Transmission line lightning stroke and non-lightning stroke fault identification method based on wavelet packet decomposition
Through the combination of wavelet packet decomposition and K nearest neighbor algorithm, the transmission line lightning strike and non-lightning strike faults are quickly and automatically identified, solving the problem of low fault identification efficiency in the existing technology, reducing operation and maintenance costs, and ensuring the safety and stability of the power grid.
Patent Information
- Application Number
- CN202410922213.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-10
- Publication Date
- 2024-11-08
AI Technical Summary
The existing transmission line fault identification technology is inefficient, which leads to high cost of detecting hidden dangers and detection of hidden dangers and is difficult to quickly distinguish between lightning strikes and non-lightning strikes, affecting the safety and stability of the power grid.
The wavelet packet decomposition technology is used to extract the traveling wave characteristics of fault current, and combined with the K nearest neighbor algorithm, it realizes rapid and automatic identification of lightning strikes and non-lightning strike faults, reducing the cost and difficulty of line patrol.
Through the combination of wavelet packet decomposition and K nearest neighbor algorithm, rapid automatic identification of transmission line fault types is achieved, operation and maintenance costs are reduced, and the safe and stable operation of the power grid is ensured.
Smart Images

Figure CN118914742A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power transmission line fault identification, and in particular to a method for identifying lightning strike and non-lightning strike faults of power transmission lines based on wavelet packet decomposition. Background Art
[0002] my country's power transmission line corridors cover a wide area with a complex and harsh geographical environment. The lines are exposed to the wild for a long time and are prone to failures due to environmental factors such as oversized trees and air pollution. In South China, power transmission lines are also prone to tripping due to extreme weather such as thunderstorms, heavy rains, and typhoons.
[0003] After a fault occurs, the power department will arrange operation and maintenance personnel to patrol the fault area, find out the specific cause of the fault, and then organize professionals to repair the fault and form a fault analysis report. However, the transmission lines cover a wide range and are mostly distributed in remote areas. It will take a lot of manpower, material resources and time to find the cause of the fault through traditional line patrol methods. The present invention extracts the traveling wave characteristics of the transmission line fault through wavelet packet decomposition, and combines the K nearest neighbor algorithm to realize fast automatic classification of transmission line faults, which can reduce the patrol cost and difficulty of the operation and maintenance department. Summary of the invention
[0004] In view of the above existing problems, the present invention is proposed.
[0005] Therefore, the present invention provides a method for identifying lightning and non-lightning faults in transmission lines based on wavelet packet decomposition, which can solve the problem of low efficiency in distinguishing and finding hidden danger discharges in existing transmission lines, reduce the cost required for troubleshooting hidden danger discharges in transmission lines, and ensure the safety and stability of transmission lines.
[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for identifying lightning and non-lightning faults of power transmission lines based on wavelet packet decomposition, comprising:
[0007] Extract the fault current traveling wave of the fault phase from the fault recording system and process the data, and perform wavelet packet decomposition on the fault current traveling wave;
[0008] Take the first layer of components of wavelet packet decomposition, continue to decompose the wavelet packet, and calculate the proportion of each layer of component energy to the total energy after two wavelet packet decompositions;
[0009] The calculated energy proportion of each layer is used as the feature vector as the input of the K nearest neighbor algorithm to realize the identification of lightning strike and non-lightning strike faults.
[0010] As a preferred solution of the method for identifying lightning and non-lightning faults of transmission lines based on wavelet packet decomposition described in the present invention, the data processing includes extracting historical fault traveling wave data from the fault recording system, and placing the data in different folders, and naming each folder according to the type of lightning and non-lightning faults.
[0011] As a preferred solution of the method for identifying lightning and non-lightning faults of power transmission lines based on wavelet packet decomposition of the present invention, wherein: the wavelet packet decomposition of the fault current traveling wave includes selecting a mother wavelet and a decomposition coefficient n, the selection of the mother wavelet depends on the analysis target and the signal characteristics, and the decomposition level n determines the depth of decomposition, that is, the frequency band pattern of the signal decomposition;
[0012] The signal passes through a set of low-pass filters h and high-pass filters g to obtain the approximate coefficient A0 and detail coefficient D0:
[0013] D0[n]=∑ k g[k]·x[2n-k]
[0014] Where x[n] is the input signal, A0[n] and D0[n] are the first-order approximation coefficients and detail coefficients, respectively.
[0015] As a preferred solution of the method for identifying lightning and non-lightning faults of power transmission lines based on wavelet packet decomposition of the present invention, wherein: the wavelet packet decomposition of the fault current traveling wave also includes that in the wavelet packet decomposition, the approximate part A0 and the detail part D0 will be further decomposed, and each level of decomposition will generate new approximate coefficients and detail coefficients. The approximate coefficients and detail coefficients of the i-th level decomposition are obtained by applying the same low-pass and high-pass filters to the approximate coefficients and detail coefficients of the i-1th level, and are obtained by downsampling. The calculation process is as follows:
[0016] A i [n] = ∑ k h[k]·A i-1 [2n-k]
[0017] D i [n] = Σ k g[k]·D i-1 [2n-k]
[0018] A Di [n] = ∑ k h[k]·D i-1 [2n-k]
[0019] D Di [n] = Σ k h[k]·D i-1 [2n-k]
[0020] In the formula, A i and D i is the approximation coefficient and detail coefficient, A Di and D Di Respectively represent the new approximate coefficient and detail coefficient obtained from the decomposition of the detail part;
[0021] The decomposition process is repeated until the preset decomposition level is reached. Each level of decomposition is performed on the basis of the previous level of decomposition, continuously generating new approximation and detail coefficients.
[0022] As a preferred solution of the method for identifying lightning and non-lightning faults of power transmission lines based on wavelet packet decomposition of the present invention, the wavelet packet decomposition of the fault current traveling wave also includes reconstructing the original signal or part of the signal using all levels of approximation and detail coefficients. The reconstruction process is the inverse process of the decomposition process. The corresponding inverse filter coefficients are used. The reconstruction formula is expressed as:
[0023]
[0024] In the formula, and are the low-pass inverse filter coefficients and the high-pass inverse filter coefficients respectively.
[0025] As a preferred solution of the method for identifying lightning and non-lightning faults of power transmission lines based on wavelet packet decomposition according to the present invention, the calculation of the wavelet packet decomposition twice includes:
[0026] The energy of each frequency band is calculated for the decomposed signal. After the signal is decomposed by wavelet packets, the coefficients of multiple frequency bands are obtained. Each coefficient represents the performance of the signal in the current frequency band. The energy calculation process of each frequency band is as follows:
[0027] Ei=ΣkCi,k| 2
[0028] Where E i is the energy of the ith frequency band, C i,k is the kth coefficient in the ith frequency band;
[0029] Calculate the proportion of energy in each frequency band to the total energy. The calculation process is as follows:
[0030]
[0031] Where E i % is the proportion of the energy of the i-th frequency band to the total energy.
[0032] As a preferred embodiment of the method for identifying lightning strike and non-lightning strike faults in transmission lines based on wavelet packet decomposition according to the present invention, wherein: the identification of lightning strike and non-lightning strike faults includes calculating the energy of each frequency band of all historical fault current traveling wave data as a feature vector, and the set is {E1%, E2%, E3%,..., E i %}, and preparing labels N according to the fault type, N takes 1, 2, corresponding to lightning strike faults and non-lightning strike faults respectively. After randomly shuffling all the data, the training set and the test set are selected according to the ratio of 7:3;
[0033] Calculate the Manhattan distance between the test set samples and the training set samples. The calculation formula is as follows:
[0034]
[0035] In the formula, x and y represent two feature vectors, n is the vector dimension, x i and y i are the values of the vector x and the vector y in the i-th dimension respectively;
[0036] Sort the training set samples in ascending order according to the Manhattan distance from high to low; the sorting order changes with the change of parameters;
[0037] Select the first k training samples with the smallest Manhattan distance (k < n), count the frequencies S of the first k training samples in each category, and determine the category of the test set samples according to the category with the highest returned frequency.
[0038] As a preferred embodiment of the method for identifying lightning strike and non-lightning strike faults in transmission lines based on wavelet packet decomposition according to the present invention, wherein: the identification of lightning strike and non-lightning strike faults further includes that the value of k in the selected first k training samples should be selected before calculation.
[0039] A computer device includes a memory and a processor. The memory stores a computer program. The characteristic is that when the processor executes the computer program, the steps of the method for identifying lightning strike and non-lightning strike faults in transmission lines based on wavelet packet decomposition are realized.
[0040] A computer-readable storage medium stores a computer program. The characteristic is that when the computer program is executed by a processor, the steps of the method for identifying lightning strike and non-lightning strike faults in transmission lines based on wavelet packet decomposition are realized.
[0041] The beneficial effects of the present invention: A method for identifying lightning strike and non-lightning strike faults in transmission lines based on wavelet packet decomposition according to the present invention can realize the rapid and automatic identification of the fault types of transmission lines, reduce the inspection cost of the operation and maintenance department, and ensure the safe and stable operation of the power grid. Description of the Drawings
[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.
[0043] Figure 1 A schematic flow chart of a method for identifying lightning and non-lightning faults in power transmission lines based on wavelet packet decomposition is provided in accordance with an embodiment of the present invention.
[0044] Figure 2 A transmission line lightning and non-lightning fault current traveling wave waveform diagram of a transmission line lightning and non-lightning fault identification method based on wavelet packet decomposition provided by an embodiment of the present invention.
[0045] Figure 3 A diagram showing the result of performing the first wavelet packet decomposition of the fault current traveling wave in a method for identifying lightning and non-lightning faults in a transmission line based on wavelet packet decomposition provided by an embodiment of the present invention.
[0046] Figure 4 A diagram showing the result of performing a second wavelet packet decomposition on a fault current traveling wave in a method for identifying lightning and non-lightning faults in a transmission line based on wavelet packet decomposition provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0047] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.
[0048] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.
[0049] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.
[0050] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.
[0051] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.
[0052] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0053] Example 1
[0054] Reference Figure 1-Figure 4 , which is the first embodiment of the present invention, provides a method for identifying lightning and non-lightning faults in power transmission lines based on wavelet packet decomposition, comprising:
[0055] like Figure 1 The present invention provides a method for identifying lightning and non-lightning faults in power transmission lines based on wavelet packet decomposition, and the process specifically includes the following steps:
[0056] Step 1: Extract the fault current traveling wave of the fault phase from the fault recording system and process the data. This example collects 700 pieces of waveform data of different types of hidden danger discharge current of the transmission line. First, read the sequence of current and time from the fault current data text file according to the established rules. Then label the data according to its type.
[0057] Step 2: Secondly, perform wavelet packet decomposition on the fault current traveling wave. The calculation process is as follows:
[0058] (1) Select a suitable mother wavelet and decomposition level. First, based on the characteristics of the signal and the analysis requirements, select a suitable mother wavelet (such as Daubechies, Symlet, etc.) and the decomposition level. The decomposition level determines the fineness of the frequency resolution. In this example, the db8 wavelet is selected, and the decomposition level is 3.
[0059] (2) First-level decomposition: The signal first passes through a set of low-pass filters h and high-pass filters g to obtain the approximate coefficients (A0) and detail coefficients (D0).
[0060] A0[n]=∑ k h[k]·x[2n-k]
[0061] D0[n]=∑ k g[k]·x[2n-k]
[0062] Where x[n] is the input signal, A0[n] and D0[n] are the first-order approximation coefficients and detail coefficients, respectively.
[0063] (3) Further decomposition. In the wavelet packet decomposition, the approximate part A0 and the detail part D0 will be further decomposed. Each level of decomposition will produce new approximate coefficients and detail coefficients. The approximate coefficients and detail coefficients of the i-th level decomposition can be obtained by applying the same low-pass and high-pass filters to the approximate coefficients and detail coefficients of the i-1th level, and then downsampling. The calculation process is as follows:
[0064] A i [n] = ∑ k h[k]·A i-1 [2n-k]
[0065] D i [n] = ∑ k g[k]·D i-1 [2n-k]
[0066] A Di [n] = ∑ k h[k]·D i-1 [2n-k]
[0067] D Di [n] = ∑ k h[k]·D i-1 [2n-k]
[0068] In the formula, A i and D i is the approximation coefficient and detail coefficient, A Di and D Di They represent the new approximation coefficient and detail coefficient obtained from the decomposition of the detail part respectively.
[0069] (4) Repeat the above decomposition process until the preset decomposition level is reached. Each level of decomposition is based on the previous level of decomposition, and new approximation and detail coefficients are continuously generated.
[0070] (5) Reconstruct the signal. Using all levels of approximation and detail coefficients, the original signal or part of the signal can be reconstructed. The reconstruction process is the inverse of the decomposition process, using the corresponding inverse filter coefficients. The reconstruction formula can be expressed as:
[0071]
[0072] In the formula, and are the low-pass inverse filter coefficients and the high-pass inverse filter coefficients respectively.
[0073] Get as Figure 3 After the result is shown, take the first frequency band signal obtained by wavelet packet decomposition, continue to perform wavelet packet decomposition according to the above process, select db8 wavelet as the mother wavelet, and select 4 as the decomposition level, and get the following Figure 4 Results shown.
[0074] Calculate the energy of each frequency band for the decomposed signal. After the signal is decomposed into wavelet packets, multiple frequency band coefficients will be obtained, and each coefficient represents the performance of the signal in that frequency band. The energy calculation process for each frequency band is as follows:
[0075] Ei=ΣkCi,k| 2
[0076] Where E i is the energy of the ith frequency band, C i,k is the kth coefficient in this frequency band.
[0077] Calculate the proportion of energy in each frequency band to the total energy. The calculation process is as follows:
[0078]
[0079] Where E i % is the proportion of the energy of the i-th frequency band to the total energy.
[0080] The proportion of the energy of each frequency band of the fault current to the total energy is used as the feature vector, and the K nearest neighbor algorithm is used to identify the fault type. The algorithm flow is as follows:
[0081] (1) Prepare the data set. Calculate the energy of each frequency band for all historical fault current traveling wave data as the feature vector, such as {E1%, E2%, E3%, ..., E i%, and prepare label N according to its fault type. N takes 1 or 2, corresponding to lightning strike faults and non-lightning strike faults respectively. After randomly shuffling all the data, the training set and the test set are selected in a ratio of 7:3.
[0082] (2) Calculate the Manhattan distance between the test set samples and the training set samples. The calculation formula is as follows:
[0083]
[0084] In the formula, x and y represent two feature vectors, n is the vector dimension, x i and y i are the values of vector x and vector y in the i-th dimension respectively.
[0085] (3) Sort the training set samples in ascending order according to the Manhattan distance; the sorting order changes with the change of parameters;
[0086] (4) Select the top k training samples (k < n) with the smallest Manhattan distance, and count the frequency S of these top k training samples in each category. In this example, the value of k is selected as 7;
[0087] (5) Return the category with the highest frequency and the test set sample belongs to this category.
[0088] Embodiment 2
[0089] The second embodiment of the present invention is different from the previous embodiment in that:
[0090] If the described function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. And the aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical disks, etc., which can store program codes.
[0091] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0092] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0093] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0094] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.
[0095] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.
Claims
1. A method for identifying lightning and non-lightning faults in power transmission lines based on wavelet packet decomposition, characterized in that: including extracting the fault current traveling wave of the fault phase from the fault recording system and performing data processing, and performing wavelet packet decomposition on the fault current traveling wave; taking the first-layer component of the wavelet packet decomposition, continuing with the wavelet packet decomposition, and calculating the proportion of the energy of each layer component after the two wavelet packet decompositions in the total energy; using the calculated energy proportion of each layer as a feature vector as the input of the K-nearest neighbor algorithm to realize the identification of lightning strike and non-lightning strike faults.
2. The method for identifying lightning and non-lightning faults in power transmission lines based on wavelet packet decomposition according to claim 1, characterized in that: The data processing includes extracting historical fault traveling wave data from the fault recording system, placing the data in different folders, and naming each folder according to the fault type according to the lightning strike and non-lightning strike fault types.
3. The method for identifying lightning and non-lightning faults in power transmission lines based on wavelet packet decomposition as claimed in claim 2, characterized in that: The wavelet packet decomposition of the fault current traveling wave includes selecting the mother wavelet and the decomposition coefficient n. The selection of the mother wavelet depends on the analysis target and signal characteristics, and the decomposition level n determines the decomposition depth, that is, the frequency band pattern of the signal decomposition; The signal passes through a group of low-pass filters h and high-pass filters g to obtain the approximation coefficient A0 and the detail coefficient D0: D0[n]=∑ k g[k]·x[2n-k] where x[n] is the input signal, and A0[n] and D0[n] are the first-level approximation coefficient and detail coefficient respectively.
4. The method for identifying lightning and non-lightning faults in power transmission lines based on wavelet packet decomposition as claimed in claim 3, characterized in that: The wavelet packet decomposition of the fault current traveling wave also includes that in the wavelet packet decomposition, the approximation part A0 and the detail part D0 will be further decomposed. Each level of decomposition generates new approximation coefficients and detail coefficients. The approximation coefficients and detail coefficients of the i-th level of decomposition are obtained by applying the same low-pass and high-pass filters to the approximation coefficients and detail coefficients of the i-1-th level and through downsampling. The calculation process is as follows: A i [n]=∑ k h[k]·A i-1 [2n-k] <h2 style=";text-align:left;direction:ltr">D<h2 style=";text-align:left;direction:ltr"> i <h2 style=";text-align:left;direction:ltr"> [n]=∑<h2 style=";text-align:left;direction:ltr"> k <h2 style=";text-align:left;direction:ltr"> g[k]·D<h2 style=";text-align:left;direction:ltr"> i-1 <h2 style=";text-align:left;direction:ltr"> [2n-k] A Di [n]=∑ k h[k]·D i-1 [2n-k] D Di [n]=∑ k h[k]·D i-1 [2n-k] In the formula, A i and D i is the approximation coefficient and detail coefficient, A Di and D Di Respectively represent the new approximate coefficient and detail coefficient obtained from the decomposition of the detail part; Repeat the decomposition process until the preset decomposition level is reached. Each level of decomposition is based on the previous level of decomposition, continuously generating new approximation coefficients and detail coefficients.
5. The method for identifying lightning and non-lightning faults in power transmission lines based on wavelet packet decomposition as claimed in claim 4, characterized in that: The wavelet packet decomposition of the fault current traveling wave also includes using all levels of approximation and detail coefficients to reconstruct the original signal or part of the signal. The reconstruction process is the inverse process of the decomposition process, using the corresponding inverse filter coefficients. The reconstruction formula is expressed as: In the formula, and are the low-pass inverse filter coefficients and the high-pass inverse filter coefficients respectively.
6. The method for identifying lightning and non-lightning faults in power transmission lines based on wavelet packet decomposition as claimed in claim 5, characterized in that: The calculation of the two wavelet packet decompositions includes calculating the energy of each frequency band for the signal after the decomposition is completed. After the signal is completed with wavelet packet decomposition, coefficients of multiple frequency bands are obtained. Each coefficient represents the performance of the signal in the current frequency band. The energy calculation process of each frequency band is as follows: AND i =∑ k |C i,k | 2 Where E i is the energy of the ith frequency band, C i,k is the kth coefficient in the ith frequency band; calculating the proportion of the energy of each frequency band in the total energy. The calculation process is as follows: Where E i % is the proportion of the energy of the i-th frequency band to the total energy.
7. The method for identifying lightning and non-lightning faults in power transmission lines based on wavelet packet decomposition as claimed in claim 6, characterized in that: The identification of lightning and non-lightning faults includes calculating the energy of each frequency band as a feature vector for all historical fault current traveling wave data, and the set is {E1%, E2%, E3%, ..., E i %}, and prepare label N according to the fault type, N is 1 or 2, corresponding to lightning fault and non-lightning fault. After randomly shuffling all data, the training set and test set are selected in a ratio of 7:3; calculating the Manhattan distance between the test set sample and the training set sample. The calculation formula is as follows: In the formula, x and y represent two feature vectors, n is the vector dimension, and x i and i are the values of vector x and vector y in the i-th dimension respectively; sorting the training set samples in ascending order according to the Manhattan distance from high to low; the sorting order changes with the change of parameters; selecting the first k training samples (k < n) with the smallest Manhattan distance, counting the frequency S of the first k training samples in each category, and determining the category of the test set sample according to the category with the highest returned frequency.
8. The method for identifying lightning and non-lightning faults in power transmission lines based on wavelet packet decomposition according to claim 7, characterized in that: The realization of the identification of lightning strike and non-lightning strike faults also includes that the value of k in the selected first k training samples should be selected before the calculation.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, it realizes the steps of the method described in any one of claims 1 to 8.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it realizes the steps of the method described in any one of claims 1 to 8.
Citation Information
Patent Citations
Power distribution network lightning stroke and non-lightning stroke fault identification method based on fault current frequency band distribution difference
CN112162173A
Power transmission line lightning stroke monitoring method and system based on distributed traveling wave positioning technology
CN113109633A
Power transmission line fault identification method and system based on fault traveling wave data
CN117805551A
Cited By
Lightning stroke type identification method for flexible direct current transmission line
CN120539521A
