CN116087683A

CN116087683A - Power distribution network fault detection method, device, computer equipment and storage medium

Info

Publication number: CN116087683A
Application number: CN202211624192.4A
Authority: CN
Inventors: 杨宇翔; 林长盛; 黄光磊; 刘雪飞; 李俊; 田启东; 胡明曜
Original assignee: Shenzhen Power Supply Bureau Co Ltd
Current assignee: Shenzhen Power Supply Bureau Co Ltd
Priority date: 2022-12-15
Filing date: 2022-12-15
Publication date: 2023-05-09

Abstract

The application relates to a power distribution network fault detection method, a device, a computer device, a storage medium and a computer program product. The method comprises the following steps: periodically acquiring acquisition data of each bus in a plurality of buses in a power distribution network; normalizing the target acquisition matrix to obtain a normalized matrix, wherein the target acquisition matrix consists of acquisition data of a current period and acquisition data of each period in a preset time period before the current period; determining an initial fault detection index based on the eigenvalue of the normalized matrix; acquiring fault voltage under the condition that the initial fault detection index exceeds a preset index threshold value; based on the fault voltage, the dimension of the target acquisition matrix is increased, and the acquisition matrix after dimension increase is determined; updating an initial fault detection index based on the acquisition matrix after dimension increase; and under the condition that the updated fault detection index exceeds a preset index threshold value, determining that the power distribution network has faults. By adopting the method, the accuracy of power distribution network fault detection can be improved.

Description

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

Technical Field

The present application relates to the field of power distribution network technologies, and in particular, to a power distribution network fault detection method, a device, a computer device, a storage medium, and a computer program product.

Background

In a power system, a power distribution network is an important end link and directly supplies electric energy to various users. With the development of power systems, the power grid scale is larger and larger, the duty ratio of new energy is increased continuously, and in order to ensure safe and reliable operation of a large-scale power grid, it is important to detect faults of the power distribution network timely and accurately after various power system faults occur.

The existing power distribution network fault detection method often judges whether a power distribution network has faults or not by detecting key data when the power distribution network operates. However, under the influence of factors such as communication problems and electromagnetic interference, measurement noise or bad data exists in the data acquisition process, so that missed judgment or misjudgment occurs. Therefore, the existing power distribution network fault detection method has the problem of low power distribution network fault detection accuracy.

Disclosure of Invention

Based on this, it is necessary to provide a power distribution network fault detection method, apparatus, computer device, computer readable storage medium and computer program product capable of improving the power distribution network fault detection accuracy, aiming at the problem of low fault detection accuracy in the existing power distribution network fault detection method.

In a first aspect, the present application provides a power distribution network fault detection method. The method comprises the following steps:

periodically acquiring acquisition data of each bus in a plurality of buses in a power distribution network;

normalizing the target acquisition matrix to obtain a normalized matrix, wherein the target acquisition matrix consists of acquisition data of a current period and acquisition data of each period in a preset time period before the current period;

determining an initial fault detection index based on the eigenvalue of the normalized matrix;

acquiring fault voltage under the condition that the initial fault detection index exceeds a preset index threshold value; based on the fault voltage, the dimension of the target acquisition matrix is increased, and the acquisition matrix after dimension increase is determined;

updating an initial fault detection index based on the acquisition matrix after dimension increase; and under the condition that the updated fault detection index exceeds a preset index threshold value, determining that the power distribution network has faults.

In one embodiment, the step of increasing the dimension of the target acquisition matrix based on the fault voltage, and determining the increased dimension acquisition matrix includes:

based on the fault voltage, obtaining a true value voltage through state estimation;

acquiring normal voltage of normal operation of a power distribution network;

taking the difference between the normal voltage and the fault voltage as a fault signal;

Taking the difference between the fault voltage and the true value voltage as a noise signal;

determining a signal-to-noise ratio based on the fault signal and the noise signal;

and based on the signal-to-noise ratio, the dimension of the target acquisition matrix is increased, and the acquisition matrix after dimension increase is determined.

In one embodiment, the step of increasing the dimension of the target acquisition matrix based on the signal-to-noise ratio, and the step of determining the increased dimension acquisition matrix includes:

based on the signal-to-noise ratio and the mapping relation between the signal-to-noise ratio and the dimension-increasing multiple, determining the dimension-increasing multiple comprising a row dimension-increasing multiple and a column dimension-increasing multiple;

and respectively copying row dimension increasing multiples of each row of data of the target acquisition matrix, and respectively copying column dimension increasing multiples of each column of data of the target acquisition matrix to obtain the acquisition matrix after dimension increasing.

In one embodiment, after determining that the power distribution network has a fault, the method further includes:

for each busbar in the plurality of busbars, determining an augmentation matrix corresponding to the current busbar based on the target acquisition matrix and the weight corresponding to the current busbar; determining a reference matrix corresponding to the current bus based on the target acquisition matrix and the augmentation matrix corresponding to the current bus; determining a first fault index corresponding to the current bus based on the augmentation 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;

And determining the bus with faults based on the first fault index corresponding to each bus and the second fault index corresponding to each bus.

In one embodiment, determining a bus that fails based on a first failure index corresponding to each bus and a second failure index corresponding to each bus includes:

for each bus of the plurality of buses, obtaining the square of the difference between a first fault index corresponding to the current bus and a second fault index corresponding to the current bus; summing squares of differences in each period in a preset duration to obtain a summation result corresponding to the current bus;

and determining the bus corresponding to the maximum value of the summation result as the bus with faults.

In one embodiment, determining the initial fault detection indicator based on the eigenvalues of the normalized matrix includes:

acquiring a plurality of eigenvalues of a normalization matrix;

and taking the quotient between the maximum characteristic value in the plurality of characteristic values and the geometric average value of the plurality of characteristic values as an initial fault detection index.

In a second aspect, the application further provides a power distribution network fault detection device. The device comprises:

the data acquisition module is used for periodically acquiring acquisition data of each bus in the plurality of buses in the power distribution network;

The normalization module is used for carrying out normalization processing on a target acquisition matrix to obtain a normalization matrix, wherein the target acquisition matrix consists of acquisition data of a current period and acquisition data of each period in a preset time period before the current period;

the initial index determining module is used for determining an initial fault detection index based on the characteristic value of the normalization matrix;

the dimension increasing module is used for acquiring fault voltage under the condition that the initial fault detection index exceeds a preset index threshold value; based on the fault voltage, the dimension of the target acquisition matrix is increased, and the acquisition matrix after dimension increase is determined;

the fault determining module is used for updating the initial fault detection index based on the acquisition matrix after the dimension increase; and under the condition that the updated fault detection index exceeds a preset index threshold value, determining that the power distribution network has faults.

In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:

In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:

In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:

According to the power distribution network fault detection method, the power distribution network fault detection device, the computer equipment, the storage medium and the computer program product, the acquisition data of each bus in the plurality of buses in the power distribution network are periodically acquired, the target acquisition matrix is subjected to normalization processing to obtain the normalization matrix, and the initial fault detection index is determined based on the characteristic value of the normalization matrix. Under the condition that the initial fault detection index exceeds a preset index threshold value, the fault of the power distribution network is initially determined, the fault voltage is acquired, the dimension of the target acquisition matrix is increased based on the fault voltage, the acquisition matrix after dimension increase is determined, then the initial fault detection index is updated based on the acquisition matrix after dimension increase, the fault of the power distribution network is determined under the condition that the updated fault detection index exceeds the preset index threshold value, the influence of noise on the real state of the power distribution network is weakened after dimension increase, and the accuracy of power distribution network fault detection is improved.

Drawings

FIG. 1 is an application environment diagram of a power distribution network fault detection method in one embodiment;

FIG. 2 is a flow chart of a method of detecting a power distribution network fault in one embodiment;

FIG. 3 is a schematic diagram of a sub-process of S204 in one embodiment;

FIG. 4 is a schematic diagram of a sub-process of S308 in one embodiment;

FIG. 5 is a schematic diagram of a sub-process of S205 in one embodiment;

FIG. 6 is a schematic diagram of an IEEE standard example wiring of a power distribution network in one embodiment;

FIG. 7 is a general flow diagram of a method of power distribution network fault detection in one embodiment;

FIG. 8 is a block diagram of a power distribution network fault detection device in one embodiment;

fig. 9 is an internal structural diagram of a computer device in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.

The power distribution network fault detection method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the distribution network 104 via a network. The data storage system may store data that the server needs to process. The data storage system may be integrated on a server or may be placed on a cloud or other network server. The method for detecting the fault of the power distribution network provided in the embodiment of the present application may be executed by the terminal 102 or the server alone, or may be executed by the terminal 102 and the server cooperatively, so that the terminal 102 alone performs the following steps: periodically acquiring acquisition data of each bus in a plurality of buses in a power distribution network; normalizing the target acquisition matrix to obtain a normalized matrix, wherein the target acquisition matrix consists of acquisition data of a current period and acquisition data of each period in a preset time period before the current period; determining an initial fault detection index based on the eigenvalue of the normalized matrix; acquiring fault voltage under the condition that the initial fault detection index exceeds a preset index threshold value; based on the fault voltage, the dimension of the target acquisition matrix is increased, and the acquisition matrix after dimension increase is determined; updating an initial fault detection index based on the acquisition matrix after dimension increase; and under the condition that the updated fault detection index exceeds a preset index threshold value, determining that the power distribution network has faults. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices, where the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The server may be implemented as a stand-alone server or as a server cluster composed of a plurality of servers.

In one embodiment, as shown in fig. 2, a method for detecting a fault in a power distribution network is provided, and the method is applied to a computer device (the computer device may be the terminal 102 or the server in fig. 1) for illustration, and includes the following steps:

s201, periodically acquiring acquisition data of each bus in a plurality of buses in the power distribution network.

The bus is made of high-conductivity metal materials, is used for transmitting electric energy, has the capability of collecting and distributing electric power, and is a total wire for transmitting electric energy by a power distribution station or a transformer substation. And the electric energy output by the generator, the transformer or the rectifier is transmitted to each user or other power substations through the bus. The distribution network comprises a plurality of buses. The bus for collecting data collects the electrical data, and the types of the collected data include, but are not limited to, voltage, current, voltage amplitude and power angle. And the computer equipment periodically acquires acquisition data of each bus in the plurality of buses in the power distribution network.

S202, normalizing the target acquisition matrix to obtain a normalized matrix, wherein the target acquisition matrix consists of acquisition data of the current period and acquisition data of each period in a preset time period before the current period.

The target acquisition matrix consists of acquisition data of a current period and acquisition data of each period in a preset time period before the current period. The normalization process refers to transforming each element in the target acquisition matrix so as to map to the same scale. In some embodiments, the target acquisition matrix is normalized to obtain a normalized matrix, specifically, the target acquisition matrix is normalized to obtain a normalized matrix, and the covariance matrix of the normalized matrix is determined as the normalized matrix. And carrying out standardization processing on the target acquisition matrix, wherein the standardization processing is shown in the following formula:

wherein: x is X _1,i Is an element in the standardized matrix; mu (X) _i ) The average value of the ith row element in the matrix is acquired for the target; sigma (X) _i ) The standard deviation of the ith row element in the matrix is acquired for the target.

The normalized matrix satisfies a distribution with a mean value of 0 and a standard deviation of 1. Further solving covariance matrix of the normalized matrix, wherein the covariance matrix is represented by the following formula:

R＝X ₁ X ₁ ^T

wherein: r is a normalization matrix; x is X ₁ ^T Is the transpose of the normalized matrix.

The normalized matrix obtained was non-Hermitian (non-hermitian matrix) matrix. When the number of rows and columns of the normalized matrix are all tend to be infinite, the row-column ratio of the normalized matrix is more than 0 and less than or equal to 1, and each element in the normalized matrix is a random variable meeting independent same distribution, the characteristic value distribution of the singular value equivalent matrix of the normalized matrix is that the radius of the inner ring is (1-c) ^L/2 And the radius of the outer ring is 1, and the limit spectrum distribution function of the matrix is shown in the following formula:

wherein Z is _std Representing the multiplication of L non-Hermitian matrices;

is a matrix Z _std Is a characteristic value of (2); c=n/T, representing the matrix rank ratio.

S203, determining an initial fault detection index based on the eigenvalue of the normalized matrix.

Wherein the computer device obtains a plurality of eigenvalues of the normalized matrix. The computer device determines an initial fault detection indicator by normalizing the eigenvalues of the matrix. The initial fault detection indicator is used to characterize the degree to which the maximum eigenvalue deviates from the average eigenvalue.

S204, acquiring fault voltage under the condition that the initial fault detection index exceeds a preset index threshold value; and based on the fault voltage, the dimension of the target acquisition matrix is increased, and the acquisition matrix after dimension increase is determined.

When no fault occurs in the power distribution network, the initial fault detection index calculated by the normalization matrix is lower than a preset index threshold, and if the acquired data of the bus of the power distribution network fluctuates due to the fault of the power distribution network, the initial fault detection index calculated by the normalization matrix can exceed the preset index threshold. And under the condition that the initial fault detection index exceeds a preset index threshold value, acquiring fault voltage. And under the condition that the initial fault detection index exceeds a preset index threshold value, the fault voltage is the acquisition voltage of the power distribution network bus acquired by the computer equipment.

The dimension increase means that the rows or columns of the target acquisition matrix are duplicated, so that the rows or columns of the target acquisition matrix are increased, and the acquisition matrix after dimension increase is obtained. The multiple of the dimension increase may be determined by the fault voltage.

S205, updating an initial fault detection index based on the acquisition matrix after dimension increase; and under the condition that the updated fault detection index exceeds a preset index threshold value, determining that the power distribution network has faults.

The number of rows or columns of the acquisition matrix after the dimension increase is larger than that of the normalization matrix, and the computer equipment updates the initial fault detection index based on the acquisition matrix after the dimension increase. And under the condition that the updated fault detection index exceeds a preset index threshold value, the computer equipment determines that the power distribution network has faults. The influence of noise on the real electric quantity data of the power distribution network is weakened after the maintenance is increased, the real information of the electric quantity of each node can be mined in the calculation of the fault detection index, and the updated fault detection index has higher accuracy.

According to the power distribution network fault detection method, the acquisition data of each bus in the plurality of buses in the power distribution network are periodically acquired, the target acquisition matrix is normalized, the normalized matrix is obtained, and the initial fault detection index is determined based on the characteristic value of the normalized matrix. Under the condition that the initial fault detection index exceeds a preset index threshold value, the fault of the power distribution network is initially determined, the fault voltage is acquired, the dimension of the target acquisition matrix is increased based on the fault voltage, the acquisition matrix after dimension increase is determined, then the initial fault detection index is updated based on the acquisition matrix after dimension increase, the fault of the power distribution network is determined under the condition that the updated fault detection index exceeds the preset index threshold value, the influence of noise on the real state of the power distribution network is weakened after dimension increase, and the accuracy of power distribution network fault detection is improved.

In one embodiment, as shown in fig. 3, the step of increasing the dimension of the target acquisition matrix based on the fault voltage, and determining the increased dimension acquisition matrix includes:

s302, obtaining a true voltage through state estimation based on the fault voltage.

The state estimation is a method for estimating the internal state of the dynamic system according to the available measurement data. The data obtained by measuring the input and output of the system can only reflect the external characteristics of the system, and the dynamic law of the system needs to be described by internal (usually not directly measured) state variables, so that the state estimation has important significance for knowing and controlling a system. The true voltage is based on the fault voltage through state estimation. The difference between the fault voltage and the true voltage is the noise voltage.

S304, obtaining the normal voltage of the normal operation of the power distribution network.

The computer equipment obtains the voltage of the power distribution network in normal operation, namely the normal voltage. In some embodiments, the voltage of each bus of the plurality of buses of the power distribution network can be obtained when the bus works normally.

S306, taking the difference between the normal voltage and the fault voltage as a fault signal; taking the difference between the fault voltage and the true value voltage as a noise signal; based on the fault signal and the noise signal, a signal-to-noise ratio is determined.

The computer equipment takes the difference between the normal voltage and the fault voltage as a fault signal and takes the difference between the fault voltage and the true voltage as a noise signal. The computer device determines a signal-to-noise ratio based on the fault signal and the noise signal. The formula for calculating the signal-to-noise ratio is as follows:

wherein V is _S And V _N Voltages representing the fault signal and the noise signal, respectively; SNR stands for signal-to-noise ratio.

And S308, performing dimension increase on the target acquisition matrix based on the signal-to-noise ratio, and determining the acquisition matrix after dimension increase.

And determining the dimension increase multiple based on the signal-to-noise ratio, and increasing the dimension of the target acquisition matrix through the dimension increase multiple to obtain the acquisition matrix after the dimension increase.

In this embodiment, the true voltage is obtained by the fault voltage and the state estimation, 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. And determining a signal-to-noise ratio based on the fault signal and the noise signal, increasing the dimension of the target acquisition matrix based on the signal-to-noise ratio, and determining the acquisition matrix after the dimension increase. Because the condition of detection failure is easy to exist in the low signal-to-noise ratio environment, the accuracy of power distribution network fault detection is reduced, and therefore, the problem of fault detection omission judgment in the low signal-to-noise ratio environment is solved by adopting a dimension increasing method. The method for determining the signal to noise ratio by obtaining the true value voltage through the state estimation has higher accuracy in the signal to noise ratio, so that the dimension of the target acquisition matrix is increased, and the dimension is increased according to the scenes of different signal to noise ratios, thereby being beneficial to improving the accuracy of the fault detection of the power distribution network.

In one embodiment, as shown in fig. 4, the step of increasing the dimension of the target acquisition matrix based on the signal-to-noise ratio, and determining the increased dimension acquisition matrix includes:

s402, based on the signal-to-noise ratio and the mapping relation between the signal-to-noise ratio and the dimension-increasing multiple, determining the dimension-increasing multiple, wherein the dimension-increasing multiple comprises a row dimension-increasing multiple and a column dimension-increasing multiple.

The mapping relation between the signal to noise ratio and the dimension increase multiple is used for indicating the magnitude relation between the signal to noise ratio and the dimension increase multiple and is determined according to a historical experiment. And the computer equipment brings the signal-to-noise ratio into the mapping relation between the signal-to-noise ratio and the dimension-increasing multiple to obtain the dimension-increasing multiple. The dimension-increasing multiple comprises a row dimension-increasing multiple and a column dimension-increasing multiple. In some embodiments, through a large number of simulation experiments, it is concluded that when the signal-to-noise ratio of the noise signal and the fault signal is greater than 5dB, the dimension-increasing processing of the target acquisition matrix is not needed; when the signal-to-noise ratio of the noise signal and the fault signal is between 3dB and 5dB, the expected effect can be achieved by carrying out 5 multiplication on the dimension of the target acquisition matrix; when the signal to noise ratio of the noise signal and the fault signal is smaller than 3dB, the target acquisition matrix dimension is optimally subjected to 10 multiplication dimensions.

S404, respectively copying row dimension increasing multiples of each row data of the target acquisition matrix, respectively copying column dimension increasing multiples of each column data of the target acquisition matrix, and obtaining the acquisition matrix after dimension increasing.

The computer equipment respectively copies the row data and the column data of the target acquisition matrix by the row dimension increasing multiple to obtain the acquisition matrix after dimension increasing.

In this embodiment, the dimension increase multiple is determined based on the signal-to-noise ratio and the mapping relationship between the signal-to-noise ratio and the dimension increase multiple, each row of data of the target acquisition matrix is copied to the row dimension increase multiple, and each column of data of the target acquisition matrix is copied to the column dimension increase multiple, so as to obtain the acquisition matrix after dimension increase. The method for determining the dimension increase multiple through the mapping relation between the signal to noise ratio and the dimension increase multiple is beneficial to improving the accuracy of the fault detection of the power distribution network by determining the optimal dimension increase multiple according to the actual test condition because the signal to noise ratio is different in different power distribution network noise environments.

In one embodiment, as shown in fig. 5, after determining that the power distribution network has a fault, the method further includes:

s502, determining an augmentation matrix corresponding to the current bus based on the target acquisition matrix and the weight corresponding to the current bus for each bus in the plurality of buses; determining a reference matrix corresponding to the current bus based on the target acquisition matrix and the augmentation matrix corresponding to the current bus; determining a first fault index corresponding to the current bus based on the augmentation matrix corresponding to the current bus; and determining a second fault index corresponding to the current bus based on the reference matrix corresponding to the current bus.

Where after determining that a power distribution network has a fault, it is often also necessary to determine which bus in particular has the fault. The computer equipment determines an augmentation matrix corresponding to the current bus based on the target acquisition matrix and the weight corresponding to the current bus for each bus in the plurality of buses. Specifically, since the target acquisition matrix includes acquired data of a plurality of buses, the weight corresponding to the current bus is set as a preset weight, so that the data corresponding to the current bus is copied into a preset weight row, the copied data is located below the data corresponding to the current bus, and the obtained matrix is the augmentation matrix corresponding to the current bus. The dimension of the augmentation matrix corresponding to the current bus is larger than the dimension of the target acquisition matrix. And sequentially amplifying each bus in the plurality of buses to obtain an amplification matrix corresponding to each bus.

The computer equipment determines a reference matrix corresponding to the current bus based on the target acquisition matrix and the augmentation matrix corresponding to the current bus. The computer equipment obtains the dimension corresponding to the augmentation matrix corresponding to the current bus and determines the dimension of the reference matrix corresponding to the current bus. Subtracting the dimension of the target acquisition matrix from the dimension of the reference matrix corresponding to the current bus, and taking the obtained result as the dimension of the random noise matrix. The computer device generates a random noise matrix based on the dimensions of the random noise matrix. Each element in the random noise matrix conforms to a gaussian distribution.

The computer equipment determines a first fault index corresponding to the current bus based on the augmentation matrix corresponding to the current bus; and determining a second fault index corresponding to the current bus based on the reference matrix corresponding to the current bus. Specifically, the computer equipment performs normalization processing on the augmentation matrix corresponding to the current bus to obtain a first normalization matrix, and determines a first fault index based on a characteristic value of the first normalization matrix. And the computer equipment performs normalization processing on the reference matrix corresponding to the current bus to obtain a second normalization matrix, and determines a second fault index based on the second normalization matrix.

S504, determining the bus with faults based on the first fault index corresponding to each bus and the second fault index corresponding to each bus.

The method comprises the steps that for any bus in a plurality of buses, the computer equipment obtains the Euclidean distance between a first fault index corresponding to the current bus and a corresponding second fault index, and the bus with the largest Euclidean distance is determined to be the bus with the fault.

In this embodiment, by amplifying each bus of the plurality of buses to obtain an amplified matrix corresponding to each bus, and determining the first fault index and the second fault index based on the amplified matrix and the reference matrix, thereby determining the bus with fault.

In one embodiment, determining a faulty bus based on a first fault indicator corresponding to each bus and a second fault indicator corresponding to each bus includes: for each bus of the plurality of buses, obtaining the square of the difference between a first fault index corresponding to the current bus and a second fault index corresponding to the current bus; summing squares of differences in each period in a preset duration to obtain a summation result corresponding to the current bus; and determining the bus corresponding to the maximum value of the summation result as the bus with faults.

Wherein, for each bus of the plurality of buses, the computer device obtains a square of a difference between a first fault indicator corresponding to the current bus and a second fault indicator corresponding to the current bus. And summing the squares of the differences in each period in the preset duration to obtain a summation result corresponding to the current bus. And obtaining the summation result corresponding to each bus. The summation result corresponding to each bus is used for indicating the Euclidean distance between the augmentation matrix corresponding to each bus and the reference matrix. And the terminal determines the bus corresponding to the maximum value of the summation result as the bus with faults.

In this embodiment, by obtaining the square of the difference between the first fault index and the second fault index corresponding to each bus, the bus corresponding to the maximum value of the sum of squares of the differences in each period within the preset time period is determined as the bus with the fault, and the method for determining the bus with the fault in the power distribution network improves the precision and accuracy of the power distribution network fault detection.

In one embodiment, determining the initial fault detection indicator based on the eigenvalues of the normalized matrix includes: acquiring a plurality of eigenvalues of a normalization matrix; and taking the quotient between the maximum characteristic value in the plurality of characteristic values and the geometric average value of the plurality of characteristic values as an initial fault detection index.

The computer equipment acquires a plurality of eigenvalues of the normalized matrix, arranges the eigenvalues according to the order of magnitude, determines the maximum eigenvalue in the eigenvalues, and acquires the geometric average value of the eigenvalues. And taking the quotient between the maximum characteristic value in the plurality of characteristic values and the geometric average value of the plurality of characteristic values as an initial fault detection index. In some embodiments, when the preset duration is long, the eigenvalues of the normalized matrix satisfy the following formula:

wherein: sigma (sigma) _v ² Is the variance of the noise matrix Q, lambda _i Representing a plurality of eigenvalues of a normalized matrix, lambda _Max Represents the maximum eigenvalue, lambda, of the plurality of eigenvalues _Min Representing the minimum feature value among a plurality of feature values, T _w And N represents the number of columns and rows of the normalized matrix respectively,

representing the geometric mean of the plurality of feature values.

/>

Wherein MGME represents an initial failure detection indicator.

In this embodiment, by acquiring a plurality of eigenvalues of the normalized matrix, and taking a quotient between a maximum eigenvalue of the plurality of eigenvalues and a geometric average value of the plurality of eigenvalues as an initial fault detection index, the method for determining the initial fault detection index of the power distribution network by the eigenvalues of the normalized matrix can primarily determine whether the power distribution network has a fault.

In order to describe the power distribution network fault detection method and effect in detail, the following description is made by using one most detailed embodiment:

and the computer equipment periodically acquires acquisition data of each bus in the plurality of buses in the power distribution network. Fig. 6 shows an IEEE (Institute of Electrical and Electronics Engineers ) standard example wiring diagram of the distribution network. And carrying out normalization processing on the target acquisition matrix to obtain a normalization matrix, wherein the target acquisition matrix consists of acquisition data of the current period and acquisition data of each period in a preset time period before the current period. And determining an initial fault detection index based on the eigenvalue of the normalization matrix, and acquiring fault voltage under the condition that the initial fault detection index exceeds a preset index threshold. Fig. 7 is a general flow chart of a fault detection method of the power distribution network.

And based on the fault voltage, the dimension of the target acquisition matrix is increased, and the acquisition matrix after dimension increase is determined. Specifically, based on the fault voltage, a true voltage is obtained through state estimation, a normal voltage of normal operation of the power distribution network is obtained, the difference between the normal voltage and the fault voltage is used as a fault signal, and the difference between the fault voltage and the true voltage is used as a noise signal. Based on the fault signal and the noise signal, a signal-to-noise ratio is determined. And determining the dimension increase multiple based on the signal-to-noise ratio and the mapping relation between the signal-to-noise ratio and the dimension increase multiple, wherein the dimension increase multiple comprises a row dimension increase multiple and a column dimension increase multiple. And respectively copying row dimension increasing multiples of each row of data of the target acquisition matrix, and respectively copying column dimension increasing multiples of each column of data of the target acquisition matrix to obtain the acquisition matrix after dimension increasing.

Illustratively, the dimension of the target acquisition matrix is NxT _w The target acquisition matrix is as follows:

the row dimension of the matrix is increased by m times, the column dimension is increased by N times, and the dimension of the matrix after processing is (m x N) x (N x T) _w ) Acquisition matrix after dimension increase

The following are provided:

if the increment quantity is too small, the progressive convergence condition of the matrix dimension cannot be met; if the number of the increment is too large, the fault detection speed is reduced, and the real-time performance of fault detection cannot be ensured, so that the self-adaptive rank replication ratio method is provided. The number of matrix dimensions is different due to the difference of signal to noise ratios when different faults occur, namely the number of matrix dimensions is changed along with the difference of the signal to noise ratios of the faults, and after a large number of simulations, a conclusion is obtained: by the self-adaptive dimension increasing method for fault detection according to the signal-to-noise ratio during fault, the dimension of the matrix can be increased, and the condition of gradual convergence can be met, and the requirement of real-time fault detection can be met. The matrix after the dimension increase does not destroy the original data structure, and the dimension of the matrix is increased while the space-time distribution characteristics of the target acquisition matrix are saved.

And updating the initial fault detection index based on the acquisition matrix after the dimension increase. The error of the calculated updated initial fault detection index is smaller than that of the initial fault detection index, so that in the calculation process of the initial fault detection index, the fault detection by adopting the matrix after dimension increase is obviously reduced compared with the detection miss rate by adopting the target acquisition matrix. And under the condition that the updated fault detection index exceeds a preset index threshold value, determining that the power distribution network has faults.

After the computer equipment determines that the power distribution network has faults, determining an augmentation matrix corresponding to the current bus based on the target acquisition matrix and the weight corresponding to the current bus for each bus in the plurality of buses; determining a reference matrix corresponding to the current bus based on the target acquisition matrix and the augmentation matrix corresponding to the current bus; determining a first fault index corresponding to the current bus based on the augmentation matrix corresponding to the current bus; and determining a second fault index corresponding to the current bus based on the reference matrix corresponding to the current bus. For each bus of the plurality of buses, obtaining the square of the difference between a first fault index corresponding to the current bus and a second fault index corresponding to the current bus; and summing squares of differences in each period within a preset duration to obtain a summation result corresponding to the current bus, and determining the bus corresponding to the maximum value of the summation result as the bus with faults.

An augmentation random matrix is constructed based on the target acquisition matrix, the augmentation random matrix reflects the influence of the concerned variable on the system, meanwhile, a reference random matrix with the same dimension as the augmentation random matrix is constructed to serve as a reference, and the influence of the concerned physical quantity on the whole system is represented by comparing the difference of the characteristic values of the two matrices. The construction of the augmented random matrix is shown as follows:

Wherein: x is X _r A P x T weight matrix is represented, where P is the number of rows that need to be replicated.

For node i of interest, row vector x is selected _i And duplicate P times to construct a weight matrix X _r ：

X _r ＝[x _i ¹ ，x _i ² ，x _i ³ …x _i ^P ] ^T

On the other hand, we can construct a reference matrix X _C ：

Wherein: n (N) ₃ Is provided with sum X _r Gaussian white noise matrix of the same dimension.

And constructing an augmentation matrix by using different bus voltage data of the power distribution network, comparing the augmentation matrix with a reference random matrix, and considering that a bus with a large Euclidean distance is a bus with a fault.

The bus with the fault of the power distribution network is determined based on the fault moment of the updated fault detection index, so that the system abnormality can be found timely. The fault region positioning method based on the augmentation matrix can accurately position the suspicious fault region by comparing Euclidean distances between the augmentation matrix of different influence factors and fault detection indexes corresponding to the reference matrix, and is beneficial to the fault detection.

It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides a power distribution network fault detection device for realizing the power distribution network fault detection method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the fault detection device for a power distribution network provided below may be referred to the limitation of the fault detection method for a power distribution network hereinabove, and will not be described herein.

In one embodiment, as shown in fig. 8, there is provided a power distribution network fault detection apparatus 100, including: a data acquisition module 110, a normalization module 120, an initial indicator determination module 130, a dimension-enhancement module 140, and a fault determination module 150, wherein:

the data acquisition module 110 is configured to periodically acquire acquired data of each of a plurality of buses in the power distribution network;

the normalization module 120 is configured to normalize a target acquisition matrix to obtain a normalized matrix, where the target acquisition matrix is composed of acquisition data of a current period and acquisition data of each period in a preset duration before the current period;

an initial indicator determining module 130, configured to determine an initial fault detection indicator based on the eigenvalue of the normalized matrix;

the dimension increasing module 140 is configured to obtain a fault voltage when the initial fault detection indicator exceeds a preset indicator threshold; based on the fault voltage, the dimension of the target acquisition matrix is increased, and the acquisition matrix after dimension increase is determined;

the fault determining module 150 is configured to update an initial fault detection index based on the increased acquisition matrix; and under the condition that the updated fault detection index exceeds a preset index threshold value, determining that the power distribution network has faults.

According to the power distribution network fault detection device, the collected data of each bus in the plurality of buses in the power distribution network are periodically obtained, the target collection matrix is normalized, the normalized matrix is obtained, and the initial fault detection index is determined based on the characteristic value of the normalized matrix. Under the condition that the initial fault detection index exceeds a preset index threshold value, the fault of the power distribution network is initially determined, the fault voltage is acquired, the dimension of the target acquisition matrix is increased based on the fault voltage, the acquisition matrix after dimension increase is determined, then the initial fault detection index is updated based on the acquisition matrix after dimension increase, the fault of the power distribution network is determined under the condition that the updated fault detection index exceeds the preset index threshold value, the influence of noise on the real state of the power distribution network is weakened after dimension increase, and the accuracy of power distribution network fault detection is improved.

In one embodiment, in terms of increasing dimensions of the target acquisition matrix based on the fault voltage, determining the increased dimensions of the acquisition matrix, the dimension increasing module 140 is further configured to: based on the fault voltage, obtaining a true value voltage through state estimation; acquiring normal voltage of normal operation of a power distribution network; taking the difference between the normal voltage and the fault voltage as a fault signal; taking the difference between the fault voltage and the true value voltage as a noise signal; determining a signal-to-noise ratio based on the fault signal and the noise signal; and based on the signal-to-noise ratio, the dimension of the target acquisition matrix is increased, and the acquisition matrix after dimension increase is determined.

In one embodiment, in terms of increasing the dimension of the target acquisition matrix based on the signal-to-noise ratio, determining the increased dimension acquisition matrix, the dimension increasing module 140 is further configured to: based on the signal-to-noise ratio and the mapping relation between the signal-to-noise ratio and the dimension-increasing multiple, determining the dimension-increasing multiple comprising a row dimension-increasing multiple and a column dimension-increasing multiple; and respectively copying row dimension increasing multiples of each row of data of the target acquisition matrix, and respectively copying column dimension increasing multiples of each column of data of the target acquisition matrix to obtain the acquisition matrix after dimension increasing.

In one embodiment, after determining that the power distribution network has a fault, the fault determination module 150 is further configured to: for each busbar in the plurality of busbars, determining an augmentation matrix corresponding to the current busbar based on the target acquisition matrix and the weight corresponding to the current busbar; determining a reference matrix corresponding to the current bus based on the target acquisition matrix and the augmentation matrix corresponding to the current bus; determining a first fault index corresponding to the current bus based on the augmentation 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; and determining the bus with faults based on the first fault index corresponding to each bus and the second fault index corresponding to each bus.

In one embodiment, in determining a faulty bus based on the first fault indicator corresponding to each bus and the second fault indicator corresponding to each bus, the fault determination module 150 is further configured to: for each bus of the plurality of buses, obtaining the square of the difference between a first fault index corresponding to the current bus and a second fault index corresponding to the current bus; summing squares of differences in each period in a preset duration to obtain a summation result corresponding to the current bus; and determining the bus corresponding to the maximum value of the summation result as the bus with faults.

In one embodiment, in determining the initial fault detection indicator based on the eigenvalues of the normalized matrix, the initial indicator determination module 130 is further configured to: acquiring a plurality of eigenvalues of a normalization matrix; and taking the quotient between the maximum characteristic value in the plurality of characteristic values and the geometric average value of the plurality of characteristic values as an initial fault detection index.

The modules in the power distribution network fault detection device can be all or partially realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, a computer device is provided, which may be a terminal, and the internal structure thereof may be as shown in fig. 9. The computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input means. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program, when executed by a processor, implements a method for detecting faults in a power distribution network.

It will be appreciated by those skilled in the art that the structure shown in fig. 9 is merely a block diagram of a portion of the structure associated with the present application and is not limiting of the computer device to which the present application applies, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:

periodically acquiring acquisition data of each bus in a plurality of buses in a power distribution network; normalizing the target acquisition matrix to obtain a normalized matrix, wherein the target acquisition matrix consists of acquisition data of a current period and acquisition data of each period in a preset time period before the current period; determining an initial fault detection index based on the eigenvalue of the normalized matrix; acquiring fault voltage under the condition that the initial fault detection index exceeds a preset index threshold value; based on the fault voltage, the dimension of the target acquisition matrix is increased, and the acquisition matrix after dimension increase is determined; updating an initial fault detection index based on the acquisition matrix after dimension increase; and under the condition that the updated fault detection index exceeds a preset index threshold value, determining that the power distribution network has faults.

In one embodiment, the processor when executing the computer program further performs the steps of:

based on the fault voltage, obtaining a true value voltage through state estimation; acquiring normal voltage of normal operation of a power distribution network; taking the difference between the normal voltage and the fault voltage as a fault signal; taking the difference between the fault voltage and the true value voltage as a noise signal; determining a signal-to-noise ratio based on the fault signal and the noise signal; and based on the signal-to-noise ratio, the dimension of the target acquisition matrix is increased, and the acquisition matrix after dimension increase is determined.

based on the signal-to-noise ratio and the mapping relation between the signal-to-noise ratio and the dimension-increasing multiple, determining the dimension-increasing multiple comprising a row dimension-increasing multiple and a column dimension-increasing multiple; and respectively copying row dimension increasing multiples of each row of data of the target acquisition matrix, and respectively copying column dimension increasing multiples of each column of data of the target acquisition matrix to obtain the acquisition matrix after dimension increasing.

for each busbar in the plurality of busbars, determining an augmentation matrix corresponding to the current busbar based on the target acquisition matrix and the weight corresponding to the current busbar; determining a reference matrix corresponding to the current bus based on the target acquisition matrix and the augmentation matrix corresponding to the current bus; determining a first fault index corresponding to the current bus based on the augmentation 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; and determining the bus with faults based on the first fault index corresponding to each bus and the second fault index corresponding to each bus.

for each bus of the plurality of buses, obtaining the square of the difference between a first fault index corresponding to the current bus and a second fault index corresponding to the current bus; summing squares of differences in each period in a preset duration to obtain a summation result corresponding to the current bus; and determining the bus corresponding to the maximum value of the summation result as the bus with faults.

acquiring a plurality of eigenvalues of a normalization matrix; and taking the quotient between the maximum characteristic value in the plurality of characteristic values and the geometric average value of the plurality of characteristic values as an initial fault detection index.

In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:

In one embodiment, the computer program when executed by the processor further performs the steps of:

In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:

It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data are required to comply with the related laws and regulations and standards of the related countries and regions.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.

Claims

1. A method for detecting a power distribution network fault, the method comprising:

normalizing a target acquisition matrix to obtain a normalized matrix, wherein the target acquisition matrix consists of acquisition data of a current period and acquisition data of each period in a preset time period before the current period;

Determining an initial fault detection index based on the eigenvalue of the normalization matrix;

updating the initial fault detection index based on the increased acquisition matrix; and under the condition that the updated fault detection index exceeds a preset index threshold value, determining that the power distribution network has faults.

2. The method of claim 1, wherein the step of increasing the dimension of the target acquisition matrix based on the fault voltage to determine an increased dimension acquisition matrix comprises:

based on the fault voltage, obtaining a true voltage through state estimation;

acquiring normal voltage of normal operation of a power distribution network;

taking the difference between the fault voltage and the true voltage as a noise signal;

and based on the signal-to-noise ratio, carrying out dimension increase on the target acquisition matrix, and determining the acquisition matrix after dimension increase.

3. The method of claim 2, wherein the step of increasing the dimension of the target acquisition matrix based on the signal-to-noise ratio to determine an increased dimension acquisition matrix comprises:

based on the signal-to-noise ratio and the mapping relation between the signal-to-noise ratio and the dimension-increasing multiple, determining the dimension-increasing multiple, wherein the dimension-increasing multiple comprises a row dimension-increasing multiple and a column dimension-increasing multiple;

and respectively copying the row data and the column data of the target acquisition matrix to obtain the acquisition matrix after dimension increase.

4. The method of claim 1, wherein after determining that the power distribution network has a fault, further comprising:

for each busbar in a plurality of busbars, determining an augmentation matrix corresponding to the current busbar based on the target acquisition matrix and the weight corresponding to the current busbar; determining a reference matrix corresponding to the current bus based on the target acquisition matrix and an augmentation matrix corresponding to the current bus; determining a first fault index corresponding to the current bus based on the augmentation 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;

5. The method of claim 4, wherein determining the failed bus bar based on the first failure indicator corresponding to each bus bar and the second failure indicator corresponding to each bus bar comprises:

for each bus of a plurality of buses, obtaining the square of the difference between a first fault index corresponding to the current bus and a second fault index corresponding to the current bus; summing the squares of the differences in each period within the preset duration to obtain a summation result corresponding to the current bus;

6. The method of claim 1, wherein the determining an initial fault detection indicator based on eigenvalues of the normalized matrix comprises:

acquiring a plurality of characteristic values of the normalization matrix;

taking the quotient between the maximum eigenvalue of the eigenvalues and the geometric mean value of the eigenvalues as an initial fault detection index.

7. A power distribution network fault detection apparatus, the apparatus comprising:

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.

9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.