Electric power data processing method and system based on intelligent operation and maintenance

Abstract

The invention provides an electric power data processing method and system based on intelligent operation and maintenance, and the method comprises the steps: obtaining a basic fault operation and maintenance node in electric power intelligent operation and maintenance data and a plurality of corresponding derivative fault operation and maintenance nodes, and determining the discrimination information of the derivative fault operation and maintenance nodes and the basic fault operation and maintenance node in the same electric power operation and maintenance feature domain; target power operation and maintenance feature domains corresponding to the power operation and maintenance feature domains are determined from the multiple derivative fault operation and maintenance nodes, the target power operation and maintenance feature domains are converged, and target derivative fault operation and maintenance nodes are generated. According to the method, the accuracy and efficiency of power data processing are effectively improved, and finer and more intelligent support is provided for power operation and maintenance.

Description

Technical Field

[0001] The present application relates to the field of intelligent operation and maintenance technology, and specifically, to an electric power data processing method and system based on intelligent operation and maintenance. Background Art

[0002] In the field of power operation and maintenance, as the power system continues to develop and become more complex, the processing and analysis of power data has become increasingly important. Traditional power data processing methods often rely on manual experience and rules, and it is difficult to effectively deal with large-scale and diverse power operation and maintenance data. In particular, when a power system fails, it is necessary to quickly and accurately locate the fault point, and analyze the possible causes and impact range of the fault, so as to take timely repair measures.

[0003] In order to improve the intelligence level of power data processing, power data processing methods based on smart operation and maintenance have emerged in recent years. These methods use advanced data analysis technology and machine learning algorithms to conduct in-depth mining and intelligent processing of power operation and maintenance data. However, existing smart operation and maintenance methods still have some limitations when processing power fault operation and maintenance data. For example, they can often only process a single fault operation and maintenance node, and it is difficult to consider the derivative relationship and mutual influence between faults. In addition, when processing derivative fault operation and maintenance nodes, existing methods lack an effective mechanism to distinguish and select target feature domains in different power operation and maintenance feature domains. Summary of the invention

[0004] In view of this, the purpose of this application is to provide a power data processing method and system based on intelligent operation and maintenance.

[0005] According to a first aspect of the present application, a method for processing power data based on intelligent operation and maintenance is provided, the method comprising:

[0006] Obtaining a basic fault operation and maintenance node in the electric power smart operation and maintenance data, and a plurality of derived fault operation and maintenance nodes corresponding to the basic fault operation and maintenance node, wherein the derived fault operation and maintenance node is a fault operation and maintenance node generated by deriving and simulating the basic fault operation and maintenance node using derived knowledge points, and the combination of derived knowledge points in different derived fault operation and maintenance nodes is inconsistent;

[0007] Determine the distinguishing information between the derived fault operation and maintenance node and the basic fault operation and maintenance node in the same power operation and maintenance feature domain;

[0008] For each power operation and maintenance feature domain corresponding to the basic fault operation and maintenance node and the derived fault operation and maintenance node, based on the distinguishing information, determine a target power operation and maintenance feature domain corresponding to each power operation and maintenance feature domain from the multiple derived fault operation and maintenance nodes;

[0009] The target power operation and maintenance feature domains corresponding to the various power operation and maintenance feature domains are aggregated to generate a target derived fault operation and maintenance node.

[0010] In a possible implementation of the first aspect, the method further includes:

[0011] According to the basic fault operation and maintenance nodes in the electric power smart operation and maintenance data, basic derived fault operation and maintenance nodes are generated based on the derived knowledge points;

[0012] According to the basic fault operation and maintenance nodes in the electric power smart operation and maintenance data, the derived knowledge points constituting the basic derived fault operation and maintenance nodes are optimized to generate advanced derived fault operation and maintenance nodes.

[0013] In a possible implementation manner of the first aspect, optimizing the derived knowledge points constituting the basic derived fault operation and maintenance nodes according to the basic fault operation and maintenance nodes in the electric power smart operation and maintenance data to generate advanced derived fault operation and maintenance nodes includes:

[0014] Generate iterative distribution features based on the basic fault operation and maintenance nodes in the electric power smart operation and maintenance data and the distribution features of the derived knowledge points in the basic derived fault operation and maintenance nodes;

[0015] Based on the iterative distribution characteristics, the derived knowledge points constituting the basic derived fault operation and maintenance node are optimized to generate an advanced derived fault operation and maintenance node.

[0016] In a possible implementation manner of the first aspect, the generating a basic derived fault operation and maintenance node based on the derived knowledge point according to the basic fault operation and maintenance node in the electric power smart operation and maintenance data includes:

[0017] Determining a knowledge point mapping area on a basic fault operation and maintenance node in the electric power smart operation and maintenance data;

[0018] A basic derived fault operation and maintenance node is generated according to the knowledge point mapping area and the derived knowledge point.

[0019] In a possible implementation manner of the first aspect, generating a basic derived fault operation and maintenance node according to the knowledge point mapping area and the derived knowledge point includes:

[0020] Obtain a target attribute necklace of the basic fault operation and maintenance node in the knowledge point mapping area;

[0021] Based on the target attribute necklace, attribute values ​​are assigned to the derived knowledge points in the knowledge point mapping area to generate a basic derived fault operation and maintenance node.

[0022] In a possible implementation manner of the first aspect, generating iterative distribution features based on the basic fault operation and maintenance nodes in the electric power smart operation and maintenance data and the distribution features of the derived knowledge points in the basic derived fault operation and maintenance nodes includes:

[0023] Determine the power operation and maintenance feature domain to be updated of the basic derived fault operation and maintenance node;

[0024] According to the basic fault operation and maintenance nodes in the electric power smart operation and maintenance data, the distribution characteristics of the derived knowledge points of the to-be-updated electric power operation and maintenance feature domain in the basic derived fault operation and maintenance nodes are updated to generate iterative distribution characteristics.

[0025] In a possible implementation manner of the first aspect, determining the distinguishing information between the derived fault operation and maintenance node and the basic fault operation and maintenance node in the same power operation and maintenance feature domain includes:

[0026] Determine target distinguishing information of the basic derived fault operation and maintenance node and the basic fault operation and maintenance node in the same power operation and maintenance feature domain;

[0027] The step of determining the power operation and maintenance feature domain to be updated of the basic derived fault operation and maintenance node includes:

[0028] Based on the target distinguishing information, the power operation and maintenance feature domain to be updated is determined from the basic derived fault operation and maintenance node.

[0029] In a possible implementation of the first aspect, the method further includes:

[0030] Obtain calibration operation and maintenance knowledge points;

[0031] Determining a derived knowledge point based on a category label corresponding to the calibrated operation and maintenance knowledge point, wherein a sub-label of the derived knowledge point includes the calibrated operation and maintenance knowledge point;

[0032] After the target power operation and maintenance feature domains corresponding to the respective power operation and maintenance feature domains are aggregated to generate a target derived fault operation and maintenance node, the method further includes:

[0033] According to the calibrated operation and maintenance knowledge points, the derived knowledge points constituting the target derived fault operation and maintenance node are semantically transformed to generate an iterative target derived fault operation and maintenance node. The iterative target derived fault operation and maintenance node is a fault operation and maintenance node generated by deriving and simulating the basic fault operation and maintenance node based on the calibrated operation and maintenance knowledge points.

[0034] In a possible implementation manner of the first aspect, after the semantic conversion of the derived knowledge points constituting the target derived fault operation and maintenance node is performed according to the calibrated operation and maintenance knowledge points to generate the iterative target derived fault operation and maintenance node, the method further includes:

[0035] Cross-analyze the calibrated operation and maintenance knowledge points constituting the iterative target derived fault operation and maintenance node to generate operation and maintenance knowledge points to be expanded and operation and maintenance knowledge points to be cleared, wherein the operation and maintenance knowledge points to be expanded and the operation and maintenance knowledge points to be cleared have semantic intersections;

[0036] Based on the operation and maintenance knowledge points to be cleaned up, the operation and maintenance knowledge points to be expanded in the iteration target derived fault operation and maintenance node are extended to generate extended operation and maintenance knowledge points, where the extended operation and maintenance knowledge points include the operation and maintenance knowledge points to be cleaned up;

[0037] Based on the extended operation and maintenance knowledge points, the operation and maintenance knowledge points to be cleaned up in the iteration target derived fault operation and maintenance node are removed to generate an optimized iteration target derived fault operation and maintenance node.

[0038] For example, in a possible implementation of the first aspect, based on the extended operation and maintenance knowledge point, removing the operation and maintenance knowledge point to be cleaned in the iteration target derived fault operation and maintenance node to generate an optimized iteration target derived fault operation and maintenance node includes:

[0039] Determining the attribute necklace of the extended operation and maintenance knowledge point according to the attribute necklace of the operation and maintenance knowledge point to be extended and the attribute necklace of the operation and maintenance knowledge point to be cleared;

[0040] Determine a candidate power operation and maintenance feature domain corresponding to the extended operation and maintenance knowledge point from the basic fault operation and maintenance node;

[0041] Determining operation and maintenance knowledge point maintenance information of the extended operation and maintenance knowledge point based on the attribute necklace of the candidate power operation and maintenance feature domain and the attribute necklace of the extended operation and maintenance knowledge point;

[0042] Based on the operation and maintenance knowledge point maintenance information of the extended operation and maintenance knowledge point, the operation and maintenance knowledge point to be cleaned up in the iteration target derived fault operation and maintenance node is removed to generate an optimized iteration target derived fault operation and maintenance node.

[0043] For example, in a possible implementation of the first aspect, the method further includes:

[0044] Acquire an operation and maintenance knowledge sequence of operation and maintenance knowledge points constituting the target derived fault operation and maintenance node and a data structure of the environment to be migrated, wherein the operation and maintenance knowledge sequence includes knowledge features of each operation and maintenance knowledge point constituting the target derived fault operation and maintenance node;

[0045] Based on the data structure, a knowledge feature of each operation and maintenance knowledge point in the operation and maintenance knowledge sequence is subjected to structural conversion processing to obtain an updated operation and maintenance knowledge sequence;

[0046] The updated operation and maintenance knowledge sequence is sent to the environment to be migrated, so as to present a simulated fault operation and maintenance node composed of each operation and maintenance knowledge point in the updated operation and maintenance knowledge sequence in the environment to be migrated.

[0047] According to the second aspect of the present application, a power data processing system based on smart operation and maintenance is provided, wherein the power data processing system based on smart operation and maintenance comprises a machine-readable storage medium and a processor, wherein the machine-readable storage medium stores machine-executable instructions, and when the processor executes the machine-executable instructions, the power data processing system based on smart operation and maintenance implements the aforementioned power data processing method based on smart operation and maintenance.

[0048] According to a third aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed, the aforementioned power data processing method based on smart operation and maintenance is implemented.

[0049] According to any one of the above aspects, the technical effect of the present application is:

[0050] By obtaining the basic fault operation and maintenance nodes and their corresponding multiple derived fault operation and maintenance nodes in the power smart operation and maintenance data, and determining the difference information between these derived fault operation and maintenance nodes and the basic fault operation and maintenance nodes in the same power operation and maintenance feature domain, the target power operation and maintenance feature domain corresponding to each power operation and maintenance feature domain is determined from multiple derived fault operation and maintenance nodes, and these target power operation and maintenance feature domains are aggregated to generate target derived fault operation and maintenance nodes. This method effectively improves the accuracy and efficiency of power data processing and provides more refined and intelligent support for power operation and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0052] Figure 1 A flowchart of a method for processing power data based on intelligent operation and maintenance provided in an embodiment of the present application.

[0053] Figure 2 A schematic diagram of the component structure of an electric power data processing system based on intelligent operation and maintenance provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical scheme and advantages of the embodiment of the present application clearer, the technical scheme in the embodiment of the present application will be clearly and completely described below according to the drawings in the embodiment of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description, and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the embodiment of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add multiple other operations to the flowchart under the guidance of the content of the present application, and can also destroy multiple operations from the flowchart.

[0055] Figure 1 The flowchart of the power data processing method and system based on smart operation and maintenance provided by the embodiment of the present application is shown. It should be understood that in other embodiments, the order of some steps in the power data processing method based on smart operation and maintenance of this embodiment can be shared with each other according to actual needs, or some steps can be omitted or maintained. The detailed steps of the power data processing method based on smart operation and maintenance include:

[0056] Step S110, obtaining a basic fault operation and maintenance node in the electric power smart operation and maintenance data, and a plurality of derived fault operation and maintenance nodes corresponding to the basic fault operation and maintenance node, wherein the derived fault operation and maintenance node is a fault operation and maintenance node generated by deriving and simulating the basic fault operation and maintenance node using derived knowledge points, and the combination of derived knowledge points in different derived fault operation and maintenance nodes is inconsistent.

[0057] In this embodiment, the server is responsible for managing the intelligent operation and maintenance data of a large power system. In this power system, there are various equipment and lines, such as transformers, switch cabinets, transmission lines, etc.

[0058] Example of a basic fault operation and maintenance node: Assume that a transformer has an overheating fault, which is identified as a basic fault operation and maintenance node. Its related characteristic information includes: the specific value of the overheating, the duration of the overheating, the model and location of the transformer, etc.

[0059] Generation of derived fault operation and maintenance nodes: Different derived knowledge points are used to derive and simulate the basic fault operation and maintenance node. For example, the first derived fault operation and maintenance node may be based on the basic fault operation and maintenance node, with the addition of the derived knowledge point of excessively high ambient temperature, which considers that the overheating fault is not only a problem of the transformer itself, but may also be affected by the external ambient temperature. In addition to the characteristic information of the basic fault operation and maintenance node, its characteristic information also includes the specific value of the ambient temperature.

[0060] The second derived fault operation and maintenance node may be based on the basic fault operation and maintenance node, adding the derived knowledge point of transformer overload, and assuming that the overheating fault is caused by the load exceeding the rated load of the transformer. Its characteristic information will include the specific value of the load, etc.

[0061] The third derivative fault operation and maintenance node may be based on the basic fault operation and maintenance node, adding the derivative knowledge point of transformer internal insulation aging, and assuming that overheating is caused by increased resistance due to insulation aging. Its characteristic information will include relevant data such as the degree of aging of the insulation material.

[0062] The combination of derivative knowledge points in different derivative fault operation and maintenance nodes is inconsistent, so that various factors that may cause basic failures can be fully considered.

[0063] Step S120, determining the distinguishing information between the derived fault operation and maintenance node and the basic fault operation and maintenance node in the same power operation and maintenance feature domain.

[0064] Taking the transformer overheating fault as an example, for the first derived fault operation and maintenance node (considering the ambient temperature is too high), in the power operation and maintenance feature domain "temperature related", the difference between it and the basic fault operation and maintenance node is the addition of the ambient temperature measurement value, while the basic fault operation and maintenance node only has the transformer's own temperature measurement value.

[0065] For the second derivative fault operation and maintenance node (considering excessive load), in the "load-related" feature domain, the distinguishing information is the addition of the specific value of the load, which is not available in the basic fault operation and maintenance node.

[0066] For the third derived fault operation and maintenance node (considering insulation aging), in the "insulation related" feature domain, the distinguishing information is the addition of assessment data on the degree of insulation aging, which is not included in the basic fault operation and maintenance node.

[0067] The server compares and analyzes the data in these feature domains to accurately determine the difference between each derived fault operation and maintenance node and the basic fault operation and maintenance node.

[0068] Step S130, for each power operation and maintenance feature domain corresponding to the basic fault operation and maintenance node and the derived fault operation and maintenance node, based on the distinguishing information, determine the target power operation and maintenance feature domain corresponding to each power operation and maintenance feature domain from the multiple derived fault operation and maintenance nodes.

[0069] Continuing with the transformer overheating fault as an example, in the "temperature-related" feature domain, the server analysis found that the newly added ambient temperature information in the first derivative fault operation and maintenance node is of great significance for fully understanding and solving the overheating problem, so it is determined as the target power operation and maintenance feature domain of this feature domain.

[0070] In the "load-related" feature domain, the server assessment believes that the newly added load value in the second derivative fault operation and maintenance node is crucial for accurately determining the cause of overheating and taking measures, so it is determined as the target power operation and maintenance feature domain of this feature domain.

[0071] In the "insulation-related" feature domain, the server determines based on the analysis results that the data on the degree of insulation aging in the third derivative fault operation and maintenance node is the key to solving the problem, and thus selects it as the target power operation and maintenance feature domain of this feature domain.

[0072] Step S140: Aggregate the target power operation and maintenance feature domains corresponding to the various power operation and maintenance feature domains to generate a target derived fault operation and maintenance node.

[0073] The server integrates and aggregates the target power operation and maintenance feature domains determined in each power operation and maintenance feature domain.

[0074] For example, the ambient temperature information selected in the "temperature-related" feature domain, the load value selected in the "load-related" feature domain, and the insulation aging degree data selected in the "insulation-related" feature domain, bring together key information from different derived fault operation and maintenance nodes to form a new, comprehensive target derived fault operation and maintenance node.

[0075] This target-derived fault operation and maintenance node contains the most comprehensive and critical information, which can provide a more accurate and effective basis for subsequent fault diagnosis, maintenance decisions and preventive measures, and help improve the operation and maintenance efficiency and reliability of the power system.

[0076] Based on the above steps, the embodiment of the present application obtains the basic fault operation and maintenance node and its corresponding multiple derived fault operation and maintenance nodes in the electric power intelligent operation and maintenance data, and determines the difference information between these derived fault operation and maintenance nodes and the basic fault operation and maintenance nodes in the same electric power operation and maintenance feature domain, and then determines the target electric power operation and maintenance feature domain corresponding to each electric power operation and maintenance feature domain from multiple derived fault operation and maintenance nodes, and aggregates these target electric power operation and maintenance feature domains to generate a target derived fault operation and maintenance node. This method effectively improves the accuracy and efficiency of electric power data processing, and provides more refined and intelligent support for electric power operation and maintenance.

[0077] In a possible implementation, the method further includes:

[0078] Step A110, according to the basic fault operation and maintenance nodes in the electric power smart operation and maintenance data, basic derived fault operation and maintenance nodes are generated based on the derived knowledge points.

[0079] Step A120, based on the basic fault operation and maintenance nodes in the electric power smart operation and maintenance data, the derived knowledge points constituting the basic derived fault operation and maintenance nodes are optimized to generate advanced derived fault operation and maintenance nodes.

[0080] In a possible implementation, step A120 includes:

[0081] Step A121, generating iterative distribution features based on the basic fault operation and maintenance nodes in the electric power smart operation and maintenance data and the distribution features of the derived knowledge points in the basic derived fault operation and maintenance nodes.

[0082] Step A122: Based on the iterative distribution characteristics, the derived knowledge points constituting the basic derived fault operation and maintenance node are optimized to generate an advanced derived fault operation and maintenance node.

[0083] In this embodiment, it is assumed that there is a basic fault operation and maintenance node, which is a short circuit fault of a transformer of a specific model. Its related characteristic information includes the time when the short circuit occurred, the magnitude of the short circuit current, the location and model of the transformer, etc.

[0084] According to the basic fault operation and maintenance nodes in the power smart operation and maintenance data, basic derived fault operation and maintenance nodes are generated based on derived knowledge points:

[0085] The server first determines the knowledge point mapping area on the basic fault operation and maintenance node in the power smart operation and maintenance data. For example, the electrical parameters, operating environment, maintenance records, etc. related to the transformer short circuit fault are determined as the knowledge point mapping area.

[0086] Next, based on these knowledge point mapping areas and existing derived knowledge points, such as "recently, large electrical equipment in the vicinity has started up, causing voltage fluctuations", a basic derived fault operation and maintenance node is generated. In addition to the feature information of the basic fault operation and maintenance node, this basic derived fault operation and maintenance node also includes the time when large electrical equipment started up, the amplitude of voltage fluctuations, etc.

[0087] Based on the basic fault operation and maintenance nodes in the power smart operation and maintenance data, the derived knowledge points that constitute the basic derived fault operation and maintenance nodes are optimized to generate advanced derived fault operation and maintenance nodes:

[0088] The server generates iterative distribution features based on the basic fault operation and maintenance nodes in the power smart operation and maintenance data and the distribution characteristics of the derived knowledge points in the basic derived fault operation and maintenance nodes.

[0089] For example, server analysis found that the derived knowledge points about voltage fluctuation in the basic derived fault operation and maintenance node are more concentrated in certain time periods, and the short-circuit current in the basic fault operation and maintenance node also has obvious changes in a specific time period. Combining this information, iterative distribution features are generated, such as finding that there is a certain correlation pattern between voltage fluctuation and short-circuit current in a specific time period.

[0090] Based on the generated iterative distribution characteristics, the server optimizes the derived knowledge points that constitute the basic derived fault operation and maintenance nodes. For example, if it is found that the voltage fluctuation is strongly correlated with the short-circuit current, the weight of this derived knowledge point may be further strengthened, or more detailed information related to the voltage fluctuation may be added, such as the frequency of the fluctuation. After such optimization, an advanced derived fault operation and maintenance node is generated.

[0091] Advanced derivative fault operation and maintenance nodes may contain more precise and comprehensive information, such as not only detailed information on voltage fluctuations, but also information on interactions with other surrounding power equipment, making fault analysis and diagnosis more accurate and in-depth.

[0092] By continuously repeating the above process, the server processes and optimizes a large number of basic fault operation and maintenance nodes, thereby continuously improving the fault analysis and processing capabilities of the power intelligent operation and maintenance system and improving the reliability and stability of the entire power system.

[0093] Suppose a new basic fault operation and maintenance node appears, which is a transmission line with frequent tripping faults. The server also follows the above steps to process. First, determine the knowledge point mapping area, which may include the material of the line, the geographical environment it passes through, and the climate conditions.

[0094] Then, based on the derived knowledge points, such as "there is a construction site near the line that causes line vibration", the basic derived fault operation and maintenance node is generated. Its characteristic information includes the specific time of construction, the scale of construction, the amplitude of line vibration, etc.

[0095] Next, the server generates iterative distribution features based on the distribution characteristics of the derived knowledge points in the basic fault operation and maintenance nodes and the basic derived fault operation and maintenance nodes, such as finding that the line vibration amplitude is more obvious under specific weather conditions.

[0096] Based on this iterative distribution feature, the derived knowledge points are optimized, such as adding considerations for the types of construction machinery and detailed analysis of the impact of weather conditions on line vibration, to generate advanced derived fault operation and maintenance nodes.

[0097] In actual power systems, such processing and optimization processes are ongoing. The server will accumulate a large amount of optimization experience and data models, and can handle new basic fault operation and maintenance nodes faster and more accurately, providing strong guarantees for the safe and stable operation of the power system.

[0098] For another example, for a basic fault operation and maintenance node where a switch cabinet fails, the knowledge point mapping area determined by the server may cover the internal structure, connection lines, service life, etc. of the switch cabinet.

[0099] Based on the derived knowledge point "equipment upgrade and renovation has been carried out recently", a basic derived fault operation and maintenance node is generated, and its characteristics include the specific content and time of the upgrade and renovation.

[0100] The server analyzes the distribution characteristics of derived knowledge points in the basic fault operation and maintenance nodes and the basic derived fault operation and maintenance nodes. For example, it finds that some upgraded and renovated components are closely related to the location where the fault occurs, and generates iterative distribution characteristics.

[0101] Optimize derived knowledge points based on iterative distribution characteristics. For example, deeply analyze the impact of material quality and installation technology used in upgrades and renovations on faults, and generate advanced derived fault operation and maintenance nodes.

[0102] By performing such processing and optimization on various types of basic fault operation and maintenance nodes, the server can build a comprehensive, accurate and constantly evolving knowledge system for intelligent power operation and maintenance, and effectively respond to various complex power fault situations.

[0103] In a possible implementation, step A110 includes:

[0104] Step A111, determining a knowledge point mapping area on a basic fault operation and maintenance node in the electric power smart operation and maintenance data.

[0105] Step A112: Generate a basic derived fault operation and maintenance node based on the knowledge point mapping area and the derived knowledge point.

[0106] In a possible implementation, step A112 includes:

[0107] Step A1121, obtaining the target attribute necklace of the basic fault operation and maintenance node in the knowledge point mapping area.

[0108] Step A1122: Based on the target attribute necklace, attribute values ​​are assigned to the derived knowledge points in the knowledge point mapping area to generate a basic derived fault operation and maintenance node.

[0109] In this embodiment, it is assumed that there is a basic fault operation and maintenance node, which is a circuit breaker in a substation that frequently trips. The server first determines the knowledge point mapping area on this basic fault operation and maintenance node. For the problem of circuit breaker tripping, the knowledge point mapping area determined by the server may include the model specification, installation location, operating years, recent operation records, and connection status of peripheral equipment of the circuit breaker.

[0110] Next, map the area and existing derived knowledge points based on these knowledge points, such as "the area has recently been struck by lightning". The server obtains the target attribute necklace of the basic fault operation and maintenance node in the area mapped by this knowledge point. Taking the operating years as an example, the target attribute necklace may be "has been in operation for 8 years, exceeding the average service life by 5 years". Based on this target attribute necklace, assign attributes to the derived knowledge point "the area has recently been struck by lightning". For example, the value assigned is "in the case of exceeding the average service life, it has recently been struck by lightning, increasing the risk of circuit breaker tripping", thereby generating a basic derived fault operation and maintenance node.

[0111] For example, another basic fault operation and maintenance node is the discharge of an insulator on a transmission line. The knowledge point mapping area determined by the server can be the material of the insulator, the voltage level of the line, the geographical environment (mountainous area, plain, etc.), and the climate conditions (humidity, wind speed, etc.).

[0112] Assume that the derived knowledge point is "There is a chemical plant nearby that emits corrosive gas". The server obtains the target attribute necklace of the insulator material, such as "Using ordinary ceramic material, the corrosion resistance is average". Based on this, attribute values ​​are assigned to the derived knowledge point, such as "In the case of ordinary ceramic material with average corrosion resistance, the corrosive gas emitted by the nearby chemical plant may cause the insulator discharge fault to worsen", thereby generating the basic derived fault operation and maintenance node.

[0113] For example, the basic fault operation and maintenance node is an overheating of a power capacitor. The knowledge point mapping area determined by the server includes the capacity, working voltage, heat dissipation conditions, etc. of the capacitor.

[0114] The derived knowledge point is "the harmonic content of the power grid exceeds the standard". The server obtains the target attribute necklace of the capacitor capacity, such as "the capacity is 50 microfarads and is in full load working state". Then, based on the target attribute necklace, attribute values ​​are assigned, such as "when the capacity is 50 microfarads and working at full load, the harmonic content of the power grid exceeds the standard and easily causes capacitor overheating", thereby generating a basic derived fault operation and maintenance node.

[0115] In this way, the server can make full use of the relevant information and derived knowledge points of the basic fault operation and maintenance nodes to generate more targeted and comprehensive basic derived fault operation and maintenance nodes, providing a richer and more accurate basis for subsequent fault analysis and processing.

[0116] In a possible implementation manner, the generating of iterative distribution features based on the basic fault operation and maintenance nodes in the electric power smart operation and maintenance data and the distribution features of the derived knowledge points in the basic derived fault operation and maintenance nodes includes:

[0117] Determine the power operation and maintenance feature domain to be updated of the basic derived fault operation and maintenance node.

[0118] According to the basic fault operation and maintenance nodes in the electric power smart operation and maintenance data, the distribution characteristics of the derived knowledge points of the to-be-updated electric power operation and maintenance feature domain in the basic derived fault operation and maintenance nodes are updated to generate iterative distribution characteristics.

[0119] In a possible implementation manner, the determining the distinguishing information of the derived fault operation and maintenance node and the basic fault operation and maintenance node in the same power operation and maintenance feature domain includes:

[0120] Determine target distinction information of the basic derived fault operation and maintenance node and the basic fault operation and maintenance node in the same power operation and maintenance feature domain.

[0121] The step of determining the power operation and maintenance feature domain to be updated of the basic derived fault operation and maintenance node includes:

[0122] Based on the target distinguishing information, the power operation and maintenance feature domain to be updated is determined from the basic derived fault operation and maintenance node.

[0123] In a possible implementation, the method further includes:

[0124] Obtain knowledge points on calibration and operation.

[0125] Based on the category label corresponding to the calibrated operation and maintenance knowledge point, a derived knowledge point is determined, and the sub-label of the derived knowledge point includes the calibrated operation and maintenance knowledge point.

[0126] After the target power operation and maintenance feature domains corresponding to the respective power operation and maintenance feature domains are aggregated to generate a target derived fault operation and maintenance node, the method further includes:

[0127] According to the calibrated operation and maintenance knowledge points, the derived knowledge points constituting the target derived fault operation and maintenance node are semantically transformed to generate an iterative target derived fault operation and maintenance node. The iterative target derived fault operation and maintenance node is a fault operation and maintenance node generated by deriving and simulating the basic fault operation and maintenance node based on the calibrated operation and maintenance knowledge points.

[0128] In a possible implementation manner, after the semantic transformation of the derived knowledge points constituting the target derived fault operation and maintenance node is performed based on the calibrated operation and maintenance knowledge points to generate the iterative target derived fault operation and maintenance node, the method further includes:

[0129] The calibrated operation and maintenance knowledge points constituting the iterative target derived fault operation and maintenance node are cross-analyzed to generate operation and maintenance knowledge points to be expanded and operation and maintenance knowledge points to be cleared, wherein the operation and maintenance knowledge points to be expanded and the operation and maintenance knowledge points to be cleared have semantic intersections.

[0130] Based on the operation and maintenance knowledge points to be cleaned up, the operation and maintenance knowledge points to be expanded in the iteration target derived fault operation and maintenance node are expanded to generate expanded operation and maintenance knowledge points, and the expanded operation and maintenance knowledge points include the operation and maintenance knowledge points to be cleaned up.

[0131] Based on the extended operation and maintenance knowledge points, the operation and maintenance knowledge points to be cleaned up in the iteration target derived fault operation and maintenance node are removed to generate an optimized iteration target derived fault operation and maintenance node.

[0132] For example, in a possible implementation, based on the extended operation and maintenance knowledge point, removing the operation and maintenance knowledge point to be cleaned in the iteration target derived fault operation and maintenance node to generate an optimized iteration target derived fault operation and maintenance node includes:

[0133] The attribute necklace of the extended operation and maintenance knowledge point is determined according to the attribute necklace of the operation and maintenance knowledge point to be expanded and the attribute necklace of the operation and maintenance knowledge point to be cleared.

[0134] A candidate power operation and maintenance feature domain corresponding to the extended operation and maintenance knowledge point is determined from the basic fault operation and maintenance node.

[0135] Based on the attribute necklace of the candidate power operation and maintenance feature domain and the attribute necklace of the extended operation and maintenance knowledge point, the operation and maintenance knowledge point maintenance information of the extended operation and maintenance knowledge point is determined.

[0136] Based on the operation and maintenance knowledge point maintenance information of the extended operation and maintenance knowledge point, the operation and maintenance knowledge point to be cleaned up in the iteration target derived fault operation and maintenance node is removed to generate an optimized iteration target derived fault operation and maintenance node.

[0137] For example, in a possible implementation, the method further includes:

[0138] An operation and maintenance knowledge sequence of the operation and maintenance knowledge points constituting the target derived fault operation and maintenance node and a data structure of the environment to be migrated are obtained, wherein the operation and maintenance knowledge sequence includes knowledge features of each operation and maintenance knowledge point constituting the target derived fault operation and maintenance node.

[0139] Based on the data structure, a structural conversion process is performed on the knowledge features of each operation and maintenance knowledge point in the operation and maintenance knowledge sequence to obtain an updated operation and maintenance knowledge sequence.

[0140] The updated operation and maintenance knowledge sequence is sent to the environment to be migrated, so as to present a simulated fault operation and maintenance node composed of each operation and maintenance knowledge point in the updated operation and maintenance knowledge sequence in the environment to be migrated.

[0141] In this embodiment, it is assumed that there is a basic fault operation and maintenance node, which is a large transformer with a serious oil leakage fault. The server first obtains the relevant information of the basic fault operation and maintenance node, including the transformer model, installation time, operating environment, speed and location of the oil leakage, etc.

[0142] At the same time, the server also obtains the basic derived fault operation and maintenance node generated based on this basic fault operation and maintenance node. This basic derived fault operation and maintenance node contains derived knowledge points such as "large-scale construction has been carried out in the surrounding area recently, which has caused strong vibrations."

[0143] The server begins to determine the power operation and maintenance feature domain to be updated for the basic derived fault operation and maintenance node. Through analysis, it is found that the feature domain "vibration impact" needs to be updated. Because the target difference information that the server determines that the basic derived fault operation and maintenance node and the basic fault operation and maintenance node are in the same power operation and maintenance feature domain (such as "external environmental impact") is that there is no detailed description of construction vibration in the basic fault operation and maintenance node. Based on this target difference information, the server determines the power operation and maintenance feature domain "vibration impact" from the basic derived fault operation and maintenance node as the power operation and maintenance feature domain to be updated.

[0144] Next, the server updates the distribution characteristics of the derivative knowledge points of the power operation and maintenance feature domain to be updated, "vibration impact", based on the basic fault operation and maintenance nodes in the power smart operation and maintenance data. The server obtains more detailed data on the frequency and amplitude of construction vibration, thereby updating the distribution characteristics of this feature domain and generating iterative distribution characteristics.

[0145] The server also obtained calibration operation and maintenance knowledge points, such as "Aging standard of transformer seals". Based on the category label "Equipment aging related" corresponding to this calibration operation and maintenance knowledge point, the server determined derived knowledge points, such as "Material and service life of transformer seals".

[0146] After aggregating the target power operation and maintenance feature domains corresponding to each power operation and maintenance feature domain, the server generates a target derived fault operation and maintenance node. Then, based on the calibrated operation and maintenance knowledge points, the server performs semantic conversion on the derived knowledge points that constitute the target derived fault operation and maintenance node. For example, converting "the material and service life of the transformer seal" into "assessing the seal status according to the aging standard" generates an iterative target derived fault operation and maintenance node.

[0147] After cross-analyzing the calibrated operation and maintenance knowledge points that constitute the iterative target derived fault operation and maintenance nodes, the server generated the operation and maintenance knowledge points to be expanded, "the degree of influence of seals of different materials on oil leakage" and the operation and maintenance knowledge points to be cleared, "construction vibration data not related to seals". Based on the operation and maintenance knowledge points to be cleared, the server performs expansion processing on the operation and maintenance knowledge points to be expanded in the iterative target derived fault operation and maintenance nodes. For example, the specific influence of seals of different materials on oil leakage under specific aging degrees and operating environments is analyzed in detail to generate expanded operation and maintenance knowledge points.

[0148] Based on the attribute necklace of the extended operation and maintenance knowledge point, such as "the probability of oil leakage of a seal made of material A after aging for 5 years is 30%", and the attribute necklace of the operation and maintenance knowledge point to be cleaned, such as "there is no direct impact on the seal when the construction vibration frequency is X", the server determines that the attribute necklace of the extended operation and maintenance knowledge point is "the probability of oil leakage of a seal made of material A after aging for 5 years is 30% below a specific vibration frequency X".

[0149] From the basic fault operation and maintenance nodes, the server determines the candidate power operation and maintenance feature domain corresponding to the extended operation and maintenance knowledge point, such as "the relationship between seal aging and oil leakage speed". Based on the attribute necklace of the candidate power operation and maintenance feature domain and the attribute necklace of the extended operation and maintenance knowledge point, the server determines the operation and maintenance knowledge point maintenance information of the extended operation and maintenance knowledge point, such as "under certain conditions, seal aging is the main factor causing oil leakage, and the impact of vibration can be ignored".

[0150] Based on the operation and maintenance knowledge point maintenance information of the extended operation and maintenance knowledge point, the server removes the operation and maintenance knowledge point to be cleaned up "construction vibration data not related to seals" in the iteration target derived fault operation and maintenance node, and generates an optimized iteration target derived fault operation and maintenance node.

[0151] In addition, the server obtains the operation and maintenance knowledge sequence of the operation and maintenance knowledge points that constitute the target derivative fault operation and maintenance node, such as "seal material, aging degree, oil leakage speed", etc., as well as the data structure of the environment to be migrated, such as a specific data format and storage method. Based on the data structure of the environment to be migrated, the server performs structural conversion processing on the knowledge features of each operation and maintenance knowledge point in the operation and maintenance knowledge sequence to obtain an updated operation and maintenance knowledge sequence, such as converting the knowledge features into a format and encoding that meets the requirements of the environment to be migrated.

[0152] Finally, the server sends the updated operation and maintenance knowledge sequence to the environment to be migrated, so as to present a simulated fault operation and maintenance node composed of each operation and maintenance knowledge point in the updated operation and maintenance knowledge sequence in the environment to be migrated, so as to help relevant personnel to perform fault analysis and processing in the new environment.

[0153] Assume that another basic fault operation and maintenance node is the tilt of a transmission line tower. The server also processes according to the above steps. Determine the power operation and maintenance feature domain to be updated, such as "the impact of soil softness on tower stability". Obtain calibrated operation and maintenance knowledge points, such as "tower design standards", determine the derived knowledge points and perform subsequent processing and optimization. During the processing, the operation and maintenance knowledge points to be expanded "carrying capacity of different soil types" and the operation and maintenance knowledge points to be cleaned "surrounding vegetation information not related to towers" are generated, and expansion and cleaning operations are performed to generate the optimized iterative target derived fault operation and maintenance node. At the same time, the operation and maintenance knowledge sequence is structurally converted and sent to the environment to be migrated.

[0154] By continuously repeating this processing process, the server can conduct comprehensive, in-depth and accurate analysis and optimization of various power fault operation and maintenance nodes, providing strong support for the safe and stable operation of the power system.

[0155] Figure 2 The electric power data processing system 100 based on smart operation and maintenance shown includes: a processor 1001 and a memory 1003. Among them, the processor 1001 and the memory 1003 are connected, such as through a bus 1002. Optionally, the electric power data processing system 100 based on smart operation and maintenance may also include a transceiver 1004, and the transceiver 1004 may be used for data interaction between the server and other servers, such as data transmission and / or data reception. It should be noted that the transceiver 1004 is not limited to one in actual scheduling, and the structure of the electric power data processing system 100 based on smart operation and maintenance does not constitute a limitation on the embodiments of the present application.

[0156] Processor 1001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 1001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0157] The bus 1002 may include a path to transmit information between the above components. The bus 1002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 1002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0158] The memory 1003 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, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), magnetic disk storage medium, other magnetic storage devices, or any other medium that can be used to carry or store program code and can be read by a computer, without limitation herein.

[0159] The memory 1003 is used to store program codes for executing the embodiments of the present application, and the execution is controlled by the processor 1001. The processor 1001 is used to execute the program codes stored in the memory 1003 to implement the steps shown in the above method embodiments.

[0160] An embodiment of the present application provides a computer-readable storage medium having program code stored thereon. When the program code is executed by a processor, the steps and corresponding contents of the aforementioned method embodiment can be implemented.

[0161] It should be understood that, although each operation step is characterized by directed lines in the flow chart of the embodiment of the present application, the implementation order of these steps is not limited to the order covered by the directed lines. Unless there is clear explanation in this article, in some implementation scenarios of the embodiment of the present application, the implementation steps in each flow chart can be performed in other orders based on demand. In addition, some or all of the steps in each flow chart may include multiple sub-steps or multiple stages according to actual implementation scenarios, and some or all of these sub-steps or stages may be performed in the same stage, and each sub-step or stage in these sub-steps or stages may also be performed in different stages respectively. Under different scenarios in the execution stage, the execution order of these sub-steps or stages can be flexibly configured based on demand, and the embodiment of the present application does not limit this.

[0162] The above is only an optional implementation method for some implementation scenarios of the present application. It should be pointed out that for ordinary technicians in this technical field, without departing from the technical concept of the solution of the present application, other similar implementation methods based on the technical ideas of the present application are also within the protection scope of the embodiments of the present application.

Claims

1. A method for processing power data based on intelligent operation and maintenance, characterized in that: The method comprises: Obtaining a basic fault operation and maintenance node in the electric power smart operation and maintenance data, and a plurality of derived fault operation and maintenance nodes corresponding to the basic fault operation and maintenance node, wherein the derived fault operation and maintenance node is a fault operation and maintenance node generated by deriving and simulating the basic fault operation and maintenance node using derived knowledge points, and the combination of derived knowledge points in different derived fault operation and maintenance nodes is inconsistent; Determine the distinguishing information between the derived fault operation and maintenance node and the basic fault operation and maintenance node in the same power operation and maintenance feature domain; For each power operation and maintenance feature domain corresponding to the basic fault operation and maintenance node and the derived fault operation and maintenance node, based on the distinguishing information, determine a target power operation and maintenance feature domain corresponding to each power operation and maintenance feature domain from the multiple derived fault operation and maintenance nodes; The target power operation and maintenance feature domains corresponding to the various power operation and maintenance feature domains are aggregated to generate a target derived fault operation and maintenance node.

2. The power data processing method based on intelligent operation and maintenance according to claim 1 is characterized in that: The method further comprises: According to the basic fault operation and maintenance nodes in the electric power smart operation and maintenance data, basic derived fault operation and maintenance nodes are generated based on the derived knowledge points; According to the basic fault operation and maintenance nodes in the electric power smart operation and maintenance data, the derived knowledge points constituting the basic derived fault operation and maintenance nodes are optimized to generate advanced derived fault operation and maintenance nodes.

3. The power data processing method based on intelligent operation and maintenance according to claim 2 is characterized in that: The step of optimizing the derived knowledge points constituting the basic derived fault operation and maintenance nodes according to the basic fault operation and maintenance nodes in the electric power smart operation and maintenance data to generate advanced derived fault operation and maintenance nodes includes: Generate iterative distribution features based on the basic fault operation and maintenance nodes in the electric power smart operation and maintenance data and the distribution features of the derived knowledge points in the basic derived fault operation and maintenance nodes; Based on the iterative distribution characteristics, the derived knowledge points constituting the basic derived fault operation and maintenance node are optimized to generate an advanced derived fault operation and maintenance node.

4. The power data processing method based on intelligent operation and maintenance according to claim 2 is characterized in that: The generating of basic derived fault operation and maintenance nodes based on the derived knowledge points according to the basic fault operation and maintenance nodes in the electric power smart operation and maintenance data includes: Determining a knowledge point mapping area on a basic fault operation and maintenance node in the electric power smart operation and maintenance data; A basic derived fault operation and maintenance node is generated according to the knowledge point mapping area and the derived knowledge point.

5. The power data processing method based on intelligent operation and maintenance according to claim 4 is characterized in that: The step of generating a basic derived fault operation and maintenance node based on the knowledge point mapping area and the derived knowledge point includes: Obtain a target attribute necklace of the basic fault operation and maintenance node in the knowledge point mapping area; Based on the target attribute necklace, attribute values ​​are assigned to the derived knowledge points in the knowledge point mapping area to generate a basic derived fault operation and maintenance node.

6. The power data processing method based on intelligent operation and maintenance according to claim 3 is characterized in that: The generating of iterative distribution features based on the basic fault operation and maintenance nodes in the electric power smart operation and maintenance data and the distribution features of the derived knowledge points in the basic derived fault operation and maintenance nodes includes: Determine the power operation and maintenance feature domain to be updated of the basic derived fault operation and maintenance node; According to the basic fault operation and maintenance nodes in the electric power smart operation and maintenance data, the distribution characteristics of the derived knowledge points of the to-be-updated electric power operation and maintenance feature domain in the basic derived fault operation and maintenance nodes are updated to generate iterative distribution characteristics.

7. The power data processing method based on intelligent operation and maintenance according to claim 6 is characterized in that: The determining of the distinguishing information of the derived fault operation and maintenance node and the basic fault operation and maintenance node in the same power operation and maintenance feature domain includes: Determine target distinguishing information of the basic derived fault operation and maintenance node and the basic fault operation and maintenance node in the same power operation and maintenance feature domain; The step of determining the power operation and maintenance feature domain to be updated of the basic derived fault operation and maintenance node includes: Based on the target distinguishing information, the power operation and maintenance feature domain to be updated is determined from the basic derived fault operation and maintenance node.

8. The power data processing method based on intelligent operation and maintenance according to claim 1 is characterized in that: The method further comprises: Obtain calibration operation and maintenance knowledge points; Determining a derived knowledge point based on a category label corresponding to the calibrated operation and maintenance knowledge point, wherein a sub-label of the derived knowledge point includes the calibrated operation and maintenance knowledge point; After the target power operation and maintenance feature domains corresponding to the respective power operation and maintenance feature domains are aggregated to generate a target derived fault operation and maintenance node, the method further includes: According to the calibrated operation and maintenance knowledge points, the derived knowledge points constituting the target derived fault operation and maintenance node are semantically transformed to generate an iterative target derived fault operation and maintenance node. The iterative target derived fault operation and maintenance node is a fault operation and maintenance node generated by deriving and simulating the basic fault operation and maintenance node based on the calibrated operation and maintenance knowledge points.

9. The power data processing method based on intelligent operation and maintenance according to claim 8 is characterized in that: After the derivative knowledge points constituting the target derived fault operation and maintenance node are semantically converted according to the calibrated operation and maintenance knowledge points to generate the iterative target derived fault operation and maintenance node, the method further includes: Cross-analyze the calibrated operation and maintenance knowledge points constituting the iterative target derived fault operation and maintenance node to generate operation and maintenance knowledge points to be expanded and operation and maintenance knowledge points to be cleared, wherein the operation and maintenance knowledge points to be expanded and the operation and maintenance knowledge points to be cleared have semantic intersections; Based on the operation and maintenance knowledge points to be cleaned up, the operation and maintenance knowledge points to be expanded in the iteration target derived fault operation and maintenance node are extended to generate extended operation and maintenance knowledge points, where the extended operation and maintenance knowledge points include the operation and maintenance knowledge points to be cleaned up; Based on the extended operation and maintenance knowledge points, the operation and maintenance knowledge points to be cleaned up in the iteration target derived fault operation and maintenance node are removed to generate an optimized iteration target derived fault operation and maintenance node.

10. A power data processing system based on intelligent operation and maintenance, characterized in that: It includes a processor and a computer-readable storage medium, wherein the computer-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are executed by the processor, the power data processing method based on smart operation and maintenance described in any one of claims 1 to 9 is implemented.

Images