Substation Equipment Condition Assessment and Early Warning System and Method Based on Digital Twin Platform

Abstract

A substation equipment status assessment and early warning system and method based on a digital twin platform includes the following steps: parsing the digital twin model to obtain basic equipment information and creating an equipment information mapping table; matching equipment types to select assessment algorithms and rules, and generating an equipment status assessment model; parsing inspection system data to match equipment information points; forming an equipment inspection information point table; instantiating equipment assessment objects and matching information points, algorithm parameters, and rules; initiating status assessment using a sliding window and event triggering mechanism to generate an assessment result file; analyzing historical data to predict equipment status and issuing alarms when anomalies occur. This method establishes an assessment model for complex primary and secondary equipment in substations, abstracts and concretizes multi-source data such as primary equipment, secondary equipment, monitoring, inspection, and operation and maintenance systems, and adopts flexible combinations of algorithms and evaluation rules to shield the differences between equipment and the diversity of algorithms, thereby improving the accuracy of the assessment and early warning function and the standardization of assessment results.

Description

Technical Field

[0001] This invention belongs to the field of power system dispatch automation, particularly to intelligent substation monitoring systems and digital twin systems, and provides a method for unified status analysis, evaluation and early warning of power equipment. Background Technology

[0002] With the development of smart grids and the construction of digital twin substations, the deep integration of advanced digital technologies and business operations will accelerate further. Digital transformation and the construction of digital grids will continue to deepen, urgently requiring improvements in the efficiency and effectiveness of substation operation and maintenance support systems. Technological innovation is needed to drive the replacement of manual labor, effectively alleviating the contradictions of insufficient grid operation and maintenance personnel, weakened equipment control, weak technical support capabilities, and the inability of existing operation and maintenance management models to adapt to the rapid growth of equipment. Various power grid companies have made various attempts to achieve real-time monitoring of substation equipment operation status, timely detection of potential faults, and timely repair and prevention. Currently, the assessment of substation equipment health status often deals with specific types of equipment, using independent algorithms and evaluation systems. These methods fail to fully utilize the massive amounts of correlated information data from smart substations based on digital twin platforms, and fail to effectively establish a unified equipment health model to accurately reflect the health status of primary and secondary equipment. The assessment algorithms, algorithm parameters, and evaluation rules are scattered and independent, lacking an efficient and integrated system assessment method. This makes it difficult to meet the requirements of power users to understand the real-time operating status of primary and secondary equipment, analyze equipment operating trends, and achieve intelligent operation and maintenance for early accident prevention. Summary of the Invention

[0003] To address the shortcomings of existing technologies, this invention provides a substation equipment status assessment and early warning method based on a digital twin platform. The aim is to leverage the existing digital twin system platform and technology in smart substations, using a standardized substation information model to uniformly construct assessment models for primary and secondary equipment within the substation and instantiate assessment objects. Through panoramic multi-dimensional data information and advanced assessment and early warning algorithms, the method achieves real-time and accurate analysis, evaluation, and early warning of equipment status, providing a solid foundation for realizing intelligent operation and maintenance.

[0004] To facilitate understanding of the technical solution of this invention, the technical terms that may appear in this invention are explained as follows:

[0005] SCD (Substation Configuration Description) substation configuration description file: contains information such as voltage level model, bay model and primary equipment topology model, geographical area model within the substation, primary equipment model, secondary equipment model, and auxiliary equipment model. Auxiliary equipment includes environmental monitoring, security, fire protection monitoring terminals, interlocking, and gateway devices.

[0006] Equipment resource information configuration file: used for information exchange between the station monitoring system and the patrol system. It mainly includes monitoring index number, equipment name, equipment type, and all remote signaling and telemetry information that need to be linked. Its format and content follow the standard definition.

[0007] CIM / E Power System Data Markup Language: This is a language based on the CIM (Common Information Model) standard and uses XML to mark up power system data. It is characterized by its simplicity, efficiency, and applicability to power systems.

[0008] The specific solution of the present invention is as follows:

[0009] A method for substation equipment condition assessment and early warning based on a digital twin platform, the method comprising the following steps:

[0010] (1) Create a basic equipment information mapping table. Parse, extract and form a set of detailed monitoring data points related to the primary and secondary equipment to be evaluated from the model, monitoring system and intelligent inspection system in the digital twin substation SCD file, and create a basic equipment information mapping table.

[0011] (2) By matching the equipment manufacturer, type and model, select the evaluation algorithm and evaluation rules corresponding to the equipment to be evaluated, associate the parameter combination and equipment parameters, load the independent variable point information feature template and calculate the associated parameter template, and create an equipment status evaluation model;

[0012] (3) Parse the relevant field information of the equipment resource information configuration file of the intelligent inspection system, combine the area model and monitoring system information in the SCD file, match the inspection points and the corresponding primary and secondary equipment, and obtain the name of the equipment to be monitored and evaluated, the name of the information point, the type and the monitoring point ID, and generate the equipment inspection information point table according to the equipment name;

[0013] Based on the equipment resource information configuration file, the information on switchyards, bays, intelligent devices, and monitoring systems that have been parsed from the SCD file will be combined. By matching the names and IED names with the inspection points and primary and secondary equipment, the names, information point names, types, and monitoring point IDs of the equipment to be monitored and evaluated will be obtained. An equipment inspection information point table will be created according to the equipment name.

[0014] (4) Based on the equipment basic information mapping table, comprehensively obtain the status assessment model of the corresponding equipment, match the information points in the equipment inspection information point table, the parameters used in the assessment algorithm, the score criteria, the evaluation rule criteria, and the equipment maintenance information and family information, etc., to instantiate the equipment assessment object for the equipment to be assessed;

[0015] (5) The evaluation process is started using both sliding time window and event triggering methods to determine the current status of the equipment and generate a standard format evaluation result file;

[0016] (6) Predict the future status of the equipment based on the historical data of the equipment monitoring information points, and issue an alarm signal when the equipment is in an unhealthy state.

[0017] The present invention further includes the following preferred embodiments.

[0018] In step (1), the primary equipment topology, primary equipment, secondary equipment, online monitoring, voltage level, interval, geographical area, and equipment ledger model in the SCD file are parsed. The identification, name, model, information, voltage level, interval, connection point, and location relationship of the primary equipment, secondary equipment, and auxiliary equipment are analyzed. The monitoring point table of the secondary equipment itself and the point table of the secondary equipment and the online monitoring equipment associated with the primary equipment are obtained. The manufacturer, type, and model information of the primary and secondary equipment are obtained. The monitoring system measurement point ID is obtained through point reference. Irrelevant points are filtered out to form a set of detailed information points related to the equipment to be monitored and evaluated. The equipment name is used as the key value to create a basic information mapping table of the equipment.

[0019] In step (2), the evaluation algorithm, evaluation rules, family information and operation parameter configuration corresponding to the device to be evaluated are pre-stored in the expert knowledge base;

[0020] For the secondary equipment to be evaluated, the corresponding evaluation algorithms include the hierarchical monitoring information importance algorithm, the rule-based reasoning analysis algorithm, and the operating condition evaluation algorithm based on online / offline hybrid big data.

[0021] For the primary equipment to be evaluated, the corresponding evaluation rules include the evaluation rules for the absolute gas production rate, the evaluation rules for the relative gas production rate, the evaluation rules for the hot spot temperature, the evaluation rules for the aging rate calculation, the evaluation rules for the cumulative lifespan, the evaluation rules for the overload capacity, the evaluation rules for the oil leak identification and analysis, the evaluation rules for the damage analysis, and the evaluation rules for the noise and vibration analysis.

[0022] Obtain the main operating parameters related to the equipment, including rated current, rated voltage, rated short-circuit current, rated current carrying capacity, and rated capacity. Based on the selected evaluation algorithm, load the corresponding algorithm interface library, score criteria, evaluation rules, independent variable point information features, and calculation parameter templates. Use the equipment manufacturer, type, and model as unique identifiers, in the format of manufacturer_type_model, to create an equipment status evaluation model.

[0023] In step (2), after selecting the evaluation algorithm and evaluation rules corresponding to the device to be evaluated, the corresponding independent variable point information feature template and the calculation association parameter combination template are loaded;

[0024] The independent variable point information feature template includes the state quantity information and quantity measurement information of the device to be evaluated, and the calculation association parameter combination template includes the rated current, rated voltage, rated short-circuit current, rated current carrying capacity, and rated capacitance of the device to be evaluated.

[0025] The status information includes critical signals, abnormal signals, and attention signals;

[0026] Among them, serious signals include incorrect equipment parameters, ROM and checksum errors, EEPROM errors, setting errors, CPU communication interruption, device malfunction, RAM errors, flash memory errors, damage, oil leakage, overheating, smoke, and fire.

[0027] Abnormal signals include: setpoint pointer error, SRAM self-test error, FLASH self-test error, soft pressure board error, SV board communication interruption, system setpoint error, EEPROM error, system configuration error, configuration table error, logic table error, system operation abnormality, circuit breaker tripping, inter-interval communication interruption, GOOSE error, setpoint error, inter-interval communication interruption, system operation abnormality, AD error, and MMI communication abnormality.

[0028] Note the following signals: PT disconnection, PT undervoltage, spring not charged alarm, DIO board output abnormality, DIO board communication abnormality, control circuit disconnection, input abnormality, output abnormality, abnormal input input, inconsistent dual position input, input self-test circuit error, output test error, output blockage, output normally open, zero drift not adjusted, scale not adjusted, CT disconnection, zero drift verification error, invalid sampling data, GPS time synchronization abnormality, SV data communication interruption, MU sampling out of sync, zero drift exceeding limit, network interface abnormality, and overload alarm.

[0029] The measured information includes equipment temperature, CPU temperature, power supply voltage, board voltage, board temperature, CPU utilization, optical port received light intensity, optical port transmitted light intensity, port flow, port rate, SV packet loss count, contact temperature, three-phase current, dissolved gas in oil, iron core grounding current, oil level, internal humidity, ambient temperature, and vibration.

[0030] In step (3), the generated inspection point table includes information point descriptions, point evaluation status levels, and the devices associated with the points.

[0031] In step (4), by traversing the equipment basic information mapping table, the equipment status assessment model corresponding to the equipment to be assessed is obtained one by one. Based on the independent variable point information features and calculation parameter templates in the equipment status assessment model, the detailed information point set of the equipment and the information points in the equipment inspection information point table are automatically matched. The monitoring points are automatically selected from the detailed information point set of the equipment to be assessed and the equipment inspection information point table. The monitoring information point / algorithm mapping table and the equipment inspection information point / algorithm mapping table are created. They are then integrated with the calculation parameters, score criterion configuration evaluation rules, equipment family information, and the quality status factors formed by the equipment operation and maintenance information and family information obtained by the operation and maintenance system, and the equipment assessment object to be assessed is instantiated.

[0032] In step (5), the evaluation process is initiated using a dynamic cycle and a sudden event triggering method with the evaluation results as reference factors. The status evaluation of the equipment to be evaluated is carried out online by taking the equipment evaluation object as a unit and using the equipment status evaluation model evaluation algorithm to perform online diagnostic calculations on the monitoring information points of the equipment in the evaluation object. The output value is judged according to the score criteria to obtain the score of each monitoring information point. The scores of all information points are accumulated to obtain the total score of the equipment to be evaluated. Then, the current status of the equipment is determined according to the evaluation rules in the object, and the monitoring information point scores and equipment status evaluation results are saved to the historical database.

[0033] The assessment process generates a standard assessment result file in CIM / E language format by combining the scores of the monitoring information points and the equipment status assessment results.

[0034] In step (6), the historical data of the stored equipment monitoring information points are weighted and averaged according to the three dimensions of time, day and month. The time series prediction analysis method is used to analyze and calculate the predicted scores of all monitoring information points under the equipment and accumulate them to obtain the total predicted score of the equipment. The future status of the equipment is predicted according to the evaluation rules in the equipment evaluation object. When the equipment is in an unhealthy state, an alarm signal is issued.

[0035] This application also discloses a substation equipment condition assessment and early warning system based on a digital twin platform, including an equipment basic information parsing module, an equipment condition assessment model generation module, an equipment inspection information point table generation module, a device to be assessed instantiation module, an equipment condition assessment diagnosis module, and an alarm module, characterized in that:

[0036] The equipment basic information parsing module parses, extracts, and forms a set of detailed monitoring data points related to the primary and secondary equipment to be evaluated from the model, monitoring system, and intelligent inspection system in the digital twin substation SCD file, and creates an equipment basic information mapping table.

[0037] The equipment status assessment model generation module is responsible for querying and matching the corresponding equipment status assessment algorithm based on basic information such as equipment model and parameters, loading the feature templates required by the assessment algorithm based on equipment parameters to determine the input variables required for algorithm assessment, querying and matching the status evaluation rules of the equipment to determine the score criteria for different states, and comprehensively encapsulating the assessment algorithm, input features, status criteria, etc. into an equipment status assessment model.

[0038] The equipment inspection information point table generation module is responsible for associating and matching the regional model information in the SCD file with the equipment information in the monitoring system, determining the primary and secondary equipment corresponding to the intelligent inspection points, and forming an equipment inspection information point table to record the inspection data point information of each device.

[0039] The device instantiation module is responsible for instantiating an evaluation object for each specific physical device, loading the corresponding device status evaluation model for the evaluation object, associating the evaluation object with the monitoring data points and inspection data points in the device basic information mapping table, and completing the binding of the evaluation algorithm and data points for the specific device.

[0040] The equipment status assessment and diagnosis module is responsible for acquiring real-time monitoring data and inspection data of the equipment at certain time intervals or triggered by events, inputting the data into a predefined status assessment model, running an assessment algorithm to calculate the current status of the equipment, and generating a standard format equipment status assessment result file.

[0041] The alarm module is responsible for issuing an alarm if the device is in an abnormal state based on the status assessment results, predicting the future state of the device based on the changing trends of the data points in the status assessment, and issuing an early warning if the prediction result indicates an unhealthy state.

[0042] Compared with existing technologies, the present invention achieves the following beneficial technical effects. Specifically, compared with existing technologies, this method can mask the differences between different equipment and health status assessment methods within a substation, abstracting a universal assessment model that can describe the health status of the equipment, thus realizing an evaluation system with a unified architecture, standardization, flexible scalability, and high assessment accuracy. The main approach employs an information feature element abstraction and generalization technology based on a full model of a substation digital twin system. It extracts information feature element tables related to equipment status from data sources such as primary equipment, secondary equipment, monitoring systems, inspection systems, and operation and maintenance systems. A unified virtual health model is constructed using the corresponding algorithms, algorithm parameters, scoring criteria, and evaluation rules for these feature elements. Available data from various operating systems within the actual substation are combined to form comprehensive equipment information, which is dynamically integrated with the virtual health model. Instantiable evaluation variables are extracted, and optimal algorithms, evaluation rules, and parameters are flexibly matched to instantiate substation primary and secondary equipment health status evaluation objects equivalent to the actual equipment entities. This deep integration and analysis of multi-source, multi-dimensional, heterogeneous data and dynamic evaluation systems across the entire substation enables real-time assessment and prediction of equipment status, creating conditions for building a preventative, intelligent operation and maintenance model. Attached Figure Description

[0043] Figure 1 It is an instantiated device evaluation object;

[0044] Figure 2 This is a diagram of the evaluation results file structure;

[0045] Figure 3 This is a schematic diagram of the substation equipment condition assessment and early warning system. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of this invention. The embodiments described in this application are merely some embodiments of this invention, and not all embodiments. Based on the spirit of this invention, other embodiments obtained by those skilled in the art without creative effort are all within the protection scope of this invention.

[0047] A method for substation equipment condition assessment and early warning based on a digital twin platform, the method comprising the following steps:

[0048] (1) Create a basic equipment information mapping table. Parse, extract and form a set of detailed monitoring data points related to the primary and secondary equipment to be evaluated from the model, monitoring system and intelligent inspection system in the digital twin substation SCD file, and create a basic equipment information mapping table.

[0049] In step (1), the primary equipment topology, primary equipment, secondary equipment, online monitoring, voltage level, interval, geographical area, and equipment ledger model in the SCD file are parsed. The identification, name, model, information, voltage level, interval, connection point, and location relationship of the primary equipment, secondary equipment, and auxiliary equipment are analyzed. The monitoring point table of the secondary equipment itself and the point table of the secondary equipment and the online monitoring equipment associated with the primary equipment are obtained. The manufacturer, type, and model information of the primary and secondary equipment are also obtained. The monitoring system measurement point ID is obtained through point reference. Irrelevant points are filtered out to form a set of detailed information points related to the equipment to be monitored and evaluated. The equipment name is used as the key value to create a basic information mapping table of the equipment.

[0050] (2) By matching the equipment manufacturer, type and model, select the evaluation algorithm and evaluation rules corresponding to the equipment to be evaluated, associate the parameter combination and equipment parameters, load the independent variable point information feature template and calculate the associated parameter template, and create an equipment status evaluation model;

[0051] In step (2), the evaluation algorithm, evaluation rules, family information and operation parameter configuration corresponding to the device to be evaluated are pre-stored in the expert knowledge base;

[0052] For the secondary equipment to be evaluated, the corresponding evaluation algorithms include the hierarchical monitoring information importance algorithm, the rule-based reasoning analysis algorithm, and the operating condition evaluation algorithm based on online / offline hybrid big data.

[0053] For the primary equipment to be evaluated, the corresponding evaluation rules include the evaluation rules for the absolute gas production rate, the evaluation rules for the relative gas production rate, the evaluation rules for the hot spot temperature, the evaluation rules for the aging rate calculation, the evaluation rules for the cumulative lifespan, the evaluation rules for the overload capacity, the evaluation rules for the oil leak identification and analysis, the evaluation rules for the damage analysis, and the evaluation rules for the noise and vibration analysis.

[0054] Obtain the main operating parameters related to the equipment, including rated current, rated voltage, rated short-circuit current, rated current carrying capacity, and rated capacity. Based on the selected evaluation algorithm, load the corresponding algorithm interface library, score criteria, evaluation rules, independent variable point information features, and calculation parameter templates. Use the equipment manufacturer, type, and model as unique identifiers, in the format of manufacturer_type_model, to create an equipment status evaluation model.

[0055] After selecting the evaluation algorithm and evaluation rules corresponding to the equipment to be evaluated, load the corresponding independent variable point information feature template and calculate the associated parameter combination template;

[0056] The independent variable point information feature template includes the state quantity information and quantity measurement information of the device to be evaluated, and the calculation association parameter combination template includes the rated current, rated voltage, rated short-circuit current, rated current carrying capacity, and rated capacitance of the device to be evaluated.

[0057] The status information includes critical signals, abnormal signals, and attention signals;

[0058] Among them, serious signals include incorrect equipment parameters, ROM and checksum errors, EEPROM errors, setting errors, CPU communication interruption, device malfunction, RAM errors, flash memory errors, damage, oil leakage, overheating, smoke, and fire.

[0059] Abnormal signals include: setpoint pointer error, SRAM self-test error, FLASH self-test error, soft pressure board error, SV board communication interruption, system setpoint error, EEPROM error, system configuration error, configuration table error, logic table error, system operation abnormality, circuit breaker tripping, inter-interval communication interruption, GOOSE error, setpoint error, inter-interval communication interruption, system operation abnormality, AD error, and MMI communication abnormality.

[0060] Note the following signals: PT disconnection, PT undervoltage, spring not charged alarm, DIO board output abnormality, DIO board communication abnormality, control circuit disconnection, input abnormality, output abnormality, abnormal input input, inconsistent dual position input, input self-test circuit error, output test error, output blockage, output normally open, zero drift not adjusted, scale not adjusted, CT disconnection, zero drift verification error, invalid sampling data, GPS time synchronization abnormality, SV data communication interruption, MU sampling out of sync, zero drift exceeding limit, network interface abnormality, and overload alarm.

[0061] The measured information includes equipment temperature, CPU temperature, power supply voltage, board voltage, board temperature, CPU utilization, optical port received light intensity, optical port transmitted light intensity, port flow, port rate, SV packet loss count, contact temperature, three-phase current, dissolved gas in oil, iron core grounding current, oil level, internal humidity, ambient temperature, and vibration.

[0062] (3) Parse the relevant field information of the equipment resource information configuration file of the intelligent inspection system, combine the area model and monitoring system information in the SCD file, match the inspection points and the corresponding primary and secondary equipment, and obtain the name of the equipment to be monitored and evaluated, the name of the information point, the type and the monitoring point ID, and generate the equipment inspection information point table according to the equipment name;

[0063] Based on the equipment resource information configuration file, the information on switchyards, bays, intelligent devices, and monitoring systems that have been parsed from the SCD file will be combined. By matching the names and IED names with the inspection points and primary and secondary equipment, the names, information point names, types, and monitoring point IDs of the equipment to be monitored and evaluated will be obtained. An equipment inspection information point table will be created according to the equipment name.

[0064] The generated inspection point table includes information point descriptions, point assessment status levels, and associated equipment.

[0065] (4) Figure 1 As shown, based on the equipment basic information mapping table, the status assessment model of the corresponding equipment is comprehensively obtained, and the information points in the equipment inspection information point table, the parameters used in the assessment algorithm, the score criteria, the evaluation rule criteria, and the equipment maintenance quality information and family information are matched to instantiate the equipment assessment object for the equipment to be assessed.

[0066] In step (4), by traversing the equipment basic information mapping table, the equipment status assessment model corresponding to the equipment to be assessed is obtained one by one. Based on the independent variable point information features and calculation parameter templates in the equipment status assessment model, the detailed information point set of the equipment and the information points in the equipment inspection information point table are automatically matched. The monitoring points are automatically selected from the detailed information point set of the equipment to be assessed and the equipment inspection information point table. The monitoring information point / algorithm mapping table and the equipment inspection information point / algorithm mapping table are created. They are then integrated with the calculation parameters, score criterion configuration evaluation rules, equipment family information, and the quality status factors formed by the equipment operation and maintenance information and family information obtained by the operation and maintenance system, and the equipment assessment object to be assessed is instantiated.

[0067] (5) The evaluation process is initiated using both sliding time window and event triggering methods to determine the current status of the equipment and generate a standard format evaluation result file; the file structure is as follows: Figure 3 As shown.

[0068] In step (5), the evaluation process is initiated using a dynamic cycle and a sudden event triggering method with the evaluation results as a reference factor. The status evaluation of the equipment to be evaluated is carried out online by the monitoring information points of the equipment in the evaluation object through the equipment status evaluation algorithm. The output value is judged according to the score criteria to obtain the score of each monitoring information point. The scores of all information points are accumulated and averaged to obtain the total score of the equipment to be evaluated. Then, the current status of the equipment is determined according to the evaluation rules in the object. The monitoring information point scores and equipment status evaluation results are saved to the historical database.

[0069] The assessment process generates a standard assessment result file in CIM / E language format, based on the monitoring information point scores and equipment status assessment results. The assessment result file is categorized into primary and secondary equipment, with equipment arranged sequentially by type within each category. Each piece of equipment contains assessment result information and assessment information for each monitoring information point. The file structure is designed as follows: Figure 3 As shown.

[0070] (6) Predict the future status of the equipment based on the historical data of the scores of the equipment monitoring information points, and issue an alarm signal when the equipment is in an unhealthy state;

[0071] In step (6), the historical data of the stored equipment monitoring information points are weighted and averaged according to the three dimensions of time, day and month. The time series prediction analysis method is used to analyze and calculate the predicted scores of all monitoring information points under the equipment and accumulate them to obtain the total predicted score of the equipment. The future status of the equipment is predicted according to the evaluation rules in the equipment evaluation object. When the equipment is in an unhealthy state, an alarm signal is issued.

[0072] In a preferred embodiment of the present invention, the specific content of the evaluation result file is defined as follows:

[0073] Attribute Name meaning illustrate Serial Number Serial Number The "#" character is the first character, and the numbers are arranged sequentially from 1. ID index This device's unique digital index Device Index Equipment Name Equipment naming as defined by DL / T 860 and related standards Equipment Description Equipment Description Equipment Chinese Description Evaluation results Status evaluation results Equipment status: Normal / Caution / Abnormal / Critical State score Equipment evaluation score The score obtained by the equipment evaluation algorithm Assessment time Assessment time Time to evaluate equipment

[0074] The monitoring information point is used as the evaluation information node in the evaluation result file: Item::Entity Name, where the "Entity Name" part is the description of the device, and the column definitions are as follows:

[0075]

[0076] This application also discloses an assessment and early warning system for a substation equipment status assessment method based on the aforementioned digital twin platform, including an equipment basic information parsing module, an equipment status assessment model generation module, an equipment inspection information point table generation module, a device to be assessed instantiation module, an equipment status assessment diagnosis module, and an alarm module, characterized in that:

[0077] The equipment basic information parsing module parses, extracts, and forms a set of detailed monitoring data points related to the primary and secondary equipment to be evaluated from the model, monitoring system, and intelligent inspection system in the digital twin substation SCD file, and creates an equipment basic information mapping table.

[0078] The equipment status assessment model generation module is responsible for querying and matching the corresponding equipment status assessment algorithm based on basic information such as equipment model and parameters, loading the feature templates required by the assessment algorithm based on equipment parameters to determine the input variables required for algorithm assessment, querying and matching the status evaluation rules of the equipment to determine the score criteria for different states, and comprehensively encapsulating the assessment algorithm, input features, status criteria, etc. into an equipment status assessment model.

[0079] The equipment inspection information point table generation module is responsible for associating and matching the regional model information in the SCD file with the equipment information in the monitoring system, determining the primary and secondary equipment corresponding to the intelligent inspection points, and forming an equipment inspection information point table to record the inspection data point information of each device.

[0080] The device instantiation module is responsible for instantiating an evaluation object for each specific physical device, loading the corresponding device status evaluation model for the evaluation object, associating the evaluation object with the monitoring data points and inspection data points in the device basic information mapping table, and completing the binding of the evaluation algorithm and data points for the specific device.

[0081] The equipment status assessment and diagnosis module is responsible for acquiring real-time monitoring data and inspection data of the equipment at certain time intervals or triggered by events, inputting the data into a predefined status assessment model, running an assessment algorithm to calculate the current status of the equipment, and generating a standard format equipment status assessment result file.

[0082] The alarm module is responsible for issuing alarms if the equipment status is abnormal based on the status assessment results, predicting the future status of the equipment based on the changing trends of the status assessment data points, and issuing early warnings if the prediction result indicates an unhealthy status. The specific implementation of this invention has been described in detail above. This method is based on a digital twin platform, uses a substation model combined with expert system resources, dynamically creates virtual equipment assessment models according to different algorithms, shields specific assessment algorithms and evaluation standards, integrates multi-source and multi-dimensional information, realizes dynamic prediction of primary and secondary equipment status and early warnings, and outputs standardized assessment results for easy parsing and display by various operating systems.

[0083] This application addresses different equipment and health status assessment methods within substations. This method can mask the differences between equipment, abstracting a universal assessment model that describes equipment health status, thus achieving an evaluation system with a unified architecture, standardization, flexible scalability, and high assessment accuracy. It primarily employs an information feature element abstraction and generalization technology based on a full model of the substation digital twin system. From data sources such as primary equipment, secondary equipment, monitoring systems, inspection systems, and operation and maintenance systems, it extracts information feature element tables related to equipment status. A unified virtual health model is constructed using the corresponding algorithms, algorithm parameters, scoring criteria, and evaluation rule parameters for these feature elements. Available data from various operating systems within the actual substation is combined to form equipment information containing all data, dynamically integrated with the virtual health model. Instantiable assessment variables are extracted, and optimal algorithms, evaluation rules, and parameters are flexibly matched to instantiate substation primary and secondary equipment health status assessment objects equivalent to the actual equipment entities. Deep integration and analysis of multi-source, multi-dimensional heterogeneous data and dynamic evaluation systems across the entire substation enable real-time assessment and prediction of equipment status, creating conditions for building a preventative, intelligent operation and maintenance model.

[0084] This disclosure can be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of this disclosure.

[0085] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0086] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0087] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0088] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. A method for substation equipment condition assessment and early warning based on a digital twin platform, characterized in that, The method includes the following steps: (1) Parse, extract and form a set of detailed monitoring data points related to the primary and secondary equipment to be evaluated from the model, monitoring system and intelligent inspection system in the digital twin substation SCD file, and create a basic information mapping table of equipment; (2) By matching the equipment manufacturer, type and model, select the evaluation algorithm and evaluation rules corresponding to the equipment to be evaluated, load the independent variable point information feature template and calculate the associated parameter template, and create an equipment status evaluation model; The independent variable point information feature template includes the state quantity information and quantity measurement information of the device to be evaluated, and the calculation association parameter template includes the rated current, rated voltage, rated short-circuit current, rated current carrying capacity, and rated capacitance of the device to be evaluated. (3) Parse the relevant field information of the equipment resource information configuration file of the intelligent inspection system, combine the area model and monitoring system information in the SCD file, match the inspection points and the corresponding primary and secondary equipment, and obtain the name of the equipment to be monitored and evaluated, the name of the information point, the type and the monitoring point ID, and generate the equipment inspection information point table according to the equipment name; (4) Obtain the status assessment model of the corresponding equipment according to the equipment basic information mapping table, match the information points in the equipment inspection information point table, the parameters used in the assessment algorithm, the evaluation rules, the equipment maintenance information and family information content, and form an instantiated equipment assessment object to be assessed. (5) The evaluation process is started using both sliding time window and event triggering methods to determine the current status of the equipment and generate a standard format evaluation result file; The status assessment of the equipment to be assessed is initiated by a dynamic cycle and a sudden event triggering method with the assessment results as reference factors. The monitoring information points of the equipment to be assessed are diagnosed and calculated online through the equipment status assessment model. The output value is judged according to the score criteria to obtain the score of each monitoring information point. The scores of all information points are accumulated to obtain the total score of the equipment to be assessed. Then, the current status of the equipment is determined according to the evaluation rules in the object. The monitoring information point scores and equipment status assessment results are saved to the historical database. (6) Predict the future status of the equipment based on the historical data of the equipment monitoring information points, and issue an alarm signal when the equipment is in an unhealthy state.

2. The substation equipment condition assessment and early warning method according to claim 1, characterized in that: In step (1), the primary equipment topology, primary equipment, secondary equipment, online monitoring system, voltage level, interval, geographical area, and equipment ledger model in the SCD file are parsed. The identification, name, model, type, voltage level, interval, connection point, and location relationship of the primary equipment, secondary equipment, and auxiliary equipment are analyzed. The monitoring point table of the secondary equipment itself and the point table of the secondary equipment and the online monitoring equipment associated with the primary equipment are obtained. The manufacturer, type, and model information of the primary and secondary equipment are also obtained. The monitoring system measurement point ID is obtained through point references to form a set of detailed information points related to the equipment to be monitored and evaluated. The equipment name is used as the key value to create a basic information mapping table of the equipment.

3. The substation equipment condition assessment and early warning method according to claim 1, characterized in that: In step (2), the evaluation algorithm, evaluation rules, family information, and operating parameter configuration corresponding to the equipment to be evaluated are pre-stored in the expert knowledge base; For the secondary equipment to be evaluated, the corresponding evaluation algorithms include the hierarchical monitoring information importance algorithm, the rule-based reasoning analysis algorithm, and the operating condition evaluation algorithm based on online / offline hybrid big data. For the primary equipment to be evaluated, the corresponding evaluation rules include the evaluation rules for the absolute gas production rate, the evaluation rules for the relative gas production rate, the evaluation rules for the hot spot temperature, the evaluation rules for the aging rate calculation, the evaluation rules for the cumulative lifespan, the evaluation rules for the overload capacity, the evaluation rules for the oil leak identification and analysis, the evaluation rules for the damage analysis, and the evaluation rules for the noise and vibration analysis.

4. The substation equipment condition assessment and early warning method according to claim 3, characterized in that: The status information includes critical signals, abnormal signals, and attention signals; Among them, serious signals include incorrect equipment parameters, ROM and checksum errors, EEPROM errors, setting errors, CPU communication interruption, device malfunction, RAM errors, flash memory errors, damage, oil leakage, overheating, smoke, and fire. Abnormal signals include: setpoint pointer error, SRAM self-test error, FLASH self-test error, soft pressure board error, SV board communication interruption, system setpoint error, EEPROM error, system configuration error, configuration table error, logic table error, system operation abnormality, circuit breaker tripping, inter-interval communication interruption, GOOSE error, setpoint error, inter-interval communication interruption, system operation abnormality, AD error, and MMI communication abnormality. Note the following signals: PT disconnection, PT undervoltage, spring not charged alarm, DIO board output abnormality, DIO board communication abnormality, control circuit disconnection, input abnormality, output abnormality, abnormal input input, inconsistent dual position input, input self-test circuit error, output test error, output blockage, output normally open, zero drift not adjusted, scale not adjusted, CT disconnection, zero drift verification error, invalid sampling data, GPS time synchronization abnormality, SV data communication interruption, MU sampling out of sync, zero drift exceeding limit, network interface abnormality, and overload alarm.

5. The substation equipment condition assessment and early warning method according to claim 4, characterized in that: The measured information includes equipment temperature, CPU temperature, power supply voltage, board voltage, board temperature, CPU utilization, optical port received light intensity, optical port transmitted light intensity, port flow, port rate, SV packet loss count, contact temperature, three-phase current, dissolved gas in oil, iron core grounding current, oil level, internal humidity, ambient temperature, and vibration.

6. The substation equipment condition assessment and early warning method according to claim 1, characterized in that: In step (3), the generated inspection point table includes information point descriptions, point evaluation status levels, and the devices associated with the points.

7. The substation equipment condition assessment and early warning method according to claim 1, characterized in that: In step (4), by traversing the equipment basic information mapping table, the equipment status assessment model corresponding to the equipment to be assessed is obtained one by one. Based on the independent variable point information features and calculation parameter templates in the equipment status assessment model, the detailed information point set of the equipment and the information points in the equipment inspection information point table are automatically matched. Monitoring points are selected from the detailed information point set of the equipment to be assessed and the equipment inspection information point table. Monitoring information point / algorithm mapping table and equipment inspection information point / algorithm mapping table are created. The calculation parameters, evaluation rules, equipment family information corresponding to the assessment algorithm, and equipment operation and maintenance information obtained from the operation and maintenance system are loaded to instantiate the equipment to be assessed.

8. The substation equipment condition assessment and early warning method according to claim 7, characterized in that: The scores of the monitoring information points and the equipment status assessment results are used to generate a standard assessment result file in CIM / E language format.

9. The substation equipment condition assessment and early warning method according to claim 1, characterized in that: In step (6), the historical data of the stored equipment monitoring information points are weighted and averaged according to the three dimensions of time, day and month. The time series prediction analysis method is used to analyze and calculate the predicted scores of all monitoring information points under the equipment and accumulate them to obtain the total predicted score of the equipment. The future status of the equipment is predicted according to the evaluation rules in the equipment evaluation object. When the equipment is in an unhealthy state, an alarm signal is issued.

10. A substation equipment condition assessment and early warning system based on a digital twin platform, comprising an equipment basic information parsing module, an equipment condition assessment model generation module, an equipment inspection information point table generation module, a device to be assessed instantiation module, an equipment condition assessment diagnosis module, and an alarm module, characterized in that: The equipment basic information parsing module parses, extracts, and forms a set of detailed monitoring data points related to the primary and secondary equipment to be evaluated from the model, monitoring system, and intelligent inspection system in the digital twin substation SCD file, and creates an equipment basic information mapping table. The equipment status assessment model generation module is responsible for querying and matching the corresponding equipment status assessment algorithm based on the equipment model and basic parameter information, loading the feature templates required by the assessment algorithm based on the equipment parameters to determine the input variables required for the algorithm assessment, querying and matching the status evaluation rules of the equipment to determine the score criteria for different states, and comprehensively encapsulating the assessment algorithm, input features, and status criteria into an equipment status assessment model. After selecting the evaluation algorithm and evaluation rules corresponding to the equipment to be evaluated, load the corresponding independent variable point information feature template and calculate the associated parameter template; The independent variable point information feature template includes the state quantity information and quantity measurement information of the device to be evaluated, and the calculation association parameter template includes the rated current, rated voltage, rated short-circuit current, rated current carrying capacity, and rated capacitance of the device to be evaluated. The equipment inspection information point table generation module is responsible for associating and matching the relevant field information of the equipment resource information configuration file of the intelligent inspection system with the regional model information in the SCD file and the equipment information in the monitoring system to determine the primary and secondary equipment corresponding to the intelligent inspection points and form an equipment inspection information point table to record the inspection data point information of each equipment. The device instantiation module is responsible for instantiating an evaluation object for each specific physical device, loading the corresponding device status evaluation model for the evaluation object, associating the evaluation object with the monitoring data points and inspection data points in the device basic information mapping table, and completing the binding of the evaluation algorithm and data points for the specific device. The equipment status assessment and diagnosis module is responsible for acquiring real-time monitoring data and inspection data of the equipment at certain time intervals or triggered by events, inputting the data into a predefined status assessment model, running an assessment algorithm to calculate the current status of the equipment, and generating a standard format equipment status assessment result file. The status assessment of the equipment to be assessed is initiated by a dynamic cycle and a sudden event triggering method with the assessment results as reference factors. The monitoring information points of the equipment to be assessed are diagnosed and calculated online through the equipment status assessment model. The output value is judged according to the score criteria to obtain the score of each monitoring information point. The scores of all information points are accumulated to obtain the total score of the equipment to be assessed. Then, the current status of the equipment is determined according to the evaluation rules in the object. The monitoring information point scores and equipment status assessment results are saved to the historical database. The alarm module is responsible for issuing an alarm if the device is in an abnormal state based on the status assessment results, predicting the future state of the device based on the changing trends of the data points in the status assessment, and issuing an early warning if the prediction result indicates an unhealthy state.

Images