Power distribution network fault detection method and device, computer device and storage medium

Abstract

The application relates to a power distribution network fault detection method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: periodically acquiring collection data of each bus in a plurality of buses in a power distribution network; performing normalization processing on a target collection matrix to obtain a normalized matrix, the target collection matrix being composed of collection data of the current period and collection data of each period within a preset time length before the current period; determining an initial fault detection index based on eigenvalues of the normalized matrix; in the case that the initial fault detection index exceeds a preset index threshold, acquiring a fault voltage; performing dimensionality augmentation on the target collection matrix based on the fault voltage to determine an augmented collection matrix; updating the initial fault detection index based on the augmented collection matrix; and in the case that the updated fault detection index exceeds the preset index threshold, determining that the power distribution network has a fault. The method can improve the accuracy of power distribution network fault detection.

Description

Technical Field

[0001] This application relates to the field of power distribution network technology, and in particular to a method, apparatus, computer equipment, storage medium and computer program product for detecting power distribution network faults. Background Technology

[0002] In a power system, the distribution network is a crucial end-point, directly supplying electricity to various users. With the development of power systems, the grid size is increasing, and the proportion of renewable energy sources is constantly rising. To ensure the safe and reliable operation of large-scale power grids, timely and accurate fault detection of the distribution network after various power system failures is particularly important.

[0003] Existing methods for detecting faults in power distribution networks often rely on analyzing key operational data to determine if a fault exists. However, factors such as communication problems and electromagnetic interference can introduce measurement noise or faulty data during data acquisition, leading to missed or false diagnoses. Therefore, existing methods suffer from low accuracy in detecting power distribution network faults. Summary of the Invention

[0004] Therefore, it is necessary to address the problem of low accuracy in existing power distribution network fault detection methods by providing a power distribution network fault detection method, device, computer equipment, computer-readable storage medium, and computer program product that can improve the accuracy of power distribution network fault detection.

[0005] Firstly, this application provides a method for detecting faults in a power distribution network. The method includes:

[0006] Periodically acquire data from each of the multiple busbars in the distribution network;

[0007] The target acquisition matrix is ​​normalized to obtain a normalized matrix. The target acquisition matrix consists of the acquisition data of the current period and the acquisition data of each period within the preset time period before the current period.

[0008] Initial fault detection indicators are determined based on the eigenvalues ​​of the normalized matrix.

[0009] If the initial fault detection index exceeds the preset index threshold, the fault voltage is acquired; based on the fault voltage, the dimension of the target acquisition matrix is ​​increased, and the dimension-increased acquisition matrix is ​​determined.

[0010] Based on the augmented acquisition matrix, the initial fault detection index is updated; if the updated fault detection index exceeds the preset index threshold, a fault is determined to exist in the distribution network.

[0011] In one embodiment, the target acquisition matrix is ​​augmented based on the fault voltage to determine the augmented acquisition matrix, including:

[0012] Based on the fault voltage, the true voltage is obtained through state estimation;

[0013] Obtain the normal voltage for normal operation of the power distribution network;

[0014] The difference between the normal voltage and the fault voltage is used as the fault signal;

[0015] The difference between the fault voltage and the true voltage is used as the noise signal;

[0016] The signal-to-noise ratio is determined based on the fault signal and the noise signal;

[0017] Based on the signal-to-noise ratio, the dimension of the target acquisition matrix is ​​increased to determine the acquired matrix after dimension increase.

[0018] In one embodiment, the target acquisition matrix is ​​dimension-enlarged based on the signal-to-noise ratio to determine the dimension-enlarged acquisition matrix, including:

[0019] Based on the signal-to-noise ratio (SNR) and the mapping relationship between SNR and dimensionality increase factor, the dimensionality increase factor is determined, which includes the row dimensionality increase factor and the column dimensionality increase factor.

[0020] The data in each row of the target acquisition matrix is ​​copied by the row-level dimensionality multiplier, and the data in each column of the target acquisition matrix is ​​copied by the column-level dimensionality multiplier to obtain the dimension-multiplied acquisition matrix.

[0021] In one embodiment, after determining that a fault exists in the distribution network, the method further includes:

[0022] For each of the multiple buses, based on the target acquisition matrix and the weights corresponding to the current bus, determine the augmented matrix corresponding to the current bus; based on the target acquisition matrix and the augmented matrix corresponding to the current bus, determine the reference matrix corresponding to the current bus; based on the augmented matrix corresponding to the current bus, determine the first fault indicator corresponding to the current bus; based on the reference matrix corresponding to the current bus, determine the second fault indicator corresponding to the current bus.

[0023] Based on the first fault indicator and the second fault indicator corresponding to each bus, the bus that has failed is determined.

[0024] In one embodiment, the busbar that has failed is determined based on a first fault indicator and a second fault indicator corresponding to each busbar, including:

[0025] For each of the multiple buses, obtain the square of the difference between the first fault indicator and the second fault indicator corresponding to the current bus; sum the squares of the differences in each cycle within a preset time period to obtain the summation result corresponding to the current bus.

[0026] The bus corresponding to the maximum value of the summation result is identified as the bus that has experienced the fault.

[0027] In one embodiment, initial fault detection metrics are determined based on the eigenvalues ​​of the normalized matrix, including:

[0028] Obtain multiple eigenvalues ​​of the normalized matrix;

[0029] The quotient between the largest eigenvalue and the geometric mean of the eigenvalues ​​is used as the initial fault detection index.

[0030] Secondly, this application also provides a power distribution network fault detection device. The device includes:

[0031] The data acquisition module is used to periodically acquire the collected data of each of the multiple busbars in the distribution network;

[0032] The normalization module is used to normalize the target acquisition matrix to obtain a normalized matrix. The target acquisition matrix consists of the acquisition data of the current period and the acquisition data of each period within a preset time period before the current period.

[0033] The initial index determination module is used to determine the initial fault detection index based on the eigenvalues ​​of the normalized matrix.

[0034] The dimension-enhancing module is used to acquire the fault voltage when the initial fault detection index exceeds a preset index threshold; and to enhance the dimension of the target acquisition matrix based on the fault voltage to determine the dimension-enhanced acquisition matrix.

[0035] The fault determination module is used to update the initial fault detection index based on the dimension-enhanced acquisition matrix; if the updated fault detection index exceeds a preset index threshold, it is determined that there is a fault in the distribution network.

[0036] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0037] Periodically acquire data from each of the multiple busbars in the distribution network;

[0038] The target acquisition matrix is ​​normalized to obtain a normalized matrix. The target acquisition matrix consists of the acquisition data of the current period and the acquisition data of each period within the preset time period before the current period.

[0039] Initial fault detection indicators are determined based on the eigenvalues ​​of the normalized matrix.

[0040] If the initial fault detection index exceeds the preset index threshold, the fault voltage is acquired; based on the fault voltage, the dimension of the target acquisition matrix is ​​increased, and the dimension-increased acquisition matrix is ​​determined.

[0041] Based on the augmented acquisition matrix, the initial fault detection index is updated; if the updated fault detection index exceeds the preset index threshold, a fault is determined to exist in the distribution network.

[0042] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0043] Periodically acquire data from each of the multiple busbars in the distribution network;

[0044] The target acquisition matrix is ​​normalized to obtain a normalized matrix. The target acquisition matrix consists of the acquisition data of the current period and the acquisition data of each period within the preset time period before the current period.

[0045] Initial fault detection indicators are determined based on the eigenvalues ​​of the normalized matrix.

[0046] If the initial fault detection index exceeds the preset index threshold, the fault voltage is acquired; based on the fault voltage, the dimension of the target acquisition matrix is ​​increased, and the dimension-increased acquisition matrix is ​​determined.

[0047] Based on the augmented acquisition matrix, the initial fault detection index is updated; if the updated fault detection index exceeds the preset index threshold, a fault is determined to exist in the distribution network.

[0048] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0049] Periodically acquire data from each of the multiple busbars in the distribution network;

[0050] The target acquisition matrix is ​​normalized to obtain a normalized matrix. The target acquisition matrix consists of the acquisition data of the current period and the acquisition data of each period within the preset time period before the current period.

[0051] Initial fault detection indicators are determined based on the eigenvalues ​​of the normalized matrix.

[0052] If the initial fault detection index exceeds the preset index threshold, the fault voltage is acquired; based on the fault voltage, the dimension of the target acquisition matrix is ​​increased, and the dimension-increased acquisition matrix is ​​determined.

[0053] Based on the augmented acquisition matrix, the initial fault detection index is updated; if the updated fault detection index exceeds the preset index threshold, a fault is determined to exist in the distribution network.

[0054] The aforementioned distribution network fault detection method, device, computer equipment, storage medium, and computer program product periodically acquire data from each of multiple busbars in the distribution network, normalize the target acquisition matrix to obtain a normalized matrix, and determine initial fault detection indicators based on the eigenvalues ​​of the normalized matrix. If the initial fault detection indicators exceed a preset threshold, a fault is preliminarily determined in the distribution network. The fault voltage is acquired, and based on the fault voltage, the target acquisition matrix is ​​augmented to determine the augmented acquisition matrix. Then, based on the augmented acquisition matrix, the initial fault detection indicators are updated. If the updated fault detection indicators exceed the preset threshold, a fault is confirmed in the distribution network. Dimensional augmentation weakens the impact of noise on the actual state of the distribution network, improving the accuracy of distribution network fault detection. Attached Figure Description

[0055] Figure 1 This is an application environment diagram of a power distribution network fault detection method in one embodiment;

[0056] Figure 2 This is a flowchart illustrating a power distribution network fault detection method in one embodiment;

[0057] Figure 3 This is a schematic diagram of a sub-process of S204 in one embodiment;

[0058] Figure 4 This is a schematic diagram of a sub-process of S308 in one embodiment;

[0059] Figure 5 This is a schematic diagram of a sub-process of S205 in one embodiment;

[0060] Figure 6 This is a schematic diagram of the wiring of a distribution network according to the IEEE standard example in one embodiment;

[0061] Figure 7 This is a schematic diagram of the overall process of a power distribution network fault detection method in one embodiment;

[0062] Figure 8 This is a structural block diagram of a power distribution network fault detection device in one embodiment;

[0063] Figure 9 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0065] The power distribution network fault detection method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, terminal 102 communicates with distribution network 104 via a network. A data storage system can store data that the server needs to process. The data storage system can be integrated on the server or placed in the cloud or on other network servers. The distribution network fault detection method provided in this application embodiment can be executed by terminal 102 or the server alone, or by terminal 102 and the server in collaboration. Taking execution by terminal 102 alone as an example: periodically acquire the collected data of each bus in multiple buses in the distribution network; normalize the target acquisition matrix to obtain a normalized matrix, which consists of the collected data of the current period and the collected data of each period within a preset time period before the current period; determine the initial fault detection index based on the eigenvalues ​​of the normalized matrix; acquire the fault voltage when the initial fault detection index exceeds a preset index threshold; increase the dimension of the target acquisition matrix based on the fault voltage to determine the dimension-enhanced acquisition matrix; update the initial fault detection index based on the dimension-enhanced acquisition matrix; determine that a fault exists in the distribution network when the updated fault detection index exceeds the preset index threshold. The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle systems. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The server can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0066] In one embodiment, such as Figure 2 As shown, a method for detecting faults in a power distribution network is provided, which can be applied to a computer device (the computer device can be...) Figure 1 Taking terminal 102 or server as an example, the following steps are included:

[0067] S201 periodically acquires the collected data of each of the multiple busbars in the distribution network.

[0068] A busbar, made of highly conductive metallic material, is a product used to transmit electrical energy and has the ability to collect and distribute power. It is the main conductor used for transmitting electrical energy in a substation or distribution station. Through the busbar, the electrical energy output from generators, transformers, or rectifiers is transmitted to various users or other substations. A distribution network includes multiple busbars. The busbars that collect data acquire electrical data, including but not limited to voltage, current, voltage amplitude, and power angle. Computer equipment periodically acquires the collected data from each of the multiple busbars in the distribution network.

[0069] S202, normalize the target acquisition matrix to obtain a normalized matrix. The target acquisition matrix consists of the acquisition data of the current period and the acquisition data of each period within the preset time period before the current period.

[0070] The target acquisition matrix consists of the acquisition data from the current period and the acquisition data from each period within a preset time period prior to the current period. Normalization refers to transforming the elements of the target acquisition matrix to map them to the same scale. In some embodiments, the target acquisition matrix is ​​normalized to obtain a normalized matrix. Specifically, the target acquisition matrix is ​​standardized to obtain a standardized matrix, and the covariance matrix of the standardized matrix is ​​determined as the normalized matrix. The standardization of the target acquisition matrix is ​​shown in the following equation:

[0071]

[0072] In the formula: X 1,i For the elements in the standardized matrix; μ(X) i ) represents the mean of the elements in the i-th row of the target acquisition matrix; σ(X) i ) represents the standard deviation of the element in the i-th row of the target acquisition matrix.

[0073] The standardized matrix follows a distribution with a mean of 0 and a standard deviation of 1. Further calculation of the covariance matrix of the standardized matrix is ​​shown in the following equation:

[0074] R = X1X1 T

[0075] In the formula: R is the normalized matrix; X1 T This is the transpose of the standardized matrix.

[0076] The resulting normalized matrix is ​​a non-Hermitian matrix. When the number of rows and columns of the normalized matrix approaches infinity, the row-to-column ratio of the normalized matrix is ​​greater than 0 and less than or equal to 1, and all elements in the normalized matrix are independent and identically distributed random variables, the eigenvalues ​​of the singular value equivalent matrix of the normalized matrix are distributed within an inner ring of radius (1-c). L / 2Between the outer ring and the ring with radius 1, the limiting spectral distribution function of the matrix is ​​as follows:

[0077]

[0078]

[0079] In the formula, Z std This indicates that there are L non-Hermitian matrices being multiplied; It is matrix Z std The eigenvalues; c = N / T, representing the row-to-column ratio of the matrix.

[0080] S203. Determine the initial fault detection index based on the eigenvalues ​​of the normalized matrix.

[0081] The computer equipment acquires multiple eigenvalues ​​of the normalized matrix. Using these eigenvalues, the computer equipment determines an initial fault detection index. This initial index characterizes the degree to which the largest eigenvalue deviates from the average eigenvalue.

[0082] S204. If the initial fault detection index exceeds the preset index threshold, acquire the fault voltage; based on the fault voltage, increase the dimension of the target acquisition matrix and determine the acquired matrix after dimension increase.

[0083] When there are no faults in the distribution network, the initial fault detection index calculated by the normalized matrix is ​​lower than the preset threshold. If a fault in the distribution network causes fluctuations in the data collected from the distribution network bus, the initial fault detection index calculated by the normalized matrix will exceed the preset threshold. When the initial fault detection index exceeds the preset threshold, the fault voltage is acquired. The fault voltage is the voltage collected from the distribution network bus by the computer equipment when the initial fault detection index exceeds the preset threshold.

[0084] Dimensionality enhancement refers to copying a row or column of the target acquisition matrix, thereby increasing the number of rows or columns and obtaining a dimension-enhanced acquisition matrix. The dimension enhancement factor can be determined by the fault voltage.

[0085] S205, based on the augmented acquisition matrix, update the initial fault detection index; if the updated fault detection index exceeds the preset index threshold, determine that there is a fault in the distribution network.

[0086] In this process, the number of rows or columns in the augmented acquisition matrix is ​​greater than that of the normalized matrix. Based on this augmented matrix, the computer equipment updates the initial fault detection indicators. If the updated fault detection indicators exceed a preset threshold, the computer equipment determines that a fault exists in the distribution network. Dimensional augmentation reduces the impact of noise on the actual electrical quantity data of the distribution network, allowing for a more accurate extraction of the true electrical quantity information at each node during the calculation of fault detection indicators. The updated fault detection indicators thus exhibit higher accuracy.

[0087] In the aforementioned power distribution network fault detection method, data from each of multiple busbars in the power distribution network is periodically acquired. The target acquisition matrix is ​​then normalized to obtain a normalized matrix. Based on the eigenvalues ​​of the normalized matrix, initial fault detection indicators are determined. If the initial fault detection indicators exceed a preset threshold, a fault is preliminarily identified in the power distribution network. The fault voltage is then acquired. Based on the fault voltage, the target acquisition matrix is ​​augmented to determine the augmented acquisition matrix. The initial fault detection indicators are then updated based on the augmented acquisition matrix. If the updated fault detection indicators exceed the preset threshold, a fault is confirmed in the power distribution network. Dimensional augmentation weakens the impact of noise on the actual state of the power distribution network, thus improving the accuracy of fault detection.

[0088] In one embodiment, such as Figure 3 As shown, based on the fault voltage, the dimension of the target acquisition matrix is ​​increased to determine the dimension-increased acquisition matrix, including:

[0089] S302, based on the fault voltage, obtains the true voltage through state estimation.

[0090] State estimation is a method for estimating the internal state of a dynamic system based on available measurement data. Data obtained by measuring the system's inputs and outputs only reflects its external characteristics; the system's dynamic laws need to be described using internal (usually not directly measurable) state variables. State estimation is crucial for understanding and controlling a system. The true voltage is obtained through state estimation based on the fault voltage. The difference between the fault voltage and the true voltage is the noise voltage.

[0091] S304 obtains the normal voltage for normal operation of the power distribution network.

[0092] In this system, the computer equipment acquires the voltage of the power distribution network when it is operating normally, which is referred to as the normal voltage. In some embodiments, this can be achieved by acquiring the voltage of each of the multiple busbars in the power distribution network when it is operating normally.

[0093] S306: The difference between the normal voltage and the fault voltage is used as the fault signal; the difference between the fault voltage and the true voltage is used as the noise signal; the signal-to-noise ratio is determined based on the fault signal and the noise signal.

[0094] The computer equipment uses the difference between the normal voltage and the fault voltage as the fault signal, and the difference between the fault voltage and the true voltage as the noise signal. Based on the fault signal and the noise signal, the computer equipment determines the signal-to-noise ratio (SNR). The formula for calculating the SNR is as follows:

[0095]

[0096] In the formula, V S and V N These represent the voltages of the fault signal and the noise signal, respectively; SNR represents the signal-to-noise ratio.

[0097] S308, based on the signal-to-noise ratio, increases the dimension of the target acquisition matrix to determine the acquired matrix after dimension increase.

[0098] Specifically, based on the signal-to-noise ratio, the dimension-increasing factor is determined, and the dimension of the target acquisition matrix is ​​increased by the dimension-increasing factor to obtain the dimension-increasing acquisition matrix.

[0099] In this embodiment, the true voltage is obtained through state estimation using the fault voltage. The difference between the normal voltage and the fault voltage is used as the fault signal, and the difference between the fault voltage and the true voltage is used as the noise signal. Based on the fault signal and the noise signal, the signal-to-noise ratio (SNR) is determined. Based on the SNR, the target acquisition matrix is ​​augmented to determine the augmented acquisition matrix. Since detection failures are prone to occur in low SNR environments, reducing the accuracy of distribution network fault detection, a dimensionality augmentation method is used to address the problem of missed fault detection in low SNR environments. This method, which obtains the true voltage through state estimation and then determines the SNR, yields a highly accurate SNR result. Augmenting the target acquisition matrix according to different SNR scenarios further improves the accuracy of distribution network fault detection.

[0100] In one embodiment, such as Figure 4 As shown, based on the signal-to-noise ratio, the dimension of the target acquisition matrix is ​​increased to determine the dimension-increased acquisition matrix, including:

[0101] S402. Based on the signal-to-noise ratio and the mapping relationship between the signal-to-noise ratio and the dimensionality increase factor, the dimensionality increase factor is determined. The dimensionality increase factor includes the row dimensionality increase factor and the column dimensionality increase factor.

[0102] The signal-to-noise ratio (SNR) and dimensionality increase factor mapping relationship, used to indicate the magnitude of the SNR and dimensionality increase factor, is determined based on historical experiments. The computer equipment inputs the SNR into the SNR-dimensionality increase factor mapping relationship to obtain the dimensionality increase factor. The dimensionality increase factor includes row dimensionality increase factor and column dimensionality increase factor. In some embodiments, after extensive simulation experiments, it was concluded that when the SNR of noise and fault signals is greater than 5dB, no dimensionality increase processing of the target acquisition matrix is ​​required; when the SNR of noise and fault signals is between 3dB and 5dB, a 5-fold dimensionality increase of the target acquisition matrix can achieve the desired effect; when the SNR of noise and fault signals is less than 3dB, a 10-fold dimensionality increase of the target acquisition matrix is ​​optimal.

[0103] S404, copy each row of the target acquisition matrix by the row-level dimensionality multiplier, and copy each column of the target acquisition matrix by the column-level dimensionality multiplier to obtain the dimension-enhanced acquisition matrix.

[0104] The computer equipment copies each row of the target acquisition matrix by a row-to-dimensionality multiplication factor and copies each column of the target acquisition matrix by a column-to-dimensionality multiplication factor to obtain the dimension-enhanced acquisition matrix.

[0105] In this embodiment, the dimensionality increase factor is determined based on the signal-to-noise ratio (SNR) and its mapping relationship with the dimensionality increase factor. Each row of the target acquisition matrix is ​​copied by the row dimensionality increase factor, and each column of the target acquisition matrix is ​​copied by the column dimensionality increase factor, resulting in the dimensionality-enhanced acquisition matrix. This method of determining the dimensionality increase factor based on the mapping relationship between SNR and dimensionality increase factor is beneficial for improving the accuracy of distribution network fault detection, as the SNR varies in different distribution network noise environments.

[0106] In one embodiment, such as Figure 5 As shown, after determining that a fault exists in the distribution network, the following steps are also included:

[0107] S502, for each of the multiple buses, based on the target acquisition matrix and the weight corresponding to the current bus, determine the augmented matrix corresponding to the current bus; based on the target acquisition matrix and the augmented matrix corresponding to the current bus, determine the reference matrix corresponding to the current bus; based on the augmented matrix corresponding to the current bus, determine the first fault indicator corresponding to the current bus; based on the reference matrix corresponding to the current bus, determine the second fault indicator corresponding to the current bus.

[0108] After confirming a fault in the distribution network, it is often necessary to determine which specific busbar is faulty. For each of the multiple buses, the computer equipment determines the augmented matrix corresponding to the current busbar based on the target acquisition matrix and the weights corresponding to that busbar. Specifically, since the target acquisition matrix includes data from multiple buses, the weights corresponding to the current busbar are reset to preset weights. The row data corresponding to the current busbar is then copied to the preset weight row, with the copied row data positioned below the row data corresponding to the current busbar. The resulting matrix is ​​the augmented matrix corresponding to the current busbar. The dimension of the augmented matrix corresponding to the current busbar is greater than the dimension of the target acquisition matrix. This augmentation process is repeated for each of the multiple buses to obtain the augmented matrix corresponding to each busbar.

[0109] The computer equipment determines the reference matrix corresponding to the current bus based on the target acquisition matrix and the augmented matrix corresponding to the current bus. The computer equipment obtains the dimension of the augmented matrix corresponding to the current bus and determines the dimension of the reference matrix corresponding to the current bus. The dimension of the target acquisition matrix is ​​subtracted from the dimension of the reference matrix corresponding to the current bus, and the result is used as the dimension of the random noise matrix. The computer equipment generates a random noise matrix based on the dimension of the random noise matrix. Each element in the random noise matrix follows a Gaussian distribution.

[0110] The computer equipment determines a first fault indicator for the current bus based on the augmented matrix corresponding to the current bus, and a second fault indicator based on the reference matrix corresponding to the current bus. Specifically, the computer equipment normalizes the augmented matrix corresponding to the current bus to obtain a first normalized matrix, and determines the first fault indicator based on the eigenvalues ​​of the first normalized matrix. The computer equipment also normalizes the reference matrix corresponding to the current bus to obtain a second normalized matrix, and determines the second fault indicator based on the second normalized matrix.

[0111] S504, based on the first fault index and the second fault index corresponding to each busbar, determine the busbar that has failed.

[0112] Specifically, for any one of the multiple busbars, the computer equipment obtains the Euclidean distance between the first fault indicator and the corresponding second fault indicator of the current busbar, and determines the busbar with the largest Euclidean distance as the busbar that has experienced a fault.

[0113] In this embodiment, by augmenting each of the multiple busbars, an augmented matrix corresponding to each busbar is obtained. Based on the augmented matrix and the reference matrix, the first fault index and the second fault index are determined respectively, thereby identifying the busbar that has experienced a fault. This method of determining the busbar that has experienced a fault by augmenting the matrix and setting the reference matrix is ​​beneficial to improving the accuracy and precision of fault detection in the distribution network.

[0114] In one embodiment, determining the faulty bus based on the first fault index and the second fault index corresponding to each bus includes: for each of the multiple buses, obtaining the square of the difference between the first fault index and the second fault index corresponding to the current bus; summing the squares of the differences in each period within a preset time period to obtain the summation result corresponding to the current bus; and determining the bus corresponding to the maximum value of the summation result as the faulty bus.

[0115] Specifically, for each of the multiple buses, the computer device obtains the squared difference between the first fault indicator and the second fault indicator corresponding to the current bus. The squared differences over each cycle within a preset time period are summed to obtain the summation result for the current bus. This yields the summation results for each bus. The summation results for each bus are used to indicate the Euclidean distance between the augmented matrix and the reference matrix for each bus. The terminal identifies the bus with the maximum summation result as the faulty bus.

[0116] In this embodiment, by obtaining the square of the difference between the first fault index and the corresponding second fault index for each bus, the bus corresponding to the maximum value of the sum of the squares of the differences in each cycle within a preset time period is determined as the bus that has experienced a fault. This method of determining the faulty bus in the distribution network improves the accuracy and precision of fault detection in the distribution network.

[0117] In one embodiment, determining an initial fault detection index based on the eigenvalues ​​of a normalized matrix includes: obtaining multiple eigenvalues ​​of the normalized matrix; and using the quotient between the largest eigenvalue and the geometric mean of the multiple eigenvalues ​​as the initial fault detection index.

[0118] The computer device acquires multiple eigenvalues ​​of the normalized matrix, arranges these eigenvalues ​​in ascending order, determines the largest eigenvalue, and obtains the geometric mean of the eigenvalues. The quotient between the largest eigenvalue and the geometric mean of the eigenvalues ​​is used as the initial fault detection index. In some embodiments, when the preset time is long, the eigenvalues ​​of the normalized matrix satisfy the following formula:

[0119]

[0120]

[0121] Where: σ v 2 Let λ be the variance of the noise matrix Q. i λ represents the multiple eigenvalues ​​of the normalized matrix. Max λ represents the largest eigenvalue among multiple eigenvalues.Min T represents the smallest eigenvalue among multiple eigenvalues. w and N represent the number of columns and rows of the normalized matrix, respectively. It represents the geometric mean of multiple eigenvalues.

[0122]

[0123] MGME stands for Initial Fault Detection Index.

[0124] In this embodiment, by obtaining multiple eigenvalues ​​of the normalized matrix, the quotient between the largest eigenvalue and the geometric mean of the multiple eigenvalues ​​is used as the initial fault detection index. This method of determining the initial fault detection index of the distribution network through the eigenvalues ​​of the normalized matrix can preliminarily determine whether there is a fault in the distribution network.

[0125] To illustrate the distribution network fault detection method and its effectiveness in this solution in detail, a specific embodiment is described below:

[0126] Computer equipment periodically acquires data from each of the multiple busbars in a power distribution network. For example... Figure 6 The diagram shown is a standard IEEE (Institute of Electrical and Electronics Engineers) wiring diagram for a distribution network. The target acquisition matrix is ​​normalized to obtain a normalized matrix, which consists of the acquisition data from the current cycle and the acquisition data from each cycle within a preset time period prior to the current cycle. Based on the eigenvalues ​​of the normalized matrix, initial fault detection indicators are determined. If the initial fault detection indicators exceed a preset threshold, the fault voltage is acquired. For example... Figure 7 The diagram shows the overall flow chart of the power distribution network fault detection method.

[0127] Based on the fault voltage, the target acquisition matrix is ​​dimension-enlarged to determine the dimension-enlarged acquisition matrix. Specifically, based on the fault voltage, the true voltage is obtained through state estimation, and the normal voltage of the distribution network under normal operation is acquired. The difference between the normal voltage and the fault voltage is taken as the fault signal, and the difference between the fault voltage and the true voltage is taken as the noise signal. The signal-to-noise ratio (SNR) is determined based on the fault signal and the noise signal. Based on the SNR and the mapping relationship between the SNR and the dimension-enlargement factor, the dimension-enlargement factor is determined, including the row dimension-enlargement factor and the column dimension-enlargement factor. Each row of the target acquisition matrix is ​​copied by the row dimension-enlargement factor, and each column of the target acquisition matrix is ​​copied by the column dimension-enlargement factor to obtain the dimension-enlarged acquisition matrix.

[0128] For example, the dimension of the target acquisition matrix is ​​N×T. w The target acquisition matrix is ​​shown below:

[0129]

[0130] By increasing the row dimension of the matrix to m times its original dimension and the column dimension to n times its original dimension, the resulting matrix has a dimension of (m*N)×(n*T). w ), the increased-dimensional acquisition matrix as follows:

[0131]

[0132] If the number of dimension increases is too small, the asymptotic convergence condition of the matrix dimension cannot be met; if the number of dimension increases is too large, the fault detection speed will decrease, and the real-time performance of fault detection cannot be guaranteed. Therefore, an adaptive row-column replication ratio method is proposed. The number of matrix dimension increases varies depending on the signal-to-noise ratio (SNR) at the time of the fault. After extensive simulations, it is concluded that the adaptive dimension increase method based on the SNR at the time of the fault satisfies both the asymptotic convergence condition and the real-time requirement of fault detection. The dimension-increased matrix does not destroy its original data structure, preserving the spatiotemporal distribution characteristics of the target acquisition matrix while increasing the matrix dimension.

[0133] Based on the augmented acquisition matrix, the initial fault detection index is updated. The error of the updated initial fault detection index is smaller than that of the initial fault detection index. Therefore, in the calculation of the initial fault detection index, using the augmented matrix for fault detection significantly reduces the false negative rate compared to using the target acquisition matrix. If the updated fault detection index exceeds a preset threshold, a fault is determined to exist in the distribution network.

[0134] After determining a fault in the distribution network, the computer equipment, for each of the multiple buses, determines the augmented matrix corresponding to the current bus based on the target acquisition matrix and the weights corresponding to the current bus; it also determines the reference matrix corresponding to the current bus based on the target acquisition matrix and the augmented matrix corresponding to the current bus; based on the augmented matrix corresponding to the current bus, it determines the first fault indicator corresponding to the current bus; and based on the reference matrix corresponding to the current bus, it determines the second fault indicator corresponding to the current bus. For each of the multiple buses, the square of the difference between the first fault indicator and the second fault indicator corresponding to the current bus is obtained; the squares of the differences in each cycle within a preset time period are summed to obtain the summation result corresponding to the current bus; and the bus corresponding to the maximum value of the summation result is determined as the bus where the fault occurred.

[0135] An augmented random matrix is ​​constructed based on the target acquisition matrix. This augmented random matrix reflects the influence of the variable of interest on the system. Simultaneously, a reference random matrix of the same dimension as the augmented random matrix is ​​constructed for reference. The influence of the physical quantity of interest on the overall system is characterized by comparing the differences in the eigenvalues ​​of the two matrices. The construction of the augmented random matrix is ​​shown in the following equation:

[0136]

[0137] In the formula: X r Let P represent a weight matrix of size P×T, where P is the number of rows to be copied.

[0138] For the node i of interest, select row vector x. i And replicate it P times to construct the weight matrix X r :

[0139] X r =[x i 1 x i 2 x i 3 …x i P ] T

[0140] On the other hand, we can construct a reference matrix X C :

[0141]

[0142] In the formula: N3 is a combination of X and r Gaussian white noise matrices of the same dimension.

[0143] An augmented matrix is ​​constructed using different bus voltage data of the distribution network, and the Euclidean distance is compared with that of a reference random matrix. The bus with the larger Euclidean distance is considered to be the bus where the fault occurred.

[0144] This application determines the faulty bus in the distribution network based on the fault time of the updated fault detection indicators, which helps to detect system anomalies in a timely manner. The fault area localization method based on augmented matrices can accurately locate suspected fault areas by comparing the Euclidean distance between the fault detection indicators corresponding to the augmented matrices and reference matrices of different influencing factors, which is helpful for fault investigation.

[0145] The aforementioned distribution network fault detection method, device, computer equipment, storage medium, and computer program product periodically acquire data from each of multiple busbars in the distribution network, normalize the target acquisition matrix to obtain a normalized matrix, and determine initial fault detection indicators based on the eigenvalues ​​of the normalized matrix. If the initial fault detection indicators exceed a preset threshold, a fault is preliminarily determined in the distribution network. The fault voltage is acquired, and based on the fault voltage, the target acquisition matrix is ​​augmented to determine the augmented acquisition matrix. Then, based on the augmented acquisition matrix, the initial fault detection indicators are updated. If the updated fault detection indicators exceed the preset threshold, a fault is confirmed in the distribution network. Dimensional augmentation weakens the impact of noise on the actual state of the distribution network, improving the accuracy of distribution network fault detection.

[0146] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0147] Based on the same inventive concept, this application also provides a power distribution network fault detection device for implementing the power distribution network fault detection method described above. The solution provided by this device is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more embodiments of the power distribution network fault detection device provided below can be found in the limitations of the power distribution network fault detection method described above, and will not be repeated here.

[0148] In one embodiment, such as Figure 8 As shown, a power distribution network fault detection device 100 is provided, including: a data acquisition module 110, a normalization module 120, an initial index determination module 130, a dimension enhancement module 140, and a fault determination module 150, wherein:

[0149] The data acquisition module 110 is used to periodically acquire the collected data of each busbar among multiple busbars in the distribution network;

[0150] The normalization module 120 is used to normalize the target acquisition matrix to obtain a normalized matrix. The target acquisition matrix consists of the acquisition data of the current period and the acquisition data of each period within the preset time period before the current period.

[0151] The initial index determination module 130 is used to determine the initial fault detection index based on the eigenvalues ​​of the normalized matrix.

[0152] The dimension-enhancing module 140 is used to acquire the fault voltage when the initial fault detection index exceeds the preset index threshold; based on the fault voltage, the dimension of the target acquisition matrix is ​​enhanced to determine the dimension-enhanced acquisition matrix.

[0153] The fault determination module 150 is used to update the initial fault detection index based on the dimension-enhanced acquisition matrix; if the updated fault detection index exceeds the preset index threshold, it is determined that there is a fault in the distribution network.

[0154] The aforementioned power distribution network fault detection device periodically acquires data from each of multiple busbars in the power distribution network, normalizes the target acquisition matrix to obtain a normalized matrix, and determines initial fault detection indicators based on the eigenvalues ​​of the normalized matrix. If the initial fault detection indicators exceed a preset threshold, a fault is preliminarily determined in the power distribution network. The fault voltage is then acquired, and based on the fault voltage, the target acquisition matrix is ​​augmented to determine the augmented acquisition matrix. The initial fault detection indicators are then updated based on the augmented acquisition matrix. If the updated fault detection indicators exceed the preset threshold, a fault is confirmed in the power distribution network. Dimensional augmentation weakens the impact of noise on the actual state of the power distribution network, improving the accuracy of fault detection.

[0155] In one embodiment, in terms of increasing the dimension of the target acquisition matrix based on the fault voltage and determining the increased dimension acquisition matrix, the dimension-increasing module 140 is further configured to: obtain the true voltage based on the fault voltage through state estimation; obtain the normal voltage of the distribution network in normal operation; use the difference between the normal voltage and the fault voltage as the fault signal; use the difference between the fault voltage and the true voltage as the noise signal; determine the signal-to-noise ratio based on the fault signal and the noise signal; and increase the dimension of the target acquisition matrix based on the signal-to-noise ratio to determine the increased dimension acquisition matrix.

[0156] In one embodiment, in terms of increasing the dimension of the target acquisition matrix based on the signal-to-noise ratio (SNR) and determining the dimension-increased acquisition matrix, the dimension-increased module 140 is further configured to: determine the dimension-increased factor based on the SNR and the mapping relationship between the SNR and the dimension-increased factor, wherein the dimension-increased factor includes the row dimension-increased factor and the column dimension-increased factor; copy the row dimension-increased factor of each row of the target acquisition matrix and copy the column dimension-increased factor of each column of the target acquisition matrix to obtain the dimension-increased acquisition matrix.

[0157] In one embodiment, after determining that a fault exists in the distribution network, the fault determination module 150 is further configured to: for each of the multiple buses, determine the augmented matrix corresponding to the current bus based on the target acquisition matrix and the weight corresponding to the current bus; determine the reference matrix corresponding to the current bus based on the target acquisition matrix and the augmented matrix corresponding to the current bus; determine the first fault index corresponding to the current bus based on the augmented matrix corresponding to the current bus; determine the second fault index corresponding to the current bus based on the reference matrix corresponding to the current bus; and determine the bus that has experienced a fault based on the first fault index and the second fault index corresponding to each bus.

[0158] In one embodiment, in determining the faulty bus based on the first fault index and the second fault index corresponding to each bus, the fault determination module 150 is further configured to: for each of the multiple buses, obtain the square of the difference between the first fault index and the second fault index corresponding to the current bus; sum the squares of the differences in each cycle within a preset time period to obtain the summation result corresponding to the current bus; and determine the bus corresponding to the maximum value of the summation result as the faulty bus.

[0159] In one embodiment, in determining the initial fault detection index based on the eigenvalues ​​of the normalized matrix, the initial index determination module 130 is further configured to: obtain multiple eigenvalues ​​of the normalized matrix; and use the quotient between the largest eigenvalue and the geometric mean of the multiple eigenvalues ​​as the initial fault detection index.

[0160] Each module in the aforementioned power distribution network fault detection device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0161] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 9As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a power distribution network fault detection method.

[0162] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0163] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0164] The system periodically acquires data from each of the multiple busbars in the distribution network; it normalizes the target acquisition matrix to obtain a normalized matrix, which consists of the acquisition data from the current period and the acquisition data from each period within a preset time period prior to the current period; it determines initial fault detection indicators based on the eigenvalues ​​of the normalized matrix; it acquires the fault voltage when the initial fault detection indicators exceed a preset threshold; it increases the dimensionality of the target acquisition matrix based on the fault voltage to determine the increased-dimensional acquisition matrix; it updates the initial fault detection indicators based on the increased-dimensional acquisition matrix; and it determines that a fault exists in the distribution network when the updated fault detection indicators exceed the preset threshold.

[0165] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0166] Based on the fault voltage, the true voltage is obtained through state estimation; the normal voltage of the distribution network is obtained; the difference between the normal voltage and the fault voltage is used as the fault signal; the difference between the fault voltage and the true voltage is used as the noise signal; the signal-to-noise ratio is determined based on the fault signal and the noise signal; based on the signal-to-noise ratio, the dimension of the target acquisition matrix is ​​increased to determine the dimension-increased acquisition matrix.

[0167] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0168] Based on the signal-to-noise ratio (SNR) and the mapping relationship between SNR and dimensionality increase factor, the dimensionality increase factor is determined, which includes the row dimensionality increase factor and the column dimensionality increase factor. Each row of the target acquisition matrix is ​​copied by the row dimensionality increase factor, and each column of the target acquisition matrix is ​​copied by the column dimensionality increase factor to obtain the dimensionality-increased acquisition matrix.

[0169] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0170] For each of the multiple buses, based on the target acquisition matrix and the weights corresponding to the current bus, determine the augmented matrix corresponding to the current bus; based on the target acquisition matrix and the augmented matrix corresponding to the current bus, determine the reference matrix corresponding to the current bus; based on the augmented matrix corresponding to the current bus, determine the first fault indicator corresponding to the current bus; based on the reference matrix corresponding to the current bus, determine the second fault indicator corresponding to the current bus; based on the first fault indicator and the second fault indicator corresponding to each bus, determine the bus that has experienced a fault.

[0171] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0172] For each of the multiple buses, obtain the square of the difference between the first fault indicator and the second fault indicator corresponding to the current bus; sum the squares of the differences in each cycle within a preset time period to obtain the summation result corresponding to the current bus; determine the bus corresponding to the maximum value of the summation result as the bus that has experienced a fault.

[0173] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0174] Obtain multiple eigenvalues ​​of the normalized matrix; use the quotient between the largest eigenvalue and the geometric mean of the multiple eigenvalues ​​as the initial fault detection index.

[0175] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0176] The system periodically acquires data from each of the multiple busbars in the distribution network; it normalizes the target acquisition matrix to obtain a normalized matrix, which consists of the acquisition data from the current period and the acquisition data from each period within a preset time period prior to the current period; it determines initial fault detection indicators based on the eigenvalues ​​of the normalized matrix; it acquires the fault voltage when the initial fault detection indicators exceed a preset threshold; it increases the dimensionality of the target acquisition matrix based on the fault voltage to determine the increased-dimensional acquisition matrix; it updates the initial fault detection indicators based on the increased-dimensional acquisition matrix; and it determines that a fault exists in the distribution network when the updated fault detection indicators exceed the preset threshold.

[0177] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0178] Based on the fault voltage, the true voltage is obtained through state estimation; the normal voltage of the distribution network is obtained; the difference between the normal voltage and the fault voltage is used as the fault signal; the difference between the fault voltage and the true voltage is used as the noise signal; the signal-to-noise ratio is determined based on the fault signal and the noise signal; based on the signal-to-noise ratio, the dimension of the target acquisition matrix is ​​increased to determine the dimension-increased acquisition matrix.

[0179] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0180] Based on the signal-to-noise ratio (SNR) and the mapping relationship between SNR and dimensionality increase factor, the dimensionality increase factor is determined, which includes the row dimensionality increase factor and the column dimensionality increase factor. Each row of the target acquisition matrix is ​​copied by the row dimensionality increase factor, and each column of the target acquisition matrix is ​​copied by the column dimensionality increase factor to obtain the dimensionality-increased acquisition matrix.

[0181] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0182] For each of the multiple buses, based on the target acquisition matrix and the weights corresponding to the current bus, determine the augmented matrix corresponding to the current bus; based on the target acquisition matrix and the augmented matrix corresponding to the current bus, determine the reference matrix corresponding to the current bus; based on the augmented matrix corresponding to the current bus, determine the first fault indicator corresponding to the current bus; based on the reference matrix corresponding to the current bus, determine the second fault indicator corresponding to the current bus; based on the first fault indicator and the second fault indicator corresponding to each bus, determine the bus that has experienced a fault.

[0183] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0184] For each of the multiple buses, obtain the square of the difference between the first fault indicator and the second fault indicator corresponding to the current bus; sum the squares of the differences in each cycle within a preset time period to obtain the summation result corresponding to the current bus; determine the bus corresponding to the maximum value of the summation result as the bus that has experienced a fault.

[0185] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0186] Obtain multiple eigenvalues ​​of the normalized matrix; use the quotient between the largest eigenvalue and the geometric mean of the multiple eigenvalues ​​as the initial fault detection index.

[0187] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0188] The system periodically acquires data from each of the multiple busbars in the distribution network; it normalizes the target acquisition matrix to obtain a normalized matrix, which consists of the acquisition data from the current period and the acquisition data from each period within a preset time period prior to the current period; it determines initial fault detection indicators based on the eigenvalues ​​of the normalized matrix; it acquires the fault voltage when the initial fault detection indicators exceed a preset threshold; it increases the dimensionality of the target acquisition matrix based on the fault voltage to determine the increased-dimensional acquisition matrix; it updates the initial fault detection indicators based on the increased-dimensional acquisition matrix; and it determines that a fault exists in the distribution network when the updated fault detection indicators exceed the preset threshold.

[0189] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0190] Based on the fault voltage, the true voltage is obtained through state estimation; the normal voltage of the distribution network is obtained; the difference between the normal voltage and the fault voltage is used as the fault signal; the difference between the fault voltage and the true voltage is used as the noise signal; the signal-to-noise ratio is determined based on the fault signal and the noise signal; based on the signal-to-noise ratio, the dimension of the target acquisition matrix is ​​increased to determine the dimension-increased acquisition matrix.

[0191] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0192] Based on the signal-to-noise ratio (SNR) and the mapping relationship between SNR and dimensionality increase factor, the dimensionality increase factor is determined, which includes the row dimensionality increase factor and the column dimensionality increase factor. Each row of the target acquisition matrix is ​​copied by the row dimensionality increase factor, and each column of the target acquisition matrix is ​​copied by the column dimensionality increase factor to obtain the dimensionality-increased acquisition matrix.

[0193] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0194] For each of the multiple buses, based on the target acquisition matrix and the weights corresponding to the current bus, determine the augmented matrix corresponding to the current bus; based on the target acquisition matrix and the augmented matrix corresponding to the current bus, determine the reference matrix corresponding to the current bus; based on the augmented matrix corresponding to the current bus, determine the first fault indicator corresponding to the current bus; based on the reference matrix corresponding to the current bus, determine the second fault indicator corresponding to the current bus; based on the first fault indicator and the second fault indicator corresponding to each bus, determine the bus that has experienced a fault.

[0195] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0196] For each of the multiple buses, obtain the square of the difference between the first fault indicator and the second fault indicator corresponding to the current bus; sum the squares of the differences in each cycle within a preset time period to obtain the summation result corresponding to the current bus; determine the bus corresponding to the maximum value of the summation result as the bus that has experienced a fault.

[0197] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0198] Obtain multiple eigenvalues ​​of the normalized matrix; use the quotient between the largest eigenvalue and the geometric mean of the multiple eigenvalues ​​as the initial fault detection index.

[0199] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0200] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0201] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0202] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A power distribution network fault detection method characterized by, The method comprises: Periodically acquiring collection data of each bus in a plurality of buses in a power distribution network; Normalizing a target collection matrix to obtain a normalized matrix, the target collection matrix being composed of collection data of a current period and collection data of each period within a preset time length before the current period; Determining an initial fault detection index based on eigenvalues of the normalized matrix; In a case where the initial fault detection index exceeds a preset index threshold, acquiring a fault voltage; based on the fault voltage, performing dimension augmentation on the target collection matrix to determine an augmented collection matrix; Based on the augmented collection matrix, updating the initial fault detection index; in a case where the updated fault detection index exceeds the preset index threshold, determining that the power distribution network has a fault; The method comprises: Based on the fault voltage, obtaining a true value voltage through state estimation; Acquiring a normal voltage under normal operation of the power distribution network; Taking a difference between the normal voltage and the fault voltage as a fault signal; Taking a difference between the fault voltage and the true value voltage as a noise signal; Based on the fault signal and the noise signal, determining a signal-to-noise ratio; Based on the signal-to-noise ratio, performing dimension augmentation on the target collection matrix to determine an augmented collection matrix.

2. The method of claim 1, wherein, The method comprises: Based on the signal-to-noise ratio and a mapping relationship between the signal-to-noise ratio and a dimension augmentation multiple, determining a dimension augmentation multiple, the dimension augmentation multiple comprising a row dimension augmentation multiple and a column dimension augmentation multiple; Copying each row of data of the target collection matrix by the row dimension augmentation multiple, and copying each column of data of the target collection matrix by the column dimension augmentation multiple to obtain the augmented collection matrix.

3. The method of claim 1, wherein, After determining that the power distribution network has a fault, the method further comprises: For each bus in the plurality of buses, determining an augmented matrix corresponding to the current bus based on the target collection matrix and a weight corresponding to the current bus; determining a reference matrix corresponding to the current bus based on the target collection matrix and the augmented matrix corresponding to the current bus; determining a first fault index corresponding to the current bus based on the augmented matrix corresponding to the current bus; determining a second fault index corresponding to the current bus based on the reference matrix corresponding to the current bus; Based on the first fault index corresponding to each bus and the second fault index corresponding to each bus, determining a bus that has a fault.

4. The method of claim 3, wherein, The method comprises: For each bus in the plurality of buses, acquiring a square of a difference between the first fault index corresponding to the current bus and the second fault index corresponding to the current bus; summing the square of the difference under each period within the preset time length to obtain a summation result corresponding to the current bus; Determining a bus corresponding to a maximum value of the summation result as a bus that has a fault.

5. The method of claim 1, wherein, The method comprises: obtaining a plurality of eigenvalues of the normalized matrix; taking a quotient between a maximum eigenvalue in the plurality of eigenvalues and a geometric mean of the plurality of eigenvalues as an initial fault detection index.

6. A power distribution network fault detection apparatus characterized by, The apparatus comprises: a data obtaining module configured to periodically obtain collected data of each bus in a plurality of buses in a power distribution network; a normalization module configured to perform normalization processing on a target collected matrix to obtain a normalized matrix, the target collected matrix being composed of collected data of a current period and collected data of each period within a preset time length before the current period; an initial index determining module configured to determine an initial fault detection index based on eigenvalues of the normalized matrix; a dimension increasing module configured to, in a case where the initial fault detection index exceeds a preset index threshold, obtain a fault voltage, perform dimension increasing on the target collected matrix based on the fault voltage to determine a dimension-increased collected matrix; a fault determining module configured to update the initial fault detection index based on the dimension-increased collected matrix, and determine that the power distribution network has a fault in a case where an updated fault detection index exceeds the preset index threshold; the dimension increasing module is further configured to obtain a true value voltage through state estimation based on the fault voltage, obtain a normal voltage of the power distribution network in normal operation, take a difference between the normal voltage and the fault voltage as a fault signal, take a difference between the fault voltage and the true value voltage as a noise signal, determine a signal-to-noise ratio based on the fault signal and the noise signal, and perform dimension increasing on the target collected matrix based on the signal-to-noise ratio to determine a dimension-increased collected matrix. 7.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-6 when the computer program is executed by the processor. The processor, when executing the computer program, implements the steps of the method of any one of claims 1 to 5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by the processor, implements the steps of the method of any one of claims 1 to 5.

9. A computer program product comprising a computer program, characterized in that, The computer program, when executed by the processor, implements the steps of the method of any one of claims 1 to 5.

Images