Operation and Maintenance Management Method and Platform Based on Digital Twin

Abstract

The present application relates to an operation and maintenance management method and platform based on digital twin, which is applied to the field of data processing. The method includes: obtaining various key values and data of grid equipment in an edge substation, determining the first grid equipment and the equipment strongly associated with it as key equipment according to the equipment key values, and for the second grid equipment among multiple grid equipment other than the first grid equipment, determining key equipment and non-key equipment from the second grid equipment according to the operation duration, failure times, service life and equipment key values of each second grid equipment, accurately realizing the classification of key equipment and non-key equipment, constructing digital twin models with different precisions for key equipment and non-key equipment, not only ensuring the fine management of key equipment, but also avoiding resource waste on non-key equipment, improving the construction efficiency of the digital twin model and reducing the maintenance cost.

Description

Technical Field

[0001] This application relates to the field of data processing, and in particular, to an operation and maintenance management method and platform based on digital twin. Background Art

[0002] With the rapid development of technology, the smart grid, as an important part of the modern power system, the intelligentization and high efficiency of its operation and maintenance management have become an important development direction in the power industry. The smart grid realizes the comprehensive monitoring and control of the power transmission and distribution system by integrating advanced sensing technologies, communication technologies, information processing technologies, and automatic control technologies, greatly improving the reliability and operation efficiency of the power grid.

[0003] Currently, for the operation and maintenance management of the smart grid, a common practice is to deploy data acquisition and monitoring devices at key nodes of the power grid to collect device data of power equipment in real time and transmit it to the central processing center for centralized processing through wired or wireless means. The central processing center uses cloud computing and big data technologies to deeply mine and analyze the massive data and build a digital twin model for functions such as fault warning.

[0004] However, in the huge network of the smart grid, as a key node in power transmission, the edge substation has a wide variety of old and new equipment. Since building a digital twin model for each power grid device requires a large amount of data, the construction efficiency of the digital twin model of the edge substation is low and the maintenance cost is high. Summary of the Invention

[0005] The purpose of this application is to provide an operation and maintenance management method and platform based on digital twin, which can improve the construction efficiency of the digital twin model and reduce the maintenance cost.

[0006] In a first aspect, an operation and maintenance management method based on digital twin is provided, including:

[0007] Obtain the device key values and device data corresponding to multiple power grid devices in the edge substation, where the device data includes operation duration, number of faults, and service life;

[0008] According to the device key values corresponding to multiple power grid devices, determine several first power grid devices belonging to key devices from the multiple power grid devices; the several first power grid devices include: power grid devices with device key values greater than a preset device criticality threshold and power grid devices strongly associated with power grid devices with device key values greater than the preset device criticality threshold;

[0009] For the second power grid devices other than the first power grid device among multiple power grid devices, determine the key devices and non-key devices from the second power grid devices according to the operation duration, number of faults, service life, and device key value of each second power grid device;

[0010] Construct digital twin models corresponding to the key devices and non-key devices respectively to obtain the digital twin model corresponding to the edge substation; wherein, the modeling accuracy of the first digital twin model corresponding to the key device is higher than that of the second digital twin model corresponding to the non-key device;

[0011] Perform operation and maintenance management based on the digital twin model of the edge substation.

[0012] In a preferred example of the present application, it can be further configured that the process of determining strongly associated power grid devices includes:

[0013] Determine the corresponding associated devices according to the directed connection graph of the power grid devices whose device key values are greater than the preset device criticality threshold;

[0014] Obtain the abnormal time sequence, abnormal degree, and abnormal frequency of the associated devices when the power grid devices with device key values greater than the preset device criticality threshold are abnormal, and the abnormal time sequence is the order in which the power grid devices have abnormalities in the abnormal event;

[0015] Determine the influence value of the associated devices on the power grid devices whose device key values are greater than the preset device criticality threshold according to the abnormal time sequence, abnormal degree, and abnormal frequency of the associated devices;

[0016] Determine strongly associated devices from the associated devices based on the influence value.

[0017] In a preferred example of the present application, it can be further configured that the operation and maintenance management based on the digital twin model of the edge substation includes:

[0018] When it is determined that the operation state of the power grid device is abnormal, determine the relevant information of the power grid device with abnormal operation state through the digital twin model of the edge substation, and the relevant information at least includes: device location information, location information of the abnormal component, and importance value of the abnormal component;

[0019] Predict the abnormal cause of the abnormal component;

[0020] Match a number of maintenance suggestions corresponding to the abnormal component from the operation and maintenance dictionary according to the abnormal cause;

[0021] Determine an inspection trajectory based on the relevant information of the grid equipment with abnormal operating status. The inspection trajectory includes: the inspection order of the grid equipment with abnormal operating status, and the inspection duration of the grid equipment with abnormal operating status. The inspection duration includes the duration of displaying the component part and the duration of displaying a number of maintenance suggestions.

[0022] After detecting an inspection start instruction, provide navigation guidance for the user in the virtual scene according to the inspection trajectory. When inspecting the abnormal component part, display a number of corresponding maintenance suggestions in the virtual scene.

[0023] In a preferred example, the present application can be further configured as: the determining of the inspection trajectory according to the relevant information of the grid equipment with abnormal operating status includes:

[0024] Cluster the grid equipment according to the abnormal causes of the abnormal component parts of the grid equipment with abnormal operating status to obtain a number of equipment groups.

[0025] For each equipment group, determine the first order of the grid equipment in the equipment group according to the average importance value corresponding to the importance value of the abnormal component part of the grid equipment in the equipment group.

[0026] Determine the second order of the equipment group according to the number of key equipment in each equipment group and the average importance value corresponding to the importance value of the abnormal component part of the grid equipment in the equipment group.

[0027] Based on the first order, the second order, the equipment location information, and the location information of the abnormal component part, determine the inspection order.

[0028] Determine the duration of displaying a number of maintenance suggestions according to the content length of the number of maintenance suggestions.

[0029] Determine the duration of displaying the component part according to the importance value and complexity of the abnormal component part.

[0030] In a preferred example, the present application can be further configured as: the grid equipment is a device with a multi-level structure hierarchy, and the non-root level structure hierarchy is composed of at least two sub-level structures.

[0031] After constructing the digital twin models corresponding to the key equipment and the non-key equipment respectively and obtaining the digital twin model corresponding to the edge substation, it further includes:

[0032] Obtain a first preset verification parameter and the first actual operation and maintenance information corresponding to the first preset verification parameter. The first preset verification parameter includes verification parameters corresponding to multiple structural levels of the grid equipment; and, obtain a second preset verification parameter and the second actual operation and maintenance information corresponding to the second preset verification parameter.

[0033] According to the verification parameters corresponding to the preset structural levels in the first preset verification parameters of the power grid equipment, input the digital twin model to obtain the first operation and maintenance information corresponding to the preset structural levels; according to the first operation and maintenance information and the actual operation and maintenance information corresponding to the preset structural levels in the first actual operation and maintenance information of the power grid equipment, verify the effectiveness of the preset structural levels of the digital twin model corresponding to the edge substation; when the verification of the preset structural levels fails, adjust the model parameters of the preset structural levels and verify again until the verification is successful, and then verify the next same-level preset structural levels;

[0034] When all the preset structural levels are successfully verified, based on the association graph of the power grid equipment, determine the relevance between the components of the preset structural levels, and the components are the sub-structural levels of the preset structural levels; use the verification parameters regarding the preset structural levels in the second preset verification parameters and the actual operation and maintenance information corresponding to the preset structural levels in the second actual operation and maintenance information of the power grid equipment to verify the relevant components again; if the verification of the relevant components fails, adjust the model parameters of the target components until the verification is successful, and the target components are the relevant and failed components;

[0035] If the verification of the relevant components is successful, perform the verification of the next-level structural levels until all the structural levels are verified and adjusted, and obtain the final digital twin model corresponding to the edge substation.

[0036] In a preferred example of the present application, it can be further configured that: if the preset structural level is a non-root-level structural level, performing the verification of the next same-level preset structural levels includes:

[0037] Sort the other preset structural levels of the same level according to the number of sub-structural levels that coincide with the verified preset structural levels to obtain the first sequence;

[0038] Verify the other preset structural levels of the same level in sequence according to the first sequence;

[0039] When verifying the target other preset structural levels, if the verification fails, adjust the model parameters of the non-coincident sub-structural levels to perform the verification and model parameter adjustment of the other preset structural levels, and the target other preset structural levels are any structural levels among the other preset structural levels of the same level.

[0040] In a preferred example of the present application, it can be further configured that: performing operation and maintenance management based on the digital twin model of the edge substation includes:

[0041] Obtain the current operation compression data corresponding to each of multiple power grid devices in the edge substation, where the current operation compression data includes multi-dimensional compression data, and each dimension of compression data is the compression data of a varying dimension;

[0042] Decompress the current operation compression data to obtain the current operation data;

[0043] Monitor the operation status of multiple power grid devices in the edge substation according to the current operation data by using the digital twin model of the edge substation.

[0044] In a second aspect, a digital twin-based operation and maintenance management platform is provided, including:

[0045] An acquisition module for acquiring the device key values and device data corresponding to each of multiple power grid devices in the edge substation, where the device key values are determined based on the roles and importance of the power grid devices in the power grid, and the device data includes the operation duration, the number of faults, and the service life;

[0046] A device classification module for determining, from multiple power grid devices, a number of first power grid devices belonging to critical devices according to the device key values corresponding to each of the multiple power grid devices; the number of first power grid devices includes: power grid devices with device key values greater than a preset device criticality threshold and power grid devices strongly associated with power grid devices with device key values greater than the preset device criticality threshold;

[0047] And, for the second power grid devices other than the first power grid devices among the multiple power grid devices, determine critical devices and non-critical devices from the second power grid devices according to the operation duration, the number of faults, the service life, and the device key values of each second power grid device;

[0048] A construction module for constructing digital twin models corresponding to the critical devices and non-critical devices respectively to obtain the digital twin model corresponding to the edge substation; where the modeling accuracy of the first digital twin model corresponding to the critical devices is higher than the modeling accuracy of the second digital twin model corresponding to the non-critical devices;

[0049] A management module for performing operation and maintenance management based on the digital twin model of the edge substation.

[0050] In a third aspect, an electronic device is provided, including:

[0051] One or more processors;

[0052] A memory;

[0053] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to: execute the steps of the method according to any one of the first aspects.

[0054] In a fourth aspect, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method as shown in any possible implementation manner of the first aspect.

[0055] In summary, the present application includes at least one of the following beneficial technical effects: obtaining various key values and data of grid devices in a substation at the edge, classifying them according to the criticality of the devices in the grid, determining a first grid device and the devices strongly associated with it as critical devices according to the device key values, and for a second grid device other than the first grid device among a plurality of grid devices, determining critical devices and non-critical devices from the second grid devices according to the operation duration, the number of faults, the service life and the device key values of each second grid device, accurately realizing the classification of critical devices and non-critical devices, constructing digital twin models with different precisions for critical devices and non-critical devices, not only ensuring the fine management of critical devices, but also avoiding resource waste on non-critical devices, improving the construction efficiency of digital twin models and reducing the maintenance cost, and furthermore, performing operation and maintenance management based on these refined digital twin models. Description of the Drawings

[0056] Figure 1 is a schematic flowchart of a method for operation and maintenance management based on digital twins provided by an embodiment of the present application;

[0057] Figure 2 is a schematic diagram of a multi-level structure provided by an embodiment of the present application;

[0058] Figure 3 is a schematic diagram of the structure of an operation and maintenance management platform based on digital twins provided by an embodiment of the present application;

[0059] Figure 4 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Detailed Embodiments

[0060] This specific embodiment is only an interpretation of the present application and does not limit the present application. Those skilled in the art can make modifications without creative contributions to this embodiment according to needs after reading this specification, but as long as they are within the scope of the claims of the present application, they are protected by the patent law.

[0061] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are some, but not all, of the embodiments of this application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts belong to the scope of protection of this application.

[0062] In addition, the term "and / or" in this article is merely an association relationship describing associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after, unless otherwise specified.

[0063] Specifically, the embodiments of this application provide an operation and maintenance management method based on digital twins. The method provided in the embodiments of this application can be executed by an electronic device, which is a server. The server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the electronic device can be directly or indirectly connected through wired or wireless communication methods. The embodiments of this application do not limit this, as Figure 1 shown, the method includes:

[0064] S101. Obtain the device key values and device data respectively corresponding to multiple grid devices in the edge substation;

[0065] The device key values are determined based on the roles and importance of the grid devices in the power grid. The device data includes the operation duration, the number of failures, and the service life;

[0066] Edge substations are usually located in remote areas, where there is a wide variety and uneven age of grid equipment. The construction and maintenance of digital twin models face huge challenges, and it is difficult to ensure the model accuracy. Grid equipment refers to various equipment in edge substations used to realize functions such as power conversion, distribution, monitoring, and protection, including but not limited to transformers, circuit breakers, switchgear, capacitor banks, power supply equipment, etc. The key value of the equipment is determined based on the role and importance of the grid equipment in the power grid. Specifically, it is an evaluation value set by technicians based on experience. Equipment data refers to various parameters and records describing the operating conditions of grid equipment, including but not limited to the operating duration (indicating the total working time of the equipment since it was put into operation), the number of failures (recording the number of failures of the equipment within a specific period, reflecting the reliability of the equipment), and the service life (the time from the date when the equipment was put into operation to the present, reflecting the degree of aging of the equipment).

[0067] In the embodiment of the present application, by using the automatic monitoring system of the substation, the operation records and maintenance reports of grid equipment are summarized and extracted, and information such as the operating duration and the number of failures of the grid equipment is extracted from them. Combining the service life data in the equipment files, the structure, size, and performance of the grid equipment, etc., a complete equipment data set is constructed.

[0068] S102. According to the key values of the respective grid equipment of multiple grid equipment, determine a number of first grid equipment belonging to key equipment from the multiple grid equipment;

[0069] The number of first grid equipment includes: grid equipment with a key value greater than the preset equipment criticality threshold and grid equipment strongly associated with grid equipment with a key value greater than the preset equipment criticality threshold;

[0070] The preset equipment criticality threshold is a pre-set numerical standard. When the key value of the grid equipment exceeds this threshold, it indicates that the equipment has an important impact on the safe and stable operation of the power grid, and it is regarded as a key equipment.

[0071] Strongly associated grid equipment represents equipment that is strongly associated with grid equipment that has an important impact on the safe and stable operation of the power grid. This strong association includes grid equipment that has a close connection in physical connection, functional cooperation, or fault impact. When a key equipment fails or malfunctions, these strongly associated equipment may also be directly or indirectly affected.

[0072] In the embodiment of the present application, in one implementation, a database of grid equipment is established to store data such as the key value, function description, location information, and association relationship of each grid equipment. Then, the system internally sets a preset equipment criticality threshold and automatically compares and analyzes the key values of the equipment in the database. For equipment with a key value greater than the threshold, other equipment that is strongly associated with these equipment is searched to obtain a list of the first grid equipment.

[0073] S103. For the second power grid devices among multiple power grid devices excluding the first power grid device, determine the critical devices and non-critical devices from the second power grid devices according to the operation duration, number of failures, service life, and device key value of each second power grid device;

[0074] In the embodiment of the present application, by combining the relevant information of each second power grid device, the power grid devices are classified to obtain critical devices and non-critical devices.

[0075] Among them, the operation duration represents the cumulative working time length of the power grid device since it was put into operation, and is an important indicator for evaluating the aging degree and usage status of the device. The number of failures: records the number of failures that occur during the operation of the power grid device, reflecting the reliability and stability of the device. The service life: refers to the longest time length from the power grid device being put into use.

[0076] Optionally, an implementation method includes: determining a first value corresponding to each second power grid device according to the operation duration, number of failures, and service life of each second power grid device; performing weighted calculation based on the device key value and the first value of each second power grid device to obtain a second value of each second power grid device, and determining critical devices and non-critical devices from the second power grid devices according to the second value.

[0077] Among them, the first value = , where α is a weight factor used to adjust the relative importance of the usage rate in the comprehensive performance evaluation, and the user can set the size according to the actual situation; the first value represents the comprehensive performance index of the power grid device. The larger the first value, the higher the comprehensive performance index, the better the device performance, and the fewer abnormal situations of the device with excellent performance, and it is more stable. The second value = (1 - the first value) * the first weight + the device key value * the second weight / the device key value limit, where the first weight value and the second weight value can be set by the user according to the actual situation. Set a threshold, and regard the second power grid devices greater than the threshold as critical devices, and other second power grid devices as non-critical devices.

[0078] Of course, it can also be specified by the user, and the embodiment of the present application does not make any further limitations as long as it can achieve the purpose of the embodiment of the present application.

[0079] S104. Construct digital twin models corresponding to the critical devices and non-critical devices respectively to obtain the digital twin model corresponding to the edge substation;

[0080] Among them, the modeling accuracy of the first digital twin model corresponding to the critical device is higher than that of the second digital twin model corresponding to the non-critical device;

[0081] The higher the modeling accuracy, the more accurately the model can reflect the actual situation of physical entities, thus providing more valuable predictions and decision-making support. Among them, there are differences in modeling accuracy between the digital twin models constructed for critical equipment and non-critical equipment. Due to its importance to the safe and stable operation of the power grid, the first digital twin model corresponding to critical equipment requires higher modeling accuracy to ensure the accurate simulation and prediction of the behavior of critical equipment. For the second digital twin model corresponding to non-critical equipment, although the modeling accuracy is relatively low, it still needs to meet the accurate description of the basic state and behavior of the equipment.

[0082] For critical equipment, complex and precise modeling techniques are adopted, such as physics-based simulation models, deep learning models, etc., to ensure the accuracy and reliability of the model. For non-critical equipment, relatively simplified modeling methods can be adopted, such as statistical models or rule-based reasoning models, etc., to reduce the modeling cost and complexity.

[0083] S105. Perform operation and maintenance management based on the digital twin model of the edge substation.

[0084] The constructed digital twin model of the edge substation intelligently manages the operation and maintenance work of the substation, including but not limited to equipment status monitoring, fault warning, performance evaluation, operation and maintenance decision-making support, etc.

[0085] It can be seen that in the embodiment of the present application, various key values and data of grid equipment in the edge substation are obtained, classified according to the criticality of the equipment in the power grid, and the first grid equipment and the equipment strongly associated with it are determined according to the equipment key values as critical equipment. For the second grid equipment other than the first grid equipment among multiple grid equipment, according to the operation duration, number of faults, service life and equipment key values of each second grid equipment, critical equipment and non-critical equipment are determined from the second grid equipment, accurately realizing the classification of critical equipment and non-critical equipment. Different-precision digital twin models are constructed for the equipment of critical equipment and non-critical equipment, which not only ensures the fine management of critical equipment, but also avoids resource waste on non-critical equipment, improves the construction efficiency of the digital twin model and reduces the maintenance cost. Furthermore, operation and maintenance management is carried out based on these refined digital twin models.

[0086] Furthermore, the process of determining strongly associated grid equipment includes: S201-S204 (not shown in the drawings), where:

[0087] S201. Determine the associated equipment corresponding to the connection directed graph of grid equipment with equipment key values greater than the preset equipment criticality threshold;

[0088] The directed graph of the connections of power grid devices is used to represent the connection relationships among devices in the power grid. In the directed graph, each device is represented as a node, and the connections between devices are represented as directed edges, enabling an intuitive understanding of the power grid structure and the mutual influence among devices. The directed graph of the connections of power grid devices is stored in a graph database, and key value attributes are set for each device node. Device nodes with key values greater than a preset threshold are filtered out through query statements, and the graph traversal function of the graph database is used to find the associated devices of these key devices.

[0089] S202. When a power grid device with a device key value greater than a preset device criticality threshold is abnormal, obtain the abnormal time sequence, abnormal degree, and abnormal frequency of the associated devices. The abnormal time sequence is the order in which power grid devices become abnormal in an abnormal event.

[0090] Obtain the historical operation information of power grid devices. The historical operation information includes multiple abnormal events. Each abnormal event includes the abnormal time sequence, abnormal degree, and abnormal frequency of all abnormal devices in that abnormal state or fault condition. Among them, the abnormal time sequence: when a power grid device becomes abnormal, it is the time sequence in which different devices become abnormal. This time sequence is of great significance for analyzing the propagation path of abnormal events, determining the fault source, and formulating emergency response strategies. The abnormal degree represents the degree to which a power grid device deviates from the normal operation state in an abnormal state. The abnormal frequency refers to the number of times a power grid device becomes abnormal within a certain period of time. The level of abnormal frequency can reflect the stability and reliability of the device.

[0091] S203. Determine the influence value of the associated devices on the power grid devices with device key values greater than the preset device criticality threshold according to the abnormal time sequence, abnormal degree, and abnormal frequency of the associated devices.

[0092] The influence value represents a quantitative value of the influence degree or range of the associated device on the key device.

[0093] In an implementable solution, the influence value is determined based on Ii = α / (Ti + ) + β·Si + γ·log(Fi + 1), where:

[0094] Ti: The quantization value of the abnormal time sequence of the i-th associated device (for example, the inverse time difference from the current time, the closer the greater the influence);

[0095] is a very small positive number used to prevent the denominator from being zero;

[0096] Si: The abnormal degree of the i-th associated device, |actual value - normal value| / normal value;

[0097] Fi: abnormal frequency of the i-th associated device within a period of time;

[0098] α, β, γ: are the weight coefficients of time sequence, abnormality degree and abnormality frequency respectively, and α+β+γ=1.

[0099] Ii: The impact value of the i-th associated device on the power grid equipment.

[0100] S204: Determine strongly associated devices from the associated devices based on the influence value.

[0101] Based on the impact value, we further filter out the associated devices that have the greatest impact on key devices, namely strongly associated devices. We can determine strongly associated devices from the associated devices by setting an impact value threshold, or we can use a sorting method to sort all associated devices from highest to lowest impact value and select the top-ranked associated devices as strongly associated devices based on actual needs.

[0102] It can be seen that in the embodiment of the present application, in the process of determining strongly associated power grid devices, potential associated devices are identified based on the directed graph of device connections, and then by analyzing the abnormal performance (time sequence, degree and frequency) of the associated devices when the first power grid device is abnormal, their impact on key devices is quantified to screen out strongly associated devices.

[0103] Furthermore, S105 performs operation and maintenance management based on the digital twin model of the edge substation, including: S1051-S1055 (not shown in the figure), where:

[0104] S1051. When it is determined that the operating state of the power grid equipment is abnormal, determine, using the digital twin model of the edge substation, relevant information of the power grid equipment with the abnormal operating state, wherein the relevant information includes at least: equipment location information, location information of the abnormal component, and important values of the abnormal component;

[0105] When it is determined that the operating state of the power grid device deviates from a normal or expected range, it is determined that the operating state of the power grid device is abnormal.

[0106] In this embodiment of the present application, the term "abnormal component" refers to the specific component or area within the power grid equipment that causes the abnormal operating status. Location information refers to the specific location of the abnormal component within the power grid equipment. Importance value: A numerical value used to quantify the impact of the abnormal component on the operation of the power grid equipment, using a comprehensive assessment of factors including fault severity, impact scope, and repair difficulty.

[0107] Specifically, when the power grid monitoring system issues an abnormal alarm, the detailed data and simulation functions in the digital twin model are used to further determine the specific location information of the device, including its layout position within the substation and its relative position relative to other devices. At the same time, the model can also analyze the specific components that cause the device abnormality and give the specific location information of these components inside or outside the device. Finally, based on the evaluation function of the digital twin model, the importance value of the abnormal components is calculated.

[0108] By using the digital twin model of the edge substation, relevant information can be quickly determined when grid equipment malfunctions, including equipment location, abnormal component location, importance value, etc., which can improve the fault response speed.

[0109] S1052. Predict the abnormal cause of the abnormal component;

[0110] Abnormal component: refers to the specific component or area in grid equipment whose operating state deviates from the normal or expected range.

[0111] By analyzing the current state, historical data, and environmental factors of the abnormal component, the root cause of the abnormality of this component is inferred.

[0112] Specifically, obtain a historical data set containing the status data of the abnormal component and its corresponding abnormal causes, obtain a machine learning model (such as decision tree, random forest, support vector machine, etc.), and use the historical data set to train the model; after training is completed, input the status data of the current abnormal component into the model, and the model will output the predicted abnormal cause.

[0113] S1053. According to the abnormal cause, match several corresponding maintenance suggestions for the abnormal component from the operation and maintenance dictionary;

[0114] The operation and maintenance dictionary stores a database or knowledge base about various problems that may be encountered during system operation and maintenance and corresponding solution strategies.

[0115] According to the known abnormal cause and component, search and match in the dictionary to find maintenance suggestions. In some embodiments, the operation and maintenance dictionary can be designed as a database that supports keyword search. The operation and maintenance personnel can input the abnormal cause and component as keywords, and the system quickly locates the relevant maintenance suggestions through full-text search technology. To improve the matching accuracy, the operation and maintenance dictionary can also introduce a weight assignment mechanism to assign different importance to different abnormal components, so as to give higher priority during the matching process. The system can also provide an interactive interface, allowing the operation and maintenance personnel to further screen or adjust the search conditions according to the matching results to obtain more accurate maintenance suggestions.

[0116] By quickly matching the corresponding maintenance suggestions for the abnormal components from the operation and maintenance dictionary, operation and maintenance personnel can more accurately locate problems, reduce diagnosis time, and avoid misjudgment or omission caused by insufficient experience or lack of knowledge. In addition, the operation and maintenance dictionary also plays a role in knowledge inheritance and standardization, enabling operation and maintenance personnel at different levels to handle problems according to unified processes and standards, improving the standardization and consistency of operation and maintenance work.

[0117] S1054. Determine a patrol track based on the relevant information of the power grid equipment with abnormal operating status. The patrol track includes: the patrol order of the power grid equipment with abnormal operating status, and the patrol duration of the power grid equipment with abnormal operating status. The patrol duration includes the display component duration and the display duration of several maintenance suggestions.

[0118] In an implementable manner, S1054. Determine a patrol track based on the relevant information of the power grid equipment with abnormal operating status, including: SA1 - SA6 (not shown in the attached drawings), where:

[0119] SA1. Cluster the power grid equipment according to the abnormal causes of the abnormal components of the power grid equipment with abnormal operating status to obtain several equipment groups.

[0120] After detecting that a device has an abnormality in the operation status monitoring system of the power grid equipment, it is necessary to quickly locate the abnormal device and analyze its abnormal cause in order to take corresponding measures to restore the normal operation of the device or prevent the further expansion of the fault.

[0121] During the clustering analysis process, the clustering algorithm can be used and reasonable parameters (such as the number of clusters, similarity threshold, etc.) can be set.

[0122] Specifically, obtain the abnormal causes and the number of clusters of multiple power grid equipment; randomly determine the number of initial cluster centers equal to the number of clusters from multiple power grid equipment; for the abnormal causes of multiple power grid equipment, use the Euclidean distance to determine the weights of multiple power grid equipment corresponding to the initial cluster centers; according to the weights of multiple power grid equipment corresponding to the initial cluster centers, remove duplicates to obtain the power grid equipment corresponding to each initial cluster center; obtain several equipment groups.

[0123] SA2. For each equipment group, determine the first order of the power grid equipment in the equipment group according to the average importance value corresponding to the importance value of the abnormal components of the power grid equipment in the equipment group.

[0124] The first order is the order obtained after sorting the power grid equipment in the equipment group.

[0125] In this step, by determining the first-order devices in the device group, the system can prioritize the processing of faults that have the greatest impact on or are the most urgent for grid operation, thereby quickly restoring the stability and reliability of the grid.

[0126] SA3. Determine the second order of the device group according to the number of key devices in each device group and the weighted average value corresponding to the importance value of the abnormal components of the grid devices in the device group;

[0127] Specifically, according to Scorei = w1Ni + w2Yi, where Ni is the number of key devices in device group i, Yi is the weighted average value corresponding to the importance value of the abnormal components of the grid devices in device group i, w1 is the weight of the number of key devices, and w1 is the weight of the weighted average value; for example,

[0128] Suppose there are three device groups with the following data:

[0129] Device group 1: N1 = 5, Y1 = 10;

[0130] Device group 2: N2 = 3, Y2 = 7.5;

[0131] Device group 3: N3 = 4, Y3 = 8;

[0132] If we choose w1 = 0.6 and w2 = 0.4, then:

[0133] Score of device group 1: Score1 = 0.6 * 5 + 0.4 * 10 = 3 + 4 = 7;

[0134] Score of device group 2: Score2 = 0.6 * 3 + 0.4 * 7.5 = 1.8 + 3 = 4.8;

[0135] Score of device group 3: Score3 = 0.6 * 4 + 0.4 * 8 = 2.4 + 3.2 = 5.6.

[0136] After obtaining Scorei, sort all device groups to get the second order, that is, device group 3 - device group 2 - device group 1.

[0137] SA4. Determine the inspection order based on the first order, the second order, the device location information, and the location information of the abnormal components;

[0138] SA5. Determine the display duration of several maintenance suggestions according to the content length of the several maintenance suggestions;

[0139] When the content length is the text length, determine the display duration of several maintenance suggestions according to the content length at the preset reading speed;

[0140] When the content length is equal to the audio - video playback length, determine the duration for displaying a number of maintenance suggestions according to the content length at a preset reading speed.

[0141] SA6. Determine the display duration of the component according to the importance value of the abnormal component and the complexity of the abnormal component.

[0142] The higher the importance value, the greater the impact of the abnormal component on the device. Complexity refers to the degree of complexity of the abnormal component in terms of structure, function, or repair difficulty. The higher the complexity, the more difficult it is to analyze, diagnose, or repair this part.

[0143] The display duration of the component refers to the time length for displaying the abnormal component structure in the display interface or report. This duration may vary according to the importance value and complexity, so that users can give priority to paying attention to and dealing with more important or more complex abnormal components.

[0144] Furthermore, a dynamic adjustment strategy can be adopted. After determining the duration for displaying a number of maintenance suggestions and the display duration of the component, it is also possible to dynamically adjust the display duration according to the user's interaction behavior (such as clicking, zooming in, viewing detailed information, etc.) during the actual inspection process and real - time data updates. For example, if the user frequently views the detailed information of a certain abnormal component, the system can increase the display duration of this component; if the status of a certain abnormal component is alleviated or repaired, the system can reduce its display duration.

[0145] It can be seen that in the embodiment of this application, during the process of determining the inspection trajectory, clustering devices according to the abnormal causes helps to centrally process devices with similar problems; through the dual considerations of the importance value and the number of key devices, it ensures that devices and areas with greater impact on the power grid are given priority for processing. Combining the refined adjustment of location information and display duration further improves the efficiency and effect of the inspection work.

[0146] S1055. After detecting the inspection start instruction, provide navigation guidance for the user in the virtual scene according to the inspection trajectory. When an abnormal component is inspected, display corresponding a number of maintenance suggestions in the virtual scene.

[0147] After the user operation, scheduled task, or external system call is triggered, generate an inspection start instruction; conduct inspections based on the inspection trajectory.

[0148] Furthermore, augmented reality (AR) technology can also be used to display virtual scenarios and inspection trajectories in the AR device worn by the user, capture images of the real world through the camera, and overlay virtual information on the real world. When the user inspects an abnormal component, the system will display maintenance suggestions in real time in the AR device and remind the user to pay attention through various means such as vision and hearing. This method can provide a more intuitive and immersive inspection experience.

[0149] It can be seen that in the embodiment of this application, in the operation and maintenance management stage, this method uses the digital twin model to quickly respond to the abnormal state of power grid equipment. Once an abnormality is detected, detailed equipment information and abnormal details are immediately obtained through the model, and then the cause of the abnormality is predicted and corresponding maintenance suggestions are matched. It can also plan the inspection trajectory based on the equipment status and abnormal information, including the optimal inspection sequence and duration allocation, ensuring the efficiency and pertinence of the inspection work. Furthermore, combined with the navigation guidance and display of maintenance suggestions in the virtual scene, it greatly improves the operation convenience and response speed of operation and maintenance personnel, reduces the operation and maintenance cost, and improves the operation and maintenance efficiency.

[0150] Furthermore, for power grid equipment, there may be complex structures. After generating the digital twin model of the power grid equipment, the digital twin model of the power grid equipment can be verified. For complex structures, it may be verified at multiple levels separately to improve the accuracy of verification.

[0151] Specifically, referring to Figure 2 , the power grid equipment is a device with multiple hierarchical structures, and the non-root hierarchical structure is composed of at least two sub-level structures;

[0152] After constructing the digital twin models corresponding to the key equipment and non-key equipment respectively and obtaining the digital twin model corresponding to the edge substation, it further includes: SC1-SC4 (not shown in the drawings), where:

[0153] SC1, obtain the first preset verification parameter and the first actual operation and maintenance information corresponding to the first preset verification parameter. The first preset verification parameter includes verification parameters corresponding to multiple hierarchical structures of the power grid equipment; and, obtain the second preset verification parameter and the second actual operation and maintenance information corresponding to the second preset verification parameter;

[0154] The preset verification parameters involve different hierarchical structures of the power grid equipment, such as input data of the equipment as a whole, subsystems, and components. The actual operation and maintenance information refers to the actual operation data or status information corresponding to the preset verification parameters during the actual operation of the power grid equipment.

[0155] SC2. According to the verification parameters corresponding to the preset structural levels in the first preset verification parameters of the grid equipment, input them into the digital twin model to obtain the first operation and maintenance information corresponding to the preset structural levels; according to the first operation and maintenance information and the actual operation and maintenance information corresponding to the preset structural levels in the first actual operation and maintenance information of the grid equipment, verify the effectiveness of the preset structural levels of the digital twin model corresponding to the edge substation; when the verification of the preset structural levels fails, adjust the model parameters of the preset structural levels and verify again until the verification is successful, and then proceed to verify the next same-level preset structural levels;

[0156] Refer to Figure 2 , specifically, the execution process of the steps is as follows:

[0157] First, select the verification parameters corresponding to the currently required preset structural levels from the first preset verification parameters. Taking the second level 1 as an example, first obtain the verification parameters corresponding to the second level 1;

[0158] Use these verification parameters as input conditions and input them into the established digital twin model, and run the model to obtain the first operation and maintenance information corresponding to this structural level;

[0159] Extract the actual operation and maintenance information corresponding to the same preset structural level from the first actual operation and maintenance information of the grid equipment.

[0160] Compare the first operation and maintenance information with the first actual operation and maintenance information to evaluate the consistency between the simulation results of the digital twin model at this structural level and the actual operation status;

[0161] If the verification result shows that the simulation results are inconsistent with the actual operation status, that is, the verification fails, then the model parameters of this preset structural level need to be adjusted to improve the accuracy of the model;

[0162] After adjustment, run the digital twin model again and verify, repeating this process until the verification is successful.

[0163] When the verification of the current preset structural level is successful, continue to verify the next same-level preset structural level (such as the second level 2) until all the structural levels (the second level) that need to be verified are completed.

[0164] SC3. When all the preset structural levels are verified successfully, then based on the association graph of the grid equipment, determine the association between the components of the preset structural levels; use the verification parameters regarding the preset structural levels in the second preset verification parameters and the actual operation and maintenance information corresponding to the preset structural levels in the second actual operation and maintenance information of the grid equipment to verify the associated components again; if the verification of the associated components fails, adjust the model parameters of the target components until the verification is successful, and the target components are the associated and failed components;

[0165] The associated graph of power grid equipment shows a network structure diagram for describing the relationships between the components of power grid equipment, as Figure 2 shown. The associated graph can display a diagram of the interconnections and dependencies between the components, subsystems, or functional modules of the equipment. For example, the multiple components at the second level 1 are: root level 1 and root level 2.

[0166] Specifically, the execution process is as follows:

[0167] Determine the relevance: According to the associated graph of the power grid equipment, analyze and determine the relevance between the components in the preset structural hierarchy;

[0168] Prepare verification parameters and information: Select the verification parameters related to the currently required preset structural hierarchy or components from the second preset verification parameters; Extract the actual operation and maintenance information corresponding to these components from the second actual operation and maintenance information of the power grid equipment;

[0169] Verify: Use the selected verification parameters and the extracted actual operation and maintenance information to verify each component with relevance one by one. The verification process may involve comparing simulated values with actual values, evaluating whether the performance indicators meet the standards, etc.;

[0170] Process the verification results: If the verification results show that the components with relevance fail to meet the predetermined verification standards or conditions, that is, the verification fails;

[0171] Adjust the model parameters: For the components that fail the verification, adjust their model parameters to optimize the accuracy and reliability of the model. The adjustment process may need to be repeated until the verification is successful.

[0172] SC4. If the verification of the components with relevance is successful, then proceed to the verification of the next-level structural hierarchy until the verification and adjustment of all structural hierarchies are completed, and the digital twin model corresponding to the final edge substation is obtained.

[0173] It can be seen that in the embodiment of this application, after constructing the digital twin model of the edge substation, for power grid equipment with complex structures, a multi-level verification mechanism is introduced. Specifically, by comparing the preset verification parameters with the actual operation and maintenance information, the effectiveness of each preset structural hierarchy in the digital twin model is ensured; when the verification of a certain level fails, the model parameters of that level can be adjusted specifically and the verification is repeated until successful; after the verification of all preset structural hierarchies is successful, the relevance between the components is determined through the associated graph, and the components with relevance are verified again, further refining the verification process and ensuring the consistency and accuracy of the model in the complex structural hierarchy; through step-by-step verification and adjustment, a comprehensive, accurate, and reliable digital twin model of the edge substation is obtained.

[0174] Further, if the preset structure level is a non-root level structure, verification of the next same-level preset structure level is performed in SC2, including:

[0175] Sort other preset structure levels of the same level according to the number of child structure levels that coincide with the verified preset structure level to obtain a first sequence;

[0176] Verify other preset structure levels of the same level in sequence according to the first sequence;

[0177] When verifying a target other preset structure level, if the verification fails, adjust the model parameters of the non-coincident child structure levels to perform verification and model parameter adjustment for other preset structure levels, where the target other preset structure level is any structure level among other preset structure levels of the same level.

[0178] Among them, the child structure is a component. When the verified one is the second level 1, the number of child structure levels that coincide with the second level 2 is 2, the number of child structure levels that coincide with the second level 3 is 1, the number of child structure levels that coincide with the second level 4 is 0, and the number of child structure levels that coincide with the second level 5 is 0. The obtained first sequence is the second level 2 - the second level 3 - the second level 4 / second level 5. Then verify and adjust the model in sequence according to the first sequence.

[0179] It can be seen that in the embodiment of the present application, when verifying the preset structure level of the non-root level structure, by comparing the number of coincident child structure levels in different preset structure levels, other preset structure levels of the same level are sorted, so as to preferentially verify those structure levels with high similarity to the verified level, which not only improves the verification efficiency, but also can more accurately locate the problem when the verification fails, that is, the non-coincident child structure levels, and then perform targeted model parameter adjustment.

[0180] Further, S105 performs operation and maintenance management based on the digital twin model of the edge substation, including:

[0181] Obtain the current operation compressed data corresponding to each of the multiple grid devices in the edge substation. The current operation compressed data includes multi-dimensional compressed data, and each dimension of compressed data is the compressed data of the changing dimension;

[0182] Decompress the current operation compressed data to obtain the current operation data;

[0183] Monitor the operation status of multiple grid devices in the edge substation according to the current operation data by using the digital twin model of the edge substation.

[0184] In the embodiments of the present application, when the power grid equipment is operating normally, a large amount of real-time data is continuously generated. Directly storing and transmitting this data not only occupies a large amount of resources but may also lead to low processing efficiency due to the large amount of data. Therefore, in practical applications, these real-time data are usually compressed to reduce the storage and transmission space requirements.

[0185] Specifically, the pre-operational compressed data refers to the data set obtained after compressing the real-time data of the power grid equipment, aiming to reduce the storage and transmission space requirements of the data while retaining the main features and change information of the data. The multi-dimensional compressed data indicates that the compressed data contains information in multiple dimensions, and each dimension corresponds to a specific aspect or parameter during the operation of the power grid equipment. These dimensions can be voltage, current, temperature, power factor, etc. Each dimension of the compressed data is the dimension data that varies greatly over time or conditions. This compression of the varying dimensions aims to more accurately retain the change trend and abnormal information of the data. After obtaining the current operational compressed data, the detailed operational data of the power grid equipment can be decompressed for subsequent analysis or monitoring.

[0186] It can be seen that in the embodiments of the present application, when performing operation and maintenance management based on the digital twin model of the edge substation, a multi-dimensional compressed data decompression technology is introduced; the data is efficiently compressed, reducing the storage and transmission burden, not only improving the efficiency and accuracy of data processing but also enabling real-time and accurate monitoring of the operating status of the power grid equipment without sacrificing data integrity.

[0187] In the embodiments of the present application, an operation and maintenance management platform 300 based on digital twin is provided, as Figure 3 shown, including:

[0188] An acquisition module 310, configured to acquire the device key values and device data corresponding to multiple power grid devices in the edge substation. The device criticality is determined based on the role and importance of the power grid device in the power grid. The device data includes the operation duration, the number of faults, and the service life;

[0189] A device classification module 320, configured to determine, from multiple power grid devices, a number of first power grid devices belonging to critical devices according to the device key values corresponding to the multiple power grid devices; the number of first power grid devices includes: power grid devices with device key values greater than a preset device criticality threshold and power grid devices strongly associated with power grid devices with device key values greater than the preset device criticality threshold;

[0190] And, for the second power grid devices other than the first power grid devices among the multiple power grid devices, determine critical devices and non-critical devices from the second power grid devices according to the operation duration, the number of faults, the service life, and the device key values of each second power grid device;

[0191] A building module 330 is configured to build digital twin models corresponding to critical devices and non-critical devices respectively, so as to obtain a digital twin model corresponding to an edge substation. Among them, the modeling accuracy of the first digital twin model corresponding to the critical device is higher than that of the second digital twin model corresponding to the non-critical device.

[0192] A management module 340 is configured to perform operation and maintenance management based on the digital twin model of the edge substation.

[0193] In an implementable embodiment, the device classification module 320 is further configured to:

[0194] Determine associated devices according to the directed connection graph of power grid devices whose device critical values are greater than a preset device criticality threshold.

[0195] Obtain the abnormal time sequence, abnormal degree, and abnormal frequency of the associated devices when a power grid device with a device critical value greater than the preset device criticality threshold is abnormal. The abnormal time sequence is the order in which the power grid device becomes abnormal in the abnormal event.

[0196] Determine the influence value of the associated devices on the power grid devices whose device critical values are greater than the preset device criticality threshold according to the abnormal time sequence, abnormal degree, and abnormal frequency of the associated devices.

[0197] Determine strongly associated devices from the associated devices based on the influence value.

[0198] In an implementable embodiment, the management module 340 is further configured to:

[0199] When it is determined that the operating state of a power grid device is abnormal, determine the relevant information of the power grid device with the abnormal operating state through the digital twin model of the edge substation. The relevant information at least includes: device location information, location information of the abnormal component, and importance value of the abnormal component.

[0200] Predict the cause of the abnormality of the abnormal component.

[0201] Match a number of corresponding maintenance suggestions for the abnormal component from the operation and maintenance dictionary according to the cause of the abnormality.

[0202] Determine an inspection trajectory according to the relevant information of the power grid device with the abnormal operating state. The inspection trajectory includes: the inspection order of the power grid device with the abnormal operating state, and the inspection duration of the power grid device with the abnormal operating state. The inspection duration includes the display duration of the component and the display duration of a number of maintenance suggestions.

[0203] When an inspection start instruction is detected, provide navigation guidance for the user in the virtual scene according to the inspection trajectory. When the abnormal component is inspected, display a number of corresponding maintenance suggestions in the virtual scene.

[0204] In an implementable embodiment, the management module 340 is further configured to: cluster grid devices according to the abnormal causes of the abnormal components of the grid devices with abnormal operating states to obtain several device groups;

[0205] For each device group, determine the first order of the grid devices in the device group according to the average importance value corresponding to the importance value of the abnormal components of the grid devices in the device group;

[0206] Determine the second order of the device group according to the number of key devices in each device group and the average importance value corresponding to the importance value of the abnormal components of the grid devices in the device group;

[0207] Determine the inspection order based on the first order, the second order, the device location information, and the location information of the abnormal components;

[0208] Determine the display duration of several maintenance suggestions according to the content lengths of the several maintenance suggestions;

[0209] Determine the display duration of the components according to the importance value of the abnormal components and the complexity of the abnormal components.

[0210] In an implementable embodiment, the grid device is a device with a multi-level structural hierarchy, and the non-root structural hierarchy is composed of at least two sub-level structures;

[0211] The platform further includes: a verification module 350, configured to:

[0212] Obtain a first preset verification parameter and first actual operation and maintenance information corresponding to the first preset verification parameter, where the first preset verification parameter includes verification parameters corresponding to multiple structural hierarchies of the grid device; and, obtain a second preset verification parameter and second actual operation and maintenance information corresponding to the second preset verification parameter;

[0213] According to the verification parameter corresponding to the preset structural hierarchy in the first preset verification parameter of the grid device, input it into the digital twin model to obtain the first operation and maintenance information corresponding to the preset structural hierarchy; according to the first operation and maintenance information and the actual operation and maintenance information corresponding to the preset structural hierarchy in the first actual operation and maintenance information of the grid device, verify the effectiveness of the preset structural hierarchy of the digital twin model corresponding to the edge substation; when the verification of the preset structural hierarchy fails, adjust the model parameters of the preset structural hierarchy and verify again until the verification is successful, and then verify the next same-level preset structural hierarchy;

[0214] When all the preset structural levels are successfully verified, the relevance between the components of the preset structural level is determined based on the association map of the grid equipment, and the components are the sub-structural levels of the preset structural level; the verification parameters regarding the preset structural level in the second preset verification parameters and the actual operation and maintenance information corresponding to the preset structural level in the second actual operation and maintenance information of the grid equipment are used to verify the components with relevance again; if the verification of the components with relevance fails, the model parameters of the target component are adjusted until the verification is successful, and the target component is the component with relevance and failed verification.

[0215] If the verification of the components with relevance is successful, the verification of the next-level structural level is carried out until the verification and adjustment of all structural levels are completed, and the digital twin model corresponding to the final edge substation is obtained.

[0216] In an implementable embodiment, the verification module 350 is further configured to:

[0217] Sort other preset structural levels of the same level according to the number of sub-structural levels that coincide with the verified preset structural level to obtain a first sequence;

[0218] Verify other preset structural levels of the same level in sequence according to the first sequence;

[0219] When verifying a target other preset structural level, if the verification fails, adjust the model parameters of the non-coincident sub-structural level to perform the verification and model parameter adjustment of the other preset structural level, and the target other preset structural level is any structural level among other preset structural levels of the same level.

[0220] In an implementable embodiment, the acquisition module 310 is configured to:

[0221] Acquire the current operation compressed data corresponding to multiple grid equipment in the edge substation, where the current operation compressed data includes multi-dimensional compressed data, and each dimension of compressed data is the compressed data of the changing dimension;

[0222] Decompress the current operation compressed data to obtain the current operation data;

[0223] Monitor the operation status of multiple grid equipment in the edge substation according to the current operation data by using the digital twin model of the edge substation.

[0224] In the embodiment of the present application, an electronic device is provided, as Figure 4 shown, Figure 4The electronic device 300 shown includes: a processor 301 and a memory 303. Among them, the processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may further include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation to the embodiments of the present application.

[0225] The processor 301 may be a CPU (Central Processing Unit, central processor), a general-purpose processor, a DSP (Digital Signal Processor, data signal processor), an ASIC (Application Specific Integrated Circuit, application-specific integrated circuit), an FPGA (Field Programmable Gate Array, field programmable gate array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logic blocks, modules, and circuits described in connection with the disclosure of the present application. The processor 301 may also be a combination that implements computing functions, such as a combination including one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0226] The bus 302 may include a path for transmitting information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus or an EISA (Extended Industry Standard Architecture, extended industry standard architecture) bus, etc. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 4 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0227] The memory 303 can be a ROM (Read Only Memory), or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory), or other types of dynamic storage devices that can store information and instructions. It can also be an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0228] The memory 303 is used to store the application program code for executing the solution of this application, and is controlled and executed by the processor 301. The processor 301 is used to execute the application program code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0229] Among them, the electronic device includes but is not limited to: mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The illustrated electronic device is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of this application.

[0230] The embodiments of this application provide a computer-readable storage medium, on which a computer program is stored. When it runs on a computer, it enables the computer to execute the corresponding content in the foregoing method embodiments.

[0231] The embodiments of this application provide a computer program product, including a computer program. When the computer program is executed by a processor, it implements the corresponding content in the foregoing method embodiments.

[0232] It should be understood that although the steps in the flowchart of the accompanying drawings are shown sequentially according to the indication of the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless there is a clear indication in this text, there is no strict order restriction for the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0233] The above are only some implementation manners of the present application. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present application, several improvements and refinements can still be made, and these improvements and refinements should also be regarded as the protection scope of the present application.

Claims

1. An operation and maintenance management method based on digital twins, characterized in that: Including: Obtain the device key values and device data corresponding to multiple power grid devices in the edge substation, where the device data includes operation duration, number of faults, and service life; According to the device key values corresponding to multiple power grid devices, determine several first power grid devices belonging to key devices from the multiple power grid devices; The several first power grid devices include: power grid devices with device key values greater than the preset device criticality threshold and power grid devices strongly associated with power grid devices with device key values greater than the preset device criticality threshold; For the second power grid devices other than the first power grid devices among the multiple power grid devices, determine key devices and non-key devices from the second power grid devices according to the operation duration, number of faults, service life, and device key values of each second power grid device; Construct digital twin models corresponding to the key devices and non-key devices respectively to obtain the digital twin model corresponding to the edge substation; among them, the modeling accuracy of the first digital twin model corresponding to the key device is higher than that of the second digital twin model corresponding to the non-key device; the modeling techniques used for key devices include physics-based simulation models and deep learning models; for non-key devices, the modeling methods used include statistical models and rule-based reasoning models; Obtain the first preset verification parameter and the first actual operation and maintenance information corresponding to the first preset verification parameter; obtain the second preset verification parameter and the second actual operation and maintenance information corresponding to the second preset verification parameter; According to the verification parameter corresponding to the preset structure level in the first preset verification parameter of the power grid device, input it into the digital twin model to obtain the first operation and maintenance information corresponding to the preset structure level; verify the effectiveness of the preset structure level of the digital twin model corresponding to the edge substation according to the actual operation and maintenance information corresponding to the preset structure level in the first operation and maintenance information and the first actual operation and maintenance information of the power grid device; When all the preset structure levels are verified successfully, then based on the association map of the power grid device, determine the association between the components of the preset structure level; use the verification parameter regarding the preset structure level in the second preset verification parameter and the actual operation and maintenance information corresponding to the preset structure level in the second actual operation and maintenance information of the power grid device to verify the associated components again; if the associated components are verified successfully, perform the verification of the next-level structure level until all structure levels are verified and adjusted to obtain the final digital twin model; Carry out operation and maintenance management based on the digital twin model of the edge substation.

2. The method according to claim 1, wherein The process of determining strongly associated power grid devices includes: According to the connected directed graph of power grid devices with device key values greater than the preset device criticality threshold, determine the corresponding associated devices; Obtain the abnormal time sequence, abnormal degree, and abnormal frequency of the associated devices when the power grid devices with device key values greater than the preset device criticality threshold are abnormal, where the abnormal time sequence is the order in which the power grid devices have abnormalities in the abnormal event; According to the abnormal time sequence, abnormal degree, and abnormal frequency of the associated devices, determine the influence value of the associated devices on the power grid devices with device key values greater than the preset device criticality threshold; Determine strongly associated devices from associated devices based on influence values.

3. The method according to claim 1, wherein The operation and maintenance management based on the digital twin model of the edge substation includes: When it is determined that the operating state of a grid device is abnormal, relevant information of the grid device with the abnormal operating state is determined through the digital twin model of the edge substation. The relevant information includes at least: device location information, location information of abnormal components, and importance values of abnormal components; Predict the abnormal causes of abnormal components; According to the abnormal causes, match several corresponding maintenance suggestions for the abnormal components from the operation and maintenance dictionary; Determine an inspection trajectory according to the relevant information of the grid device with the abnormal operating state. The inspection trajectory includes: the inspection order of the grid device with the abnormal operating state, and the inspection duration of the grid device with the abnormal operating state. The inspection duration includes the display duration of the component and the display duration of several maintenance suggestions; When an inspection start instruction is detected, provide navigation guidance for the user in the virtual scene according to the inspection trajectory. When the abnormal component is inspected, display several corresponding maintenance suggestions in the virtual scene.

4. The method according to claim 3, characterized in that, The determination of the inspection trajectory according to the relevant information of the grid device with the abnormal operating state includes: Cluster the grid devices according to the abnormal causes of the abnormal components of the grid device with the abnormal operating state to obtain several device groups; For each device group, determine the first order of the grid devices in the device group according to the average importance value corresponding to the importance value of the abnormal components of the grid devices in the device group; Determine the second order of the device group according to the number of key devices in each device group and the average importance value corresponding to the importance value of the abnormal components of the grid devices in the device group; Based on the first order, the second order, the device location information, and the location information of the abnormal components, determine the inspection order; Determine the display duration of several maintenance suggestions according to the content length of several maintenance suggestions; Determine the display duration of the component according to the importance value of the abnormal component and the complexity of the abnormal component.

5. The method according to claim 1, characterized in that, The grid device is a device with a multi-level hierarchical structure, and the non-root hierarchical structure is composed of at least two sub-level structures; The method further includes: When the preset hierarchical verification fails, adjust the model parameters of the preset hierarchical structure and verify again until the verification is successful, and then verify the next same-level preset hierarchical structure; If the verification of the associated components fails, adjust the model parameters of the target components until the verification is successful. The target components are the associated components that have failed the verification.

6. The method according to claim 5, characterized in that, If the preset hierarchical level is a non-root hierarchical structure, the verification of the next same-level preset hierarchical structure includes: Sort the other preset hierarchical structures of the same level according to the number of sub-level hierarchical structures that coincide with the verified preset hierarchical structure to obtain a first sequence; Verify the other preset hierarchical structures of the same level in sequence according to the first sequence; When verifying other preset structural levels of the target, if the verification fails, adjust the model parameters of the non-coincident sub-structural levels to verify other preset structural levels and adjust the model parameters. The target other preset structural level is any structural level in other preset structural levels of the same level.

7. The method according to any one of claims 1 to 6, characterized in that, Perform operation and maintenance management based on the digital twin model of the edge substation, including: Obtain the current operation compressed data corresponding to multiple power grid devices in the edge substation. The current operation compressed data includes multi-dimensional compressed data, and each dimension of compressed data is the compressed data of the changing dimension; Decompress the current operation compressed data to obtain the current operation data; Monitor the operation status of multiple power grid devices in the edge substation according to the current operation data using the digital twin model of the edge substation.

8. An operation and maintenance management platform based on digital twin, characterized in that, Including: An acquisition module for acquiring the device key values and device data corresponding to multiple power grid devices in the edge substation. The device key values are determined based on the role and importance of the power grid devices in the power grid, and the device data includes the operation duration, the number of faults, and the service life; A device classification module for determining a number of first power grid devices belonging to key devices from multiple power grid devices according to the device key values corresponding to the multiple power grid devices; The number of first power grid devices includes: power grid devices with device key values greater than the preset device criticality threshold and power grid devices strongly associated with power grid devices with device key values greater than the preset device criticality threshold; And for the second power grid devices other than the first power grid devices among the multiple power grid devices, determine key devices and non-key devices from the second power grid devices according to the operation duration, the number of faults, the service life, and the device key values of each second power grid device; A construction module for constructing digital twin models corresponding to key devices and non-key devices respectively to obtain the digital twin model corresponding to the edge substation; among them, the modeling accuracy of the first digital twin model corresponding to the key device is higher than that of the second digital twin model corresponding to the non-key device; the modeling technologies adopted for key devices include physics-based simulation models and deep learning models; for non-key devices, the modeling methods adopted include statistical models and rule-based inference models; A verification module, configured to obtain a first preset verification parameter and first actual operation and maintenance information corresponding to the first preset verification parameter; obtain a second preset verification parameter and second actual operation and maintenance information corresponding to the second preset verification parameter; input, according to the verification parameter corresponding to the preset structure level in the first preset verification parameter of the power grid device, into the digital twin model to obtain first operation and maintenance information corresponding to the preset structure level; verify the effectiveness of the preset structure level of the digital twin model corresponding to the edge substation according to the actual operation and maintenance information corresponding to the preset structure level in the first operation and maintenance information and the first actual operation and maintenance information of the power grid device; when all the preset structure levels are verified successfully, determine the relevance between the components of the preset structure level based on the association graph of the power grid device; use the verification parameter regarding the preset structure level in the second preset verification parameter and the actual operation and maintenance information corresponding to the preset structure level in the second actual operation and maintenance information of the power grid device to verify the components with relevance again; if the components with relevance are verified successfully, perform verification on the next-level structure level until all structure levels are verified and adjusted to obtain the final digital twin model; A management module, configured to perform operation and maintenance management based on the digital twin model of the edge substation.

9. An electronic device, characterized in that, Comprising: One or more processors; A memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to: execute the steps of the operation and maintenance management method based on digital twin according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A storage medium stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, at least one program, a code set or an instruction set is loaded and executed by a processor to execute the steps of the operation and maintenance management method based on digital twin according to any one of claims 1 to 7.

Images