descriptive information, predictive information, and / or instruction information regarding the scenario of the operation(s) in the facility.

[0021] In some embodiments, one or more automated operations at the facility may be performed based on instruction information and / or other information regarding the operation(s) at the facility.

[0022] In some embodiments, the facility operation component may be configured to provide a visualization of descriptive information, predictive information, and / or instruction information regarding the operation(s) at the facility. The facility operation component may be configured to provide a visualization of descriptive information, predictive information, and / or instruction information regarding a scenario of the operation(s) at the facility.

[0023] These and other objects, features, and characteristics of the systems and / or methods disclosed herein, as well as the manner of operation and functions of the related elements and combinations of components of the structures, and the economies of manufacture, will become more apparent from the following description and the appended claims, when considered in conjunction with the accompanying drawings. All of them form a part of this specification, and like reference numerals in the various figures indicate corresponding parts. However, it should be clearly understood that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the invention. As used in the specification and claims, the singular forms "a", "an", and "the" include the plural referents unless the context clearly dictates otherwise.

Brief Description of the Drawings

[0024]

Figure 1

Figure 2A

Figure 2B

Figure 3

Figure 4

Figure 5

Best Mode for Carrying Out the Invention

[0025] The present disclosure relates to facilitating facility operation. A digital twin of a facility defines the relationships between different components of the facility and the facility's record system. Information from various monitoring systems of the facility is associated with events by the digital twin of the facility. Machine learning models are trained using the operation history information of the facility. The trained machine learning models facilitate operation at the facility by providing descriptive information, predictive information, and / or instructional information regarding the operation(s) at the facility.

[0026] The methods and systems of the present disclosure may be implemented by and / or in a system such as system 10 shown in FIG. 1. System 10 may include one or more of a processor 11, an interface 12 (e.g., a bus, a wireless interface), an electronic storage device 13, a display 14, and / or other components. Operation history information and / or other information of the facility may be obtained by processor 11. The operation history information of the facility may be obtained based on the digital twin of the facility and / or other information. The digital twin of the facility may define the relationships between the components of the facility and the record system of the facility. The machine learning model may be trained by processor 11 using the operation history information and / or other information of the facility. The trained machine learning model may facilitate one or more operations at the facility by outputting descriptive information, predictive information, instructional information, and / or other information regarding the operation(s) at the facility. The trained machine learning model may be stored in a storage medium by processor 11.

[0027] Facility scenario information and / or other information may be obtained by processor 11. The facility scenario information may define a scenario for a given operation at the facility. The facility scenario information may be input to the trained machine learning model by processor 11. The trained machine learning model may output descriptive information, predictive information, instructional information, and / or other information regarding a given operation at the facility.

[0028] The electronic memory device 13 may be configured to include an electronic memory medium that electronically stores information. The electronic memory device 13 may store software algorithms, information determined by the processor 11, remotely received information, and / or other information that enables the system 10 to function properly. For example, the electronic memory device 13 may store information related to the facility, operation history information, information related to the operation history at the facility, information related to the digital twin of the facility, information related to the components of the facility, information related to the relationships between the components of the facility, information related to the recording system of the facility, information related to the machine learning model, information related to the training of the machine learning model, information related to the usage method of the machine learning model, and / or other information.

[0029] The display 14 may refer to an electronic device that provides a visual presentation of information. The display 14 may include a color display and / or a non-color display. The display 14 may be configured to visually present information. The display 14 can use one or more graphical user interfaces / to present information within one or more graphical user interfaces. For example, the display 14 can present information related to the facility, operation history information, information related to the operation history at the facility, information related to the digital twin of the facility, information related to the components of the facility, information related to the relationships between the components of the facility, information related to the recording system of the facility, information related to the machine learning model, information related to the training of the machine learning model, information related to the usage method of the machine learning model, and / or other information.

[0030] Facilities may refer to locations where one or more specific activities occur. Facilities may include equipment for performing one or more activities. Facilities may include equipment for achieving one or more functions. For example, facilities may include oil platforms, oil rigs, offshore platforms, refineries, or oil and / or gas production platforms for extracting and / or processing resources (such as hydrocarbons) in subterranean rock formations. Other types of facilities are contemplated.

[0031] Process upsets may refer to disruptions (e.g., interruptions, failures, deviations, malfunctions) in the operation of a facility. A facility may be equipped with automated tools and / or manual tools to address process upsets in the facility. For example, a facility may be equipped with process control loops to automatically respond to process upsets and / or to reduce the instability of operations caused by process upsets. If a process upset is not appropriately addressed, a process alarm may prompt action by an operator of the facility. If a process upset is not addressed by a manual action by the operator, other alarms may be triggered and an automatic safety device action may be activated to partially and / or fully shut down the facility (e.g., to prevent a catastrophic failure). Such shutdown events can be costly and destructive.

[0032] A facility may be equipped with multiple monitoring systems for monitoring processes, equipment, operator actions, conditions, and / or other aspects of the operation of the facility. Different monitoring layers may be used to monitor and troubleshoot different aspects of the operation of the facility. For example, a facility may include individual monitoring of process control, alarms, bypass actions, and instrumentation protection systems. Information collected by these separate monitoring systems may be maintained separately and used separately for different purposes.

[0033] The present disclosure provides a machine learning-based tool that provides descriptive information, predictive information, and / or instructional information regarding facility operation. The machine learning-based tool can improve the reliability of the facility and reduce outages by connecting information from separate monitoring systems (siloed systems) to enable more efficient prioritization and decision-making. Information from separate monitoring systems may be contextualized and correlated using a digital twin of the facility. The contextualization and correlation of the information enables the use of machine learning models for process automation and operator response to process disturbances. The machine learning model may be trained using the operation history information of the facility. The machine learning model may digitize the knowledge / experience of the operator from the operation history information. The machine learning model may be used to describe what is happening in the facility, predict what will happen in the facility (e.g., predict the response of the facility), and / or instruct the actions to be taken by the operator. The machine learning model may be used to automate actions in the facility.

[0034] FIG. 3 shows an exemplary process 300 for facilitating operation in a facility. In process 300, the machine learning model 312 may be trained using the operation history information 302 of the facility. The operation history information 302 may include operation history information from process control 322, alarms 324, instrumentation protection systems 326, bypasses 328, and / or operator actions 330. Different portions of the operation history information 302 may be monitored, tracked, and / or stored separately. Different portions of the operation history information 302 may not be correlated.

[0035] The digital twin 340 of the facility may be used to contextualize and correlate different parts of the operation history information 302. Information from process control 322, alarms 324, instrumentation protection systems 326, bypasses 328, and / or operator actions 330 may be contextualized and correlated by the digital twin 340 of the facility. The digital twin 340 may identify, extract, and package information related to events from control 322, alarms 324, instrumentation protection systems 326, bypasses 328, and / or operator actions 330 for use in training the machine learning model 312. The machine learning model 312 may be trained using the operation history information 302 provided by the digital twin to perform classification tasks and / or regression tasks.

[0036] Based on the relationships between components of the facility and / or the facility's recording system(s), the digital twin 340 may identify, extract, and package information related to events from control 322, alarms 324, instrumentation protection systems 326, bypasses 328, and / or operator actions 330. The digital twin 340 may include piping and instrumentation diagram (P&ID) information digitized in an equipment and instrumentation ontomap format. The P&ID may include diagrams showing piping and process equipment together with instrumentation equipment (measuring instruments used to indicate, measure, and record physical quantities) and control devices. The P&ID may include diagrams showing the interconnections between process equipment and the instrumentation equipment used to control the process. The equipment ontomap may define which components are associated with a particular component and / or which components are associated with a particular event. The equipment ontology may provide information about the connections, interactions, dependencies, and / or strength of the hierarchy between components of the facility. Using the equipment ontomap, information related to events from control 322, alarms 324, instrumentation protection systems 326, bypasses 328, and / or operator actions 330 may be identified, extracted, and packaged for use in training the machine learning model 312.

[0037] The digital twin 340 may facilitate the integration of information from separate monitoring systems to improve the efficiency of facility monitoring. The process 300 may facilitate operations at the facility, such as by reducing the risk of equipment stoppages, improving the lifespan of equipment, and / or facilitating the prioritization of maintenance. The process 300 may digitalize the operator's knowledge / experience by contextualizing operator actions through the use of the digital twin, associate control loops, equipment, alarms, and bypass systems to reflect real-world relationships, enable the identification of the root causes of problems at the facility, and / or otherwise facilitate operations at the facility.

[0038] Facility scenario information 314 may be input into the machine learning model 312. The facility scenario information 314 may define a scenario of one or more operations at the facility. The machine learning model 312 outputs descriptive information, predictive information, and / or directive information regarding the operation(s) at the facility. That is, the machine learning model 312 outputs descriptive information, predictive information, and / or directive information regarding the scenario of the operation(s) defined by the facility scenario information 314. The descriptive information regarding the operation may include information that describes the operation (e.g., the machine learning model 312 identifies the operation(s) and / or event(s) occurring at the facility). The predictive information regarding the operation may include information that predicts what will happen at the facility (e.g., the machine learning model 312 predicts the result of the operation(s) at the facility, predicts the event(s) that follow / occur as a result of the operation(s)). The directive information regarding the operation may include information that recommends / requests what steps / actions should be taken at the facility (e.g., the machine learning model 312 recommends how the operation(s) at the facility should be changed, the machine learning model 312 is used to automate the change of the operation(s) at the facility). Other uses of the machine learning model 312 for facilitating facility operations are contemplated.

[0039] Returning to FIG. 1, the processor 11 may be configured to provide information processing capabilities in the system 10. Accordingly, the processor 11 may include one or more of a digital processor, an analog processor, a digital circuit designed to process information, a central processing unit, a graphics processing unit, a microcontroller, an analog circuit designed to process information, a state machine, and / or other mechanisms for electronically processing information. The processor 11 may be configured to execute one or more machine-readable instructions 100 for facilitating facility operation. The machine-readable instructions 100 may include one or more computer program components. The machine-readable instructions 100 may include an operation history component 102, a training component 104, a storage component 106, a scenario component 108, a facility operation component 110, and / or other computer program components.

[0040] The operation history component 102 may be configured to obtain facility operation history information and / or other information. The facility operation history information may include information regarding operations performed on the facility. The facility operation history information may include information regarding operations that occurred on the facility. The facility operation history information may include time-series data related to operations performed on the facility. The facility operation history information may include a set of operation characteristics measured, sensed, detected, and / or recorded on the facility at different times. For example, the facility operation history information may include timestamped information regarding the occurrence of events, sensor readings, operator actions, tolerances, and / or bypass and safety actions.

[0041] The facility operation history information can characterize the operations that occurred on the facility. The operation history information may include information regarding operation characteristics in the facility. The operation characteristics of the facility may refer to the characteristics of the facility during operation (e.g., characteristics inside and / or around the facility, characteristics of the equipment of the facility). The operation characteristics of the facility may refer to the attributes, qualities, configurations, parameters, and / or other characteristics of the objects / devices inside, within, and / or around the facility during operation.

[0042] The operation history information of the equipment can characterize the operation of the equipment by including information that defines, describes, demarcates, identifies, associates, quantizes, reflects, specifies, and / or otherwise characterizes the values of the attributes, qualities, configurations, parameters, and / or other characteristics of the objects / devices inside, within, and / or around the equipment during operation. The operation history information of the equipment can characterize the operation of the equipment by including information from which the values of the attributes, qualities, configurations, parameters, and / or other characteristics of the objects / devices inside, within, and / or around the equipment during operation can be determined. Other types of operation history information are contemplated.

[0043] Obtaining the operation history information may include one or more of accessing, acquiring, analyzing, determining, inspecting, generating, identifying, loading, ascertaining, measuring, opening, receiving, searching, reviewing, selecting, storing, and / or otherwise obtaining the operation history information. The operation history component 102 may obtain the operation history information from one or more locations. For example, the operation history component 102 may obtain the operation history information from a storage location such as the electronic storage device 13, the electronic storage device of a device accessible via a network, and / or other locations. The operation history component 102 may obtain the operation history information from one or more hardware components (e.g., computing devices, sensors) and / or one or more software components (e.g., software running on a computing device). The operation history component 102 may obtain the operation history information from multiple databases / storage locations. For example, different types of operation history information may be stored in different databases / storage locations, and a portion of the operation history information related to a particular event(s) may be obtained from different databases / storage locations.

[0044] The operation history information of the equipment may be obtained based on the digital twin of the equipment and / or other information. The digital twin of the equipment may refer to a virtual representation or digital model of the equipment. The digital twin may function as a real-time digital counterpoint of the equipment and / or the operations / processes occurring in the equipment. The digital twin of the equipment may define the relationships between the components of the equipment. The components of the equipment may refer to the devices within the equipment, the materials used in the equipment, and / or other components of the equipment. The relationships between the components of the equipment may include connections, interactions, dependencies, hierarchies, and / or other relationships between the components. The relationships between the components of the equipment may be used to obtain the operation history information of the equipment. The digital twin of the equipment may define one or more recording systems of the equipment. The recording system of the equipment may refer to an information storage and retrieval system that is a reliable source of data related to the equipment. The recording system of the equipment may refer to a collection of related and / or contextualized information about the equipment, such as design documents, equipment databases, time series data, inspection records, maintenance records, turnaround information, change management, and / or other information about the equipment, and / or the connections between them. The information may be stored in different systems / databases, and the information stored in different systems / databases may be interconnected via the digital twin. The information stored in different systems / databases may be accessed via the digital twin.

[0045] In some embodiments, the equipment operation history information may include process control information, alarm information, bypass information, safety information, operator action information, and / or other information. The process control information may refer to information from a process control system. The process control information may refer to information that defines and / or characterizes a process (e.g., an operation, a part of an operation) in the equipment and / or the control of the process in the equipment. The alarm information may refer to information from an alarm management system. The alarm information may refer to information that defines and / or characterizes an alarm triggered in the equipment and / or the operation of the alarm in the equipment. The bypass information may refer to information from a bypass management system. The bypass information may refer to information that defines and / or characterizes a bypass in the equipment (e.g., the location of the bypass, the equipment affected by the bypass, the process under the bypass). The safety information may refer to information from an instrumentation protection system (IPS). The safety information may refer to information that defines and / or characterizes a safety condition, the triggering / activation of the safety condition, and / or the operation of SIS equipment. The operator action information may refer to information regarding operation actions in the equipment. The operator action information may refer to information that defines and / or characterizes actions taken by one or more operators in the equipment.

[0046] Process control information, alarm information, bypass information, safety information, operator action information, and / or other information related to an event may be correlated for training one or more machine learning models by a digital twin. The correlation of different information may include establishing / determining the relationship between different information. An event may refer to the occurrence of one or more things. An event may refer to one or more changes in the equipment. For example, an event may include changes in pressure, temperature, and / or flow rate, the startup / stop of some equipment, the triggering of an alarm, an operator action, a change in an operation, and / or other changes in the equipment. A machine learning model may be trained using information correlated to the event. The digital twin may be used to determine which information is related to the event and which information is not related to the event.

[0047] For example, using a digital twin, some of the operation history information of an event may be identified, extracted, and / or packaged based on the relationships between components of a facility and / or the facility's record system(s). The digital twin may include a device ontology map that defines which components are associated with a particular component and / or which components are associated with a particular event. The device ontology map may be used to determine which information is relevant to an event, and the relevant information of the event may be used as the operation history information of the facility to train a machine learning model.

[0048] In some embodiments, process control information, alarm information, bypass information, safety information, operator action information, and / or other information related to an event may be correlated based on a piping and instrumentation diagram, a characteristic factor diagram, and / or other information. The piping and instrumentation diagram and the characteristic factor diagram may be used to establish relationships between different types of information. For example, the interconnection of process equipment and instrumentation equipment used to control a process in a piping and instrumentation diagram may be used to correlate different information to an event. The characteristic factor diagram may define specific sequential relationships between components, such as how components may be affected / changed based on the occurrence of a particular event (e.g., which components can be activated in response to an alarm that stops a device / facility), and the sequential relationships between components may be used to correlate different information to an event.

[0049] Figure 4 shows an overview 400 of an exemplary instrumentation protection layer and operator actions. As shown in overview 400, a piping and instrumentation diagram (P&ID) and a cause and effect diagram (C&E) may be used to establish relationships between information from different monitoring systems. The following different monitoring applications may exist between process disturbances (e.g., undesirable operating conditions such as pressure spikes, equipment malfunctions, etc.) and process safety incidents. That is, (1) automatic process control that helps regulate and stabilize the process, (2) alarms to alert the operator, (3) operator actions that manage the process disturbance and return the equipment to normal operation, and (4) activation of an instrumentation protection system to stop the equipment if a safety condition is violated. The piping and instrumentation diagram may be used to establish relationships between information from process control and alarms (e.g., associating alarms with process control loop performance), and the cause and effect diagram may be used to establish relationships between information from alarms and the instrumentation protection system. Other information (e.g., inspection records, design documents) may be used to establish relationships between information from different monitoring systems.

[0050] In some embodiments, the digital twin may output equipment operation history information based on relationships between components of the equipment, the equipment's recording system(s), and / or other information. The digital twin itself may be able to determine which portions of the operation history information are relevant to an event, and those relevant portions of the operation history information may be output by the digital twin for use in training a machine learning model.

[0051] In some embodiments, based on the piping and instrumentation diagram, the correlation of different parts of the operation history information of the equipment related to the specific event being executed (e.g., process control information, alarm information, bypass information, safety information, operator action information, and / or other information) may include: (1) the generation of a graph model of the equipment based on the piping and instrumentation diagram and / or other information, and (2) the correlation of different parts of the operation history information of the equipment related to the specific event being executed based on the graph model of the equipment and / or other information. That is, in order to determine whether different parts of the operation history information are related to a specific event (e.g., for training a machine learning model), a graph model of the equipment may be generated, and the graph model may be used to determine different parts of the operation history information related to the specific event.

[0052] The graph model may refer to a model that represents the components of the equipment using nodes and the connections between the components using edges between the nodes. The graph model of the equipment may be generated based on the piping and instrumentation diagram of the equipment and / or other information. For example, the piping and instrumentation diagram of the equipment may be converted into a graph model of the equipment. For example, the piping and instrumentation diagram of the equipment may be scanned, the component blocks of the piping and instrumentation diagram may be converted into nodes, and the lines between the component blocks may be converted into edges. Other generations of the graph model are contemplated.

[0053] The graph model of a facility may include nodes of the physical components of the facility, the control components of the facility, and / or other components of the facility. The graph model may include different types of nodes for different types of components of the facility. The physical components of the facility may refer to the parts, devices, and / or other components of the facility that process, contain, move, and / or interact with materials in other ways, operate, and / or are operated upon in the facility. The physical components of the facility may refer to the parts, devices, and / or other components of the facility that receive signals from the control components of the facility and operate according to the received signals (e.g., commands transmitted by the received signals). For example, the physical components of a fluid facility may include pumps, actuators, motors, valves, doors, and / or other physical components that can control the flow rate of the fluid.

[0054] The control components of the facility may refer to the parts, devices, and / or other components of the facility that operate and / or are operated upon to control the operation of the physical components of the facility. The control components of the facility may refer to the parts, devices, and / or other components of the facility that transmit signals to the physical components of the facility and control the operation of the physical components of the facility. The control components of the facility may refer to the parts, devices, and / or other components of the facility that receive signals from the sensors of the facility to monitor the operation of the physical components of the facility. For example, the control components of a fluid facility may include logic blocks, and the logic blocks may perform sensor measurements of the facility and transmit signals to pumps, actuators, and / or motors in response to deviations in the flow rate of the fluid in the facility from normal operating conditions to control the flow rate of the fluid in the facility.

[0055] The equipment may include separate and independent control components to maintain safe operation of the equipment. For example, the equipment may include a distributed control system and an instrumentation protection system that operate independently of each other to restore deviations in the operation of the equipment and stop the operation as necessary. Different types of control components may be represented by the same or different types of nodes in the graph model.

[0056] The graph model of the equipment may include different types of edges between nodes to represent different connections between the corresponding components of the equipment. The connections between the components of the equipment may include physical connections, logical connections, and / or other connections. Physical connections may be represented by one type of edge, and logical connections may be represented by another type of edge.

[0057] The physical connection between the components of the equipment may refer to a connection that conveys physical material between different components of the equipment. For example, the physical connection between the components of a fluid equipment may include one or more process lines between the components of the fluid equipment. The process line may include interconnected piping components such as tubes, pipes, pressure hoses, valves, separators, traps, flanges, fittings, gaskets, strainers, and / or other components. The physical connection between the components of the equipment may refer to a connection that physically links the components of the equipment. For example, the physical connection between the components of a fluid equipment may include a physical link between an actuator and a valve of the equipment.

[0058] The logical connection between the components of the equipment may refer to a connection that logically links the components of the equipment. The logical connection between the components of the equipment may refer to a connection that transmits information between different components of the equipment. For example, the local connection between the components of a fluid equipment may include one or more electrical connections (e.g., transmitting a sensor signal, transmitting a command signal, transmitting an information signal) and / or one or more input / output connections (e.g., facilitating communication) between the components of the equipment.

[0059] FIG. 5 shows an exemplary graph model 500 of a facility. The graph model 500 may represent a part of a larger graph model of the facility. The graph model 500 may include nodes 502, 512, 514, 522, 524, 526 of the physical components of the facility and nodes 532, 534, 536, 542 of the control components of the facility. The solid edges between the nodes of the graph model 500 may represent physical connections between the corresponding components. The dashed edges between the nodes of the graph model 500 may represent logical connections between the corresponding components. For example, node 502 may represent a heat exchanger, node 514 may represent a valve of the heat exchanger, and node 526 may represent an actuator of the valve. Nodes 532, 534, 536 may represent control systems / blocks that can control the actuator (by sending signals to the actuator) to operate the valve. The control systems / blocks represented by nodes 532, 534 can communicate with each other. The control system / block represented by node 536 may send signals to and / or receive signals from the heat exchanger represented by node 502. The control systems / blocks represented by nodes 532, 534, 536 may be part of a distributed control system for the facility to keep the heat exchanger and other components of the facility operating.

[0060] The facility may include an instrumentation protection system represented by node 542. The instrumentation protection system can operate independently of the distributed control system to prevent the facility from operating in a dangerous state. For example, if the distributed control system fails to return an operating deviation to normal operating conditions (e.g., the operation approaches or exceeds a safety limit), the instrumentation protection system may stop the operation in the facility. The instrumentation protection system may provide an automatic shutdown response in the facility for safety violations.

[0061] In some embodiments, different types of physical connections and / or different types of logical connections may be represented by different types of edges. For example, a logical connection to an instrumentation protection system may be represented by one type of edge, while a logical connection to a distributed control system may be represented by another type of edge.

[0062] The operation history information of the facility may include a large amount of data regarding the operations being performed on the facility. For example, the operation history information may include information regarding actions taken by multiple operators on the facility. When an event occurs in the facility, one or more operators may take actions to address the event, and one or more operators not related to the event may also take actions. For example, when an alarm is triggered, one or more operators may take actions to address the alarm, while one or more other operators may take actions unrelated to the alarm. To use the operation history information for machine learning training, it may be necessary to correlate information related to the event. That is, different parts of the history information that are related to each other may need to be correlated for use in training a machine learning model.

[0063] A graph model may be used to correlate information related to an event (e.g., a change in operation parameters, a trigger of an alarm). The operation history information of the facility may be filtered using time to identify information related to the event. For example, the operation history information may be filtered to identify information about actions taken after an alarm is triggered and before the alarm (e.g., an operation deviation / departure) is resolved. Such filtering can identify operation history information that may be temporally related to the event.

[0064] After time filtering, a graph model may be used to identify operation history information related to an event. The event may be associated with a specific node, and operation history information related to components of a facility that are at a certain distance (e.g., hops) from the node associated with the event may be identified as being related to the event. For example, referring to FIG. 5, an alarm may be triggered by a component (e.g., a control system / block, a sensor) represented by node 536. Nodes within a threshold distance range from node 536 may be identified, and operation history information of actions performed on the corresponding components may be identified as being related to the alarm. Using such identification of operation history information, a repository of actions taken for various events in a facility may be generated. Actions taken by one operator or multiple operators may be correlated with specific events in the facility.

[0065] In some embodiments, different types of edges between nodes of the graph model may be treated the same in distance (e.g., hop) calculations. For example, whether a traversed edge represents a physical connection or a logical connection may not be important when determining the distance traversed. In some embodiments, different types of edges between nodes of the graph model may be treated differently in distance calculations. For example, traversal of an edge representing a physical connection may be weighted more or less than traversal of an edge representing a logical connection. As another example, traversal of an edge representing a particular type of physical or logical connection may be weighted more or less than traversal of an edge representing another type of physical or logical connection. For example, traversal of an edge representing a logical connection to an instrumentation protection system may be weighted more or less than traversal of an edge representing a logical connection to a distributed control system. In some embodiments, the weights of the edges may be customized. For example, an edge representing a particular connection may be assigned a different weight than other edges.

[0066] The results of actions performed on the equipment may be analyzed and correlated with specific actions performed on the equipment. For example, for individual actions and / or combinations of actions taken for a particular type of event, the result(s) of the action(s) may be correlated with the action(s). The results between different actions / action combinations may be compared to determine which action(s) should be proposed / recommended to the operator and / or which action(s) should be automatically executed. For example, the actions may be ranked using the time taken by the action to resolve an operational deviation / drift and the magnitude of the change in the operational parameters due to the action. For example, the actions may be ranked based on the results using how quickly the operational deviation / drift was resolved by the action and the impact of the action on the operation of the equipment (e.g., the amount by which temperature, flow rate, pressure, etc. changed due to the action(s)). The correlation between the actions taken on the equipment and the results of the actions may be used to train one or more machine learning models, and the machine learning model(s) may be used to propose / recommend or automate operator actions based on events occurring in the equipment.

[0067] The training component 104 may be configured to train one or more machine learning models. The machine learning model(s) may be trained using the operation history information of the facility and / or other information. The machine learning model may be trained to perform a classification task and / or a regression task. That is, the trained machine learning model may perform one or more classification tasks or one or more regression tasks to generate an output. The trained machine learning model(s) can facilitate one or more operations in the facility. The trained machine learning model(s) may facilitate operations in the facility by outputting descriptive information, predictive information, instruction information, and / or other information regarding the operation(s) in the facility. The descriptive information may include information about what is happening in the facility (e.g., identification of operations / events occurring in the facility). The predictive information may include information about what will happen in the facility (e.g., prediction of events that will occur in the facility). The instruction information may include information about what steps / actions should be taken in the facility (e.g., recommendations on how the operator should change the operation(s), automatically changing the operation(s) in the facility to prevent the facility from stopping).

[0068] Training the machine learning model may include facilitating learning by the machine learning model by processing examples through the machine learning model. Pairing the operation history information with information about the desired output type may be provided to the machine learning model as examples of inputs and desired results, respectively. The operation history information may be used as the type of input received by the trained machine learning model, and the information about the desired output type paired with the operation history information may be used as the type of output generated by the machine learning model.

[0069] For example, to train a machine learning model to output descriptive information, operation history information related to an operation / event may be paired with the identification / description of the operation / event for training the machine learning model. The operation history information related to the operation / event may be paired with the identification / description of what is happening in the facility for training the machine learning model. By processing such pairing of information via the machine learning model, the machine learning model may be able to learn patterns of operation history information correlated with specific operations / events in the facility.

[0070] To train a machine learning model to output prediction information, operation history information related to an operation / event may be paired with the identification / description of an event that will occur later in the facility. The operation history information related to the operation / event may be paired with the identification / description of what happens in the facility for training the machine learning model. By processing such pairing of information via the machine learning model, the machine learning model may be able to learn patterns of operation history information correlated with specific future events in the facility.

[0071] To train a machine learning model to output instruction information, operation history information related to an operation / event may be paired with the identification / description of steps / actions performed (e.g., by an operator, automatically) in the facility. The operation history information related to the operation / event may be paired with the identification / description of steps / actions taken in the facility for training the machine learning model. By processing such pairing of information via the machine learning model, the machine learning model may be able to learn patterns of operation history information correlated with specific steps / actions to be taken in the facility.

[0072] In some embodiments, the pairing of operation history information with specific steps / actions to be performed on the facility can digitize the operator's historical actions. For example, the operator actions for various operations / events may be recorded along with the results of those actions. The operation history information may be paired with specific steps / actions based on the desired results. That is, the results of previous operator actions may be used to guide how to train a machine learning model. The operation history information may be paired with the results of previous operator actions to enable the machine learning model to provide likely results of the steps / actions output by the machine learning model. For example, in addition to recommending specific steps / actions that the operator of the facility should take, the machine learning model may output the probability(ies) of the results by performing the steps / actions recommended to the operator. The machine learning model may output multiple steps / actions that the operator can take, along with the likely results of the different steps / actions.

[0073] In some embodiments, the machine learning model(s) may include one or more sequence models. A sequence model may refer to a machine learning model that receives a data sequence as input and / or outputs a data sequence. For example, a sequence model may refer to a machine learning model that receives time-series data as input and / or outputs time-series data. For example, the machine learning model(s) may include a Markov model. The use of other types of machine learning models is contemplated.

[0074] The memory component 106 may be configured to store the trained machine learning model(s). The trained machine learning model(s) may be stored in one or more non-transitory memory media and / or other memory media. For example, the memory component 106 may store the trained machine learning model(s) / the information defining the trained machine learning model(s) in the electronic storage device 13, the electronic storage device of a device accessible via a network, and / or a storage location such as other locations. The trained machine learning model(s) may be stored for use in facilitating the operation of the facility. The trained machine learning model(s) may be used (1) when identifying what is happening in the facility (e.g., the output descriptive information identifying the operations / events occurring in the facility), (2) when predicting what will happen in the system (e.g., the output prediction information identifying the events occurring in the facility), and / or (3) when recommending / guiding what actions should be taken in the facility (e.g., the output instruction information recommending specific actions for the operator to take, the output instruction information controlling how to control the automatic operation in the facility). The trained machine learning model(s) may be stored for search / execution when facilitating the operation of the facility.

[0075] The scenario component 108 may be configured to obtain facility scenario information and / or other information. The facility scenario information may define one or more operation scenarios in the facility. The scenario(s) of the operation(s) in the facility may refer to an instance where one or more operations are occurring in the facility. The scenario(s) of the operation(s) may include a moment or a duration. The scenario(s) of the operation(s) may include the occurrence of one or more events during the operation(s). The facility scenario information may define the scenario(s) of the operation(s) in the facility by including information defining one or more contents, qualities, attributes, features, and / or other aspects of the scenario(s) of the operation(s) in the facility.

[0076] For example, the equipment scenario information may define the scenario of the operation(s) performed on the equipment by including information characterizing the operation(s) performed on the equipment. The equipment scenario information may include information regarding the operating characteristics of the equipment at a specific time (instant, duration). The equipment scenario information may include real-time equipment scenario information. The real-time equipment scenario information may refer to the equipment scenario information that defines the current operation(s) on the equipment. For example, the real-time equipment scenario information may characterize the operating characteristics of the equipment currently reported by one or more sensors and / or the operating characteristics of the equipment measured within a threshold time (e.g., the operating characteristics measured in the past minutes / hours / days). The equipment scenario information of the equipment may include information of the same type as the operation history information of the equipment. Other types of equipment scenario information are contemplated.

[0077] Obtaining equipment scenario information may include one or more of accessing, acquiring, analyzing, determining, inspecting, generating, identifying, loading, ascertaining, measuring, opening, receiving, searching, reviewing, selecting, storing, and / or obtaining by other means. Scenario component 108 may obtain equipment scenario information from one or more locations. For example, scenario component 108 may obtain equipment scenario information from a storage location such as electronic storage device 13, an electronic storage device of a device accessible via a network, and / or other locations. Scenario component 108 may obtain equipment scenario information from one or more hardware components (e.g., computing devices, sensors) and / or one or more software components (e.g., software executed on a computing device). Scenario component 108 may obtain equipment scenario information from multiple databases / storage locations. For example, different types of equipment scenario information may be stored in different databases / storage locations, and a portion of the equipment scenario information related to a particular event(s) / scenario(s) may be obtained from different databases / storage locations. Information related portions from different monitoring systems may be obtained as equipment scenario information using a digital twin of the equipment.

[0078] Equipment operation component 110 may be configured to input equipment scenario information and / or other information into a trained machine learning model(s). The trained machine learning model(s) may use the equipment scenario information to generate an output. The trained machine learning model(s) may output descriptive information, predictive information, and / or directive information regarding the equipment, and / or other information regarding an operation(s) (scenario(s) of the operation(s)).

[0079] For example, a trained machine learning model may output descriptive information regarding the operation(s) of a facility by outputting information that describes the operation(s), event(s), and / or other states in the facility. For example, based on the facility scenario information input into the trained machine learning model, the trained machine learning model may output that column flooding is occurring / has occurred in the facility. The trained machine learning model may output details regarding the column flooding, such as the location and / or timing of the column flooding, the facility component(s) / equipment affected by the column flooding, and / or the source / root cause of the column flooding.

[0080] A trained machine learning model may output predictive information regarding the operation(s) of a facility by outputting information that predicts what will happen in the facility. For example, based on the facility scenario information input into the trained machine learning model, the trained machine learning model may output a prediction regarding the time until a facility component / equipment fails due to column flooding. The trained machine learning model may output details regarding the prediction, such as which component(s) / equipment will fail, the predicted timing of the failure, and / or the predicted extent of the failure.

[0081] A trained machine learning model may output directive information regarding the operation(s) of a facility by outputting information that details which step(s) / action(s) should be taken in the facility. For example, based on the facility scenario information (e.g., pump trip) input into the trained machine learning model, the trained machine learning model may output the optimal step(s) / action(s) that one or more operators should take to prevent further disruption in the facility and restore the facility to its normal operating state. In some embodiments, one or more automated operations in the facility may be performed based on the directive information and / or other information regarding the operation(s) of the facility. That is, rather than outputting directive information to an operator to guide actions in restoring normal operation of the facility, the operation of the facility may be automatically changed in accordance with the directive information.

[0082] In some embodiments, the inputs and outputs of multiple trained machine learning models may be chained together. For example, the facility scenario information may be input into a machine learning model trained to output descriptive information and / or predictive information. The descriptive information and / or predictive information output by the trained machine learning model may be used as the facility scenario information input into a machine learning model trained to output instruction information. The machine learning model trained to output instruction information may utilize information output by other machine learning model(s) to instruct what steps / actions should be taken in the facility.

[0083] In some embodiments, the facility operation component 110 may be configured to provide a visualization of descriptive information, predictive information, and / or instruction information regarding the operation(s) in the facility (regarding the scenario(s) of the operation(s)). The visualization of the descriptive information, predictive information, and / or instruction information may include a visual / graphic representation of the descriptive information, predictive information, and / or instruction information. The visualization of the descriptive information, predictive information, and / or instruction information may be provided on the display 14 (e.g., within one or more graphical user interfaces, to one or more operators). For example, the descriptive information, predictive information, and / or instruction information may be modeled in three-dimensional space together with a three-dimensional modeling of the facility to visualize what is happening in the facility, what is predicted to happen in the facility, and / or what steps / actions should be executed in the facility. Other visualizations are also contemplated.

[0084] Embodiments of the present disclosure may be implemented in hardware, firmware, software, or any suitable combination thereof. Aspects of the disclosure may be implemented as instructions stored on a machine-readable medium, which may be read and executed by one or more processors. A machine-readable medium may include any mechanism for storing or transmitting information in a form readable by a machine (e.g., a computing device). For example, a tangible computer-readable storage medium may include read-only memory, random access memory, magnetic disk storage media, optical storage media, flash memory devices, etc., and a machine-readable transmission medium may include propagated signals such as carrier waves, infrared signals, digital signals, etc. Firmware, software, routines, or instructions may be described herein in terms of particular exemplary aspects and embodiments of the present disclosure, and in terms of performing particular actions.

[0085] In some embodiments, some or all of the functions attributed herein to system 10 may be provided by external resources not included in system 10. External resources may include hosts / sources of information, computing, and / or processing, and / or other providers of information, computing, and / or processing external to system 10.

[0086] Processor 11, electronic storage device 13, and display 14 are shown in FIG. 1 as being connected to interface 12, but may facilitate interactions between any components of system 10 using any communication medium. One or more components of system 10 may communicate with each other through wired communication, wireless communication, or both. For example, one or more components of system 10 may communicate with each other through a network. For example, processor 11 may communicate wirelessly with electronic storage device 13. By way of non-limiting example, wireless communication may include one or more of radio communication, Bluetooth communication, Wi-Fi communication, cellular communication, infrared communication, or other wireless communication. Other types of communication are also contemplated by the present disclosure.

[0087] The processor 11, the electronic memory device 13, and the display 14 are shown as a single entity in FIG. 1, but this is for illustrative purposes only. One or more of the components of the system 10 may be included within a single device or may be distributed across multiple devices. For example, the processor 11 may include multiple processing units. These processing units may be physically located within the same device, or the processor 11 may represent processing functions that operate in cooperation with multiple devices. The processor 11 may be separate from and / or a part of one or more components of the system 10. The processor 11 may be configured to execute one or more components by some combination of software, hardware, firmware, software, hardware, and / or firmware, and / or by other mechanisms for configuring processing capabilities on the processor 11.

[0088] The computer program components are shown in FIG. 1 as being located in the same place within a single processing unit, but it should be understood that one or more of the computer program components may be located remotely from other computer program components. The computer program components are described as performing or being configured to perform operations, but the computer program components may include instructions that the processor 11 and / or the system 10 may be programmed to perform the operations.

[0089] Although the computer program components are described herein as being implemented through the processor 11 via the machine-readable instructions 100, this is merely for ease of reference and is not intended to be limiting. In some embodiments, one or more functions of the computer program components described herein may be implemented via hardware (e.g., dedicated chips, field programmable gate arrays) rather than software. One or more functions of the computer program components described herein may be implemented in software, or in hardware, or in a combination of software and hardware.

[0090] The description of the functions provided by the various computer program components described herein is for illustrative purposes and is not intended to be limiting, as any of the computer program components may provide more or fewer functions than those described. For example, one or more of the computer program components may be removed, and some or all of their functions may be provided by other computer program components. As another example, the processor 11 may be configured to execute one or more additional computer program components that may perform some or all of the functions attributed to one or more of the computer program components described herein.

[0091] The electronic storage medium of the electronic storage device 13 may be provided integrally (i.e., substantially non-removably) with one or more components of the system 10 and / or may be provided as a removable storage device connectable to one or more components of the system 10 via, for example, a port (e.g., a USB port, a FireWire port, etc.) or a drive (e.g., a disk drive, etc.). The electronic storage device 13 may include one or more of an optically readable storage medium (e.g., an optical disk, etc.), a magnetically readable storage medium (e.g., a magnetic tape, a magnetic hard drive, a floppy drive, etc.), a charge-based storage medium (e.g., an EPROM, an EEPROM, a RAM, etc.), a solid-state storage medium (e.g., a flash drive, etc.), and / or other electronically readable storage media. The electronic storage device 13 may be a separate component within the system 10 or the electronic storage device 13 may be provided integrally with one or more other components of the system 10 (e.g., the processor 11). Although the electronic storage device 13 is shown as a single entity in FIG. 1, this is for illustrative purposes only. In some embodiments, the electronic storage device 13 may include a plurality of storage units. These storage units may be physically disposed within the same device or the electronic storage device 13 may represent the storage functions of a plurality of devices operating in cooperation.

[0092] FIGS. 2A and 2B show methods 200, 250 for facilitating the operation of the equipment. The operations of the methods 200, 250 shown below are for illustrative purposes. In some embodiments, the methods 200, 250 may be achieved using one or more additional operations not described and / or without using one or more of the operations described. In some embodiments, two or more of the operations may be performed substantially simultaneously.

[0093] In some embodiments, the method 200, 250 may be implemented in one or more processing devices (e.g., a digital processor, an analog processor, a digital circuit designed to process information, a central processing unit, a graphics processing unit, a microcontroller, an analog circuit designed to process information, a state machine, and / or other mechanisms for electronically processing information). The one or more processing devices may include one or more devices that execute some or all of the operations of the method 200 in response to instructions electronically stored on one or more electronic storage media. The one or more processing devices may include one or more devices configured through hardware, firmware, and / or software to be specifically designed to execute one or more of the operations of the method 200.

[0094] Referring to 2A and method 200, in operation 202, operation history information and / or other information of the facility may be obtained. The operation history information of the facility may be obtained based on the digital twin of the facility and / or other information. The digital twin of the facility may define the relationships between the components of the facility and the recording system of the facility. In some embodiments, operation 202 may be performed by a processor component that is the same as or similar to the operation history component 102 (shown in FIG. 1 and described herein).

[0095] In operation 204, the machine learning model may be trained using the operation history information and / or other information of the facility. The trained machine learning model can facilitate one or more operations in the facility by outputting descriptive information, predictive information, directive information, and / or other information regarding the operation(s) in the facility. In some embodiments, operation 204 may be performed by a processor component that is the same as or similar to component 104 (shown in FIG. 1 and described herein).

[0096] In operation 206, the trained machine learning model may be stored in a memory medium. In some embodiments, operation 206 may be performed by a processor component that is the same as or similar to the memory component 106 (shown in FIG. 1 and described herein).

[0097] Referring to 2B and method 250, in operation 252, facility scenario information and / or other information may be obtained. The facility scenario information may define a scenario of a given operation at the facility. In some embodiments, operation 252 may be performed by a component that is the same as or similar to the scenario component 108 (shown in FIG. 1 and described herein).

[0098] In operation 254, the facility scenario information may be input into the trained machine learning model. The trained machine learning model may output descriptive information, predictive information, instructional information, and / or other information regarding a given operation at the facility. In some embodiments, operation 254 may be performed by a processor component that is the same as or similar to the facility operation component 110 (shown in FIG. 1 and described herein).

[0099] The system(s) and / or method(s) of the present disclosure have been described in detail for purposes of illustration based on what is currently considered to be the most practical and preferred embodiments. However, such details are for illustrative purposes only, and the present disclosure is not limited to the disclosed embodiments. On the contrary, it is intended to cover modifications and equivalent configurations within the spirit and scope of the appended claims. For example, it should be understood that the present disclosure is intended to combine one or more features of any one embodiment with one or more features of any other embodiment whenever possible.

Claims

1. A system for facilitating equipment operation, comprising: one or more physical processors, which, by machine-readable instructions, obtain operation history information of the equipment based on a digital twin of the equipment, wherein the digital twin of the equipment defines relationships between components of the equipment and a recording system of the equipment, and the obtaining; train a machine learning model using the operation history information of the equipment, wherein the trained machine learning model facilitates the one or more operations on the equipment by outputting descriptive information, predictive information, and / or directive information regarding the one or more operations on the equipment, and the training; store the trained machine learning model in a storage medium The system is configured to perform the above.

2. The one or more physical processors, by the machine-readable instructions, obtain equipment scenario information, wherein the equipment scenario information defines a scenario of a given operation on the equipment, and the obtaining; input the equipment scenario information into the trained machine learning model, wherein the trained machine learning model outputs the descriptive information, the predictive information, and / or the directive information regarding the given operation on the equipment, and the inputting The system according to claim 1, further configured to perform the above.

3. The system according to claim 1, wherein the trained machine learning model performs a classification task.

4. The system according to claim 1, wherein the trained machine learning model performs a regression task.

5. The one or more physical processors, by the machine-readable instructions, are further configured to provide visualization of the descriptive information, the predictive information, and / or the directive information regarding the one or more operations on the equipment. The system according to claim 1.

6. One or more automatic operations on the equipment are performed based on the directive information regarding the one or more operations on the equipment. The system according to claim 1.

7. The system according to claim 1, wherein the digital twin outputs the operation history information of the equipment based on the relationships between the components of the equipment and the recording system of the equipment.

8. The system according to claim 1, wherein the machine learning model includes a sequence model. Claim 9 wherein the operation history information of the equipment includes process control information, alarm information, bypass information, safety information, and operator action information, and the process control information, the alarm information, the bypass information, the safety information, and the operator action information related to an event are correlated by the digital twin for a machine learning model The system according to claim 1. Claim 10 The system according to claim 9, wherein the process control information, the alarm information, the bypass information, the safety information, and the operator action information related to the event are correlated based on a piping and instrumentation diagram and a characteristic factor diagram. Claim 11 The correlation of the process control information, the alarm information, the bypass information, the safety information, and the operator action information related to the event based on the piping and instrumentation diagram is generation of a graph model of the equipment based on the piping and instrumentation diagram, and the correlation of the process control information, the alarm information, the bypass information, the safety information, and the operator action information related to the event being executed based on the graph model of the equipment The system according to claim 10, comprising. Claim 12 The system according to claim 11, wherein the graph model of the equipment includes nodes for physical components of the equipment and control components of the equipment. Claim 13 The system according to claim 12, wherein the graph model of the equipment includes different types of edges between nodes to represent physical and logical connections between corresponding components of the equipment. Claim 14 wherein the physical connection between components of the equipment includes a process line between components of the equipment, and the logical connection between components of the equipment includes an electrical connection and / or an input / output connection between components of the equipment The system according to claim 13. Claim 15 A method for facilitating equipment operation, comprising obtaining operation history information of the equipment based on a digital twin of the equipment, wherein the digital twin of the equipment defines relationships between components of the equipment and a recording system of the equipment, obtaining the operation history information of the equipment, Training a machine learning model using the operation history information of the equipment, wherein the trained machine learning model promotes the one or more operations on the equipment by outputting descriptive information, predictive information, and / or instruction information regarding the one or more operations on the equipment, the training; Storing the trained machine learning model in a storage medium; Obtaining equipment scenario information, wherein the equipment scenario information defines a scenario of a given operation on the equipment, obtaining the equipment scenario information; Inputting the equipment scenario information into the trained machine learning model, wherein the trained machine learning model outputs the descriptive information, the predictive information, and / or the instruction information regarding the given operation on the equipment, inputting the equipment scenario information; The method including the above.

Images