Power system fault detection method, device and equipment based on SA-BP neural network
Through the fault detection method based on SA-BP neural network, the problem of low fault detection efficiency of power system is solved, and efficient and accurate fault detection effect is achieved.
Patent Information
- Application Number
- CN202411360879.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-27
- Publication Date
- 2025-01-07
AI Technical Summary
In the prior art, the power system fault detection efficiency is low, and it is difficult to detect power system faults efficiently and accurately.
The fault detection method based on SA-BP neural network is adopted, and the fault line detection model of the BP neural network is input to determine the fault line by obtaining power system data. Then, the fault position detection model of the SA-BP neural network is used to determine the fault position.
It realizes efficient and accurate detection of power system failures, improving the accuracy and efficiency of fault detection.
Smart Images
Figure CN119269953A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of power system fault detection, and in particular to a power system fault detection method, device and equipment based on SA-BP neural network. Background Art
[0002] The power system has a complex system structure, a changeable external environment and potential failure risks. Failures may lead to abnormal grid operation, power outages and safety hazards.
[0003] At present, the traditional fault diagnosis method used is to manually and gradually cut off part of the line to determine the fault range and fault point, but the fault detection efficiency of the traditional fault diagnosis method is low.
[0004] Therefore, how to detect power system faults efficiently and accurately has become a technical problem that needs to be solved urgently. Summary of the invention
[0005] The embodiments of this specification provide a power system fault detection method based on SA-BP neural network to solve the problem of low efficiency of power system fault detection in the prior art.
[0006] To solve the above technical problems, the embodiments of this specification are implemented as follows:
[0007] In a first aspect, an embodiment of this specification provides a power system fault detection method based on a SA-BP neural network, comprising:
[0008] Acquiring power system data saved when a power failure occurs; the power system data is saved by the IEEE-39 system;
[0009] Inputting the power system data into a fault line detection model based on a BP neural network to obtain fault line data where the power fault is located;
[0010] Determine a fault location detection model based on a SA-BP neural network corresponding to the fault line data; the training samples of the fault location detection model based on the SA-BP neural network are a plurality of power fault data consisting of fault line data and fault location data;
[0011] The power system data is input into the fault location detection model to obtain fault location data of the power fault.
[0012] In a second aspect, an embodiment of the present specification provides a power system fault detection device based on a SA-BP neural network, comprising:
[0013] An acquisition module, used to acquire power system data saved when a power failure occurs; the power system data is saved by the IEEE-39 system;
[0014] A fault line determination module is used to input the power system data into a fault line detection model based on a BP neural network to obtain fault line data where the power fault is located;
[0015] A fault location detection model determination module, used to determine a fault location detection model based on a SA-BP neural network corresponding to the fault line data; the training samples of the fault location detection model based on the SA-BP neural network are a number of power fault data consisting of fault line data and fault location data;
[0016] The fault location determination module is used to input the power system data into the fault location detection model to obtain fault location data of the power fault.
[0017] In the third aspect, an embodiment of the present specification provides an SA-BP neural network-based power system fault detection device, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the SA-BP neural network-based power system fault detection method in scheme one.
[0018] An embodiment of the present specification can achieve the following beneficial effects: by inputting the power system data saved when a power fault occurs into a fault line detection model based on a BP neural network to obtain fault line data, selecting a fault location detection model based on a SA-BP neural network corresponding to the fault line data to obtain fault location data, thereby efficiently and accurately detecting power system faults. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0020] Figure 1 A schematic diagram of a flow chart of a power system fault detection method based on a SA-BP neural network provided in an embodiment of this specification;
[0021] Figure 2 A schematic diagram of the algorithm flow of the SA-BP neural network provided in the embodiments of this specification;
[0022] Figure 3A schematic diagram of the algorithm structure of the SA-BP neural network provided in the embodiments of this specification;
[0023] Figure 4 A schematic diagram of the error of the detection result of the power system fault detection based on the SA-BP neural network provided in the embodiment of this specification;
[0024] Figure 5 A schematic diagram of the structure of a power system fault detection device based on a SA-BP neural network provided in an embodiment of this specification;
[0025] Figure 6 A schematic diagram of the structure of a power system fault detection device based on a SA-BP neural network provided in an embodiment of this specification. DETAILED DESCRIPTION
[0026] In order to make the purpose, technical solutions and advantages of one or more embodiments of this specification clearer, the technical solutions of one or more embodiments of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of one or more embodiments of this specification.
[0027] In order to solve the defects in the prior art, this solution provides the following embodiments:
[0028] A power system fault detection method based on a SA-BP neural network provided in an embodiment of the specification is specifically described in conjunction with the accompanying drawings.
[0029] Figure 1 A schematic diagram of a flow chart of a power system fault detection method based on a SA-BP neural network provided in an embodiment of this specification.
[0030] like Figure 1 As shown, the process may include the following steps:
[0031] Step S110: Acquire power system data saved when a power failure occurs; the power system data is saved by the IEEE-39 system.
[0032] In the embodiments of this specification, system data during power failure can be obtained from the IEEE-39 system or other power simulation systems. These data usually include voltage, current, power, phase angle, etc. These parameters will change significantly when a fault occurs.
[0033] Step S120: inputting the power system data into a fault line detection model based on a BP neural network to obtain fault line data where the power fault is located.
[0034] In the embodiments of this specification, the structure of the BP neural network includes an input layer, a hidden layer and an output layer. The input layer receives external input signals, the hidden layer introduces nonlinear characteristics through activation functions, and the output layer generates the final output result.
[0035] The training process of BP neural network includes two stages: forward propagation and back propagation. In the forward propagation stage, the input signal is calculated by each layer and the output value is finally obtained. Then, by calculating the error between the output value and the target value, the back propagation algorithm is used to adjust the weights and biases of each layer to minimize the error function. Through continuous iterative training, BP neural network can learn and approximate complex nonlinear functions.
[0036] The power system data is input into the fault line detection model based on the BP neural network, and the fault line data can be output. The fault line data can be the code of the fault line, such as line 1, line 2, and so on.
[0037] Step S130: determining a fault location detection model based on the SA-BP neural network corresponding to the fault line data; the training samples of the fault location detection model based on the SA-BP neural network are a number of power fault data consisting of fault line data and fault location data.
[0038] In the embodiments of this specification, each fault line corresponds to a fault location detection model, a one-to-one mapping relationship between the fault line and the fault location detection model is established, and a specific SA-BP neural network model is established or specified for each fault line. Each model focuses on learning the fault location data under the fault line.
[0039] When the faulty line where the power fault is located is determined, a corresponding fault location detection model can be obtained according to the mapping relationship.
[0040] In practical applications, the power fault data consisting of fault line data and fault location data are used as training samples to train the fault location detection model based on the SA-BP neural network, which can efficiently and accurately detect power system faults.
[0041] Step S140: inputting the power system data into the fault location detection model to obtain fault location data of the power fault.
[0042] In the embodiments of this specification, the fault location data may be a fault location code or a fault distance, for example, the fault location is a location 1% of the distance from the node to line 1.
[0043] It should be understood that the order of some steps in the methods described in one or more embodiments of this specification can be interchanged according to actual needs, or some steps can be omitted or deleted.
[0044] In the present application, the power system data saved when a power failure occurs is input into a fault line detection model based on a BP neural network to obtain fault line data, and a fault location detection model based on a SA-BP neural network corresponding to the fault line data is selected to obtain fault location data, thereby efficiently and accurately detecting power system faults.
[0045] based on Figure 1 The method in this specification also provides some specific implementation plans of the method, which are described below.
[0046] In order to ensure the accuracy of the fault line detection result, optionally, before the power system data is input into the fault line detection model based on the BP neural network in the embodiment of this specification, the method may include:
[0047] Acquiring the fault line data;
[0048] Performing a first preprocessing on the power fault data to obtain first target power fault data;
[0049] The first target power fault data is input into the fault line detection model based on BP neural network for training.
[0050] In the embodiments of this specification, in order to facilitate the fault line detection model based on the BP neural network to better process data, the fault line data can be preprocessed. The preprocessing may include taking the average value, data classification, data labeling, data cleaning, etc., and the fault line detection model is iteratively trained to optimize the fault line detection model and improve the accuracy of the detection result.
[0051] Optionally, the power fault data in the embodiment of this specification includes a plurality of node data consisting of positive sequence voltage data and positive sequence angle data, and the first preprocessing of the power fault data to obtain the first target power fault data may specifically include:
[0052] The positive-sequence voltage data and the positive-sequence angle data of each of the node data are respectively averaged, and the processed node data are used as the first target fault line data.
[0053] In the embodiment of this specification, the power fault data is composed of several node data. The power fault data is shown in Table 1. Each power fault data has 39 node data in total, and each node data is a time series composed of 301 time points. The node data is shown in Table 2. The node data may include positive-sequence voltage data and positive-sequence angle data.
[0054] Table 1 Power failure data
[0055]
[0056] Table 2 Node data
[0057]
[0058]
[0059] In practical applications, the average value is taken for 301 time points, and each node data only contains a set of positive sequence voltage and positive sequence angle data. The node data after taking the average value is shown in Table 3.
[0060] Table 3 Node data after taking the average value
[0061]
[0062] After processing, the number of single power fault data is changed from the original 11739×3 to 39×2, saving detection time and reducing the difficulty of fault line detection.
[0063] In practical applications, actual data can be used to verify the data output by the model. The first target power fault data can be obtained by taking the average value of the power fault data. The first target power fault data can be input into the fault line detection model based on the BP neural network for training. The difference between the actual fault line data and the detected fault line data can be calculated. When the difference is less than 0.0001 or the number of training times reaches 25, the training is terminated to obtain the optimal fault line detection model.
[0064] Optionally, before inputting the power system data into the fault location detection model in the embodiments of this specification, the method includes:
[0065] Acquiring the power fault data;
[0066] performing a second preprocessing on the power fault data to obtain second target power fault data;
[0067] The second target power fault data is input into the fault location detection model based on the SA-BP neural network for training.
[0068] In the embodiments of the present specification, in order to facilitate the input of power fault data into the corresponding fault location detection model for training, a classifier can be used to classify the power fault data and mark the data. For example, the power fault data of line 1 includes fault line data No. 1 and fault location data No. 1. The fault line data No. 1 and fault location data No. 1 are input into the fault location detection model No. 1 for iterative training, thereby optimizing the fault location detection model and improving the accuracy of the detection results.
[0069] In practical applications, in order to detect the fault location more accurately, the single power fault data of 11739×3 can be input into the fault location detection model for iterative training.
[0070] In practical applications, actual data can be used to verify the data output by the model. The power fault data can be pre-processed by classification and marking to obtain the second target power fault data. The second target power fault data is input into the fault location detection model based on the SA-BP neural network for training. The difference between the actual fault location data and the detected fault location data is calculated. When the accuracy of the SA-BP neural network is greater than the second threshold or the maximum number of training times is reached, the training is terminated to obtain the optimal fault location detection model.
[0071] Figure 2 This is a schematic diagram of the algorithm flow of the SA-BP neural network provided in the embodiments of this specification.
[0072] like Figure 2 As shown in the figure, the simulated annealing algorithm (SA) is combined with the BP neural network, and the global search capability of the simulated annealing algorithm is used to overcome the defect that the BP neural network is prone to fall into the local optimum. The specific steps are as follows:
[0073] Step 201: Initialize the BP neural network and determine the number of input layers, hidden layers and output layers of the neural network according to the samples.
[0074] Step 202: input a training sample, which is a number of power fault data, and output is detected fault location data.
[0075] Step 203: Calculate the difference between the actual fault location data and the detected fault location data to obtain a first error, loss=labels-predicted, where loss is the error, labels is the actual fault location data, and predicted is the detected fault location data.
[0076] Step 204: Determine whether the first error is less than the first threshold value, if so, execute step 204, if not, return to step 201, wherein the first threshold value may be 0.0001. At the same time, it may also be determined whether the number of training times meets the first number of training times, the first number of training times may be 25, if so, execute step 204, if not, return to step 201, for example, when the first error is less than the first threshold value, the first number of training times is less than the first number of training times, return to step 201, when the first error is less than the first threshold value, the first number of training times is greater than or equal to the first number of training times, execute step 204.
[0077] Step 205: Use the SA algorithm to optimize the learning rate, optimize the BP neural network, adjust the weight according to the optimization result, reduce the error value of the fault location, and thus improve the accuracy of the detection result.
[0078] The weight can be adjusted by the following formula, according to lr final =lr0e -α·total_epochs , to obtain Among them, lr0 is the initial learning rate, lr final is the final learning rate, and total_epochs is the total number of training times set.
[0079] Among them, n cur Indicates the current number of training times, lr cur is the current training learning rate.
[0080] Among them, w n+1 is the updated weight, w n is the weight before updating, and w is the weight.
[0081] Step 206: Determine whether the end condition is met, where the end condition may refer to whether the error of the SA-BP neural network, i.e., the second error, is less than the second threshold, or whether the number of trainings meets the second number of trainings, where the second threshold may be 0.0001, and the second number of trainings may be 1000. When any end condition is met, the training ends, and a fault location detection model based on the SA-BP neural network is obtained.
[0082] Figure 3 This is a schematic diagram of the algorithm structure of the SA-BP neural network provided in the embodiments of this specification.
[0083] like Figure 3 As shown, the output is calculated through forward propagation, and then the weights are updated through backpropagation.
[0084] After inputting the training sample into the input layer, the positive sequence voltage and positive sequence angle corresponding to 39 nodes in a power fault data are extracted, and then the data is transformed through the hidden layer. In the hidden layer, three hidden layers are used for processing. 256 neurons are set in the first hidden layer. This layer is transformed through w 11 w 12 …w 391 …w 3939 Connected with the input layer, the second layer is set with 128 neurons, and the third layer is set with 64 neurons. In the output layer, the 64 intermediate features extracted from the third hidden layer are linearly added and then output as a value, i.e. the detected fault line. The detected fault line is subtracted from the actual fault line to obtain the error for back propagation.
[0085] When back-propagating to update the weights, the learning rate is calculated and the SA algorithm is used to update the learning rate so that the weight parameters change with a larger amplitude in the early stage and a smaller range in the later stage, thereby reducing the error to below the second threshold in a fast manner.
[0086] Figure 4 A schematic diagram of the error of the detection results of power system fault detection based on the SA-BP neural network provided in the embodiments of this specification.
[0087] Taking 50 training times as an example, Figure 4 It can be seen that the loss function value can reach a smaller value after 15 trainings.
[0088] Figure 5 This is a schematic diagram of the structure of a power system fault detection device based on a SA-BP neural network proposed in an embodiment of this specification.
[0089] The power system fault detection device based on the SA-BP neural network described in the embodiments of this specification may include:
[0090] An acquisition module 502 is used to acquire power system data saved when a power failure occurs; the power system data is saved by the IEEE-39 system;
[0091] A fault line determination module 504 is used to input the power system data into a fault line detection model based on a BP neural network to obtain fault line data where the power fault is located;
[0092] A fault location detection model determination module 506 is used to determine a fault location detection model based on a SA-BP neural network corresponding to the fault line data; the training samples of the fault location detection model based on the SA-BP neural network are a number of power fault data consisting of fault line data and fault location data;
[0093] The fault location determination module 508 is used to input the power system data into the fault location detection model to obtain fault location data of the power fault.
[0094] Optionally, before inputting the power system data into the fault line detection model based on the BP neural network in the embodiments of this specification, the following steps may be included:
[0095] A fault line detection model training module, used to obtain the power fault data;
[0096] Performing a first preprocessing on the power fault data to obtain first target power fault data;
[0097] The first target power fault data is input into the fault line detection model based on BP neural network for training.
[0098] Optionally, the power fault data in the embodiment of this specification includes a plurality of node data consisting of positive sequence voltage data and positive sequence angle data, and the first preprocessing of the power fault data to obtain the first target power fault data may specifically include:
[0099] The positive-sequence voltage data and the positive-sequence angle data of each of the node data are respectively averaged, and the processed node data are used as the first target power fault data.
[0100] Optionally, before the power system data is input into the fault location detection model in the embodiments of this specification, the following steps may be included:
[0101] A fault location detection model training module, used to obtain the power fault data;
[0102] performing a second preprocessing on the power fault data to obtain second target power fault data;
[0103] The second target power fault data is input into the fault location detection model based on the SA-BP neural network for training.
[0104] Based on the same idea, the embodiments of this specification also provide a device corresponding to the above method.
[0105] Figure 6 A schematic diagram of the structure of a power system fault detection device based on a SA-BP neural network provided in an embodiment of this specification.
[0106] like Figure 6As shown, an SA-BP neural network-based power system fault detection device provided in an embodiment of the present specification includes a memory 630, a processor 610, and a computer program 620 stored in the memory, and the processor 610 executes the computer program 620 to implement the SA-BP neural network-based power system fault detection method described in any of the above embodiments.
[0107] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. Figure 6 As for the device shown, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0108] In the 1990s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.
[0109] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.
[0110] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
[0111] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.
[0112] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take 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 code.
[0113] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks 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 produce 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.
[0114] 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 comprising 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.
[0115] 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. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0116] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0117] The memory may include non-permanent storage 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.
[0118] 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.
[0119] 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.
[0120] 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 in combination with 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.) that contain computer-usable program code.
[0121] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.
[0122] The above is only an embodiment of the present application and is 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 in the scope of the claims of the present application.
Claims
1. A power system fault detection method based on SA-BP neural network, characterized in that: include: Access to power system data saved when a power failure occurs; The power system data is stored in the IEEE-39 system; Inputting the power system data into a fault line detection model based on a BP neural network to obtain fault line data where the power fault is located; Determine a fault location detection model based on a SA-BP neural network corresponding to the fault line data; the training samples of the fault location detection model based on the SA-BP neural network are a plurality of power fault data consisting of fault line data and fault location data; The power system data is input into the fault location detection model to obtain fault location data of the power fault.
2. The method according to claim 1, characterized in that: Before inputting the power system data into a fault line detection model based on a BP neural network, the method comprises: Acquiring the power fault data; Performing a first preprocessing on the power fault data to obtain first target power fault data; The first target power fault data is input into the fault line detection model based on BP neural network for training.
3. The method according to claim 2, characterized in that The power fault data includes a plurality of node data consisting of positive sequence voltage data and positive sequence angle data. The first preprocessing is performed on the power fault data to obtain the first target power fault data, specifically including: The positive-sequence voltage data and the positive-sequence angle data of each of the node data are respectively averaged, and the processed node data are used as the first target power fault data.
4. The method according to claim 1, characterized in that: Before inputting the power system data into the fault location detection model, the method comprises: Acquiring the power fault data; performing a second preprocessing on the power fault data to obtain second target power fault data; The second target power fault data is input into the fault location detection model based on the SA-BP neural network for training.
5. A power system fault detection device based on SA-BP neural network, characterized in that: include: An acquisition module, used to acquire power system data saved when a power failure occurs; The power system data is stored in the IEEE-39 system; A fault line determination module is used to input the power system data into a fault line detection model based on a BP neural network to obtain fault line data where the power fault is located; A fault location detection model determination module, used to determine a fault location detection model based on a SA-BP neural network corresponding to the fault line data; the training samples of the fault location detection model based on the SA-BP neural network are a number of power fault data consisting of fault line data and fault location data; The fault location determination module is used to input the power system data into the fault location detection model to obtain fault location data of the power fault.
6. The device according to claim 5, characterized in that Before inputting the power system data into the fault line detection model based on the BP neural network, the method includes: A fault line detection model training module, used to obtain the power fault data; Performing a first preprocessing on the power fault data to obtain first target power fault data; The first target power fault data is input into the fault line detection model based on BP neural network for training.
7. The device according to claim 6, characterized in that The power fault data includes a plurality of node data consisting of positive sequence voltage data and positive sequence angle data. The first preprocessing is performed on the power fault data to obtain the first target power fault data, specifically including: The positive-sequence voltage data and the positive-sequence angle data of each of the node data are respectively averaged, and the processed node data are used as the first target power fault data.
8. The device according to claim 5, characterized in that Before inputting the power system data into the fault location detection model, the method includes: A fault location detection model training module, used to obtain the power fault data; performing a second preprocessing on the power fault data to obtain second target power fault data; The second target power fault data is input into the fault location detection model based on the SA-BP neural network for training.
9. A power system fault detection device based on SA-BP neural network, comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 4.