Fault line processing preplan generation method and device, terminal equipment and medium

Abstract

The application discloses a kind of fault line processing preplan generation method, device, terminal equipment and medium, the method includes: obtaining power grid primary equipment CIM full model, as training sample set;Using deep learning algorithm to the training sample set is extracted, generates line connection classification model;Using the line connection classification model constructs line model classification feature library;According to the line model classification feature library, for the feature matching of to-be-tested fault line, generates fault line processing preplan.The fault line processing preplan generation method provided in the application, when line fault processing preplan needs to be generated, obtains line connection structure feature from line model classification feature library by feature recognition, takes out response electronic preplan template, to automatically generate the line fault processing preplan, greatly reduce the human input of preplan preparation, improve line fault processing efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fault line processing preplan generation, and in particular to a fault line processing preplan generation method and device, a terminal device and a medium. BACKGROUND

[0002] With the continuous expansion of the power grid scale, the number of power equipment and lines is increasing, and the power grid maintenance work is becoming increasingly heavy. When the power grid has a fault line, if the correct response measures cannot be taken in time, it will often cause a major safety accident. In order to improve the correctness and rapidity of the power grid dispatching and substation operation personnel in handling accidents, the preparation of the fault line processing preplan is particularly important. However, the preparation of the fault line processing preplan in the dispatching information system at present mainly relies on manual maintenance of the staff, which not only needs to consume a large amount of manpower and material resources, greatly increases the work burden of the dispatching personnel, but also is difficult to guarantee the accuracy and timeliness of the prepared preplan, and cannot meet the needs of the normal operation of the power grid system. SUMMARY

[0003] The present application aims to provide a fault line processing preplan generation method, device, terminal device and medium to solve the problems of long time consumption, difficulty in implementation and low accuracy in the preparation of the fault processing preplan by relying on manual work in the prior art

[0004] To achieve the above-mentioned purpose, the present application provides a fault line processing preplan generation method, comprising:

[0005] obtaining a power grid primary equipment CIM full model as a training sample set;

[0006] using a deep learning algorithm to extract features from the training sample set to generate a line wiring classification model;

[0007] using the line wiring classification model to construct a line model classification feature library;

[0008] According to the line model classification feature library, feature matching is performed for the to-be-tested fault line to generate a fault line processing preplan.

[0009] Further, as a preferred, the use of a deep learning algorithm to extract features from the training sample set to generate a line wiring classification model comprises:

[0010] data structuring the power grid wiring of the training sample set to construct a power grid wiring diagram matrix;

[0011] using the power grid wiring diagram matrix to analyze the correlation of different power grid wiring structures to generate a line wiring classification model.

[0012] Further, as preferably, the line connection classification model is used to build a line model classification feature library, comprising:

[0013] The association between the typical line fault processing plan and the line connection classification model feature is built, and a line model classification feature library is built.

[0014] Further, as preferably, the deep learning algorithm is a regression algorithm.

[0015] The application also provides a fault line processing plan generation device, comprising:

[0016] A sample acquisition unit is configured to acquire a power grid primary equipment CIM full model as a training sample set;

[0017] A feature extraction unit is configured to use a deep learning algorithm to extract features of the training sample set, and generate a line connection classification model;

[0018] A classification library construction unit is configured to use the line connection classification model to build a line model classification feature library;

[0019] A fault plan generation unit is configured to perform feature matching for a to-be-tested fault line according to the line model classification feature library, and generate a fault line processing plan.

[0020] Further, as preferably, the feature extraction unit is further configured to:

[0021] Data structure of the power grid connection of the training sample set is structured, and a power grid connection diagram matrix is built;

[0022] The power grid connection diagram matrix is used to analyze the association between different power grid connection structures, and a line connection classification model is generated.

[0023] Further, as preferably, the classification library construction unit is further configured to:

[0024] The association between the typical line fault processing plan and the line connection classification model feature is built, and a line model classification feature library is built.

[0025] Further, as preferably, the deep learning algorithm is a regression algorithm.

[0026] The application also provides a terminal device, comprising:

[0027] One or more processors;

[0028] A memory coupled to the processor, configured to store one or more programs;

[0029] When the one or more programs are executed by the one or more processors, the one or more processors implement the fault line processing plan generation method according to any one of the above.

[0030] The application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the fault line processing plan generation method according to any one of the above.

[0031] Compared with the prior art, the application has the following beneficial effects:

[0032] The application discloses a fault line processing plan generation method and device, a terminal equipment and a medium.

[0033] The fault line processing plan generation method provided by the application can obtain the line connection structure features from the line model classification feature library through feature recognition when the line fault processing plan needs to be generated, and the response electronic plan template is taken out, so that the line fault processing plan is automatically generated, the human input for plan compilation is greatly reduced, and the line fault processing efficiency is improved. BRIEF DESCRIPTION OF DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the application, the following will briefly introduce the drawings needed to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative effort on the basis of these drawings.

[0035] Figure 1 Fig. 1 is a flowchart of the fault line processing plan generation method provided by an embodiment of the application;

[0036] Figure 2 Fig. 2 is a schematic diagram of a 3 / 2 line connection structure provided by an embodiment of the application;

[0037] Figure 3 Fig. 3 is a structural schematic diagram of the fault line processing plan generation device provided by an embodiment of the application;

[0038] Figure 4 Fig. 4 is a structural schematic diagram of the terminal equipment provided by an embodiment of the application. DETAILED DESCRIPTION

[0039] With reference to the drawings and embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of the present application.

[0040] It should be understood that the step numbers used herein are only for the convenience of description, and are not limited to the execution sequence of the steps.

[0041] It should be understood that the terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and the appended claims of the present application, the singular forms "a", "an" and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0042] The terms "comprise" and "include" indicate the presence of described features, integers, steps, operations, elements, and / or components, but do not exclude one or more other features, integers, steps, operations, elements, components, and / or sets thereof.

[0043] The term "and / or" means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0044] Please refer to Figure 1 An embodiment of the present application provides a fault line processing plan generation method. As shown in Figure 1 The fault line processing plan generation method includes steps S10 to S40. Each step is as follows:

[0045] S10, obtain a CIM full model of power grid primary equipment as a training sample set.

[0046] It should be noted that in this step, the CIM model file is a power grid equipment model data file defined according to the "Power Grid General Model Specification", which contains complete device objects and their technical parameters, as well as the connection relationship between devices. By obtaining the CIM full model of the primary equipment in the power grid, a complete device object model and data can be obtained, which are used as a training sample set.

[0047] S20, using a deep learning algorithm to extract features from the training sample set, generating a line wiring classification model.

[0048] It should be noted that the deep learning algorithm used here is preferably a regression algorithm.

[0049] In a specific embodiment, step S20 further specifically comprises:

[0050] 1) Data structuring of the power grid wiring of the training sample set, constructing a power grid wiring diagram matrix.

[0051] Before performing step 1), first, data preprocessing is performed on the training sample set, specifically, for the inventory power system primary equipment wiring diagram with classification labels, each line model data is taken as a node of an undirected graph, and the connection relationship of the line with other primary equipment such as a knife switch, a switch, and a ground knife is taken as an edge of the undirected graph, thereby constructing a line graph model data.

[0052] Further, in order to realize the line wiring model classification method based on deep learning, it is necessary to first structure the data of the power grid wiring diagram and construct a device wiring diagram matrix:

[0053] G = (V, E);

[0054] In the formula, V represents a set of vertices; E represents a set of edges.

[0055] Then, each primary equipment element in the power grid wiring diagram is taken as a vector in the input sample matrix, and the linking relationship between the elements in the wiring diagram is taken as an edge in the input graph. It can be understood that the data structuring of the power grid wiring diagram is the basis for deep learning of the power grid model. For example, the feature extraction and recognition of the 3 / 2 wiring switch in this step are taken as an example to be described. The 3 / 2 line wiring structure is as shown in Figure 2 .

[0056] As shown in Figure 2 , the device elements in the graph include switches, buses, transformers, lines, and knife switches, etc. First, a set of vertices is constructed:

[0057] V = (v1, v2,..., v n );

[0058] In the formula, v i represents an element in the wiring diagram, which is a d-dimensional vector, and d is the number of device types in the wiring diagram.

[0059] Then v i = (x i1 , x i2 ,..., x id ) T , wherein x ij = 1 represents that v i is the jth type of device, otherwise x ij = 0.

[0060] In the formula, E = (e1, e2,..., e n) is the set of edges in the wiring diagram, when there is a connection between the i, j-th device, e ij = 1, otherwise e ij = 0.

[0061] Further, based on the above matrix, the model correlation is obtained by iterative analysis, specifically: starting from the adjacent two end objects of the device model object, the model correlation algorithm analysis is iteratively performed until the data converges, the model correlation list is perfected, and the complete correlation matrix of the device model is obtained. For line equipment, the two ends connected are different substations, so two different adjacency matrices N left ,N right represent the device connection relationship.

[0062] Specifically, taking the line as an example v i , the adjacency matrix N left is calculated. Let N left corresponding to the plant wiring diagram matrix is G, in the edge set E, if e ij = 1, the device vector v j is placed in the adjacency matrix N left ; continue to search for the edge set corresponding to v j by iterative depth-first search algorithm, and place the device vector adjacent to v j in the adjacency matrix N left , until there is no other adjacent device of the searched device, thereby obtaining the adjacency matrix N left of the line, which represents the device set connected with the line v i . In the same way, the adjacency matrix N i of the line v right is calculated by using the wiring diagram of the other end of the plant, and the line wiring correlation matrix of v i is obtained, denoted as:

[0063] N = (N left ,N right ).

[0064] 2) Using the power grid wiring diagram matrix, analyze the correlation of different power grid wiring structures, and generate a line wiring classification model.

[0065] In this step, the typical line fault handling plan prepared and the wiring mode features extracted from the related line are mainly associated and analyzed. For the typical line fault handling plan, an iterative analysis calculation method is used to calculate the line wiring correlation matrix N of the line, and a line wiring classification model is generated.

[0066] S30, using the line wiring classification model to construct a line model classification feature library;

[0067] In this step, the adjacency matrix of the line to which the typical line fault handling plan is specifically set is N, and each adjacent device v in the matrix N is traversed i , and the device scheduling name is matched and searched in the fault handling plan, and the text position d located by the search is recorded i . After the traversal is completed, the text information T of the typical line fault handling plan and the position set D=(d1,..., d t ) are combined, and are set as the line fault handling plan template M=(T, D). Finally, the line information V, the line connection relationship matrix N, and the fault handling plan template M thereof are associated one by one and stored in the database.

[0068] S40, according to the line model classification feature library, the feature matching is performed for the to-be-tested fault line to generate a fault line handling plan.

[0069] In this step, the wiring structure of the primary equipment model is identified by comparing it with the defined typical line connection mode through pattern recognition technology. For the line for which the fault handling plan needs to be prepared, the line connection relationship matrix is calculated through the iteration analysis in the above step, and then the matrix similarity calculation is performed on the line connection relationship matrix of the typical line saved in the database, and the typical line with the most similar connection mode is found. For example, the line fault handling plan template M matched from the database is replaced by the corresponding device scheduling name for each position in the position set D corresponding to the position, so as to obtain a new line fault handling plan. At the same time, considering the actual application situation, there will be certain differences between the fault handling plan and the typical plan, so in this embodiment, the plan preparation can be supplemented by additionally providing a manual checking and confirming means, and through the "automatic generation + manual confirmation" means, the final line fault handling plan is formed.

[0070] The fault line handling plan generation method provided by the application can obtain the line connection structure features from the line model classification feature library through feature recognition when the line fault handling plan needs to be generated, and the electronic plan template is taken out, so as to automatically generate the line fault handling plan, which greatly reduces the human input for plan preparation and improves the line fault handling efficiency.

[0071] Please refer to Figure 3 , the embodiment of the application also provides a fault line handling plan generation device, which comprises:

[0072] A sample acquisition unit 01 is configured to acquire a power grid primary equipment CIM full model as a training sample set;

[0073] A feature extraction unit 02 is configured to perform feature extraction on the training sample set by using a deep learning algorithm to generate a line connection classification model;

[0074] a classification library construction unit 03, configured to construct a line model classification feature library by using the line connection classification model;

[0075] a fault plan generation unit 04, configured to perform feature matching for a to-be-tested fault line according to the line model classification feature library, and generate a fault line processing plan.

[0076] In an embodiment, the feature extraction unit 02 is further configured to:

[0077] perform data structuring on the power grid connection of the training sample set, and construct a power grid connection graph matrix;

[0078] analyze the correlation of different power grid connection structures by using the power grid connection graph matrix, and generate a line connection classification model.

[0079] In an embodiment, the classification library construction unit 03 is further configured to:

[0080] construct the correlation between a typical line fault processing plan and a line connection classification model feature, and construct a line model classification feature library.

[0081] In an embodiment, the deep learning algorithm is a regression algorithm.

[0082] For details, please refer to Figure 4 In an embodiment, a terminal device is provided, which includes:

[0083] one or more processors;

[0084] a memory, coupled to the processor, configured to store one or more programs;

[0085] When the one or more programs are executed by the one or more processors, the one or more processors implement the fault line processing plan generation method as described above.

[0086] The processor is configured to control overall operations of the terminal device to complete all or part of the steps of the fault line handling plan generation method described above. The memory is configured to store various types of data to support the operation of the terminal device, which can include, for example, instructions for any application or method operating on the terminal device, and application-related data. The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0087] In some example embodiments, the terminal device can be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic elements, for executing the fault line handling plan generation method as described in any of the above embodiments and achieving the technical effects consistent with the above method.

[0088] In another example embodiment, a computer-readable storage medium including a computer program is also provided, which, when executed by a processor, implements the steps of the fault line handling plan generation method as described in any of the above embodiments. For example, the computer-readable storage medium can be the above-mentioned memory including the computer program, which can be executed by the processor of the terminal device to complete the fault line handling plan generation method as described in any of the above embodiments and achieve the technical effects consistent with the above method.

[0089] The above is the preferred embodiment of the present application, it should be pointed out that, for those skilled in the art, without departing from the principles of the present application, can also make a number of improvements and refinements, these improvements and refinements are also considered to be within the scope of the present application.

Claims

1. A method for generating a fault line handling plan, characterized in that, include: Obtain the full CIM model of the primary equipment of the power grid as a training sample set; The training sample set is used to extract features using a deep learning algorithm to generate a line wiring classification model. This process includes: structuring the power grid wiring data in the training sample set to construct a power grid wiring diagram matrix; and using the power grid wiring diagram matrix to analyze the correlation relationships between different power grid wiring structures to generate a line wiring classification model. A line model classification feature library is constructed using the aforementioned line connection classification model; Based on the line model classification feature library, feature matching is performed on the faulty line to be tested to generate a faulty line handling plan. The step of using the power grid wiring diagram matrix to analyze the correlation between different power grid wiring structures and generate a line wiring classification model is as follows: The typical line fault handling plan is correlated with the wiring characteristics extracted from the typical line. For the typical line fault handling plan, the line wiring correlation matrix of the typical line is calculated by iterative analysis and calculation method to generate the line wiring classification model. The construction of a line model classification feature library using the line connection classification model specifically involves: Traverse each adjacent device in the adjacency matrix of a typical line, and perform text matching retrieval in the fault handling plan of the typical line through the scheduling name of the adjacent device, and record the text position located by the retrieval; after the traversal is completed, combine the text information of the fault handling plan of the typical line and the set of text positions to set up the line fault handling plan template; associate the line information of the typical line, the line connection relationship matrix, and the line fault handling plan template one-to-one and store them in the database. The step of performing feature matching for the faulty line under test based on the line model classification feature library and generating a faulty line handling plan is as follows: For the faulty line under test, the wiring relationship matrix of the faulty line under test is calculated by iterative analysis, and the matrix similarity is calculated with the wiring relationship matrix of the typical lines stored in the database to determine the typical line with the wiring method most similar to the faulty line under test.

2. The method for generating a fault line handling plan according to claim 1, characterized in that, The construction of a line model classification feature library using the line connection classification model includes: Establish the correlation between typical line fault handling plans and line wiring classification model features, and construct a line model classification feature library.

3. The method for generating a fault line handling plan according to claim 1, characterized in that, The deep learning algorithm mentioned is a regression algorithm.

4. A fault line handling contingency plan generation device, characterized in that, include: The sample acquisition unit is used to acquire the full CIM model of primary power grid equipment as a training sample set. The feature extraction unit is used to extract features from the training sample set using a deep learning algorithm to generate a line wiring classification model. The process of extracting features from the training sample set using a deep learning algorithm to generate the line wiring classification model includes: structuring the power grid wiring data in the training sample set to construct a power grid wiring diagram matrix; and using the power grid wiring diagram matrix to analyze the correlation between different power grid wiring structures to generate a line wiring classification model. The classification library construction unit is used to construct a line model classification feature library using the line wiring classification model. The fault contingency plan generation unit is used to perform feature matching for the faulty line under test based on the line model classification feature library, and generate a faulty line handling contingency plan. The step of using the power grid wiring diagram matrix to analyze the correlation between different power grid wiring structures and generate a line wiring classification model is as follows: The typical line fault handling plan is correlated with the wiring characteristics extracted from the typical line. For the typical line fault handling plan, the line wiring correlation matrix of the typical line is calculated by iterative analysis and calculation method to generate the line wiring classification model. The construction of a line model classification feature library using the line connection classification model specifically involves: Traverse each adjacent device in the adjacency matrix of a typical line, and perform text matching retrieval in the fault handling plan of the typical line through the scheduling name of the adjacent device, and record the text position located by the retrieval; after the traversal is completed, combine the text information of the fault handling plan of the typical line and the set of text positions to set up the line fault handling plan template; associate the line information of the typical line, the line connection relationship matrix, and the line fault handling plan template one-to-one and store them in the database. The step of performing feature matching for the faulty line under test based on the line model classification feature library and generating a faulty line handling plan is as follows: For the faulty line under test, the wiring relationship matrix of the faulty line under test is calculated by iterative analysis, and the matrix similarity is calculated with the wiring relationship matrix of the typical lines stored in the database to determine the typical line with the wiring method most similar to the faulty line under test.

5. The fault line handling contingency plan generation device according to claim 4, characterized in that, The classification library construction unit is also used for: Establish the correlation between typical line fault handling plans and line wiring classification model features, and construct a line model classification feature library.

6. The fault line handling contingency plan generation device according to claim 4, characterized in that, The deep learning algorithm mentioned is a regression algorithm.

7. A terminal device, characterized in that, include: One or more processors; A memory, coupled to the processor, for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the fault line handling plan generation method as described in any one of claims 1-3.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the fault line handling plan generation method as described in any one of claims 1-3.

Images