Power grid fault inversion dynamic correction method and system based on knowledge graph

Abstract

The invention discloses a power grid fault inversion dynamic correction method and system based on a knowledge graph. The method comprises the following steps: constructing a power grid fault knowledge graph database; analyzing the power grid fault message, taking an analysis result as a power grid fault inversion model parameter, performing query comparison with the power grid fault knowledge graph database, and constructing a power grid fault inversion model; constructing a power grid fault inversion dynamic correction model to correct parameters of the power grid fault inversion model to obtain a final power grid fault inversion model; the method has the advantage that the accuracy of power grid fault inversion is improved.

Description

Technical Field

[0001] The present invention relates to the field of power grid fault inversion, and in particular to a knowledge graph-based power grid fault inversion dynamic correction method and system. Background Art

[0002] At present, with the continuous improvement of the level of power grid intelligence, the increasing degree of grid interconnection, and the sharp increase in the amount of new energy grid-connected, the possibility of chain failures caused by power grid failures has further increased. With the increasing complexity of the amount of new energy grid-connected and the new energy grid-connected topology, the types of power grid failures have become more complex, and the changes in the electrical quantity of the power grid caused by the power grid failures have become more difficult to analyze. Rapidly identifying the type of power grid failure and realizing real-time inversion of power grid failures are important for real-time dispatching of power grid operation management and maintaining the safety and stability of the power grid. Therefore, considering the strong coupling of new energy grid-connected, flexible and changeable power grid topology, and the further complexity of power grid failure types, fast real-time power grid fault inversion is of great significance to the safety and stability of the power grid.

[0003] Chinese patent publication number CN118040600A discloses that a distribution network fault inversion model is established based on the new operation data generated during the model deduction process combined with the historical fault operation data; based on the distribution network operation model and the distribution network fault inversion model, combined with the real-time operation data of the distribution network, the distribution network relay protection setting strategy deduction and fault inversion are carried out, which can improve the operation efficiency and stability of the distribution network and provide strong protection for the safe operation of the power system. However, the fault inversion model generated by this patent application is often unable to be accurately modeled due to the complex structure of the current new energy grid connection and the complexity of the grid. Faults are many, resulting in inaccurate output fault inversion results. Summary of the invention

[0004] The technical problem to be solved by the present invention is that the fault inversion results output by the prior art power grid fault inversion model are not accurate enough.

[0005] The present invention solves the above technical problems through the following technical means: a power grid fault inversion dynamic correction method based on knowledge graph, comprising: S1. Build a knowledge graph library of power grid faults; S2, parsing the power grid fault message and using the parsing result as the power grid fault inversion model parameter to query and compare with the power grid fault knowledge graph library to build a power grid fault inversion model; S3. Construct a power grid fault inversion dynamic correction model to correct the power grid fault inversion model parameters to obtain the final power grid fault inversion model.

[0006] The present invention constructs a power grid fault inversion dynamic correction model to correct the power grid fault inversion model parameters, which is conducive to accurate modeling when the new energy grid-connected structure is complex and the power grid is complex with many faults, so that the output fault inversion result is more accurate.

[0007] Furthermore, S1 includes: The primary equipment of the power grid is taken as the entity of the power grid fault knowledge graph library, and the following classes are set: relay protection device information, power grid fault type, flow information, equipment information, and power grid fault information. Each class is set with multiple attributes to form a triple of entity-class-attribute. The historical data of the power grid is realized in one-to-one correspondence with entities in the form of the triple, thereby constructing a power grid fault knowledge graph library.

[0008] Furthermore, S2 includes: A bidirectional long short-term memory network is used to parse real-time power grid fault messages and historical power grid fault messages. The parsing results include the entity information of the primary equipment in the power grid, fault distance, power grid fault type, and transition resistance. The parsing results are used as the parameters of the power grid fault inversion model. The power grid fault inversion model parameters are matched one-to-one with the power grid fault knowledge graph library to complete the power grid fault knowledge graph matching. The power grid fault is simulated within the power grid subnet involved in the power grid fault according to the power grid fault knowledge graph matching results, thereby establishing a power grid fault inversion model.

[0009] Furthermore, the real-time power grid fault message and the historical power grid fault message include a real-time SOE information message of a power grid fault and a real-time action report of a relay protection information management system, and a historical power grid fault SOE information message and a historical action report of a relay protection information management system.

[0010] Furthermore, the use of a bidirectional long short-term memory network to parse real-time power grid fault messages and historical power grid fault messages includes: The real-time power grid fault messages and historical power grid fault messages are annotated with BIO using the power grid fault knowledge graph, and the annotation results are input into the bidirectional long short-term memory network. The output results of the bidirectional long short-term memory network are input into the CRF layer, and the CRF layer outputs the parsing results.

[0011] Furthermore, S3 includes: S31. Establishing a power grid topology adjacency matrix using the power grid fault knowledge graph matching result; the power grid fault knowledge graph matching result refers to the matching result between the power grid fault inversion model parameters and the power grid fault knowledge graph library; S32, simulating a power grid fault according to the power grid fault knowledge graph matching result, and obtaining power grid fault simulation waveforms at different nodes in the power grid; S33, constructing a power grid fault waveform feature matrix according to the power grid fault simulation waveform, and inputting the power grid fault waveform feature matrix and the power grid topology adjacency matrix into a multi-layer GCN network connected in sequence to obtain a power grid fault inversion model parameter output matrix; S34, calculating the mean value of the Pearson correlation coefficient between the grid fault simulation waveform and the actual action report waveform at different nodes in the grid as the loss function, and judging whether the loss function meets the requirements, if not, going to S35, if meeting the requirements, going to S36; S35, using the power grid fault inversion model parameter output matrix to correct the power grid fault inversion model parameters, and returning to execute S2; S36. Obtain the final power grid fault inversion model.

[0012] Furthermore, the power grid topology adjacency matrix represents the connection relationship between power grid topology nodes, each row and each column are power grid topology nodes, and each element in the power grid topology adjacency matrix uses a number to indicate whether the nodes are connected or not. Each row of the power grid fault waveform feature matrix is ​​a time point of a power grid fault simulation waveform, and each column is a power grid topology node. Each element in the power grid fault waveform feature matrix is ​​the discrete data of the time point corresponding to the power grid fault simulation waveform corresponding to the power grid topology node.

[0013] Furthermore, the determination of whether the loss function meets the requirement means that the requirement is met when the loss function value reaches the minimum, otherwise the requirement is not met.

[0014] Furthermore, the method of correcting the power grid fault inversion model parameters using the power grid fault inversion model parameter output matrix is ​​to add the original power grid fault inversion model parameters to the parameters in the power grid fault inversion model parameter output matrix as the power grid fault inversion model parameters of the next stage, and return to execute S2.

[0015] The present invention also provides a knowledge graph-based power grid fault inversion dynamic correction system, comprising: A graph library construction module, used to construct a knowledge graph library for power grid faults; An inversion model building module is used to parse the power grid fault message and use the parsing result as the power grid fault inversion model parameter to query and compare with the power grid fault knowledge graph library to build a power grid fault inversion model; The inversion model correction module is used to construct a power grid fault inversion dynamic correction model to correct the power grid fault inversion model parameters to obtain the final power grid fault inversion model.

[0016] Furthermore, the atlas library construction module is also used to: The primary equipment of the power grid is taken as the entity of the power grid fault knowledge graph library, and the following classes are set: relay protection device information, power grid fault type, flow information, equipment information, and power grid fault information. Each class is set with multiple attributes to form a triple of entity-class-attribute. The historical data of the power grid is realized in one-to-one correspondence with entities in the form of the triple, thereby constructing a power grid fault knowledge graph library.

[0017] Furthermore, the inversion model building module is also used to: A bidirectional long short-term memory network is used to parse real-time power grid fault messages and historical power grid fault messages. The parsing results include the entity information of the primary equipment in the power grid, fault distance, power grid fault type, and transition resistance. The parsing results are used as the parameters of the power grid fault inversion model. The power grid fault inversion model parameters are matched one-to-one with the power grid fault knowledge graph library to complete the power grid fault knowledge graph matching. The power grid fault is simulated within the power grid subnet involved in the power grid fault according to the power grid fault knowledge graph matching results, thereby establishing a power grid fault inversion model.

[0018] Furthermore, the real-time power grid fault message and the historical power grid fault message include a real-time SOE information message of a power grid fault and a real-time action report of a relay protection information management system, and a historical power grid fault SOE information message and a historical action report of a relay protection information management system.

[0019] Furthermore, the use of a bidirectional long short-term memory network to parse real-time power grid fault messages and historical power grid fault messages includes: The real-time power grid fault messages and historical power grid fault messages are annotated with BIO using the power grid fault knowledge graph, and the annotation results are input into the bidirectional long short-term memory network. The output results of the bidirectional long short-term memory network are input into the CRF layer, and the CRF layer outputs the parsing results.

[0020] Furthermore, the inversion model correction module is also used to: S31. Establishing a power grid topology adjacency matrix using the power grid fault knowledge graph matching result; the power grid fault knowledge graph matching result refers to the matching result between the power grid fault inversion model parameters and the power grid fault knowledge graph library; S32, simulating a power grid fault according to the power grid fault knowledge graph matching result, and obtaining power grid fault simulation waveforms at different nodes in the power grid; S33, constructing a power grid fault waveform feature matrix according to the power grid fault simulation waveform, and inputting the power grid fault waveform feature matrix and the power grid topology adjacency matrix into a multi-layer GCN network connected in sequence to obtain a power grid fault inversion model parameter output matrix; S34, calculating the mean value of the Pearson correlation coefficient between the grid fault simulation waveform and the actual action report waveform at different nodes in the grid as the loss function, and judging whether the loss function meets the requirements, if not, going to S35, if meeting the requirements, going to S36; S35, using the power grid fault inversion model parameter output matrix to correct the power grid fault inversion model parameters, and returning to execute the inversion model construction module; S36. Obtain the final power grid fault inversion model.

[0021] Furthermore, the power grid topology adjacency matrix represents the connection relationship between power grid topology nodes, each row and each column are power grid topology nodes, and each element in the power grid topology adjacency matrix uses a number to indicate whether the nodes are connected or not. Each row of the power grid fault waveform feature matrix is ​​a time point of a power grid fault simulation waveform, and each column is a power grid topology node. Each element in the power grid fault waveform feature matrix is ​​the discrete data of the time point corresponding to the power grid fault simulation waveform corresponding to the power grid topology node.

[0022] Furthermore, the determination of whether the loss function meets the requirement means that the requirement is met when the loss function value reaches the minimum, otherwise the requirement is not met.

[0023] Furthermore, the method of using the power grid fault inversion model parameter output matrix to correct the power grid fault inversion model parameters is to add the original power grid fault inversion model parameters and the parameters in the power grid fault inversion model parameter output matrix as the power grid fault inversion model parameters of the next stage, and return to execute the inversion model construction module.

[0024] The advantages of the present invention are: (1) The present invention constructs a power grid fault inversion dynamic correction model to correct the parameters of the power grid fault inversion model, which is conducive to accurate modeling when the new energy grid-connected structure is complex and the power grid is complex and has many faults, so that the output fault inversion result is more accurate.

[0025] (2) The present invention is based on the actual connection relationship between power grid topologies, sets power grid fault and relay protection related information as necessary labels and attributes, and establishes a power grid fault knowledge graph library, which can provide a data model foundation for fast and real-time power grid fault inversion.

[0026] (3) The present invention converts unstructured data in the form of text information into structured data in the form of keywords by real-time analysis of power grid fault message information, and performs entity matching between power grid fault information and power grid fault knowledge graph library, thereby realizing rapid search of power grid entities involved in power grid faults and power grid fault electrical quantity change information, and establishing a power grid fault model to provide technical reference for power grid operation management personnel.

[0027] (4) The present invention considers the connection between the grid fault waveform and the grid topology, makes full use of a large amount of historical grid fault data, and uses a graph convolutional neural network (GCN) to construct a grid fault inversion dynamic correction model. The GCN input layer receives the grid node fault waveform characteristics and the grid topology adjacency matrix of the grid topology map. The node characteristics are aggregated and transformed by GCN, and the dependency relationship and fault propagation mode between nodes are learned to enhance the expression ability of the grid fault inversion dynamic correction model. By combining the grid fault knowledge graph with the graph convolutional neural network, the waveform characteristics and topological characteristics can be closely combined, and the fault waveform is used as the feature matrix. At the same time, the parameter output matrix is ​​the basis for the correction of the grid fault parameters. The mean of the Pearson coefficient between the waveforms is the loss function, which can continuously correct the grid fault simulation model, realize the consistency between the grid fault inversion data and the actual grid fault information, and continuously improve the accuracy of the grid fault inversion, providing a basis for the safe and stable operation of the grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 A flowchart of a knowledge graph-based power grid fault inversion dynamic correction method disclosed in Example 1 of the present invention; Figure 2 A schematic diagram of a knowledge graph triple in a knowledge graph-based power grid fault inversion dynamic correction method disclosed in Example 1 of the present invention; Figure 3 A schematic diagram of a power grid fault inversion model construction process in a power grid fault inversion dynamic correction method based on a knowledge graph disclosed in Embodiment 1 of the present invention; Figure 4 A schematic diagram of structured data in a knowledge graph-based power grid fault inversion dynamic correction method disclosed in Example 1 of the present invention; Figure 5 A schematic diagram of a process in which a long short-term memory network converts unstructured data into required structured data in a power grid fault inversion dynamic correction method based on a knowledge graph disclosed in Example 1 of the present invention; Figure 6 A schematic diagram of a process for constructing a power grid fault inversion dynamic correction model in a power grid fault inversion dynamic correction method based on a knowledge graph disclosed in Embodiment 1 of the present invention; Figure 7 A flowchart of dynamically correcting a power grid fault inversion model in a power grid fault inversion dynamic correction method based on a knowledge graph disclosed in Example 1 of the present invention; Figure 8 A schematic diagram of a power grid fault waveform feature matrix in a power grid fault inversion dynamic correction method based on a knowledge graph disclosed in Example 1 of the present invention; Fig. 9A schematic diagram of a power grid topology adjacency matrix in a power grid fault inversion dynamic correction method based on a knowledge graph disclosed in Example 1 of the present invention; Fig.10 A diagram of a dynamic correction process of a power grid fault inversion for a phase A grounding fault in a knowledge graph-based power grid fault inversion dynamic correction method disclosed in Embodiment 1 of the present invention; Fig.11 This is a diagram of the dynamic correction process of AB phase short circuit power grid fault inversion in a knowledge graph-based power grid fault inversion dynamic correction method disclosed in Example 1 of the present invention. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in combination with the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] Example 1 like Figure 1 As shown, embodiment 1 of the present invention provides a power grid fault inversion dynamic correction method based on knowledge graph, comprising the following steps: S1. Build a knowledge graph library of power grid faults. The specific process is as follows: Knowledge graph technology has the ability to analyze multi-label big data reasoning knowledge and is currently widely used in the field of power systems. As the level of power grid intelligence continues to improve, the degree of grid interconnection continues to increase, and the amount of new energy connected to the grid increases dramatically, the possibility of chain failures caused by power grid failures has further increased. As the amount of new energy connected to the grid and the new energy grid connected topology become more complex, the types of power grid failures become more complex, and the changes in power grid electrical quantities caused by power grid failures become more difficult to analyze. Knowledge graph technology can use graph models to retrieve big data power grid failure real-time data, has the ability to reason about power grid failure knowledge, and is more suitable for the power grid fault inversion dynamic correction method of the present invention.

[0031] At present, the power grid operation data contains a large amount of power grid historical data. Through the power grid real-time operation database and the power grid relay protection information system platform, a large amount of power grid relay protection and power grid fault information can be obtained, and the power grid primary equipment entity and the power grid relay protection and power grid fault knowledge graph mapping model are established. The power grid fault knowledge graph library is described in the form of triples, and each low-frequency load reduction scheme knowledge can be decomposed into the following form: (subject, predicate, object). The subject is an individual, the individual is an instance of a class, and the predicate connects two individuals. The object is an individual or an instance of a data type. The power grid fault knowledge graph library is established based on the power grid entity. Therefore, the present invention is based on the actual connection relationship between the power grid topologies, sets the power grid fault and relay protection related information as necessary labels and attributes, and establishes a power grid fault knowledge graph library, which can provide a data model basis for fast real-time power grid fault inversion.

[0032] The present invention first constructs a power grid fault knowledge graph library based on the power grid historical operation data and the power grid fault historical information in the power grid relay protection information system platform. Figure 2 As shown, the present invention takes the primary equipment of the power grid as the entity of the power grid fault knowledge graph library, sets five categories of relay protection device information, power grid fault type, flow information, equipment information, and power grid fault information. The relay protection device information sets the attributes of device name, device manufacturer, device version, and protection information. The power grid fault type sets the three attributes of external fault, internal fault, and fault electrical quantity. The flow information sets the attributes of voltage, current, active power, and reactive power. The equipment information includes basic equipment information, circuit breaker opening and closing impedance, circuit breaker tripping and closing time, and line distributed impedance. The power grid fault information sets the six attributes of action time, protection action name, fault distance, phase selection result, transition resistance, and power grid fault classification. By constructing a power grid fault knowledge graph library, the power grid fault can be directly mapped to the power grid fault knowledge graph library, providing data support for power grid fault inversion. In this embodiment, a graph database is used to realize the one-to-one correspondence of power grid historical data in the form of entity-class-attribute triples, and a power grid fault knowledge graph library is automatically constructed.

[0033] S2. Analyze the power grid fault message and use the analysis result as the power grid fault inversion model parameter to query and compare with the power grid fault knowledge graph library to build a power grid fault inversion model. The specific process is as follows: like Figure 3 As shown in the figure, at present, the level of power grid intelligence is constantly improving, and the real-time information of power grid faults is directly uploaded to the power system dispatching data platform through the dispatching data network. The present invention uses a bidirectional long short-term memory network to convert the unstructured data of real-time information of power grid faults into the required structured data, such as Figure 4As shown, unstructured data refers to data in the form of original text, and structured data refers to keyword data extracted from the text. The structured data is matched with the knowledge graph library, and the analyzed power grid fault type, transition resistance, fault distance and other data are matched with the power grid fault knowledge graph library to quickly and real-time establish a power grid fault inversion simulation model and complete the rapid dynamic modeling of power grid faults.

[0034] The bidirectional long short-term memory network is used to parse the real-time SOE information message of the power grid fault, the real-time relay protection information management system action report, the historical power grid fault SOE information message and the historical relay protection information management system action report, that is, to parse the real-time power grid fault message and the historical power grid fault message. The SOE information message is mainly divided into time sequence, object, action and other information. The relay protection information management system mainly contains action time, protection action name, fault distance measurement, phase selection result, transition resistance value and other information. The unstructured data is converted into the required structured data through the long short-term memory network. The specific process is as follows: Figure 5 As shown, the real-time power grid fault message and the historical power grid fault message are in text form, and the present invention needs to match with the knowledge graph when performing fault matching, which requires keywords, so the text needs to be converted into keywords. Therefore, the present invention uses the power grid fault knowledge graph to perform BIO annotation on the real-time power grid fault message and the historical power grid fault message. The purpose of annotation is to mark the entities that appear in the text that are the same as the knowledge graph library. The entities are also divided into different classes and attributes. Therefore, the annotation results are input into a bidirectional long short-term memory network (BiLSTM), and the annotated entities are classified and scored through the bidirectional long short-term memory network, that is, the bidirectional long short-term memory network scores whether the annotated entities belong to the attributes set in the power grid fault knowledge graph library (attributes include device name, device manufacturer, device version, protection information, external fault, internal fault, fault electrical quantity, etc., refer to Figure 2 , which will not be elaborated here), the scoring results output by the bidirectional long short-term memory network are input into the CRF layer, and the CRF layer takes the attribute corresponding to the highest scoring result as the parsing result. The parsing result includes the entity information of the primary equipment of the power grid, the fault distance, the type of power grid fault, and the size of the transition resistance.

[0035] The named entity recognition result of the real-time message of the power grid fault, that is, the above-mentioned parsing result, corresponds one-to-one with the knowledge graph of the power grid fault, completes the matching of the knowledge graph of the power grid fault, and then establishes the power grid fault inversion model according to the matching result of the knowledge graph of the power grid fault in the range of the power grid subnet involved in the power grid fault according to the power grid fault sequence. The essence of establishing the power grid fault inversion model is to model and display the power grid fault corresponding to the knowledge graph of the power grid fault in the range of the power grid subnet, so that the whole process can invert the power grid fault according to the power grid fault message. At present, with the continuous increase in the capacity of the new energy grid connected to the grid, the chain tripping of the power grid fault is becoming more and more complicated. The present invention considers the expansion modeling of the power grid fault, and uses the knowledge graph of the power grid fault to quickly and dynamically query the power grid action entities of the same substation and the adjacent substation under the power grid fault sequence, so as to realize the precise expansion modeling of the power grid fault inversion.

[0036] S3, construct a power grid fault inversion dynamic correction model to correct the power grid fault inversion model parameters to obtain the final power grid fault inversion model; the specific process is as follows: The above-mentioned power grid fault inversion model is often unable to directly and accurately model in one go when the current renewable energy grid-connected structure is complex and the power grid has many complex faults. Therefore, the present invention establishes a power grid fault inversion dynamic correction model. In order to realize the dynamic correction of the power grid fault inversion model, a power grid fault inversion automatic correction model based on the power grid fault knowledge graph library is constructed. The power grid fault waveform is directly related to the power grid topology. The present invention considers the connection relationship between the power grid fault waveform and the power grid topology, makes full use of a large amount of historical power grid fault data, and constructs a power grid fault inversion dynamic correction model based on a graph convolutional neural network (GCN). The input layer of the graph convolutional neural network receives the power grid node fault waveform characteristics and the power grid topology adjacency matrix of the power grid topology graph, aggregates and transforms the node characteristics through the graph convolution layer, learns the dependency relationship and fault propagation mode between nodes, and adopts multi-layer GCN to enhance the expression ability of the power grid fault inversion dynamic correction model. At the same time, the final correction result is recorded in the power grid fault knowledge graph library to provide technical support for power grid dispatching and operation management personnel. Specifically, Figure 6As shown, firstly, according to the steps of S1 and S2, the original power grid fault inversion model is automatically constructed using the constructed power grid fault knowledge graph library, and the fault waveform of the fault point is generated. The fault waveform of the power grid fault inversion model and the historical fault recorder waveform are subjected to noise reduction, filtering, and normalization. Then, a power grid fault inversion dynamic correction model based on graph convolutional neural network (GCN) is established. The connection relationship between the nodes of the power grid fault graph database is the input connection relationship of the graph convolutional neural network, where the nodes represent electrical equipment such as busbars and transformers, the edges represent transmission lines, and the attributes on the edges represent line parameters and connection relationships. The time series waveform data of the nodes of the power grid fault inversion model after data preprocessing is the input feature vector of the graph convolutional neural network. The physical information of the power grid primary equipment, fault distance, power grid fault type, and transition resistance of each power grid node are used as output vectors. At the same time, each output vector is a dynamic correction value based on the original power grid fault inversion model parameters. The sum of the Pearson correlation coefficients of the power grid fault inversion model of each power grid node and the fault waveform of the fault recorder in the historical data is the loss function of the graph convolutional neural network, and the power grid fault inversion model is continuously and dynamically corrected. like Figure 7 As shown, the process of correcting the parameters of the power grid fault inversion model by the power grid fault inversion dynamic correction model described above can be divided into the following steps: (1) Using the method steps of S1 and S2, an original power grid fault inversion model is established according to the power grid fault knowledge graph matching results, and a power grid topology adjacency matrix is ​​established using the power grid fault knowledge graph matching results; the power grid fault knowledge graph matching results refer to the matching results between the power grid fault inversion model parameters and the power grid fault knowledge graph library; (2) Simulate power grid faults based on the power grid fault knowledge graph matching results to obtain power grid fault simulation waveforms at different nodes in the power grid; (3) Construct a power grid fault waveform feature matrix, and input the power grid fault waveform feature matrix and the power grid topology adjacency matrix into the multi-layer GCN network to obtain the power grid fault inversion model parameter output matrix; the multi-layer GCN network is a plurality of GCN networks connected sequentially, the first layer of the multi-layer GCN network receives the power grid fault waveform feature matrix and the power grid topology adjacency matrix, and the last layer of the multi-layer GCN network outputs the power grid fault inversion model parameter output matrix.

[0037] The horizontal axis (i.e., each row) of the power grid fault waveform feature matrix is ​​the time point of the fault waveform, and the vertical axis (i.e., each column) is the power grid topology node. Each element in the power grid fault waveform feature matrix is ​​the discretized data of the time point corresponding to the fault waveform corresponding to the power grid topology node. The power grid topology adjacency matrix represents the connection relationship between the power grid topology nodes. Both the horizontal and vertical axes are power grid topology nodes, corresponding to the vertical axis of the power grid fault waveform feature matrix. Each element in the power grid topology adjacency matrix uses the number 0 or 1 to indicate whether the nodes are connected or not. Figure 8 As shown in Figure 1, the fault current of the 110kV bus node at time t1 is 0.23A, and the fault current at time t2 is 0.35A. By analogy, the grid fault waveform characteristic matrix is ​​formed, as shown in Figure 1. Fig. 9 As shown, in the grid topology adjacency matrix, 1 indicates that the two grid topologies are connected, and 0 indicates that the two grid topologies are not connected.

[0038] (4) Calculate the mean Pearson correlation coefficient of the simulation waveform and the action report waveform of different power grid nodes as the loss function, and judge whether the Pearson correlation coefficient mean loss function meets the requirements. If it does not meet the requirements, go to step (5); if it meets the requirements, go to step (6); the calculation formula of the mean Pearson correlation coefficient is as follows:

[0039]

[0040] In the formula, , are the discrete sequence values ​​of the simulation waveform and the action report waveform respectively, is the waveform Pearson correlation coefficient of the first power grid node, For the The Pearson correlation coefficient of the waveform of each grid node is calculated in the same way as The same, no further elaboration is given here. is the mean value of the waveform Pearson correlation coefficient of different power grid nodes, is the covariance of x and y, for The standard deviation of for The standard deviation of is the number of grid nodes.

[0041] (5) Using the power grid fault inversion model parameter output matrix to correct the original power grid fault inversion model parameters, the specific method is to add the original power grid fault inversion model parameters to the parameters in the power grid fault inversion model parameter output matrix, which are the power grid fault inversion model parameters of the next stage, and then go to S2;

[0042] In the formula, are the modified power grid fault inversion model parameters, are the original power grid fault inversion model parameters, The parameters in the power grid fault inversion model parameter output matrix correspond to the original power grid fault inversion model parameters.

[0043] (6) Obtain the final power grid fault inversion model.

[0044] Taking the typical faults of 110kV power grid line A phase grounding fault and AB phase interphase fault as examples, the power grid fault inversion model is established using the power grid fault knowledge graph, and the dynamic correction process of power grid fault inversion is demonstrated. By continuously correcting the power grid fault distance, fault type, transition resistance size, etc. Fig.10 It can be seen that the A-phase grounding fault is constantly consistent with the fault recording waveform during the dynamic correction process. Fig.11 It can be seen that the AB phase-to-phase fault is continuously and dynamically corrected with the fault inversion, and its waveform is continuously consistent with the waveform recorded by the fault recorder. Finally, the fault waveform obtained is consistent with the actual power grid line fault recorder waveform, and the power grid fault inversion is finally completed.

[0045] Example 2 Based on Example 1, Example 2 of the present invention further provides a knowledge graph-based power grid fault inversion dynamic correction system, including: A graph library construction module, used to construct a knowledge graph library for power grid faults; An inversion model building module is used to parse the power grid fault message and use the parsing result as the power grid fault inversion model parameter to query and compare with the power grid fault knowledge graph library to build a power grid fault inversion model; The inversion model correction module is used to construct a power grid fault inversion dynamic correction model to correct the power grid fault inversion model parameters to obtain the final power grid fault inversion model.

[0046] Specifically, the atlas library construction module is also used to: The primary equipment of the power grid is taken as the entity of the power grid fault knowledge graph library, and the following classes are set: relay protection device information, power grid fault type, flow information, equipment information, and power grid fault information. Each class is set with multiple attributes to form a triple of entity-class-attribute. The historical data of the power grid is realized in one-to-one correspondence with entities in the form of the triple, thereby constructing a power grid fault knowledge graph library.

[0047] Specifically, the inversion model building module is also used to: A bidirectional long short-term memory network is used to parse real-time power grid fault messages and historical power grid fault messages. The parsing results include the entity information of the primary equipment in the power grid, fault distance, power grid fault type, and transition resistance. The parsing results are used as the parameters of the power grid fault inversion model. The power grid fault inversion model parameters are matched one-to-one with the power grid fault knowledge graph library to complete the power grid fault knowledge graph matching. The power grid fault is simulated within the power grid subnet involved in the power grid fault according to the power grid fault knowledge graph matching results, thereby establishing a power grid fault inversion model.

[0048] More specifically, the real-time power grid fault message and the historical power grid fault message include a real-time SOE information message of a power grid fault and a real-time relay protection information management system action report, and a historical power grid fault SOE information message and a historical relay protection information management system action report.

[0049] More specifically, the use of a bidirectional long short-term memory network to parse real-time power grid fault messages and historical power grid fault messages includes: The real-time power grid fault messages and historical power grid fault messages are annotated with BIO using the power grid fault knowledge graph, and the annotation results are input into the bidirectional long short-term memory network. The output results of the bidirectional long short-term memory network are input into the CRF layer, and the CRF layer outputs the parsing results.

[0050] More specifically, the inversion model correction module is also used to: S31. Establishing a power grid topology adjacency matrix using the power grid fault knowledge graph matching result; the power grid fault knowledge graph matching result refers to the matching result between the power grid fault inversion model parameters and the power grid fault knowledge graph library; S32, simulating a power grid fault according to the power grid fault knowledge graph matching result, and obtaining power grid fault simulation waveforms at different nodes in the power grid; S33, constructing a power grid fault waveform feature matrix according to the power grid fault simulation waveform, and inputting the power grid fault waveform feature matrix and the power grid topology adjacency matrix into a multi-layer GCN network connected in sequence to obtain a power grid fault inversion model parameter output matrix; S34, calculating the mean value of the Pearson correlation coefficient between the grid fault simulation waveform and the actual action report waveform at different nodes in the grid as the loss function, and judging whether the loss function meets the requirements, if not, going to S35, if meeting the requirements, going to S36; S35, using the power grid fault inversion model parameter output matrix to correct the power grid fault inversion model parameters, and returning to execute the inversion model construction module; S36. Obtain the final power grid fault inversion model.

[0051] More specifically, the power grid topology adjacency matrix represents the connection relationship between power grid topology nodes, each row and each column are power grid topology nodes, and each element in the power grid topology adjacency matrix uses a number to indicate whether the nodes are connected or not. Each row of the power grid fault waveform feature matrix is ​​a time point of a power grid fault simulation waveform, and each column is a power grid topology node. Each element in the power grid fault waveform feature matrix is ​​the discrete data of the time point corresponding to the power grid fault simulation waveform corresponding to the power grid topology node.

[0052] More specifically, judging whether the loss function meets the requirement means that the requirement is met when the loss function value reaches the minimum, otherwise the requirement is not met.

[0053] More specifically, the method of using the power grid fault inversion model parameter output matrix to correct the power grid fault inversion model parameters is to add the original power grid fault inversion model parameters and the parameters in the power grid fault inversion model parameter output matrix as the power grid fault inversion model parameters of the next stage, and return to execute the inversion model construction module.

[0054] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A knowledge graph-based power grid fault inversion dynamic correction method, characterized in that: include: S1. Build a knowledge graph library of power grid faults; S2, parsing the power grid fault message and using the parsing result as the power grid fault inversion model parameter to query and compare with the power grid fault knowledge graph library to build a power grid fault inversion model; S3. Construct a power grid fault inversion dynamic correction model to correct the power grid fault inversion model parameters to obtain the final power grid fault inversion model.

2. According to the knowledge graph-based power grid fault inversion dynamic correction method of claim 1, it is characterized in that: S1 includes: The primary equipment of the power grid is taken as the entity of the power grid fault knowledge graph library, and the following classes are set: relay protection device information, power grid fault type, flow information, equipment information, and power grid fault information. Each class is set with multiple attributes to form a triple of entity-class-attribute. The historical data of the power grid is realized in one-to-one correspondence with entities in the form of the triple, thereby constructing a power grid fault knowledge graph library.

3. The power grid fault inversion dynamic correction method based on knowledge graph according to claim 1 is characterized in that S2 include: A bidirectional long short-term memory network is used to parse real-time power grid fault messages and historical power grid fault messages. The parsing results include the entity information of the primary equipment in the power grid, fault distance, power grid fault type, and transition resistance. The parsing results are used as the parameters of the power grid fault inversion model. The power grid fault inversion model parameters are matched one-to-one with the power grid fault knowledge graph library to complete the power grid fault knowledge graph matching. The power grid fault is simulated within the power grid subnet involved in the power grid fault according to the power grid fault knowledge graph matching results, thereby establishing a power grid fault inversion model.

4. A knowledge graph-based power grid fault inversion dynamic correction method according to claim 3, characterized in that: The real-time power grid fault message and the historical power grid fault message include a real-time SOE information message of a power grid fault and a real-time relay protection information management system action report, and a historical power grid fault SOE information message and a historical relay protection information management system action report.

5. The power grid fault inversion dynamic correction method based on knowledge graph according to claim 3 is characterized in that: The method of using a bidirectional long short-term memory network to analyze real-time power grid fault messages and historical power grid fault messages includes: The real-time power grid fault messages and historical power grid fault messages are annotated with BIO using the power grid fault knowledge graph, and the annotation results are input into the bidirectional long short-term memory network. The output results of the bidirectional long short-term memory network are input into the CRF layer, and the CRF layer outputs the parsing results.

6. The power grid fault inversion dynamic correction method based on knowledge graph according to claim 3 is characterized in that S3 include: S31. Establishing a power grid topology adjacency matrix using the power grid fault knowledge graph matching result; the power grid fault knowledge graph matching result refers to the matching result between the power grid fault inversion model parameters and the power grid fault knowledge graph library; S32, simulating a power grid fault according to the power grid fault knowledge graph matching result, and obtaining power grid fault simulation waveforms at different nodes in the power grid; S33, constructing a power grid fault waveform feature matrix according to the power grid fault simulation waveform, and inputting the power grid fault waveform feature matrix and the power grid topology adjacency matrix into a multi-layer GCN network connected in sequence to obtain a power grid fault inversion model parameter output matrix; S34, calculating the mean value of the Pearson correlation coefficient between the grid fault simulation waveform and the actual action report waveform at different nodes in the grid as the loss function, and judging whether the loss function meets the requirements, if not, going to S35, if meeting the requirements, going to S36; S35, using the power grid fault inversion model parameter output matrix to correct the power grid fault inversion model parameters, and returning to execute S2; S36. Obtain the final power grid fault inversion model.

7. A knowledge graph-based power grid fault inversion dynamic correction method according to claim 6, characterized in that: The power grid topology adjacency matrix represents the connection relationship between power grid topology nodes, each row and each column are power grid topology nodes, and each element in the power grid topology adjacency matrix uses a number to represent whether the nodes are connected or not. Each row of the power grid fault waveform feature matrix is ​​a time point of a power grid fault simulation waveform, and each column is a power grid topology node. Each element in the power grid fault waveform feature matrix is ​​the discretized data of the corresponding time point of the power grid fault simulation waveform corresponding to the power grid topology node.

8. The power grid fault inversion dynamic correction method based on knowledge graph according to claim 6 is characterized in that: The determination of whether the loss function meets the requirement means that the requirement is met when the loss function value reaches the minimum, otherwise the requirement is not met.

9. The method for dynamic correction of power grid fault inversion based on knowledge graph according to claim 6, characterized in that: The method of using the power grid fault inversion model parameter output matrix to correct the power grid fault inversion model parameters is to add the original power grid fault inversion model parameters and the parameters in the power grid fault inversion model parameter output matrix as the power grid fault inversion model parameters of the next stage, and return to execute S2.

10. A knowledge graph-based power grid fault inversion dynamic correction system, characterized in that: include: A graph library construction module, used to construct a knowledge graph library for power grid faults; An inversion model building module is used to parse the power grid fault message and use the parsing result as the power grid fault inversion model parameter to query and compare with the power grid fault knowledge graph library to build a power grid fault inversion model; The inversion model correction module is used to construct a power grid fault inversion dynamic correction model to correct the power grid fault inversion model parameters to obtain the final power grid fault inversion model.

Images