A method, device and equipment for determining a fault branch of a power collection line of a wind farm

Abstract

The application discloses a wind farm power collection line fault branch determination method and device, a storage medium and an electronic equipment. The method comprises the following steps: acquiring first fault current data sets corresponding to each phase line at the end of each power collection line within a preset time range after a fault occurs; performing power collection line route selection processing based on the first fault current data sets to determine a target power collection line where the fault occurs; acquiring second fault current data sets and fault voltage data sets corresponding to each phase line at the end of the target power collection line within the preset time range after the fault occurs; and performing power collection line branch route selection processing based on the second fault current data sets and the fault voltage data sets to determine a target branch of the target power collection line where the fault occurs. The power collection line fault branch determination method can accurately determine the power collection line fault branch, save the cost of determining the fault branch, and improve the efficiency of determining the fault branch.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wind farm power collection line fault identification, and in particular to a wind farm power collection line fault branch determination method and device, a storage medium and an electronic device. BACKGROUND

[0002] Wind energy is abundant and is a rapidly developing renewable energy. However, a wind farm is a multi-branch power transmission system with a complex topology, short-distance transmission lines and a harsh working environment. The harsh operating conditions result in frequent transmission line faults, reducing wind power generation and limiting the development and utilization of wind energy. In recent studies, the main methods for diagnosing transmission line faults can be divided into three categories: impedance method, traveling wave method and intelligent algorithm-based method. Analysis of existing methods shows that the main factors limiting the diagnostic performance include fault starting angle, fault resistance, fault location, measurement noise and transmission line length. However, due to the difference in transmission line length between the wind farm and the distribution network, the wind farm is mostly composed of short-distance transmission lines. When line faults occur in two adjacent short-distance branches, the short-distance line structure will result in similar fault signal characteristics. In addition, the network structure of the wind farm is more complex than that of the distribution network. The complex multi-branch structure and the asymmetry between the power grid and the unit result in the fault signal being suppressed by both the power grid and the wind turbine. The above methods only focus on the transmission lines of the distribution network and rarely focus on the wind farm, resulting in the above methods being unable to be directly applied to the wind farm, which makes the determination efficiency of the wind farm power collection line fault branch low and the cost high. SUMMARY

[0003] Therefore, the present application provides a wind farm power collection line fault branch determination method, device, storage medium and electronic device, which mainly aims to solve the problems of high cost and low efficiency in determining the wind farm power collection line fault branch.

[0004] To solve the above problems, the present application provides a wind farm power collection line fault branch determination method, which comprises:

[0005] Obtaining a first fault current data set corresponding to each phase line at the end of each power collection line within a predetermined time range after the fault occurs;

[0006] Performing power collection line selection processing based on each first fault current data set to determine the target power collection line that has failed;

[0007] Obtaining a second fault current data set and a fault voltage data set corresponding to each phase line at the end of the target power collection line within a predetermined time range after the fault occurs;

[0008] The second fault current data set and the fault voltage data set are used to determine the target branch of the target DC line.

[0009] Optionally, the DC line selection processing based on the first fault current data set comprises:

[0010] The first fault current data set is processed by a preset vector coordinate transformation method to obtain a component current data set corresponding to each DC line.

[0011] The component current data set is processed by a preset time-frequency analysis method to obtain an energy matrix corresponding to the component current data set.

[0012] The energy matrix is calculated to determine the target DC line.

[0013] Optionally, the calculation of the energy matrix to determine the target DC line comprises:

[0014] A target component current data set corresponding to each DC line is determined based on the target fault current component.

[0015] A similarity coefficient of each target component current data set is calculated to obtain a similarity coefficient matrix corresponding to the target component.

[0016] The similarity coefficient matrix is used to determine the target DC line.

[0017] Optionally, the DC line selection processing based on the similarity coefficient matrix to determine the target DC line comprises:

[0018] Each column of the similarity coefficient matrix is added to obtain a target sub-selection matrix corresponding to the target fault current component, so as to obtain a sub-selection matrix corresponding to each component.

[0019] Each column of the sub-selection matrix is filtered to determine the minimum value of the column similarity coefficient sum in the sub-selection matrix as the fault DC line corresponding to the current sub-selection matrix.

[0020] Each fault DC line is filtered to determine the target fault DC line with the largest probability.

[0021] Optionally, the collector line branch line selection processing based on each of the second fault current data set and each of the fault voltage data set is performed to determine a target branch of the target collector line where the fault occurs, comprising:

[0022] Based on each of the second fault current data set and each of the fault voltage data set, a preset time-frequency analysis method is used for processing to generate a fault current time-frequency matrix corresponding to each of the second fault current data set and a fault voltage time-frequency matrix corresponding to each of the fault voltage data set;

[0023] The fault voltage time-frequency matrix and the fault current time-frequency matrix corresponding to the target phase line of the target sampling end of the target collector line are calculated and processed to obtain a characteristic state matrix corresponding to each phase line of the first end and the last end of the target collector line;

[0024] The collector line branch line selection processing is performed based on each of the characteristic state matrix to determine a target branch of the target collector line where the fault occurs.

[0025] Optionally, the collector line branch line selection processing based on each of the characteristic state matrix to determine a target branch of the target collector line where the fault occurs, comprising:

[0026] Each of the characteristic state matrix is spliced according to a preset rule to obtain a feature fusion matrix;

[0027] The feature fusion matrix is subjected to grayscale processing to obtain a grayscale image corresponding to the feature fusion matrix;

[0028] The grayscale image is identified based on a preset collector line branch line selection model to obtain a target branch of the target collector line where the fault occurs.

[0029] Optionally, before the collector line branch line selection model is used to identify the feature fusion matrix grayscale image to obtain a target branch of the target collector line where the fault occurs, the method further comprises: constructing a collector line branch line selection model, specifically comprising:

[0030] Based on each of the historical second fault current data set and the historical fault voltage data set corresponding to each phase line of the first end and the last end of each historical target collector line in a preset time range after each historical fault time, data processing is performed to obtain a historical grayscale image corresponding to each historical target collector line;

[0031] Based on each of the historical grayscale image, a historical sample set used for training the collector line branch line selection model is constructed, and each historical sample in the historical sample set carries a fault branch label;

[0032] Randomly obtain a preset number of historical samples in the historical sample set as a training sample set, and the remaining historical samples as a test sample set, and perform model training on the initial power collection line branch selection model to obtain the power collection line branch selection model.

[0033] To solve the above problems, the application provides a wind farm power collection line fault branch determination device, which comprises:

[0034] The first acquisition module is configured to acquire a first fault current data set corresponding to each phase line of each power collection line terminal within a preset time range after the fault occurs.

[0035] The power collection line selection processing module is configured to perform power collection line selection processing based on each of the first fault current data sets to determine a target power collection line that has failed.

[0036] The second acquisition module is configured to acquire a second fault current data set and a fault voltage data set corresponding to each phase line of the terminal and head of the target power collection line within a preset time range after the fault occurs.

[0037] The target branch determination module is configured to perform power collection line branch selection processing based on each of the second fault current data sets and each of the fault voltage data sets to determine a target branch of the target power collection line that has failed.

[0038] To solve the above problems, the application provides a storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the wind farm power collection line fault branch determination method described above.

[0039] To solve the above problems, the application provides an electronic device, which at least comprises a memory and a processor, and the memory stores a computer program, and the processor implements the steps of the wind farm power collection line fault branch determination method described above when executing the computer program on the memory.

[0040] The application determines the target power collection line that has failed through the power collection line selection part, and determines the target branch of the target power collection line that has failed through the power collection line branch selection part. The power collection line fault branch determination method of the application can accurately determine the power collection line fault branch, save the cost of determining the fault branch, and improve the efficiency of determining the fault branch.

[0041] The above description is only a summary of the technical solutions of the application. In order to more clearly understand the technical means of the application, the application can be implemented according to the content of the specification, and in order to make the above and other purposes, characteristics and advantages of the application more obvious and easy to understand, the following specific embodiments of the application are described. BRIEF DESCRIPTION OF DRAWINGS

[0042] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading and understanding the following detailed description of the preferred embodiments. The following detailed description is included to provide a complete and enabling disclosure of the application. It will be apparent, however, to those of ordinary skill in the art that various modifications and changes can be made without departing from the scope of the application as set forth in the claims. The appended drawings are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification. In the drawings:

[0043] Figure 1 A flow diagram of a method for determining a fault branch of a power collection line of a wind farm is shown;

[0044] Figure 2 A flow diagram of a method for determining a fault branch of a power collection line of a wind farm is shown;

[0045] Figure 3 A block diagram of a device for determining a fault branch of a power collection line of a wind farm is shown. DETAILED DESCRIPTION

[0046] The various aspects and features of the present application will become apparent to those of ordinary skill in the art upon reading and understanding the following detailed description of the preferred embodiments.

[0047] It should be understood that various modifications can be made to the embodiments described herein. Therefore, the above description should not be construed as limiting, but merely as exemplification of the embodiments. Those skilled in the art will envision other modifications within the scope and spirit of the application.

[0048] The accompanying drawings, which are incorporated herein and constitute part of this specification, illustrate embodiments of the application and, together with the general description of the application given above, and the detailed description of the embodiments given below, serve to explain the principles of the application.

[0049] These and other characteristics of the present application will become apparent upon reading of the following detailed description and upon referring to the attached drawings.

[0050] It should also be understood that, although the terms "first" and "second" can be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. Thus, a first element discussed below could be termed a second element without departing from the scope of the present application. Furthermore, a single element can be split into multiple elements, and / or a plurality of elements can be combined into a single element.

[0051] The above and other aspects, features, and advantages of the present application will become apparent upon reading and understanding the following detailed description of the preferred embodiments, taken in conjunction with the accompanying drawings.

[0052] Specific embodiments of the application are described herein with reference to the accompanying drawings. However, it will be understood that the application is not limited to the embodiments specifically disclosed herein, which are presented for purposes of illustration only. Rather, the application is applicable to any suitable embodiment without departing from the scope of the application. Various examples of the application are described herein with reference to the accompanying drawings. However, it will be understood that the application is not limited to the examples specifically disclosed herein, which are presented for purposes of illustration only. Rather, the application is applicable to any suitable embodiment without departing from the scope of the application. Various examples of the application are described herein with reference to the accompanying drawings. However, it will be understood that the application is not limited to the examples specifically disclosed herein, which are presented for purposes of illustration only. Rather, the application is applicable to any suitable embodiment without departing from the scope of the application.

[0053] The specification can use phrases such as "in one embodiment," "in another embodiment," "in yet another embodiment," or "in other embodiments," which can refer to one or more embodiments of the same or different embodiments of the application.

[0054] The embodiments of the application provide a wind farm power collection line fault branch determination method, as shown in the method, comprising: Figure 1

[0055] Step S101: acquiring a first fault current data set corresponding to each phase line at the end of each power collection line within a preset time range after the fault occurs;

[0056] In the specific implementation process, the wind farm power collection line has the characteristics of multiple branches and multiple fault types. In order to accurately locate the fault branch of the wind farm power collection line, the preset time interval can be 2S, 3S, etc. The application does not limit the preset time interval. Within the preset time interval, the first fault current data set corresponding to each phase line at the end of each power collection line is collected and acquired at a certain frequency. Each power collection line end has three phase lines, which are A phase, B phase and C phase respectively. Each power collection line end will correspond to three groups of first fault current data sets, which are the first fault current data set corresponding to A phase, the first fault current data set corresponding to B phase, and the first fault current data set corresponding to C phase.

[0057] Step S102: performing power collection line selection processing based on each first fault current data set to determine the target power collection line that has failed;

[0058] ​In the implementation process, based on each first fault current data set, a preset vector coordinate transformation method is used for processing to obtain each component current data set corresponding to each first fault current data set. The preset vector coordinate transformation method can be a Clarke transformation method. In each component current data set, a preset time-frequency analysis method is used for processing to obtain a time-frequency matrix and an energy matrix corresponding to each component current data set. The preset time-frequency analysis method can be a Stockwell transformation method. Based on each energy matrix, a target power collection line in which a fault occurs is determined. Specifically, based on a target fault current component, a target component current data set corresponding to each power collection line is determined. The similarity coefficients of each target component current data set are calculated to obtain a similarity coefficient matrix corresponding to the target component. Based on each similarity coefficient matrix, power collection line selection processing is performed to determine the target power collection line in which a fault occurs.

[0059] Step S103: Obtain a second fault current data set and a fault voltage data set corresponding to each phase line at the beginning and end of the target power collection line within a preset time range after the fault occurs.

[0060] In the implementation process, after the target power collection line is determined, the branches of the target power collection line in which a fault occurs need to be determined. First, a second fault current data set and a fault voltage data set corresponding to each phase line at the beginning and end of the target power collection line within a preset time range after the fault occurs are obtained. The preset time can be a time interval of 2S, 3S, etc. The application does not limit the preset time, and the second fault current data set and the fault voltage data set corresponding to each phase line at the beginning and end of the target power collection line are collected and obtained at a certain frequency within the preset time. The beginning and end are the starting end and the ending end of the target power collection line, which lays a foundation for subsequent fault collection line branch selection processing based on each second fault current data set and fault voltage data set.

[0061] Step S104: Based on each second fault current data set and each fault voltage data set, power collection line branch selection processing is performed to determine a target branch of the target power collection line in which a fault occurs.

[0062] In the implementation process, based on the second fault current data set and the fault voltage data set, a preset time-frequency analysis method is used for processing to generate a fault current time-frequency matrix corresponding to each second fault current data set and a fault voltage time-frequency matrix corresponding to each fault voltage data set. The preset time-frequency analysis method can be a Stockwell transform method. The fault voltage time-frequency matrix and the fault current time-frequency matrix corresponding to the target phase line of the target sampling end of the target collector line are calculated and processed to obtain a feature state matrix corresponding to each phase line at the first end and the end of the target collector line. Based on each feature state matrix, a collector line branch selection process is performed to determine the target branch of the target collector line that has failed. Specifically, each feature state matrix is spliced according to a preset rule to obtain a feature fusion matrix. The feature fusion matrix is subjected to grayscale processing to obtain a gray image corresponding to the feature fusion matrix. The gray image is identified based on a preset collector line branch selection model to obtain the target branch of the target collector line that has failed.

[0063] The application determines the target collector line that has failed through the collector line selection part of the wind farm, and determines the target branch of the target collector line that has failed through the collector line branch selection part. The collector line fault branch determination method of the application can accurately determine the collector line fault branch, save the cost of determining the fault branch, and improve the efficiency of determining the fault branch.

[0064] Another embodiment of the application provides another method for determining the fault branch of the collector line of the wind farm, as shown in Figure 2 The method comprises the following steps:

[0065] Step S201: Obtain a first fault current data set corresponding to each phase line at the end of each collector line within a preset time range after the failure occurs.

[0066] In the implementation process, the collector line of the wind farm has the characteristics of multiple branches and multiple fault types. In order to accurately locate the fault branch of the collector line of the wind farm, the preset time range can be 2S, 3S, etc. The application does not limit the preset time range. Within the preset time range, the first fault current data set corresponding to each phase line at the end of each collector line is collected at a certain frequency. Each end of each collector line has three phase lines, which are A phase, B phase and C phase. Each end of each collector line corresponds to three groups of first fault current data sets, which are the first fault current data set corresponding to A phase, the first fault current data set corresponding to B phase, and the first fault current data set corresponding to C phase.

[0067] Step S202: based on each of the first fault current data sets, a preset vector coordinate transformation method is used for processing to obtain each component current data set corresponding to each of the collector line;

[0068] In the specific implementation process of this step, based on each of the first fault current data sets, a preset vector coordinate transformation method is used for processing to obtain each component current data set corresponding to each of the first fault current data sets. The preset vector coordinate transformation can be a Clarke transformation method. The Clarke coordinate transformation is performed on the three-phase fault current signal of each monitoring point to obtain each component current data set corresponding to each of the collector lines, which are respectively an alpha component current data set, a beta component current data set, and a gamma component current data set. For example, when there are three collector lines, each collector line contains an alpha component current data set, a beta component current data set, and a gamma component current data set. Three collector lines will finally obtain three alpha component current data sets, three beta component current data sets, and three gamma component current data sets.

[0069] Step S203: based on each of the component current data sets, a preset time-frequency analysis method is used for processing to obtain an energy matrix corresponding to each of the component current data sets;

[0070] In the specific implementation process of this step, a preset time-frequency analysis method is used for data conversion on each of the component current data sets to obtain a time-frequency matrix corresponding to each of the component current data sets. The preset time-frequency analysis method can be a Stockwell time-frequency analysis method, and the application does not limit the time-frequency analysis method. Modulus calculation is performed on each of the time-frequency matrices to obtain an energy matrix corresponding to each of the component current data sets. The calculation mathematical formula of the time-frequency matrix corresponding to each of the component current data sets obtained by the Stockwell time-frequency analysis method is shown in the following formula (1):

[0071]

[0072] where if is any three-phase fault current; n, k, q = 0, 1, 2, …, N-1; N is the number of fault current values, which is determined by the sampling frequency; T is the sampling frequency. When this method is used for fault data analysis, the time domain and frequency domain characteristics of the fault signal can be considered. Then, modulus calculation is performed on each of the time-frequency matrices to obtain an energy matrix corresponding to each of the component current data sets. The calculation mathematical formula of the modulus calculation on each of the time-frequency matrices to obtain an energy matrix corresponding to each of the component current data sets is shown in the following formula (2):

[0073] E m×n =|S m×n | 2 (2)

[0074] wherein: m and n are the number of frequency domain analysis frequencies and the time size of time domain analysis respectively.

[0075] Step S204: determining a target component current data set corresponding to each of the collector lines based on the target fault current component;

[0076] In the implementation process, for example, when the target component is the α component and there are three collector lines, the target component current data set corresponding to each of the collector lines is determined, and three target component current data sets corresponding to the α component of the three collector lines are obtained.

[0077] Step S205: calculating the similarity coefficients of each of the target component current data sets to obtain a similarity coefficient matrix corresponding to the target component;

[0078] In the implementation process, the similarity coefficients of each of the target component current data sets of the same component are calculated to obtain a similarity coefficient matrix corresponding to the target component, for example, when there are three collector lines in the wind farm, the similarity coefficient of the target component current data set corresponding to the α component of the first collector line and the target component current data set corresponding to the α component of the first collector line is calculated to obtain the similarity coefficient a 11 in the first row and the first column; the similarity coefficient of the target component current data set corresponding to the α component of the first collector line and the target component current data set corresponding to the α component of the second collector line is calculated to obtain the similarity coefficient a 12 in the first row and the second column; the similarity coefficient of the target component current data set corresponding to the α component of the second collector line and the target component current data set corresponding to the α component of the first collector line is calculated to obtain the similarity coefficient a 21 in the second row and the first column; and the similarity coefficient of the target component current data set corresponding to the α component of the second collector line and the target component current data set corresponding to the α component of the second collector line is calculated to obtain the similarity coefficient a 22 in the second row and the second column, so as to obtain a two-row and two-column similarity coefficient matrix corresponding to the α component. When there are three collector lines, a three-row and three-column similarity coefficient matrix is obtained, and the number of rows and the number of columns of the similarity coefficient matrix are determined according to actual needs. In the same way, the similarity coefficient matrices corresponding to the β component and the γ component are calculated and obtained. 2. The similarity coefficients are obtained by calculating the similarity of the energy matrix, and the similarity coefficient function is shown in the following formula (3):

[0079]

[0080] wherein χ ij is the defined similarity coefficient; i, j = 0, 1, 2, …, N; N is the number of collector lines of the wind farm; E Miand E Mj The energy matrix is divided into sampling points Mi and Mj, r is the number of energy matrix rows, and c is the number of energy matrix columns.

[0081] Step S206: Perform addition operation processing on each similar coefficient corresponding to each column in the similar coefficient matrix to obtain a target sub-selection line matrix composed of column similar coefficients corresponding to the target component, so as to obtain a sub-selection line matrix corresponding to each component;

[0082] In the specific implementation process, for example, in step S205, a 2-row 2-column similar coefficient matrix, each similar coefficient corresponding to each column in the similar coefficient matrix is subjected to addition operation processing, and a 1-row 2-column sub-selection line matrix corresponding to the alpha component is obtained, which is composed of the sum of a 11 , a 21 , and the sum of a 12 , a 22 ; and the method is further used to obtain the sub-selection line matrices corresponding to the beta component and the gamma component respectively. The function formula of the sub-selection line matrix is shown in the following formula (4):

[0083]

[0084] Wherein, ∑χ i1 is the sum of similar coefficients of all j.

[0085] Step S207: Perform screening processing on the sum of similar coefficients in each of the sub-selection line matrices, and determine the minimum value of the sum of similar coefficients in the sub-selection line matrix as the fault busbar corresponding to the current sub-selection line matrix;

[0086] In the specific implementation process, according to the element representation of the sub-selection line matrix, the column number of the minimum element is the determination result of the sub-selection line matrix, and is respectively recorded as R α , R β , and R γ . The function of the fault line selection matrix is shown in the following formula (5):

[0087] A=[R α R β R γ ] (5)

[0088] Wherein, R α , R β , and R γ are respectively the determination results of the three sub-selection line matrices.

[0089] Step S208: Screen each of the fault busbars, and determine the fault busbar with the largest probability as the target fault busbar;

[0090] In the specific implementation process of this step, the fault bus line with the largest probability of three sub-selection line matrix determination result is determined as the target fault bus line. For example: when R α is the fault of the first bus line, R β is the fault of the first bus line, R γ is the fault of the second bus line; it is determined that the first bus line with the largest probability is faulty, and the first bus line is determined as the target bus line.

[0091] Step S209: obtaining the second fault current data set and the fault voltage data set corresponding to each phase line of the head and tail of the target bus line within a preset time range after the fault occurs;

[0092] In the specific implementation process of this step, the preset time length can be 2S, 3S, etc. The application does not limit the preset time length. Within the preset time length, the second fault current data set and the fault voltage data set corresponding to each phase line of the head and tail of the target bus line are collected and obtained at a certain frequency. The head and tail have three phase lines, respectively, which are A phase, B phase and C phase. The head and tail of the target bus line will correspond to three groups of second fault current data set and fault voltage data set, respectively, which are the first fault current data set and the fault voltage data set corresponding to A phase, the second fault current data set and the fault voltage data set corresponding to B phase, and the second fault current data set and the fault voltage data set corresponding to C phase.

[0093] Step S210: based on each second fault current data set and each fault voltage data set, a preset time-frequency analysis method is used for processing to generate a fault current time-frequency matrix corresponding to each second fault current data set and a fault voltage time-frequency matrix corresponding to each fault voltage data set;

[0094] In the specific implementation process of this step, based on each second fault current data set and each fault voltage data set, a preset time-frequency analysis method is used for processing to generate a fault current time-frequency matrix S(i f ) corresponding to each second fault current data set and a fault voltage time-frequency matrix S(v f ) corresponding to each fault voltage data set; the preset time-frequency analysis method can be a Stockwell transform method.

[0095] Step S211: calculating and processing the fault voltage time-frequency matrix and the fault current time-frequency matrix corresponding to the target phase line of the target sampling end of the target bus line to obtain the characteristic state matrix corresponding to each phase line of the head and tail of the target bus line;

[0096] In the specific implementation process of the present step, the feature state matrix is calculated based on time-frequency response analysis, and the feature state matrix calculation function is shown in the following formula (6):

[0097]

[0098] Wherein, S is the time-frequency matrix calculated by Stockwell transform; v f and i f The feature state matrix is calculated for each phase voltage and current signal at both ends of the collector line after the fault occurs, and a total of 6 feature state matrices are obtained.

[0099] Step S212: Splicing processing is performed on each feature state matrix according to a preset rule to obtain a feature fusion matrix.

[0100] In the specific implementation process of the present step, the 6 feature state matrices obtained in step S211 are denoted as The calculation function of the feature fusion matrix is shown in the following formula (7):

[0101]

[0102] Wherein, are the feature state matrices of the a, b, and c three-phase lines of the target collector line first-end M1 collection device, respectively; are the feature state matrices of the a, b, and c three-phase lines of the collector line end M2 collection device, respectively.

[0103] Step S213: Gray processing is performed on the feature fusion matrix to obtain a gray image corresponding to the feature fusion matrix.

[0104] In the specific implementation process of the present step, the gray image is obtained by gray processing of the feature fusion matrix. The feature fusion matrix gray image fully retains the correlation between different collection positions and different phases, maximally retains the fault characteristics, lays a foundation for artificial intelligence identification method, and guarantees the accuracy of the collector line branch selection.

[0105] Step S214: A collector line branch selection model is constructed.

[0106] In the implementation process of the step, the historical second fault current data set and the historical fault voltage data set corresponding to each phase line of each historical target power collection line head and tail in a preset time range after each historical fault time are processed to obtain a historical gray image corresponding to each historical target power collection line; a historical sample set for training the power collection line branch selection model is constructed based on the historical gray images, and each historical sample in the historical sample set carries a fault branch label; a preset number of historical samples in the historical sample set are randomly obtained as a training sample set, and the remaining historical samples are obtained as a test sample set to train an initial power collection line branch selection model to obtain the power collection line branch selection model. The power collection line branch selection model adopts a CNN algorithm, which has a simple principle and combines the advantages of computer vision algorithms in the image classification field. The signal is represented as a two-dimensional gray image, so that the model can intuitively classify faults to reveal advanced fault features that are not found in one-dimensional time series, and then use a small number of sensors to locate faults in the entire wind farm.

[0107] Step S215: identifying the gray image based on the power collection line branch selection model to obtain a target branch of the target power collection line that has failed.

[0108] In the implementation process of the step, the trained power collection line branch selection model is used to identify the gray image to determine the target branch of the wind farm multi-branch power collection line fault.

[0109] The application determines the target power collection line that has failed through the power collection line selection part of the wind farm, and determines the target branch of the target power collection line that has failed through the power collection line branch selection part. The reference frequency response analysis method simultaneously analyzes the signals at both ends of the fault in the frequency domain and the time domain, and calculates the time-frequency response characteristics of the fault signal in the time-frequency domain using Stockwell transform. The time-frequency response analysis method can maximize the amplification of fault characteristics to achieve the purpose of early fault detection. The three-phase signal is represented as a visual clue based on the inspiration of the computer vision algorithm in the image classification field, the signal is represented as a two-dimensional image, so that the model can intuitively classify faults to reveal advanced fault features that are not found in one-dimensional time series, and then use a small number of sensors to locate faults in the entire wind farm, save the cost of determining the fault branch of the wind farm power collection line, and improve the efficiency of determining the fault branch of the wind farm power collection line.

[0110] Another embodiment of the application provides another wind farm power collection line fault branch determination device, as shown in Figure 3 , comprising:

[0111] The first acquisition module 1 is configured to acquire a first fault current data set corresponding to each phase line at the end of each overhead line within a preset time range after the fault occurs.

[0112] The overhead line selection processing module 2 is configured to perform overhead line selection processing based on the first fault current data set to determine a target overhead line in which the fault occurs.

[0113] The second acquisition module 3 is configured to acquire a second fault current data set and a fault voltage data set corresponding to each phase line at the end of the target overhead line within a preset time range after the fault occurs.

[0114] The target branch determination module 4 is configured to perform overhead line branch selection processing based on the second fault current data set and the fault voltage data set to determine a target branch of the target overhead line in which the fault occurs.

[0115] In the specific implementation process, the overhead line selection processing module 2 is specifically configured to: based on the first fault current data set, perform processing by using a preset vector coordinate transformation method to obtain a component current data set corresponding to each overhead line; based on the component current data set, perform processing by using a preset time-frequency analysis method to obtain an energy matrix corresponding to each component current data set; and based on the energy matrix, perform calculation processing to determine the target overhead line in which the fault occurs.

[0116] In the specific implementation process, the overhead line selection processing module 2 is further configured to: based on a target fault current component, determine a target component current data set corresponding to each overhead line; calculate a similarity coefficient of each target component current data set to obtain a similarity coefficient matrix corresponding to the target component; and based on the similarity coefficient matrix, perform overhead line selection processing to determine the target overhead line in which the fault occurs.

[0117] In the specific implementation process, the overhead line selection processing module 2 is further configured to: perform addition operation processing on each similarity coefficient corresponding to each column in the similarity coefficient matrix to obtain a target sub-selection line matrix composed of column similarity coefficients and corresponding to the target fault current component, so as to obtain a sub-selection line matrix corresponding to each component; perform screening processing on each column similarity coefficient sum in each sub-selection line matrix to determine an overhead line corresponding to a minimum column similarity coefficient sum in the sub-selection line matrix as a fault overhead line corresponding to the current sub-selection line matrix; and perform screening on each fault overhead line to determine a fault overhead line with the largest probability as the target fault overhead line.

[0118] In the implementation process, the target branch determination module 4 is specifically configured to: based on each second fault current data set and each fault voltage data set, perform processing by using a preset time-frequency analysis method to generate a fault current time-frequency matrix corresponding to each second fault current data set and a fault voltage time-frequency matrix corresponding to each fault voltage data set; perform calculation and processing on the fault voltage time-frequency matrix and the fault current time-frequency matrix corresponding to the target phase line of the target sampling end of the target overhead line to obtain a feature state matrix corresponding to each phase line at the first end and the second end of the target overhead line; perform overhead line branch selection processing based on each feature state matrix to determine the target branch of the target overhead line that has failed.

[0119] In the implementation process, the target branch determination module 4 is further configured to: perform splicing processing on each feature state matrix according to a preset rule to obtain a feature fusion matrix; perform grayscale processing on the feature fusion matrix to obtain a grayscale image corresponding to the feature fusion matrix; and perform identification on the grayscale image based on a preset overhead line branch selection model to obtain the target branch of the target overhead line that has failed.

[0120] In the implementation process, the wind farm overhead line fault branch determination apparatus further includes an overhead line branch selection model construction module, which is specifically configured to: based on each historical second fault current data set and each historical fault voltage data set corresponding to each phase line at the first end and the second end of each historical target overhead line within a preset time range after each historical fault moment, perform data processing to obtain a historical grayscale image corresponding to each historical target overhead line; based on each historical grayscale image, construct a historical sample set for training the overhead line branch selection model, historical samples in the historical sample set carrying fault branch labels; randomly obtain a preset number of historical samples in the historical sample set as a training sample set and the remaining historical samples as a test sample set to perform model training on an initial overhead line branch selection model to obtain the overhead line branch selection model.

[0121] The present application determines a target overhead line that has failed through an overhead line selection part of a wind farm, and determines a target branch of the target overhead line that has failed through an overhead line branch selection part. The overhead line fault branch determination method of the present application can accurately obtain an overhead line fault branch, save the cost of determining the fault branch, and improve the efficiency of determining the fault branch.

[0122] Another embodiment of the present application provides a storage medium storing a computer program, which, when executed by a processor, implements the following method steps:

[0123] Step one, obtaining each phase line of each collector circuit end respectively corresponding first fault current data set in a preset time range after the fault time;

[0124] Step two, based on each first fault current data set, collector circuit line selection processing is performed to determine the target collector circuit line where the fault occurs;

[0125] Step three, obtaining each phase line of the target collector circuit end and end respectively corresponding second fault current data set and fault voltage data set in a preset time range after the fault time;

[0126] Step four, based on each second fault current data set and each fault voltage data set, collector circuit branch line selection processing is performed to determine the target branch of the target collector circuit line where the fault occurs.

[0127] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. Any reference to memory, storage, database or other medium used in the embodiments provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0128] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is exemplified. In actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the above-described functions.

[0129] The specific implementation process of the above method steps can refer to the embodiments of the above-mentioned any wind farm power collection line fault branch determination method, and the embodiments will not be repeated here.

[0130] The application determines the target power collection line that has failed through the power collection line selection part, and determines the target branch of the target power collection line that has failed through the power collection line branch selection part. The power collection line fault branch determination method of the application can accurately obtain the power collection line fault branch, save the cost of determining the fault branch, and improve the efficiency of determining the fault branch.

[0131] Another embodiment of the application provides an electronic device, which can be a server. The electronic device includes a processor, a memory, a network interface and a database connected through a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile and / or volatile storage medium, an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external client through a network connection. The electronic device program is executed by the processor to implement the functions or steps of the wind farm power collection line fault branch determination method on the server side.

[0132] In one embodiment, an electronic device is provided, which can be a client. The electronic device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic 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 the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external server through a network connection. The electronic device program is executed by the processor to implement the functions or steps of the wind farm power collection line fault branch determination method on the client side.

[0133] Another embodiment of the application provides an electronic device, which includes at least a memory and a processor. The memory stores a computer program. The processor implements the following method steps when executing the computer program on the memory:

[0134] Step one, obtaining a first fault current data set corresponding to each phase line at the end of each power collection line within a predetermined time range after the failure occurs;

[0135] Step two, performing power collection line selection processing based on each of the first fault current data sets to determine a target power collection line that has failed;

[0136] Step three, obtaining the second fault current data set and the fault voltage data set corresponding to each phase line of the target overhead line head and tail within a preset time range after the fault occurs;

[0137] Step four, performing overhead line branch selection processing based on each second fault current data set and each fault voltage data set to determine the target branch of the target overhead line that has failed.

[0138] The specific implementation process of the above method steps can be referred to the above embodiment of the wind farm overhead line fault branch determination method, which will not be repeated here.

[0139] The present application determines the target overhead line that has failed through the overhead line selection part of the wind farm, and determines the target branch of the target overhead line that has failed through the overhead line branch selection part. The overhead line fault branch determination method of the present application can accurately obtain the overhead line fault branch, save the cost of determining the fault branch, and improve the efficiency of determining the fault branch.

[0140] The above embodiments are only exemplary embodiments of the present application and are not used to limit the present application, and the protection scope of the present application is defined by the claims. Those skilled in the art can make various modifications or equivalent replacements to the present application within the spirit and protection scope of the present application, and such modifications or equivalent replacements shall also be considered to fall within the protection scope of the present application.

Claims

1. A method for determining a faulted section of a collection line of a wind farm, characterized in that, The method comprises the following steps: obtaining first fault current data sets corresponding to each phase line at the end of each trolley line within a preset time range after the fault occurs; performing trolley line selection processing based on the first fault current data sets to determine a target trolley line where the fault occurs; obtaining second fault current data sets and fault voltage data sets corresponding to each phase line at the end of the target trolley line within a preset time range after the fault occurs; performing trolley line branch selection processing based on the second fault current data sets and the fault voltage data sets to determine a target branch of the target trolley line where the fault occurs; the trolley line selection processing based on the first fault current data sets to determine the target trolley line where the fault occurs comprises: processing the first fault current data sets by using a preset vector coordinate transformation method to obtain component current data sets corresponding to each trolley line; processing the component current data sets by using a preset time-frequency analysis method to obtain energy matrices corresponding to the component current data sets; performing calculation processing based on the energy matrices to determine the target trolley line where the fault occurs; the calculation processing based on the energy matrices to determine the target trolley line where the fault occurs comprises: determining target component current data sets of different current components corresponding to each trolley line; calculating similarity coefficients of the target component current data sets based on the energy matrices to obtain a similarity coefficient matrix corresponding to the target component current data sets; performing trolley line selection processing based on the similarity coefficient matrix to determine the target trolley line where the fault occurs; the trolley line selection processing based on the similarity coefficient matrix to determine the target trolley line where the fault occurs comprises: performing addition operation processing on each similarity coefficient in each column of the similarity coefficient matrix to obtain a target sub-selection line matrix composed of column similarity coefficients corresponding to the current components, so as to obtain a sub-selection line matrix corresponding to each current component; performing screening processing on column similarity coefficients in each sub-selection line matrix to determine a trolley line corresponding to a minimum value of the column similarity coefficients in the sub-selection line matrix as a fault trolley line corresponding to the current sub-selection line matrix; performing screening on each fault trolley line to determine a fault trolley line with the largest probability as a target fault trolley line; the trolley line branch selection processing based on the second fault current data sets and the fault voltage data sets to determine the target branch of the target trolley line where the fault occurs comprises: processing the second fault current data sets and the fault voltage data sets by using a preset time-frequency analysis method to generate a fault current time-frequency matrix corresponding to each second fault current data set and a fault voltage time-frequency matrix corresponding to each fault voltage data set; performing calculation processing on the fault voltage time-frequency matrix and the fault current time-frequency matrix corresponding to a target phase line of a target sampling end of a target trolley line to obtain a feature state matrix corresponding to each phase line at the end of the target trolley line; Based on the characteristic state matrices, the branch selection process of the collector line is performed to determine the target branch of the target collector line where the fault has occurred.

2. The method of claim 1, wherein, The step of performing branch selection processing for the collector line based on each of the aforementioned feature state matrices to determine the target branch of the target collector line where a fault has occurred includes: The feature state matrices are concatenated according to a preset rule to obtain a feature fusion matrix; The feature fusion matrix is ​​converted to grayscale to obtain a grayscale image corresponding to the feature fusion matrix; The grayscale image is identified based on a preset collector line branch selection model to obtain the target branch of the target collector line where the fault has occurred.

3. The method of claim 2, wherein, Before identifying the target branch of the faulty target collector line by recognizing the grayscale image based on the preset collector line branch selection model, the method further includes: constructing the collector line branch selection model, specifically including: Based on the historical second fault current dataset and historical fault voltage dataset corresponding to each phase line at the beginning and end of each historical target collector line within a preset time range after each historical fault time, data processing is performed to obtain the historical grayscale image corresponding to each historical target collector line. Based on the historical grayscale images, a historical sample set is constructed for training the collector line branch selection model. The historical samples in the historical sample set carry fault branch labels. A predetermined number of historical samples are randomly selected from the historical sample set as the training sample set, and the remaining historical samples are selected as the test sample set to train the initial collector line branch selection model, thereby obtaining the collector line branch selection model.

4. An apparatus for determining a faulted section of a collection line of a wind farm, for implementing the method of any one of claims 1 to 3, characterized in that include: First acquisition module: used to acquire the first fault current dataset corresponding to each phase line at the end of each collector line within a preset time range after the fault occurs. The collector line selection processing module is used to perform collector line selection processing based on each of the first fault current datasets to determine the target collector line where the fault has occurred. The second acquisition module is used to acquire the second fault current dataset and the fault voltage dataset corresponding to each phase line at the beginning and end of the target collector line within a preset time range after the fault occurs. Target branch determination module: used to perform line selection processing of the collector line based on each of the second fault current datasets and each of the fault voltage datasets, and to determine the target branch of the target collector line where the fault has occurred.

5. A storage medium, characterized by The storage medium stores a computer program, which, when executed by a processor, implements the steps of the wind farm collector line fault branch determination method according to any one of claims 1-3.

6. An electronic device, comprising: It includes at least a memory and a processor, wherein the memory stores a computer program, and the processor, when executing the computer program in the memory, implements the steps of the wind farm collector line fault branch determination method according to any one of claims 1-3.

Images