A method and system for detecting power grid fault data

Abstract

The present invention proposes a method and system for detecting power grid fault data, which relates to the field of power grid detection, including: obtaining past detection data of the power grid; performing variable selection on the data through mutual information technology to obtain optimized variables; utilizing the optimized variables to iteratively update through a contrast divergence algorithm to obtain a weight matrix and a deviation matrix; establishing a power grid fault probability detection model; collecting data to be detected in the power grid in real time, and inputting the data into the power grid fault probability detection model to obtain a probability distribution matrix of the data to be detected; extracting eigenvalues ​​of the probability distribution matrix, and performing eigenvalue decomposition on the eigenvalues ​​to obtain principal component information; performing fault data analysis based on the principal component information to obtain a detection result of the power grid fault; the present invention reduces costs, significantly improves the detection efficiency and detection accuracy of power grid fault data, and can find a direct connection between fault characteristics and fault causes through a database, thereby improving computing efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid detection, and in particular to a method and system for detecting power grid fault data. Background Art

[0002] The power grid is a dynamic system with complex structure and operation mode, and the causes of faults are even more diverse. Sometimes the fault signal has no direct relationship with the cause of the fault, which makes it difficult to find the fault location during power grid fault detection.

[0003] While artificial intelligence methods can currently address some of the challenges of power grid fault detection, they also suffer from various shortcomings. Artificial neural networks require training samples, and power grid faults are typically small. This makes it difficult to collect diverse fault information and establish a comprehensive fault model. Furthermore, artificial neural networks cannot directly link fault characteristics with their causes. Furthermore, their computational efficiency is poor, and they sometimes fail to converge. Furthermore, they suffer from poor robustness. When power grid faults are complex, they are prone to combinatorial explosion, resulting in slow inference speeds and the inability to conduct online analysis or diagnose large power systems.

[0004] Based on this, the present application proposes a method and system for detecting power grid fault data to solve the above problems. Summary of the Invention

[0005] The object of the present invention is to provide a method and system for detecting power grid fault data, which can solve the problems of low power grid fault detection efficiency, high cost and insufficient detection accuracy in the prior art.

[0006] The technical solution of the present invention is:

[0007] In a first aspect, the present application provides a method for detecting power grid fault data, comprising the following steps:

[0008] S1. Obtain past detection data of the power grid and perform data preprocessing;

[0009] S2, using mutual information technology to select variables from the pre-processed data to obtain the optimal variables;

[0010] S3, using the optimized variables to iteratively update the weight matrix and the bias matrix through the contrast divergence algorithm;

[0011] S4. Establishing a power grid fault probability detection model based on the weight matrix and the deviation matrix;

[0012] S5. Collect the data to be detected in the power grid in real time, and input the data to be detected into the power grid fault probability detection model to obtain a probability distribution matrix of the data to be detected;

[0013] S6. extracting eigenvalues ​​of the probability distribution matrix and performing eigenvalue decomposition on the eigenvalues ​​to obtain principal component information;

[0014] S7. Perform fault data analysis based on the principal component information to obtain a detection result of the power grid fault.

[0015] Furthermore, in step S1, the above data processing method includes data normalization processing.

[0016] Furthermore, the above-mentioned power grid fault probability detection model includes a visual layer, a hidden layer and a classification layer. The above-mentioned visual layer is used to receive the data to be detected and send it to the hidden layer after encoding. The above-mentioned hidden layer is used to extract high-dimensional features of the data. The above-mentioned classification layer is used to connect the above-mentioned hidden layer to classify the data in the above-mentioned hidden layer.

[0017] Furthermore, in step S3, the calculation process of the contrast divergence algorithm is as follows:

[0018] h=Φ[WAj+a],

[0019] Bj=Φ[Wh+b],

[0020] h'=Φ[WBj+a],

[0021] Among them, W represents the weight of the connection between the original data layer and the feature extraction layer, A and B represent the original data layers, a represents the bias of the original data layer, b represents the bias of the feature extraction layer, h represents the true value of the eigenvalue matrix of the influencing factors of the feature extraction layer, h' represents the reconstructed value of the eigenvalue matrix of the influencing factors of the feature extraction layer, j represents the influencing factor, and Φ represents the sigmoid function.

[0022] Furthermore, step S7 also includes: establishing a fault information database based on past power grid fault records, and performing correlation analysis between the principal component information of the current data to be detected and the fault information database to obtain a detection result of the power grid fault.

[0023] Furthermore, the above correlation analysis includes calculating the correlation between the attributes of the data in the above fault information database using the Pearson correlation coefficient, determining the attributes whose correlation reaches or exceeds the middle value of the correlation range as feature fields, and retaining the attributes with the highest correlation.

[0024] Furthermore, the above attributes include fault duration and fault defect amount; the above correlation degree ranges from (0.1, 0.9) and the median value is 0.5.

[0025] In a second aspect, the present application provides a system for detecting power grid fault data, comprising:

[0026] Data acquisition and processing module, used to obtain past detection data of the power grid and perform data processing;

[0027] Data optimization module, used to select variables from pre-processed data using mutual information technology to obtain optimized variables;

[0028] An iterative updating module, configured to utilize the optimized variables to iteratively update the weight matrix and the bias matrix through a contrast divergence algorithm;

[0029] A model building module is used to build a power grid fault probability detection model based on the weight matrix and the deviation matrix;

[0030] An input module is used to collect the data to be detected in the power grid in real time and input the data to be detected into the power grid fault probability detection model to obtain a probability distribution matrix of the data to be detected;

[0031] Feature extraction module, used to extract the eigenvalues ​​of the probability distribution matrix and perform eigenvalue decomposition on the eigenvalues ​​to obtain principal component information;

[0032] The data analysis module is used to perform fault data analysis based on the principal component information to obtain the detection results of the power grid fault.

[0033] In a third aspect, the present application provides an electronic device, characterized by comprising:

[0034] a memory for storing one or more programs;

[0035] processor;

[0036] When the one or more programs are executed by the processor, a method for detecting power grid fault data as described in any one of the first aspects is implemented.

[0037] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for detecting power grid fault data as described in any one of the first aspects above.

[0038] Compared with the prior art, the present invention has at least the following advantages or beneficial effects:

[0039] (1) The present invention significantly improves the efficiency of power grid fault data detection and reduces costs by establishing a power grid fault probability detection model;

[0040] (2) The present invention collects the data to be detected in the power grid in real time and inputs it into the power grid fault probability detection model to obtain the probability distribution matrix of the data to be detected. Then, the eigenvalues ​​of the probability distribution matrix are extracted and the eigenvalues ​​are subjected to eigenvalue decomposition to obtain principal component information. Finally, the fault data is analyzed based on the principal component information to obtain the detection result of the power grid fault, thereby significantly improving the detection accuracy of the power grid fault and realizing real-time monitoring of the power grid fault.

[0041] (3) The present invention establishes a fault information database based on past power grid fault records, and performs correlation analysis between the principal component information of the current data to be detected and the fault information database to obtain the detection results of the power grid fault. Therefore, the direct connection between the fault characteristics and the fault causes can be found in real time through the fault information database, which significantly improves the calculation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 A diagram showing the steps of a method for detecting power grid fault data according to the present invention;

[0044] Figure 2 It is a structural diagram of the fault probability detection model;

[0045] Figure 3 The figure is a schematic structural block diagram of an electronic device according to an embodiment of the present invention.

[0046] Icon: 101, memory; 102, processor; 103, communication interface. DETAILED DESCRIPTION

[0047] To make the objectives, technical solutions, and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Generally, the components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations.

[0048] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for protection, but merely represents selected embodiments of the present application. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments in the present application without creative work are within the scope of protection of the present application.

[0049] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0050] It should be noted that, in this document, the term "comprises" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article, or apparatus that includes a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article, or apparatus. In the absence of further limitations, the elements defined by the phrase "comprises..." do not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the elements.

[0051] It should also be noted that, in the description of this application, unless otherwise expressly specified or limited, the terms "disposed" and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; mechanical connections, or electrical connections; direct connections, indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0052] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features thereof may be combined with each other.

[0053] Example 1

[0054] See also Figure 1 , Figure 1 The figure shows a step diagram of a method for detecting power grid fault data provided by an embodiment of the present application.

[0055] In a first aspect, the present application provides a method for detecting power grid fault data, comprising the following steps:

[0056] S1. Obtain past detection data of the power grid and perform data preprocessing;

[0057] S2, using mutual information technology to select variables from the pre-processed data to obtain the optimal variables;

[0058] S3, using the optimized variables to iteratively update the weight matrix and the bias matrix through the contrast divergence algorithm;

[0059] S4. Establishing a power grid fault probability detection model based on the weight matrix and the deviation matrix;

[0060] S5. Collect the data to be detected in the power grid in real time, and input the data to be detected into the power grid fault probability detection model to obtain a probability distribution matrix of the data to be detected;

[0061] S6. extracting eigenvalues ​​of the probability distribution matrix and performing eigenvalue decomposition on the eigenvalues ​​to obtain principal component information;

[0062] S7. Analyze the fault data based on the principal component information to obtain the detection result of the power grid fault. The calculation formula of the eigenvalue decomposition is:

[0063] A=Qsum Q^{-1},

[0064] Among them, Q represents the matrix composed of the eigenvectors of matrix A, sum represents the diagonal matrix, each diagonal element is an eigenvalue, and the eigenvalues ​​are arranged from large to small. The eigenvectors corresponding to these eigenvalues ​​describe the change direction of this matrix (arranged from major changes to minor changes).

[0065] As a preferred implementation, in step S1, the data processing method includes data normalization processing.

[0066] As a preferred embodiment, the power grid fault probability detection model includes a visual layer, a hidden layer and a classification layer. The visual layer is used to receive the data to be detected and send it to the hidden layer after encoding. The hidden layer is used to extract high-dimensional features of the data. The classification layer is used to connect the hidden layer to classify the data in the hidden layer.

[0067] See also Figure 2 , Figure 2 Shown is a structural diagram of the fault probability detection model.

[0068] Input real-time data to be detected, the visual layer v receives the input data and encodes it before passing it to the hidden layer h1. The output layer of RBM-1 serves as the input layer of RBM-2, and so on. The training is conducted in a greedy layer-by-layer manner, and the network parameters are adjusted through back propagation to adapt it to the target task. When the fault probability detection model is used as an unsupervised learning method to extract high-dimensional features of the data, the last hidden layer h2 is the high-dimensional feature representation of the data. When the fault probability detection model is used as a classifier for supervised learning, the last hidden layer is connected to the classifier to obtain the probability distribution matrix of the data to be detected, thereby realizing the classification of the fault data, and then performing fault data analysis to obtain the detection results of the power grid fault.

[0069] As a preferred embodiment, in step S3, the calculation process of the contrast divergence algorithm is:

[0070] h=Φ[WAj+a],

[0071] Bj=Φ[Wh+b],

[0072] h'=Φ[WBj+a],

[0073] Among them, W represents the weight of the connection between the original data layer and the feature extraction layer, A and B represent the original data layers, a represents the bias of the original data layer, b represents the bias of the feature extraction layer, h represents the true value of the eigenvalue matrix of the influencing factors of the feature extraction layer, h' represents the reconstructed value of the eigenvalue matrix of the influencing factors of the feature extraction layer, j represents the influencing factor, and Φ represents the sigmoid function.

[0074] As a preferred implementation, step S7 further includes: establishing a fault information database based on past power grid fault records, and performing correlation analysis between the principal component information of the current data to be detected and the fault information database to obtain a power grid fault detection result.

[0075] As a preferred embodiment, the correlation analysis includes using the Pearson correlation coefficient to calculate the correlation between the attributes of the data in the fault information database, determining the attributes whose correlation reaches or exceeds the middle value of the correlation range as feature fields, and retaining the attributes with the highest correlation.

[0076] As a preferred implementation, the attributes include fault duration and fault defect amount; the correlation range is (0.1, 0.9), with a median value of 0.5.

[0077] Example 2

[0078] See also Figure 3 , Figure 3 A schematic structural block diagram of an electronic device provided in an embodiment of the present application.

[0079] An electronic device includes a memory 101, a processor 102, and a communication interface 103. The memory 101, processor 102, and communication interface 103 are electrically connected to each other directly or indirectly to enable data transmission or interaction. For example, these components can be electrically connected to each other via one or more communication buses or signal lines. The memory 101 can be used to store software programs and modules, and the processor 102 executes the software programs and modules stored in the memory 101 to perform various functional applications and data processing. The communication interface 103 can be used to communicate signaling or data with other node devices.

[0080] Among them, the memory 101 can be, but is not limited to, random access memory (RAM), read only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0081] The processor 102 may be an integrated circuit chip with signal processing capabilities. The processor 102 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0082] It is understood that the structure shown in the figure is merely illustrative, and a method and system for detecting power grid fault data may include more or fewer components than shown in the figure, or have a different configuration than shown in the figure. Each component shown in the figure may be implemented using hardware, software, or a combination thereof.

[0083] In the embodiments provided in this application, it should be understood that the disclosed method or system can also be implemented in other ways. The embodiments described above are merely illustrative. For example, the flowcharts or block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0084] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0085] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0086] In summary, the present application provides a method and system for detecting power grid fault data, which obtains past power grid detection data; selects variables from the data using mutual information technology to obtain optimized variables; utilizes the optimized variables to iteratively update the weight matrix and bias matrix using the contrast divergence algorithm; establishes a power grid fault probability detection model; collects the data to be detected in the power grid in real time and inputs it into the power grid fault probability detection model to obtain a probability distribution matrix of the data to be detected; extracts the eigenvalues ​​of the probability distribution matrix and performs eigenvalue decomposition on the eigenvalues ​​to obtain principal component information; and analyzes the fault data based on the principal component information to obtain the detection results of the power grid fault. The present invention significantly improves the efficiency of power grid fault data detection, reduces costs, improves the detection accuracy of power grid faults, and realizes real-time monitoring of power grid faults.

[0087] The foregoing description is merely a preferred embodiment of the present application and is not intended to limit the present application. Persons skilled in the art will readily appreciate that various modifications and variations are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

[0088] It will be apparent to those skilled in the art that the present application is not limited to the details of the exemplary embodiments described above and that the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the present application is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A method for detecting power grid fault data, characterized in that: The following steps are involved: S1. Obtain past detection data of the power grid and perform data preprocessing; S2, using mutual information technology to select variables from the pre-processed data to obtain the optimal variables; S3. Using the optimized variables to iteratively update the contrast divergence algorithm to obtain the weight matrix and the bias matrix; the calculation process of the contrast divergence algorithm is: h = Φ [WAj + a], Bj=Φ[Wh+b], h'=Φ[WBj+a], where W represents the weight of the connection between the original data layer and the feature extraction layer, A and B represent the original data layers, a represents the bias of the original data layer, b represents the bias of the feature extraction layer, h represents the true value of the eigenvalue matrix of the influencing factors of the feature extraction layer, h' represents the reconstructed value of the eigenvalue matrix of the influencing factors of the feature extraction layer, j represents the influencing factor, and Φ represents the sigmoid function; S4. Establishing a power grid fault probability detection model based on the weight matrix and the deviation matrix; S5. Collect the data to be detected in the power grid in real time, and input the data to be detected into the power grid fault probability detection model to obtain a probability distribution matrix of the data to be detected; S6. extracting eigenvalues ​​of the probability distribution matrix and performing eigenvalue decomposition on the eigenvalues ​​to obtain principal component information; S7. Analyzing fault data based on the principal component information to obtain a detection result of a power grid fault; further comprising: establishing a fault information database based on past power grid fault records, and performing a correlation analysis between the principal component information of the current data to be detected and the fault information database to obtain a detection result of the power grid fault; The correlation analysis includes calculating the correlation between the attributes of the data in the fault information database using the Pearson correlation coefficient, determining the attributes whose correlation reaches or exceeds the middle value of the correlation range as feature fields, and retaining the attributes with the highest correlation; The attributes include fault duration and fault defect amount; the correlation range is (0.1, 0.9) with a median value of 0.

5.

2. The method for detecting power grid fault data according to claim 1, wherein: In step S1, the data preprocessing method includes data normalization processing.

3. The method for detecting power grid fault data according to claim 1, wherein: The power grid fault probability detection model includes a visual layer, a hidden layer and a classification layer. The visual layer is used to receive the data to be detected and send it to the hidden layer after encoding. The hidden layer is used to extract high-dimensional features of the data. The classification layer is used to connect the hidden layer to classify the data in the hidden layer.

4. A system for detecting power grid fault data, applying a method for detecting power grid fault data according to any one of claims 1 to 3, characterized in that: include: Data acquisition and processing module, used to obtain past detection data of the power grid and perform data processing; Data optimization module, used to select variables from pre-processed data using mutual information technology to obtain optimized variables; An iterative updating module, configured to utilize the optimized variables to iteratively update the weight matrix and the bias matrix through a contrast divergence algorithm; A model building module is used to build a power grid fault probability detection model based on the weight matrix and the deviation matrix; An input module is used to collect the data to be detected in the power grid in real time and input the data to be detected into the power grid fault probability detection model to obtain a probability distribution matrix of the data to be detected; Feature extraction module, used to extract the eigenvalues ​​of the probability distribution matrix and perform eigenvalue decomposition on the eigenvalues ​​to obtain principal component information; The data analysis module is used to perform fault data analysis based on the principal component information to obtain the detection results of the power grid fault.

5. An electronic device, characterized in that: include: a memory for storing one or more programs; processor; When the one or more programs are executed by the processor, the method for detecting power grid fault data according to any one of claims 1 to 3 is implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for detecting power grid fault data according to any one of claims 1 to 3 is implemented.

Images