A method and system for locating and identifying faults in a transmission line

Through the improved breadth-first search algorithm and transfer learning method, combining the current phasor, voltage phasor and circuit breaker state quantity, the problem of low accuracy of fault analysis and positioning of transmission lines is solved, and more efficient fault positioning and type identification are achieved .

CN114594344BActive Publication Date: 2024-11-26EAST CHINA BRANCH OF STATE GRID CORP +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210294549.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-03-24
Publication Date
2024-11-26
Estimated Expiration
2042-03-24

AI Technical Summary

Technical Problem

In the prior art, the accuracy of transmission line fault analysis and positioning is not high, it is easy to misjudgment, and it is difficult to effectively deal with multi-source data fusion and fault model establishment.

Method used

Using an improved breadth-first search algorithm combined with transfer learning method, fault location and type identification are performed by obtaining current phasor, voltage phasor and circuit breaker state quantity, training fault type identification model and applying it to the target area, and judging short circuits and disconnection Fault.

Benefits of technology

It improves the accuracy and efficiency of fault positioning of transmission lines, reduces misjudgment, and can more accurately identify fault types and locations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114594344B_ABST
    Figure CN114594344B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of electric power systems, and proposes a method and system for locating and identifying transmission line faults, including obtaining current phasors, voltage phasors, and state quantities of circuit breakers and relays before and after the target area transmission line fault; and using an improved breadth-first search algorithm to locate the target area transmission line fault. Through the above technical solution, based on the premise of Kirchhoff's law of the fault line, the breadth-first search algorithm is improved, which can achieve more accurate transmission line fault location.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a method and system for locating and identifying faults in power transmission lines. Background Art

[0002] Driven by the development and construction of energy internet and ubiquitous power internet of things, the trend of regional interconnection, multi-energy interconnection and global interconnection of power systems is becoming increasingly obvious. The continuous incorporation of various distributed renewable energy sources, cold, heat, gas, water, etc. has led to a large-scale expansion of the power grid structure. The probability of power transmission line failure is increasing, and the types of failures are increasing, making the analysis and location of power system transmission line failures more and more difficult. Accurate and rapid analysis and location of power system transmission line failures is the core and foundation for ensuring the safe and stable operation of the power system.

[0003] At present, the identification of transmission line faults is mainly based on the electrical quantities provided by the energy management system, data acquisition and monitoring control system, and wide-area measurement system in the dispatching master station. The fault voltage and current electrical quantities of the transmission line fault and the switch quantity of the protection equipment are established using traditional algorithms for fault identification and location. This reliance on manual analysis and judgment of recorded data is prone to misjudgment and low efficiency. In recent years, with the development of artificial intelligence technology, a small number of people have applied it to power line fault identification, but none of them involve multi-source data fusion and the establishment of fault models. The accuracy of fault analysis and location is not high and it is easy to misjudge. Summary of the invention

[0004] The present invention provides a method and system for locating and identifying a power transmission line fault, which solves the problem in the prior art that the analysis and locating results of the power transmission line fault are not accurate and are prone to misjudgment.

[0005] The technical solution of the present invention is as follows:

[0006] In a first aspect, a method for locating and identifying a transmission line fault comprises the following steps:

[0007] Obtain the current phasors and voltage phasors of all transmission lines ij in the target area before and after the fault, and the state quantities of circuit breakers and relays before and after the fault of the transmission line ij;

[0008] Performing a first fault location on the target area transmission line ij by using the state quantities of the circuit breaker and the relay before and after the transmission line ij fault, and determining the transmission line where the fault occurs;

[0009] Using the current phasors and voltage phasors of the transmission line ij before and after the fault, an improved breadth-first search algorithm is used to perform a second fault location on the faulty transmission line to determine the actual location of the fault;

[0010] The improved breadth-first search algorithm includes using a breadth-first algorithm for any transmission line that has a fault, and executing processing from the first node to the end point. The first node and the end point are specifically: when the original flow direction of the transmission line ij flows from node i to node j, node i is the first node and node j is the end point.

[0011] Furthermore, a fault type identification method is also included, wherein the fault type identification method includes a short circuit fault identification method and a disconnection fault identification method, and the short circuit fault identification method includes:

[0012] Obtain the current phasor, voltage phasor and fault type of the transmission line before and after the fault in the source domain;

[0013] Taking the current phasor and the voltage phasor of the transmission line before and after the fault of the source domain as input, taking the fault type as output, and training the fault type recognition model;

[0014] The trained fault type identification model is applied to the target area by using the transfer learning method, and the current phasor and voltage phasor of the transmission line before and after the fault in the target area are input to obtain the fault type of the transmission line in the target area.

[0015] In a second aspect, a system for analyzing and locating a power transmission line fault includes a fault locating module, wherein the fault locating module includes:

[0016] The first acquisition module is used to obtain the current phasor and voltage phasor of all transmission lines ij in the target area before and after the fault, and the state quantities of circuit breakers and relays before and after the fault of the transmission line ij;

[0017] A first positioning module, used to perform a first fault positioning on the transmission line ij in the target area through the state quantities of the circuit breaker and the relay before and after the fault of the transmission line ij, and determine the transmission line where the fault occurs;

[0018] The second positioning module is used to perform a second fault positioning on the faulty transmission line by using the current phasor and the voltage phasor before and after the fault of the transmission line ij, and adopt an improved breadth-first search algorithm to determine the actual position of the fault.

[0019] Furthermore, it also includes a fault type identification module, the fault type identification module includes:

[0020] The second acquisition module is used to obtain the current phasor, voltage phasor, state quantity of the circuit breaker and the relay, and the fault type before and after the source domain transmission line fault;

[0021] The first training module is used to take the current phasor, voltage phasor and state quantities of the circuit breaker and the relay before and after the fault of the source domain transmission line as input, and take the fault type of the source domain transmission line as output to train the fault type recognition model;

[0022] The first processing module is used to apply the trained fault type identification model to the target domain by adopting the transfer learning method, input the current phasor, voltage phasor and state quantities of the circuit breaker and relay before and after the transmission line fault in the target domain, and obtain the fault type of the transmission line.

[0023] In a third aspect, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method for locating and identifying a power transmission line fault are implemented.

[0024] The working principle and beneficial effects of the present invention are:

[0025] 1. The present invention proposes a method and system for locating and identifying faults in a transmission line. First, the first fault is located in the target area through the changes in the state quantities of the circuit breaker and the relay before and after the fault of the transmission line ij, and the faulty transmission line is found; further, based on Kirchhoff's law of the faulty line, the breadth-first search algorithm is improved, and the faulty line is analyzed by using the improved breadth-first search algorithm through the current phasors and voltage phasors of the faulty transmission line before and after the fault, so as to achieve more accurate fault location.

[0026] 2. The present invention also uses the type recognition model trained in the source domain to identify the fault type in the target area through the method of transfer learning. By training the fault type recognition model, the three-phase current wavelet decomposition information entropy and function threshold K3 of the three-phase short circuit and the three-phase current wavelet decomposition information entropy and function threshold K2 and phase entropy difference threshold K of the two-phase short circuit are obtained. 2AB , K 2BC , K 2CA The current phasor and voltage phasor calculation of the transmission line before and after the fault in the target area The information entropy sum function K and phase entropy difference K of the three-phase current wavelet decomposition AB , K BC , K CA In comparison, it is possible to determine well whether a faulty transmission line has a short circuit fault.

[0027] 3. The present invention also calculates the calculated current phasors of the three phases A, B, and C through the voltage phasors before the fault of the faulty line, and calculates the actual current phasors of the three phases A, B, and C through the current phasors after the fault of the faulty line. By comparing the calculated current phasors of the three phases A, B, and C with the actual current phasors, it is possible to well determine whether the faulty transmission line has a line break fault.

[0028] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is a flow chart of the method of the present invention;

[0030] Figure 2 This is a schematic diagram of the IEEE39 bus system of the present invention;

[0031] Figure 3 This is a schematic diagram of fault location of the IEEE39 bus system of the present invention;

[0032] Figure 4 This is a diagram of a transmission line fault model of the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] Example 1

[0035] like Figure 1 As shown, the present invention proposes a method for locating and identifying faults in a power transmission line, including a fault locating method and a fault identifying method.

[0036] The fault location method comprises:

[0037] Obtain the current phasors and voltage phasors of all transmission lines ij in the target area before and after the fault, as well as the state quantities of circuit breakers and relays before and after the fault of the transmission line ij;

[0038] Performing a first fault location on the transmission line in the target area by using the state quantities of the circuit breaker and the relay before and after the fault of the transmission line ij;

[0039] Using the current phasor and the voltage phasor before and after the fault of the transmission line ij and the first fault location, an improved breadth-first search algorithm is used to perform a second fault location on the transmission line in the target area;

[0040] The improved breadth-first search algorithm includes: assuming that the original power flow direction of the transmission line ij is from node i to node j, then node i is defined as the first node, node j is defined as the end point, and all transmission lines of the first fault location are processed from the first node to the end point using the breadth-first algorithm.

[0041] The fault type identification method includes a short circuit fault identification method and a disconnection fault identification method.

[0042] The short circuit fault identification method comprises:

[0043] Obtain the current phasor, voltage phasor and fault type of the transmission line before and after the fault in the source domain;

[0044] Taking the current phasor and the voltage phasor of the transmission line before and after the fault of the source domain as input, taking the fault type as output, and training the fault type recognition model;

[0045] By training the fault type recognition model, the three-phase current wavelet decomposition information entropy and function threshold K3 of three-phase short circuit and the three-phase current wavelet decomposition information entropy and function threshold K2 and phase entropy difference threshold K of two-phase short circuit are obtained. 2AB , K 2BC , K 2CA , where K2 = K 2AB +K 2BC +K 2CA ;

[0046] The three-phase current wavelet decomposition information entropy sum function K and phase entropy difference K are calculated by using the current phasor and voltage phasor of the transmission line before and after the fault in the target area. AB , K BC , K CA ;

[0047] Compare the three-phase current wavelet decomposition information entropy and function K and phase entropy difference K AB , K BC , K CA , three-phase current wavelet decomposition information entropy and function threshold K3 for three-phase short circuit, three-phase current wavelet decomposition information entropy and function threshold K2 for two-phase short circuit and phase entropy difference threshold K 2AB , K 2BC , K 2CA ;

[0048] When 0<K≤K3, it is judged as a three-phase short circuit fault;

[0049] When K AB >K 2AB When K BC >K 2BC When K CA >K 2CA When , it is judged as a CA two-phase short circuit fault;

[0050] When K3<K≤K2, it is judged as a single-phase short circuit fault.

[0051] The current phasor and voltage phasor of the transmission line before and after the fault in the target area are used to calculate the three-phase current wavelet decomposition information entropy and function K, including:

[0052] according to Calculate the wavelet information entropy W of phase A current Aj , wavelet information entropy W of phase B current Bj and the wavelet information entropy W of phase C current Cj , where j = 1, 2, ..., m, m represents the dimension of high-dimensional wavelet decomposition, E j represents the entropy value of the j-th dimension of high-dimensional wavelet decomposition, Indicates its maximum value;

[0053] Calculate the AB phase entropy difference BC phase entropy difference The difference between the phase entropy and CA

[0054] Define the information entropy and function of three-phase current wavelet decomposition as K = K AB +K BC +K CA .

[0055] The disconnection fault identification method comprises:

[0056] The calculated current phasors of the three phases A, B, and C are calculated by using the current phasors and voltage phasors of the target area transmission line before the fault: in, Respectively represent the calculated current phasors of phases A, B, and C, They represent the pre-fault voltage phasors of phases A, B, and C at the first point of the transmission line respectively; They represent the pre-fault voltage phasors of phases A, B and C at the second point of the transmission line respectively; Represents the admittance matrix of phases A, B, and C;

[0057] The actual current phasors of the three phases A, B, and C are calculated by using the current phasors and voltage phasors after the transmission line fault in the target area: in, They represent the post-fault current phasors of phases A, B, and C at the first point of the transmission line, They represent the post-fault current phasors of phases A, B and C at the second point of the transmission line respectively;

[0058] judge Is it equal to If yes, then there is no disconnection fault in phase A; if no, there is a disconnection fault in phase A;

[0059] judge Is it equal to If yes, there is no disconnection fault in phase B, if no, there is a disconnection fault in phase B;

[0060] judge Is it equal to If yes, then there is no disconnection fault in phase C; if no, there is a disconnection fault in phase C.

[0061] Among them, the characteristic of the transfer learning method is that there are fewer learning samples for the target domain, but more learning samples can be obtained in the source domain, thus solving the problem of fewer learning samples in the target domain. However, the model learned and trained in the source domain is obtained under its samples. If the samples are too different from those in the target domain, the effect of using the model in the source domain for the target domain will be reduced. Therefore, it is necessary to perform a similarity test on the training samples of the source and target domains, select the training model of the source domain sample data with a larger degree of similarity for migration, and define the maximum mean difference between the source and target domain samples:

[0062]

[0063] Where, X s represents the training sample set of the source domain; X t represents the sample set of the target domain; d H (X s ,X t ) represents the distance calculation result of Hilbert space H; function Φ represents the function of mapping high-dimensional samples to low-dimensional space; n s Represents the total number of source domain samples; n t Represents the total number of samples in the target domain.

[0064] This embodiment uses the IEEE39 bus system to verify the effectiveness of the present invention.

[0065] like Figure 2 As shown, the busbar system has a total of 39 nodes, including 10 generator nodes (node ​​31 is a balancing node), 29 load nodes, and 46 transmission lines. The system parameters are shown in Table 1.

[0066] Table 1

[0067]

[0068]

[0069] 1. Fault location

[0070] Assuming that a short-circuit grounding fault occurs in the transmission line from node 16 to node 21, the fault is simulated with a simulation time of 800ms. A short-circuit fault occurs at 200ms and the fault lasts for about 12 cycles, which is 189.7ms.

[0071] Assuming that PMU and SCADA measurement devices are installed at each node, the voltage and current phasors before and after the node is slammed can be observed through PMU, and the "four remote" quantities can be obtained through SCADA as the measurement quantity for fault location and fault type identification. The improved breadth-first search is performed through the measured current and voltage phasors to obtain the actual fault location of the transmission line, such as Figure 3 shown.

[0072] 2. Fault type identification

[0073] In order to be able to Figure 3 The target domain shown in the figure identifies 16 fault types (ABC three-phase short circuit fault, AB phase short circuit fault, BC phase short circuit fault, CA phase short circuit fault, AB phase short circuit to ground fault, BC phase short circuit to ground fault, CA phase short circuit to ground fault, A phase short circuit fault, B phase short circuit fault, C phase short circuit fault, A phase line break fault, B phase line break fault, C phase line break fault, AB phase line break fault, BC phase line break fault, CA phase line break fault), which requires the collection and training of identification model samples in the source domain.

[0074] like Figure 4 As shown in the figure, the transmission line simulation model is a 220 kV transmission line model with a length of 100 km. An external power supply is connected to each end of BUS1 and BUS2. The frequency is set to 50 Hz. The transmission line parameters are set to resistance r = 0.02 Ω / km, reactance x = 0.375 Ω / km, conductance is ignored, and susceptance is b = 0.458 × 10 -5 S / km.

[0075] Taking it as the source domain, five points at 0km, 25km, 50km, 80km and 100km away from bus 1 are selected in turn on the transmission line simulation model to perform 16 types of fault models, generating a total of 2050 groups of fault sample data. The sample data of each type of fault is shown in Table 2:

[0076] Table 2

[0077]

[0078]

[0079] Convolutional neural network learning is performed on 16 fault types in the source domain, and the batch processing of the convolutional neural network is set to one fault type, which is divided into 16 batch processing groups. The convolution layer is set to 16 groups of 2 layers of 3×3 stacked convolution layers, each group of convolution layers is connected to a layer of 2×2 pooling layer, and the number of convolution kernels in each group is set to 128 (using Adam kernel optimizer, speed decay factor set to 0.005, learning rate set to 0.001, training cycle set to 500), set 4 layers of fully connected layers, and one output layer.

[0080] The fault type recognition model trained in the source domain is used in the target domain transmission line to test 16 fault types. The test results are shown in Table 3.

[0081] Table 3

[0082]

[0083] By comparing the traditional BP neural network method and the support vector machine (SVM) method, it can be found that for the identification of 16 types of faults, the accuracy of the method in this embodiment can be maintained at more than 97%, which is about 4% higher than the other two methods.

[0084] Example 2

[0085] Based on the same inventive concept as the above-mentioned embodiment 1, the present invention further proposes a system for analyzing and locating a power transmission line fault, including a fault locating module, wherein the fault locating module includes:

[0086] The first acquisition module is used to obtain the current phasor and voltage phasor of all transmission lines ij in the target area before and after the fault, and the state quantities of circuit breakers and relays before and after the fault of the transmission line ij;

[0087] A first positioning module, used to perform a first fault positioning on the transmission line ij in the target area through the state quantities of the circuit breaker and the relay before and after the fault of the transmission line ij, and determine the transmission line where the fault occurs;

[0088] The second positioning module is used to perform a second fault positioning on the faulty transmission line by using the current phasor and the voltage phasor before and after the fault of the transmission line ij, and adopt an improved breadth-first search algorithm to determine the actual position of the fault.

[0089] Furthermore, this embodiment also includes a fault type identification module, and the fault type identification module includes:

[0090] The second acquisition module is used to obtain the current phasor, voltage phasor, state quantity of the circuit breaker and the relay, and the fault type before and after the source domain transmission line fault;

[0091] The first training module is used to take the current phasor, voltage phasor and state quantities of the circuit breaker and the relay before and after the fault of the source domain transmission line as input, and take the fault type of the source domain transmission line as output to train the fault type recognition model;

[0092] The first processing module is used to apply the trained fault type identification model to the target domain by adopting the transfer learning method, input the current phasor, voltage phasor and state quantities of the circuit breaker and relay before and after the transmission line fault in the target domain, and obtain the fault type of the transmission line.

[0093] Example 3

[0094] Based on the same inventive concept as the above-mentioned embodiment 1, the present invention also proposes a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for locating and identifying a transmission line fault are implemented.

[0095] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for locating and identifying faults in a power transmission line, characterized in that: The steps include: Get all transmission lines in the target area Current phasors, voltage phasors, and transmission lines before and after the fault State quantities of circuit breakers and relays before and after faults; Through the transmission line The state quantities of circuit breakers and relays before and after the fault, and the transmission lines in the target area Performing a first fault location to determine the transmission line where the fault occurs; Through the transmission line The current phasors and voltage phasors before and after the fault are used to locate the second fault of the faulty transmission line using an improved breadth-first search algorithm to determine the actual location of the fault; The improved breadth-first search algorithm includes: for any transmission line with a fault, a breadth-first algorithm is used to perform processing from the first node to the end point, wherein the first node and the end point are specifically: The original tidal flow direction is determined by the node Flow to Node When the node The first node, node for the end point; It also includes a fault type identification method, the fault type identification method includes a short circuit fault identification method and a disconnection fault identification method, the short circuit fault identification method includes: Obtain the current phasor, voltage phasor and fault type of the transmission line before and after the fault in the source domain; Taking the current phasor and the voltage phasor of the transmission line before and after the fault of the source domain as input, taking the fault type as output, and training the fault type recognition model; The trained fault type identification model is applied to the target area by using the transfer learning method, and the current phasor and voltage phasor of the transmission line before and after the fault in the target area are input to obtain the fault type of the transmission line in the target area.

2. A method for locating and identifying a power transmission line fault according to claim 1, characterized in that: The method of using transfer learning to apply the trained fault type recognition model to the target domain includes: The three-phase current wavelet decomposition information entropy and function threshold of three-phase short circuit are obtained by training the fault type recognition model. Information entropy and function threshold of three-phase current wavelet decomposition with two-phase short circuit and phase entropy difference threshold , , ,in ; The information entropy and function of the three-phase current wavelet decomposition are calculated by using the current phasor and voltage phasor of the transmission line before and after the fault in the target area. and phase entropy difference , , ; Compare the three-phase current wavelet decomposition information entropy and function and phase entropy difference , , , three-phase current wavelet decomposition information entropy and function threshold of three-phase short circuit , information entropy and function threshold of three-phase current wavelet decomposition for two-phase short circuit and phase entropy difference threshold , , ; when When , it is judged as a three-phase short circuit fault; when When , it is judged as AB two-phase short circuit fault. When , it is judged as a BC two-phase short circuit fault. When , it is judged as a CA two-phase short circuit fault; when When , it is judged as a single-phase short circuit fault.

3. A method for locating and identifying a transmission line fault according to claim 2, characterized in that: The current phasor and voltage phasor of the transmission line before and after the fault of the faulty transmission line passing through the target area calculates the information entropy and function of the three-phase current wavelet decomposition , include, according to Calculate the wavelet information entropy of phase A current , wavelet information entropy of phase B current and the wavelet information entropy of phase C current ,in, , represents the high-dimensional wavelet decomposition dimension, Represents high-dimensional wavelet decomposition The entropy value of the dimension, Indicates its maximum value; Calculate the AB phase entropy difference , BC phase entropy difference The difference between the phase entropy and CA ; The information entropy and function of three-phase current wavelet decomposition are defined as .

4. A method for locating and identifying a transmission line fault according to claim 2, characterized in that: The disconnection fault identification method comprises: The calculated current phasors of the three phases A, B, and C are calculated by using the current phasors and voltage phasors of the target area transmission line before the fault: ,in, , , Respectively represent the calculated current phasors of phases A, B, and C, , , They represent the pre-fault voltage phasors of phases A, B, and C at the first point of the transmission line respectively; , , They represent the pre-fault voltage phasors of phases A, B and C at the second point of the transmission line respectively; Represents the admittance matrix of phases A, B, and C; The actual current phasors of the three phases A, B, and C are calculated by using the current phasors and voltage phasors after the transmission line fault in the target area: ,in, , , They represent the post-fault current phasors of phases A, B, and C at the first point of the transmission line, , , They represent the post-fault current phasors of phases A, B and C at the second point of the transmission line respectively; judge Is it equal to , if yes, then there is no disconnection fault in phase A, if no, then there is a disconnection fault in phase A; judge Is it equal to , if yes, then there is no disconnection fault in phase B, if no, then there is a disconnection fault in phase B; judge Is it equal to If yes, then there is no disconnection fault in phase C; if no, there is a disconnection fault in phase C.

5. A system for analyzing and locating transmission line faults, characterized in that: A fault location module is included, wherein the fault location module includes: The first acquisition module is used to obtain all transmission lines in the target area Current phasors, voltage phasors, and transmission lines before and after the fault State quantities of circuit breakers and relays before and after faults; The first positioning module is used to pass through the transmission line The state quantities of circuit breakers and relays before and after the fault, and the transmission lines in the target area Performing a first fault location to determine the transmission line where the fault occurs; The second positioning module is used to pass the transmission line The current phasors and voltage phasors before and after the fault are used to locate the second fault of the faulty transmission line using an improved breadth-first search algorithm to determine the actual location of the fault; It also includes a fault type identification module, the fault type identification module includes: The second acquisition module is used to obtain the current phasor, voltage phasor, state quantity of the circuit breaker and relay, and the fault type before and after the source domain transmission line fault; The first training module is used to take the current phasor, voltage phasor and state quantities of the circuit breaker and the relay before and after the fault of the source domain transmission line as input, and take the fault type of the source domain transmission line as output to train the fault type recognition model; The first processing module is used to apply the trained fault type identification model to the target domain by adopting the transfer learning method, input the current phasor, voltage phasor and state quantities of the circuit breaker and relay before and after the transmission line fault in the target domain, and obtain the fault type of the transmission line.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of a method for locating and identifying a power transmission line fault as described in any one of claims 1 to 4 are implemented.