A method and system for evaluating the state of a multi-break filter circuit breaker

Abstract

The embodiment of the present invention provides a method and system for evaluating the state of a multi-break filter circuit breaker, which belongs to the technical field of state evaluation of a multi-break filter circuit breaker. The method comprises: obtaining component information of a multi-break filter circuit breaker; obtaining historical maintenance information of the multi-break filter circuit breaker; constructing a maintenance state matrix on a time series according to the historical maintenance information and the component information; predicting the state of the multi-break filter circuit breaker for a preset time period based on the maintenance state matrix; and evaluating the state of the multi-break filter circuit breaker according to the prediction result. The method and system can accurately predict the future state of a multi-break filter circuit breaker.

Description

Technical Field

[0001] The present invention relates to the technical field of state evaluation of a multi-break filter circuit breaker, and in particular to a state evaluation method and system of a multi-break filter circuit breaker. Background Art

[0002] As a vital protection device in the power system, the status of the circuit breaker is directly related to the safety and stable operation of the entire power network. Traditionally, the status assessment of circuit breakers mainly relies on the experience judgment of operation and maintenance personnel and regular manual inspections. Although this method is widely used in practice, it has obvious limitations. First, human subjective judgment is easily affected by personal experience, skill level and environmental conditions at the time, which may lead to deviations in the evaluation results and it is difficult to ensure high consistency and accuracy. Secondly, manual inspections can often only find some superficial or obvious problems, and it is difficult to effectively identify potential and subtle fault precursors, which undoubtedly increases the risk of power system operation.

[0003] With the continuous expansion of the scale and increase in complexity of power systems, higher requirements are placed on the accuracy and real-time performance of circuit breaker status assessment. However, existing assessment methods are inadequate when facing large-scale power grids and cannot achieve comprehensive, in-depth and continuous monitoring and analysis of all circuit breakers. In addition, the lack of scientific and accurate prediction calculation models makes it difficult for operation and maintenance personnel to predict possible failures of circuit breakers in advance, thus missing the best maintenance time, which may lead to sudden power outages, affect users' normal power experience, and may even cause more serious safety accidents. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a method and system for evaluating the state of a multi-break filter circuit breaker, which can accurately predict the future state of the multi-break filter circuit breaker.

[0005] In order to achieve the above object, an embodiment of the present invention provides a method for evaluating the state of a multi-break filter circuit breaker, comprising: Get component information of multi-break filter circuit breaker; Acquire historical maintenance information of the multi-break filter circuit breaker; Constructing a maintenance status matrix in time series according to the historical maintenance information and the component information; Predicting the state of the multi-break filter circuit breaker for a preset time period based on the maintenance state matrix; The state of the multi-break filter circuit breaker is evaluated according to the prediction result.

[0006] Optionally, the component information includes at least one of a main contact, a fixed contact, a metal electrical isolator, an operating mechanism, a transmission mechanism, a spring mechanism, a gas pressure system, a shock absorbing system, an arc chamber, a nozzle, and a pressure relief system.

[0007] Optionally, constructing a maintenance status matrix in time series according to the historical maintenance information and the component information includes: The maintenance status matrix is ​​established according to formula (1): , (1) in, is the maintenance state matrix, , , , is the status value of the corresponding component during the maintenance cycle, is the number of maintenance cycles, is the number of components.

[0008] Optionally, predicting the state of the multi-break filter circuit breaker for a preset time period based on the maintenance state matrix includes: determining the number of maintenance cycles included in the preset time period; intercepting the matrix cells in the maintenance status matrix according to the number of the maintenance cycles as actual output; In the maintenance state matrix, at a position before the intercepted matrix unit, the matrix unit in the maintenance state matrix is ​​intercepted according to a preset time span to serve as a sample unit; Taking the sample unit as input and the actual output as standard output, a training set, a test set and a validation set are constructed, wherein the ratio of the number of samples in the training set, the test set and the validation set is 7:2:1; The training set, the test set and the validation set are used to train a preset circuit breaker state prediction model to predict the state of the multi-break filter circuit breaker.

[0009] Optionally, the circuit breaker state prediction model includes: An input layer, used for converting the input matrix unit to obtain a one-dimensional sequence; Multiple hidden layers, each hidden layer is used to perform feature processing on the output of the previous layer to obtain the output of the current hidden layer; A main fully connected layer, used to make predictions based on the output of the hidden layer of the last layer to obtain a main classification result; A plurality of secondary fully connected layers, respectively used to make predictions based on the outputs of the hidden layers of the penultimate layer and the third-to-last layer, so as to obtain corresponding secondary classification results; The decision layer is used to perform weighted calculation on the primary classification results and the secondary classification results to obtain the final prediction result.

[0010] Optionally, the decision layer is used to: The first weight of the weighted calculation is calculated according to the following formula (2): , (2) in, According to the last The output prediction of the hidden layer of the layer The weight of the primary classification result or the secondary classification result.

[0011] Optionally, the method further comprises: The following formula (3) is used as the loss function of the circuit breaker state prediction model: , (3) in, is the calculated error, is the sample size, For standard output, is the predicted output.

[0012] Optionally, evaluating the state of the multi-break filter circuit breaker according to the prediction result includes: The AHP algorithm is used to calculate the evaluation results.

[0013] On the other hand, the present invention further provides a system for evaluating the status of a circuit breaker of a multi-break filter, wherein the system comprises a processor, and the processor is used to execute any of the above methods.

[0014] Through the above technical solution, the embodiment of the present invention provides a method and system for evaluating the state of a multi-port filter breaker. The method and system perform matrix processing on the component information and historical maintenance information of the multi-port filter breaker, and then perform prediction in combination with the prediction model of the multi-port filter breaker, and finally calculate the predicted results to obtain the evaluation results of the future state. Compared with the prior art, the method provided by the present invention combines the network model prediction and evaluation calculation, that is, it utilizes the advantages of the output accuracy of the network model itself, and also avoids the problem of low accuracy caused by excessive fuzzy calculation in the classification processing of the network model.

[0015] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings: Figure 1 is a flow chart of a method for evaluating a multi-port filter state according to an embodiment of the present invention; Figure 2 is a physical diagram of a multi-break filter circuit breaker according to the present invention; Figure 3 The present invention is a flowchart of a method for predicting the state of a multi-break filter circuit breaker. DETAILED DESCRIPTION

[0017] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0018] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. In the embodiments of this application, some existing solutions in the industry such as certain software, components, and models may be mentioned, which should be considered as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0019] like Figure 1 FIG. 1 is a flow chart of a method for evaluating the state of a multi-break filter circuit breaker according to an embodiment of the present invention. Figure 1 In the present invention, the evaluation method may include the following steps: In step S10, component information of a multi-break filter circuit breaker is obtained; In step S11, historical maintenance information of a multi-break filter circuit breaker is obtained; In step S12, a maintenance status matrix on a time series is constructed according to the historical maintenance information and component information; In step S13, the state of the multi-break filter breaker is predicted for a preset time period based on the maintenance state matrix; In step S14, the state of the multi-break filter breaker is evaluated according to the prediction result.

[0020] In such Figure 1 In the method shown, step S10 can be used to obtain component information of a multi-break filter circuit breaker. The component information can be in various forms known to those skilled in the art. In one example of the present invention, Figure 2Taking the multi-break filter circuit breaker shown in as an example, the multi-break filter circuit breaker may include a main contact, a fixed contact, a metal electrical isolator, an operating mechanism, a transmission mechanism, a spring mechanism, a gas pressure system, a shock absorbing system, an arc chamber, a nozzle, and a pressure relief system. Accordingly, the component information may include at least one of the main contact, the fixed contact, the metal electrical isolator, the operating mechanism, the transmission mechanism, the spring mechanism, the gas pressure system, the shock absorbing system, the arc chamber, the nozzle, and the pressure relief system.

[0021] Step S11 may be used to obtain historical maintenance information of the multi-break filter breaker, wherein the historical maintenance information may include an indicator variable including the number of times each component of the multi-break filter breaker is maintained in each maintenance cycle or whether it is maintained.

[0022] Step S12 can be used to construct a maintenance status matrix in time series based on the historical maintenance information and component information. Based on the component information of step S10 and the historical maintenance information obtained in step S11, the maintenance status matrix can be represented by the following formula (1), for example: , (1) in, To maintain the state matrix, , , , is the status value of the corresponding component during the maintenance cycle, is the number of maintenance cycles, is the number of components.

[0023] Step S13 is used to predict the state of the multi-break filter circuit breaker for a preset time period based on the maintenance state matrix. The specific method for predicting the state can be in various forms known to those skilled in the art. In one example of the present invention, the method for predicting the state may include: Figure 3 In the steps shown in Figure 3 In the method for predicting the state, the method may include the following steps: In step S20, the number of maintenance cycles included in the preset time period is determined; In step S21, the matrix cells in the maintenance status matrix are intercepted according to the number of maintenance cycles as actual output; In step S22, in the maintenance state matrix, at a position before the intercepted matrix unit, the matrix unit in the maintenance state matrix is ​​intercepted according to a preset time span to serve as a sample unit; In step S23, the sample unit is used as input, the actual output is used as the standard output, and a training set, a test set, and a validation set are constructed, wherein the ratio of the number of samples in the training set, the test set, and the validation set is 7:2:1; In step S24, a preset circuit breaker state prediction model is trained using a training set, a test set, and a validation set to predict the state of a multi-break filter circuit breaker.

[0024] The specific structure of the circuit breaker state prediction model in step S23 can be in various forms known to those skilled in the art. In one example of the present invention, the circuit breaker state prediction model may include an input layer, multiple hidden layers, a main connection layer, multiple secondary connection layers, and a decision layer. Among them, the input layer can be used to convert the input matrix unit to obtain a one-dimensional sequence. Each hidden layer can be used to perform feature processing on the output of the previous layer to obtain the output of the hidden layer of this layer. The main fully connected layer can be used to make predictions based on the output of the hidden layer of the last layer to obtain the main classification result. Multiple secondary fully connected layers can be used to make predictions based on the outputs of the hidden layers of the second to last layer and the third to last layer, respectively, to obtain corresponding secondary classification results. The decision layer can be used to perform weighted calculations on the main classification results and the secondary classification results to obtain the final prediction results. Among them, the first weight of the weighted calculation can be determined using the following formula (2), , (2) in, According to the last The output prediction of the hidden layer of the layer The weight of a primary classification result or a secondary classification result.

[0025] In addition, for the loss function in the process of training the circuit breaker state prediction model, the following formula (3) can be used: , (3) in, is the calculated error, is the sample size, For standard output, is the predicted output.

[0026] Step S14 may be used to evaluate the state of the multi-break filter breaker according to the prediction result. Specifically, in one example of the present invention, the result of the evaluation may be calculated using an AHP algorithm.

[0027] On the other hand, the present invention also provides a system for evaluating the status of a multi-break filter circuit breaker, the system comprising a processor, the processor being used to execute any of the above methods. Specifically, the method may include the following steps: In step S10, component information of a multi-break filter circuit breaker is obtained; In step S11, historical maintenance information of a multi-break filter circuit breaker is obtained; In step S12, a maintenance status matrix on a time series is constructed according to the historical maintenance information and component information; In step S13, the state of the multi-break filter breaker is predicted for a preset time period based on the maintenance state matrix; In step S14, the state of the multi-break filter breaker is evaluated according to the prediction result.

[0028] In such Figure 1 In the method shown, step S10 can be used to obtain component information of a multi-break filter circuit breaker. The component information can be in various forms known to those skilled in the art. In one example of the present invention, Figure 2 Taking the multi-break filter circuit breaker shown in as an example, the multi-break filter circuit breaker may include a main contact, a fixed contact, a metal electrical isolator, an operating mechanism, a transmission mechanism, a spring mechanism, a gas pressure system, a shock absorbing system, an arc chamber, a nozzle, and a pressure relief system. Accordingly, the component information may include at least one of the main contact, the fixed contact, the metal electrical isolator, the operating mechanism, the transmission mechanism, the spring mechanism, the gas pressure system, the shock absorbing system, the arc chamber, the nozzle, and the pressure relief system.

[0029] Step S11 may be used to obtain historical maintenance information of the multi-break filter breaker, wherein the historical maintenance information may include an indicator variable including the number of times each component of the multi-break filter breaker is maintained in each maintenance cycle or whether it is maintained.

[0030] Step S12 can be used to construct a maintenance status matrix in time series based on the historical maintenance information and component information. Based on the component information of step S10 and the historical maintenance information obtained in step S11, the maintenance status matrix can be represented by the following formula (1), for example: , (1) in, To maintain the state matrix, , , , is the status value of the corresponding component during the maintenance cycle, is the number of maintenance cycles, is the number of components.

[0031] Step S13 is used to predict the state of the multi-break filter circuit breaker for a preset time period based on the maintenance state matrix. The specific method for predicting the state can be in various forms known to those skilled in the art. In one example of the present invention, the method for predicting the state may include: Figure 3 In the steps shown in Figure 3In the method for predicting the state, the method may include the following steps: In step S20, the number of maintenance cycles included in the preset time period is determined; In step S21, the matrix cells in the maintenance status matrix are intercepted according to the number of maintenance cycles as actual output; In step S22, in the maintenance state matrix, at a position before the intercepted matrix unit, the matrix unit in the maintenance state matrix is ​​intercepted according to a preset time span to serve as a sample unit; In step S23, the sample unit is used as input, the actual output is used as the standard output, and a training set, a test set, and a validation set are constructed, wherein the ratio of the number of samples in the training set, the test set, and the validation set is 7:2:1; In step S24, a preset circuit breaker state prediction model is trained using a training set, a test set, and a validation set to predict the state of a multi-break filter circuit breaker.

[0032] The specific structure of the circuit breaker state prediction model in step S23 can be in various forms known to those skilled in the art. In one example of the present invention, the circuit breaker state prediction model may include an input layer, multiple hidden layers, a main connection layer, multiple secondary connection layers, and a decision layer. Among them, the input layer can be used to convert the input matrix unit to obtain a one-dimensional sequence. Each hidden layer can be used to perform feature processing on the output of the previous layer to obtain the output of the hidden layer of this layer. The main fully connected layer can be used to make predictions based on the output of the hidden layer of the last layer to obtain the main classification result. Multiple secondary fully connected layers can be used to make predictions based on the outputs of the hidden layers of the second to last layer and the third to last layer, respectively, to obtain corresponding secondary classification results. The decision layer can be used to perform weighted calculations on the main classification results and the secondary classification results to obtain the final prediction results. Among them, the first weight of the weighted calculation can be determined using the following formula (2), , (2) in, According to the last The output prediction of the hidden layer of the layer The weight of a primary classification result or a secondary classification result.

[0033] In addition, for the loss function in the process of training the circuit breaker state prediction model, the following formula (3) can be used: , (3) in, is the calculated error, is the sample size, For standard output, is the predicted output.

[0034] Step S14 may be used to evaluate the state of the multi-break filter breaker according to the prediction result. Specifically, in one example of the present invention, the result of the evaluation may be calculated using an AHP algorithm.

[0035] Through the above technical solution, the embodiment of the present invention provides a method and system for evaluating the state of a multi-port filter breaker. The method and system perform matrix processing on the component information and historical maintenance information of the multi-port filter breaker, and then perform prediction in combination with the prediction model of the multi-port filter breaker, and finally calculate the predicted results to obtain the evaluation results of the future state. Compared with the prior art, the method provided by the present invention combines the network model prediction and evaluation calculation, that is, it utilizes the advantages of the output accuracy of the network model itself, and also avoids the problem of low accuracy caused by excessive fuzzy calculation in the classification processing of the network model.

[0036] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0037] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0038] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0039] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0040] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0041] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0042] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0043] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0044] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for evaluating the status of a multi-break filter circuit breaker, characterized in that: The method comprises: Get component information of multi-break filter circuit breaker; Acquire historical maintenance information of the multi-break filter circuit breaker; Constructing a maintenance status matrix in time series according to the historical maintenance information and the component information; Predicting the state of the multi-break filter circuit breaker for a preset time period based on the maintenance state matrix; The state of the multi-break filter circuit breaker is evaluated according to the prediction result.

2. The method according to claim 1, characterized in that: The component information includes at least one of a main contact, a fixed contact, a metal electrical isolator, an operating mechanism, a transmission mechanism, a spring mechanism, a gas pressure system, a shock absorbing system, an arc chamber, a nozzle, and a pressure relief system.

3. The method according to claim 1, characterized in that Constructing a maintenance status matrix in time series according to the historical maintenance information and the component information, including: The maintenance status matrix is ​​established according to formula (1): ，（1） in, is the maintenance state matrix, , , , is the status value of the corresponding component during the maintenance cycle, is the number of maintenance cycles, is the number of components.

4. The method according to claim 1, characterized in that: Predicting the state of the multi-break filter circuit breaker for a preset time period based on the maintenance state matrix includes: determining the number of maintenance cycles included in the preset time period; intercepting the matrix cells in the maintenance status matrix according to the number of the maintenance cycles as actual output; In the maintenance state matrix, at a position before the intercepted matrix unit, the matrix unit in the maintenance state matrix is ​​intercepted according to a preset time span to serve as a sample unit; Taking the sample unit as input and the actual output as standard output, a training set, a test set and a validation set are constructed, wherein the ratio of the number of samples in the training set, the test set and the validation set is 7:2:1; The training set, the test set and the validation set are used to train a preset circuit breaker state prediction model to predict the state of the multi-break filter circuit breaker.

5. The method according to claim 4, characterized in that The circuit breaker state prediction model includes: An input layer, used for converting the input matrix unit to obtain a one-dimensional sequence; Multiple hidden layers, each hidden layer is used to perform feature processing on the output of the previous layer to obtain the output of the current hidden layer; A main fully connected layer, used to make predictions based on the output of the hidden layer of the last layer to obtain a main classification result; A plurality of secondary fully connected layers, respectively used to make predictions based on the outputs of the hidden layers of the penultimate layer and the third-to-last layer, so as to obtain corresponding secondary classification results; The decision layer is used to perform weighted calculation on the primary classification results and the secondary classification results to obtain the final prediction result.

6. The method according to claim 5, characterized in that The decision layer is used to: The first weight of the weighted calculation is calculated according to the following formula (2): ，（2） in, According to the last The output prediction of the hidden layer of the layer The weight of the primary classification result or the secondary classification result.

7. The method according to claim 5, characterized in that The method further comprises: The following formula (3) is used as the loss function of the circuit breaker state prediction model: ，（3） in, is the calculated error, is the sample size, For standard output, is the predicted output.

8. The method according to claim 1, characterized in that: The state of the multi-break filter circuit breaker is evaluated according to the prediction result, including: The AHP algorithm is used to calculate the evaluation results.

9. A system for evaluating the status of a multi-break filter circuit breaker, characterized in that: The evaluation system comprises a processor, and the processor is configured to execute the method according to any one of claims 1 to 8.

Images