Power transmission line fault location method based on ICEEMDAN and improved YOLOv8

Abstract

The invention discloses an ICEEMDAN and improved YOLOv8-based power transmission line fault location method, which comprises the following steps of: respectively constructing a fault identification model and a fault location model by using an improved YOLOv8 network, carrying out phase-mode transformation on a three-phase voltage transient signal of a fault line by using a Karen transform method, selecting a line-mode component as a fault traveling wave research object, decomposing the line-mode component by using an ICEEMDAN algorithm, and carrying out fault location on the three-phase voltage transient signal of the fault line. Using an NTEO algorithm to strengthen a modal component of the line mode component, highlighting fault signal features, and obtaining a fault traveling wave energy spectrogram and an amplified traveling wave energy spectrogram; an initial fault time range is determined by using a fault identification model, and then a fault time point, namely the accurate arrival time of fault traveling wave heads at two ends of the line, is obtained by using a fault positioning model according to the amplified traveling wave energy spectrogram. The method improves the precision of line fault distance measurement, is not affected by transition resistance, fault distance and transmission lines, and is high in reliability and good in practicability.

Description

Technical Field

[0001] The invention belongs to the field of power system fault location, and in particular relates to a transmission line fault distance measurement method based on ICEEMDAN and improved YOLOv8. Background Art

[0002] The rapid growth of distribution networks and the increase in load demand have made distribution networks play a vital role in urban development. However, distribution networks are prone to line failures due to a variety of events such as severe weather conditions, instantaneous contact between animals and plants, and aging infrastructure. These line failures not only incur high maintenance costs, but also cause reduced productivity and huge economic losses. Therefore, accurate and fast line fault location methods are of great significance to the safe and stable operation of distribution systems.

[0003] In real life, many principles and algorithms for locating power line faults have been proposed according to actual needs, among which the traveling wave method is widely used. However, the key to applying the traveling wave method is whether the traveling wave head can be accurately calibrated, which will directly affect the accuracy of traveling wave fault location. In addition, most improved traveling wave methods also require manual screening of the initial traveling wave head to ensure the reliability of the data.

[0004] The current method for calibrating the arrival time of traveling waves uses the wavelet modulus maximum to detect the mutation point of the traveling wave signal, calibrates the moment when the fault traveling wave arrives at the monitoring point to locate the line fault, and has achieved good results. However, the wavelet transform method requires the selection of appropriate wavelet basis functions and decomposition scales, and has poor adaptability.

[0005] The fault location method based on EMD decomposition has the phenomena of modal aliasing and endpoint effect, which will have a certain impact on the calibration of the arrival time of the traveling wave, and the transformation calculation is large, making it difficult to obtain satisfactory results. ICEEMDAN adds the decomposed noise on the basis of EMD and calculates the mean, which not only retains the effective information of the original signal, but also greatly reduces the redundant components brought by adding white noise, further improving the decomposition effect. Summary of the invention

[0006] The purpose of the present invention is to solve the above problems and provide a transmission line fault ranging method based on ICEEMDAN and improved YOLOv8, which converts the key data of the line fault signal into pictures, visualizes it and has extremely high positioning accuracy. The improved YOLOv8 is used to construct a fault identification model and a fault location model, and the problem of manual screening of the initial traveling wave head in the traveling wave method is solved.

[0007] In order to achieve the above-mentioned purpose, the technical solution provided by the present invention is a transmission line fault ranging method based on ICEEMDAN and improved YOLOv8, and a fault identification model and a fault location model are constructed using the improved YOLOv8 network respectively. The fault identification model is used to identify whether a fault has occurred and determine the initial fault time range according to the fault voltage waveform diagram; the fault location model is used to obtain a reduced fault time range or fault time point according to the fault traveling wave energy spectrum diagram.

[0008] The transmission line fault location method based on ICEEMDAN and improved YOLOv8 includes the following steps: Step 1: Collect the three-phase voltage transient signals at both ends of the line after the fault occurs, obtain the fault voltage waveform, use the Karenberg transformation method to perform phase mode transformation on the three-phase voltage transient signals, and select the line mode component as the fault traveling wave research object; Step 2: Use the ICEEMDAN algorithm to decompose the line mode components, use the NTEO algorithm to enhance the modal components of the line mode components, highlight the fault signal characteristics, and obtain the fault traveling wave energy spectrum and the amplified traveling wave energy spectrum; Step 3: Using the fault voltage waveform diagram obtained in step 1 and the fault traveling wave energy spectrum diagram and the amplified traveling wave energy spectrum diagram obtained in step 2, a traveling wave detection data set is established; Step 4: Build a fault identification model and a fault location model respectively, and train them using the traveling wave detection dataset; Step 5: For a newly occurring single-phase line grounding fault, read the voltage transient signals at both ends of the line, obtain the fault voltage waveform and input it into the fault identification model, and use the fault identification model to determine whether there is a line fault and determine the initial fault time range; Step 6: According to the initial fault time range, obtain the line mode component of the three-phase voltage transient signal in the corresponding time stage, and obtain the fault traveling wave energy spectrum after ICEEMDAN decomposition and NTEO algorithm enhancement in step 2. Input it into the fault location model to obtain the reduced fault time range. Step 7: According to the reduced fault time range, the line mode component of the three-phase voltage transient signal of the corresponding time stage is obtained, and the enlarged traveling wave energy spectrum is obtained through the ICEEMDAN decomposition and NTEO algorithm enhancement in step 2. The fault location model is used to obtain the fault time point, i.e., the accurate arrival time of the fault traveling wave head at both ends of the line according to the enlarged traveling wave energy spectrum. Step 8: Based on the accurate arrival time of the fault wave head at both ends of the line obtained in step 6, the fault point location is calculated.

[0009] Furthermore, in step 2, ICEEMDAN is used to decompose the line mode components of the fault traveling wave voltage, including: 1) Based on the original signal s, a new signal sequence is generated by adding auxiliary noise of empirical mode decomposition: ; (1) in, represents the added i-th group of zero-mean Gaussian white noise; represents the signal-to-noise ratio of the initially added noise; represents the i-th intrinsic mode function component of the empirical mode decomposition of the signal; represents the new sequence formed after adding the i-th group of auxiliary noise; 2) Find the local mean of the signal , and then take the overall average of the signal to get the first-order residual component , ; (2) ; (3) in, represents the local mean of the signal, Indicates the overall mean of the signal; 3) The first-order intrinsic mode function component of the signal is obtained by taking the difference between the original signal and the first-order residual component , ; (4) 4) Take the first-order residual component Based on this, we add multiple groups of auxiliary noise and take the mean to obtain a new second-order residual component. , and then find the difference to get the second-order intrinsic mode function component of the signal , ; (5) ; (6) In the formula represents the signal-to-noise ratio of the second noise addition; 5) Repeat the calculation to obtain the residual component of the kth stage and the kth stage intrinsic mode function component , ; (7) ; (8) In the formula , Represent the residual components of the k-1th and kth stages respectively; represents the signal-to-noise ratio of the k-th noise addition; 6) Continue iterating until the residual signal can no longer be decomposed and the decomposition termination condition is met, and all intrinsic mode function components and residual components are obtained.

[0010] Furthermore, in step 2, the NTEO algorithm includes: For continuous-time signals , TEO energy operator It is expressed as: ; (9) In the formula , Respectively The first and second derivatives of ; For discrete-time signals , the TEO energy operator is expressed as: ; (10) Introducing resolution parameters , the NTEO energy operator is expressed as: ; (11) Increasing the interval between sampling signal points can reduce the interference of continuous noise, improve the sensitivity to signal frequency, and thus enhance noise resistance.

[0011] Preferably, in step 3, the traveling wave detection data set includes: 1) Fault voltage waveform, i.e. three-phase voltage transient signal diagram after the fault occurs; 2) Fault traveling wave energy spectrum diagram. The fault three-phase voltage transient signal within the fault occurrence time range is transformed into the fault traveling wave line mode component by phase mode transformation. The line mode component is then decomposed by the ICEEMDAN algorithm to obtain the first-order intrinsic mode function component. The first-order intrinsic mode function component is enhanced by the NTEO energy operator to obtain the fault traveling wave characteristic energy spectrum diagram. 3) The enlarged traveling wave energy spectrum diagram is obtained by phase-mode transformation of the fault three-phase voltage transient signal within the reduced fault traveling wave time range to obtain the fault traveling wave line mode component, and then the line mode component is decomposed by the ICEEMDAN algorithm to obtain the first-order intrinsic mode function component. The first-order intrinsic mode function component is enhanced by the NTEO energy operator to obtain the enlarged fault traveling wave characteristic energy spectrum diagram.

[0012] Preferably, the construction process of the improved YOLOv8 network specifically includes: a) Integrate the GhostConv module in the GhostNet network into the BottleNeck module to obtain the GhostBottleNeck module; b) Use the GhostBottleNeck module to replace the BottleNeck layer of the C3 module of YOLOv5 to obtain the C3Ghost module; c) Based on the principle of scale sequence feature fusion module in ASF-YOLO network, construct ScalSeq module; d) Replace all C2f modules in the backbone network Backbone and the neck network Neck in YOLOv8 with C3Ghost modules, and replace the Concat module and Upsample module in the neck network Neck with ScalSeq modules to obtain an improved YOLOv8 network.

[0013] Preferably, the C3Ghost module includes two parallel convolutional layers Conv, one of which is connected to the terminal convolutional layer Conv via multiple GhostBottleNeck modules and a concatenation layer Concat, and the other parallel convolutional layer Conv is directly connected to the terminal convolutional layer Conv.

[0014] Preferably, the GhostBottleNeck module includes a parallel ghost convolution layer GhostConv and a depthwise separable convolution layer DWConv, the depthwise separable convolution layer DWConv is connected to the terminal fusion layer Add via the convolution layer Conv, and the ghost convolution layer GhostConv is connected to the terminal fusion layer Add via another depthwise separable convolution layer DWConv and another ghost convolution layer GhostConv.

[0015] Furthermore, in step 8, the calculating of the line fault point location includes: 1) Calculate the wave velocity of the zero mode or line mode component corresponding to the fault traveling wave of the line according to the parameters of the transmission line , the calculation formula is: ; (12) In the formula , They are the inductance and capacitance of the line per unit length under the same phase sequence respectively; 2) According to the principle of double-terminal traveling wave ranging, the location of the fault on the line is assumed to be point F, and the time of the fault is recorded as , the fault traveling wave propagates from point F to points M and N at the left and right ends of the line, where M is the left end point of the line and N is the right end point of the line; The time when the initial wave head of the fault traveling wave reaches point M is recorded as The time when it reaches point N is recorded as , then: ; (13) ; (14) ; (15) In the formula Indicates the distance from point F to point M; 3) For the mixed lines of overhead lines and cable lines, normalization is performed, and the cable lines are equivalent to overhead lines of corresponding lengths. The wave velocities of traveling waves in overhead lines and cable lines are expressed as , It means that the calculation formula for the wave speed conversion of different lines is: ; (16) In the formula is the normalized equivalent overhead line length of the cable, Indicates the length of cables in the distribution network.

[0016] The fault location system of the above-mentioned transmission line fault location method comprises: Traveling wave generation module: used to simulate and obtain the three-phase fault transient voltage signal at a sampling rate of 10MHz after a line fault occurs, and output the fault voltage waveform; Fault voltage waveform detection module: used to process the fault voltage waveform diagram to obtain the fault voltage waveform detection diagram with a boundary box, the fault target probability and the fault initial time range of the traveling wave body.

[0017] Phase mode conversion module: used to convert the three-phase fault transient voltage signal within the initial time range of the fault into the corresponding line mode component through the Karenberg transformation matrix; ICCEMDAN algorithm module: used to decompose the fault characteristics of the line mode components within a given time range through the ICCEMDAN algorithm to obtain the corresponding first-order intrinsic mode function components; NTEO algorithm module: used to enhance the fault characteristics of the first-order intrinsic mode function components within a given time range through the NTEO algorithm to obtain the corresponding energy spectrum data, as well as the fault traveling wave energy spectrum diagram or the amplified traveling wave energy spectrum diagram; Traveling wave energy spectrum detection module: used to pass the line mode components within the initial time range of the fault through the ICCEMDAN algorithm module and the NTEO algorithm module respectively, to obtain the fault traveling wave energy spectrum detection diagram with a bounding box, the fault target probability and the fault reduction time range of the traveling wave body; then filter the energy spectrum data within the fault reduction time range to obtain the enlarged traveling wave energy spectrum detection diagram with a bounding box, the fault target probability and the accurate arrival time of the traveling wave head; Line fault point calculation module: used to integrate the accurate arrival time of the traveling wave heads at both ends of the line, that is, the time corresponding to the maximum point in the energy spectrum diagram, and calculate the accurate fault point location of the line.

[0018] Compared with the prior art, the beneficial effects of the present invention include: 1) The present invention uses the Karen Bell transformation method to perform phase mode transformation on the three-phase voltage transient signal of the fault line, selects the line mode component as the research object of the fault traveling wave, adopts the ICEEMDAN algorithm to decompose the line mode component, uses the NTEO algorithm to strengthen the modal component of the line mode component, highlights the fault signal characteristics, and obtains the fault traveling wave energy spectrum diagram and the amplified traveling wave energy spectrum diagram; uses the fault identification model to determine the initial fault time range, and then uses the fault location model to obtain the fault time point, that is, the accurate arrival time of the fault traveling wave head at both ends of the line according to the amplified traveling wave energy spectrum diagram, thereby improving the accuracy of line fault ranging, and is not affected by transition resistance, fault distance and transmission line, with high reliability and good practicality.

[0019] 2) The present invention uses the ICEEMDAN algorithm to decompose the line mode components of the fault traveling wave signal, and then uses the NTEO algorithm to enhance the fault traveling wave characteristics. The obtained initial wave head time of the fault traveling wave has extremely high accuracy.

[0020] 3) The present invention improves the YOLOv8 model for the traveling wave detection task. The improved YOLOv8 model has the characteristics of being lightweight, and can automatically read the fault traveling wave information according to the key data of the traveling wave in the form of pictures, and accurately screen the initial wave head of the fault traveling wave. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0022] Figure 1 Schematic diagram of a transmission line fault location method according to an embodiment of the present invention.

[0023] Figure 2 This is a simulation circuit diagram of an embodiment of the present invention.

[0024] Figure 3 4 is a fault voltage waveform diagram of an embodiment of the present invention.

[0025] Figure 4 This is a fault traveling wave energy spectrum detection diagram of an embodiment of the present invention.

[0026] Figure 5 This is a diagram of the amplified traveling wave energy spectrum detection according to an embodiment of the present invention.

[0027] Figure 6 Schematic diagram of the double-terminal traveling wave method according to an embodiment of the present invention.

[0028] Figure 7 Schematic diagram of the structure of the improved YOLOv8 according to an embodiment of the present invention.

[0029] Figure 8 Schematic diagram of the structure of the C3Ghost module of an embodiment of the present invention.

[0030] Fig. 9 Schematic diagram of the ScalSeq module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0032] like Figure 1 As shown in FIG. 1 , the transmission line fault location method based on ICEEMDAN and improved YOLOv8 includes the following steps: Step 1: Collect a large number of three-phase voltage transient signals at both ends of the line M and N after the fault, collect the fault voltage waveform, use Karen Bell transformation to perform phase mode transformation on the three-phase voltage transient signal, obtain the line mode component and ground mode component of the voltage, and select the line mode component as the fault traveling wave research object; Use PSCAD to simulate five transmission lines, such as Figure 2 As shown, it includes pure overhead lines, pure cable lines and hybrid lines. Set one of the lines to have a single-phase grounding fault at a sampling rate of 10MHz, repeat the simulation multiple times with different fault occurrence times, different grounding resistances, different fault occurrence locations, etc., and obtain the voltage transient signal at both ends of the line each time and save the file.

[0033] Step 2: Use the ICEEMDAN algorithm to decompose the line mode components of the traveling wave voltage, use the NTEO algorithm to enhance the prominent features of the traveling wave signal, collect the fault traveling wave energy spectrum and the amplified traveling wave energy spectrum, and establish a traveling wave detection data set; Read the simulation file obtained each time, perform phase mode transformation on its three-phase transient voltage signal, and use the ICEEMDAN algorithm to decompose the line mode component of the traveling wave voltage. The specific method is as follows: 1) Based on the original signal s, a new signal sequence is generated by adding auxiliary noise decomposed by EMD: (1) in, represents the added i-th group of zero-mean Gaussian white noise; represents the signal-to-noise ratio of the noise; Represents the i-th intrinsic mode function component of a signal after EMD decomposition; Represents the new sequence formed by adding i groups of auxiliary noise.

[0034] 2) Find the local mean of the signal , and then take the overall average of the signal to get the first-order residual component : (2) (3) in, represents the local mean of the signal, It means to average the whole signal. Represents the k-th stage residual component of the original signal.

[0035] 3) The first-order intrinsic mode function component of the signal is obtained by subtracting the original signal from the first-order residual component ,Right now: (4) 4) Take the first-order residual component Based on this, multiple groups of auxiliary noises are added and the average is calculated to obtain a new second-order residual component. , and then find the difference to get the second-order intrinsic mode function component of the signal : (5) (6) 5) Repeat the calculation of the k-th stage residual component and the k-th stage IMF component: (7) (8) 6) Continue iterating until the residual signal can no longer be decomposed and the decomposition termination condition is met, and all intrinsic mode function components and residual components are obtained.

[0036] The first-order intrinsic mode function component obtained after decomposing the fault traveling wave is used to enhance the prominent features of the traveling wave signal using the NTEO algorithm. The specific method is as follows: For continuous-time signals , TEO energy operator It is expressed as: (9) In the formula , Respectively The first and second derivatives of ; For discrete-time signals , the TEO energy operator is expressed as: (10) Introducing a resolution parameter , the NTEO energy operator is expressed as: (11) Increasing the interval between sampling signal points can reduce the interference of continuous noise, improve the sensitivity to signal frequency, and thus enhance the noise resistance of the algorithm.

[0037] Step 3: Establish a traveling wave detection data set; The fault traveling wave energy spectrum diagram and the amplified traveling wave energy spectrum diagram obtained by the NTEO algorithm, as well as the fault voltage waveform diagram obtained previously, are collected to form a traveling wave detection data set.

[0038] Step 4: Build an improved YOLOv8 network and train it using the traveling wave detection dataset; Improve the YOLOv8 model such as Figure 7 As shown, the construction process of the improved YOLOv8 network specifically includes: a) Integrate the GhostConv module in the GhostNet network into the BottleNeck module to obtain the GhostBottleNeck module; b) Use the GhostBottleNeck module to replace the BottleNeck layer of the C3 module of YOLOv5 to obtain the C3Ghost module, whose structure is as follows Figure 8 As shown; c) Based on the principle of the scale sequence feature fusion module in the ASF-YOLO network, the ScalSeq module is constructed, and its structure is as follows: Fig. 9 As shown; d) Replace all C2f modules in the backbone network Backbone and the neck network Neck in YOLOv8 with C3Ghost modules, and replace the Concat module and Upsample module in the neck network Neck with ScalSeq modules to obtain an improved YOLOv8 network.

[0039] To improve the training of the YOLOv8 model, it is necessary to annotate specific targets in the dataset images. The Labelimg tool can be used to annotate the traveling wave categories and digital categories to obtain a labeled traveling wave detection dataset, and then divide the training, validation, and test sets into a ratio of 7:2:1.

[0040] Establish the operating environment, import the traveling wave detection dataset, set the corresponding training parameters, train the improved YOLOv8 model, and obtain the optimized improved YOLOv8 model for traveling wave detection.

[0041] Step 5: When a single-phase grounding fault occurs, collect the three-phase voltage transient signals at both ends of the line M and N after the fault, output the fault voltage waveform, and call the trained improved YOLOv8 model to determine the initial fault time range; Use PSCAD to simulate five transmission lines, such as Figure 2As shown in the figure, it includes pure overhead lines, pure cable lines and hybrid lines. Set one of the lines to have a single-phase grounding fault at a sampling rate of 10MHz. The fault time, grounding resistance and fault location are different from the fault conditions in the traveling wave detection data set. Obtain the voltage transient signal at both ends of the line and save the file. Output the three-phase fault voltage waveform, as shown in Figure 3 shown.

[0042] The three-phase fault voltage waveform is input into the trained improved YOLOv8 model, and the fault voltage waveform detection diagram, the probability of detecting the target, and the position and size of the detection box of the selected detection target are output. The information is integrated to obtain the initial fault time range.

[0043] Step 6: According to the initial fault time range, read the three-phase voltage transient signal of the corresponding stage, and then use the ICEEMDAN algorithm to decompose the traveling wave voltage line mode component after phase mode transformation. Use the NTEO algorithm to enhance the prominent features of the traveling wave signal to obtain the fault traveling wave energy spectrum diagram. Use the trained improved YOLOv8 model to narrow the fault time range.

[0044] Based on the fault occurrence time range obtained above, the voltage transient signal files at both ends of the line are read. First, the traveling wave voltage line mode component is obtained by phase mode transformation. Then, the ICEEMDAN algorithm is used to decompose the traveling wave voltage line mode component to obtain the first-order intrinsic mode function component. Finally, the NTEO algorithm is used to enhance the prominent features of the first-order intrinsic mode function component, making the fault traveling wave characteristics more concrete, and output the fault traveling wave energy spectrum diagram.

[0045] The fault traveling wave energy spectrum diagram is input into the trained improved YOLOv8 model, and the fault traveling wave energy spectrum detection diagram is output, as shown in Figure 4 As shown in the figure, as well as the probability of detecting the target and the position and size of the detection box of the selected detection target, the integrated information is obtained to narrow the fault time range.

[0046] Step 7: According to the narrowed fault time range, read the traveling wave characteristic signal obtained by ICEEMDAN and NTEO decomposition in the corresponding stage, output the amplified traveling wave energy spectrum, and use the trained improved YOLOv8 model to obtain the accurate arrival time of the initial fault traveling wave head at both ends of the line.

[0047] Based on the narrowed fault time range obtained above, the voltage transient signal files at both ends of the line are read, and the first-order intrinsic mode function components decomposed by ICEEMDAN within the time range are screened out. The NTEO algorithm is then used to enhance the prominent features of the traveling wave signal to obtain the amplified traveling wave energy spectrum.

[0048] The amplified traveling wave energy spectrum map is input into the trained improved YOLOv8 model, and the amplified traveling wave energy spectrum detection map is output, as shown in Figure 5 As shown in the figure, as well as the probability of detecting the target and the position and size of the detection box of the selected detection target, the accurate arrival time of the initial traveling wave head of the fault at both ends of the line is obtained by integrating the information.

[0049] Step 8: Accurately calculate the fault point location based on the accurate arrival time of the initial traveling wave head of the fault at both ends of the line.

[0050] The principle of the double-ended traveling wave method is as follows Figure 6 As shown in the figure, after obtaining the accurate arrival time of the initial traveling wave head at both ends of the line, the fault point location is calculated according to the principle. The calculation process is as follows: 1) Calculate the wave velocity of the zero mode or line mode component corresponding to the fault traveling wave of the line according to the parameters of the transmission line , the calculation formula is: (12) In the formula , They are the inductance and capacitance of the line per unit length under the same phase sequence respectively; 2) According to the principle of double-terminal traveling wave ranging, the location of the fault on the line is assumed to be point F, and the time of the fault is recorded as , the fault traveling wave propagates from point F to points M and N at the left and right ends of the line, where M is the left end point of the line and N is the right end point of the line.

[0051] The time when the initial wave head of the fault traveling wave reaches point M is recorded as The time when it reaches point N is recorded as , then: (13) (14) (15) 3) For the mixed lines of overhead lines and cable lines, normalization is performed, and the cable lines are equivalent to overhead lines of corresponding lengths. The wave velocities of traveling waves in overhead lines and cable lines are expressed as , It means that the calculation formula for the wave speed conversion of different lines is: (16) In the formula is the normalized equivalent overhead line length of the cable, Indicates the length of cables in the distribution network.

Claims

1. A transmission line fault location method based on ICEEMDAN and improved YOLOv8, characterized in that: The improved YOLOv8 network is used to construct a fault identification model and a fault location model respectively. The fault identification model is used to identify whether a fault occurs and determine the initial fault time range according to the fault voltage waveform diagram; The fault location model is used to obtain a reduced fault time range or a fault time point according to the fault traveling wave energy spectrum diagram; The method comprises the following steps: Step 1: Collect the three-phase voltage transient signals at both ends of the line after the fault occurs, obtain the fault voltage waveform, use the Karenberg transformation method to perform phase mode transformation on the three-phase voltage transient signals, and select the line mode component as the fault traveling wave research object; Step 2: Use the ICEEMDAN algorithm to decompose the line mode components, use the NTEO algorithm to enhance the modal components of the line mode components, highlight the fault signal characteristics, and obtain the fault traveling wave energy spectrum and the amplified traveling wave energy spectrum; Step 3: Using the fault voltage waveform diagram obtained in step 1 and the fault traveling wave energy spectrum diagram and the amplified traveling wave energy spectrum diagram obtained in step 2, a traveling wave detection data set is established; Step 4: Build a fault identification model and a fault location model respectively, and train them using the traveling wave detection dataset; Step 5: For a newly occurring single-phase line grounding fault, read the voltage transient signals at both ends of the line, obtain the fault voltage waveform and input it into the fault identification model, and use the fault identification model to determine whether there is a line fault and determine the initial fault time range; Step 6: According to the initial fault time range, obtain the line mode component of the three-phase voltage transient signal in the corresponding time stage, and obtain the fault traveling wave energy spectrum after ICEEMDAN decomposition and NTEO algorithm enhancement in step 2. Input it into the fault location model to obtain the reduced fault time range. Step 7: According to the reduced fault time range, the line mode component of the three-phase voltage transient signal of the corresponding time stage is obtained, and the enlarged traveling wave energy spectrum is obtained through the ICEEMDAN decomposition and NTEO algorithm enhancement in step 2. The fault location model is used to obtain the fault time point, i.e., the accurate arrival time of the fault traveling wave head at both ends of the line according to the enlarged traveling wave energy spectrum. Step 8: Based on the accurate arrival time of the fault wave head at both ends of the line obtained in step 6, the fault point location is calculated.

2. The method for measuring fault location of a power transmission line according to claim 1, characterized in that: In step 2, ICEEMDAN is used to decompose the line mode components of the fault traveling wave voltage, including: 1) Based on the original signal s, a new signal sequence is generated by adding auxiliary noise of empirical mode decomposition: ；(1) in, represents the added i-th group of zero-mean Gaussian white noise; represents the signal-to-noise ratio of the initially added noise; represents the i-th intrinsic mode function component of the empirical mode decomposition of the signal; represents the new sequence formed after adding the i-th group of auxiliary noise; 2) Find the local mean of the signal , and then take the overall average of the signal to get the first-order residual component , ；(2) ；(3) in, represents the local mean of the signal, Indicates the overall mean of the signal; 3) The first-order intrinsic mode function component of the signal is obtained by taking the difference between the original signal and the first-order residual component , ；(4) 4) Take the first-order residual component Based on this, we add multiple groups of auxiliary noise and take the mean to obtain a new second-order residual component. , and then find the difference to get the second-order intrinsic mode function component of the signal , ；(5) ；(6) In the formula represents the signal-to-noise ratio of the second noise addition; 5) Repeat the calculation to obtain the residual component of the kth stage and the kth stage intrinsic mode function component , ；(7) ；(8) In the formula , Represent the residual components of the k-1th and kth stages respectively; represents the signal-to-noise ratio of the k-th noise addition; 6) Continue iterating until the residual signal can no longer be decomposed and the decomposition termination condition is met, and all intrinsic mode function components and residual components are obtained.

3. The power transmission line fault location method according to claim 2, characterized in that: In step 2, the NTEO algorithm includes: For continuous-time signals , TEO energy operator It is expressed as: ；(9) In the formula , Respectively The first and second derivatives of ; For discrete-time signals , the TEO energy operator is expressed as: ；(10) Introducing resolution parameters , the NTEO energy operator is expressed as: ；(11) Increasing the interval between sampling signal points can reduce the interference of continuous noise, improve the sensitivity to signal frequency, and thus enhance noise resistance.

4. The power transmission line fault location method according to claim 3, characterized in that: In step 3, the traveling wave detection data set includes: 1) Fault voltage waveform, i.e. three-phase voltage transient signal diagram after the fault occurs; 2) Fault traveling wave energy spectrum diagram. The fault three-phase voltage transient signal within the fault occurrence time range is transformed into the fault traveling wave line mode component by phase mode transformation. The line mode component is then decomposed by the ICEEMDAN algorithm to obtain the first-order intrinsic mode function component. The first-order intrinsic mode function component is enhanced by the NTEO energy operator to obtain the fault traveling wave characteristic energy spectrum diagram. 3) The enlarged traveling wave energy spectrum diagram is obtained by phase-mode transformation of the fault three-phase voltage transient signal within the reduced fault traveling wave time range to obtain the fault traveling wave line mode component, and then the line mode component is decomposed by the ICEEMDAN algorithm to obtain the first-order intrinsic mode function component. The first-order intrinsic mode function component is enhanced by the NTEO energy operator to obtain the enlarged fault traveling wave characteristic energy spectrum diagram.

5. The power transmission line fault location method according to claim 1, 2, 3 or 4, characterized in that: The construction process of the improved YOLOv8 network specifically includes: a) Integrate the GhostConv module in the GhostNet network into the BottleNeck module to obtain the GhostBottleNeck module; b) Use the GhostBottleNeck module to replace the BottleNeck layer of the C3 module of YOLOv5 to obtain the C3Ghost module; c) Based on the principle of scale sequence feature fusion module in ASF-YOLO network, construct ScalSeq module; d) Replace all C2f modules in the backbone network Backbone and the neck network Neck in YOLOv8 with C3Ghost modules, and replace the Concat module and Upsample module in the neck network Neck with ScalSeq modules to obtain an improved YOLOv8 network.

6. The method for measuring fault location of a power transmission line according to claim 5, characterized in that: The C3Ghost module includes two parallel convolutional layers Conv, one of which is connected to the terminal convolutional layer Conv via multiple GhostBottleNeck modules and a concatenation layer Concat, and the other parallel convolutional layer Conv is directly connected to the terminal convolutional layer Conv.

7. The method for measuring fault location of a power transmission line according to claim 6, characterized in that: The GhostBottleNeck module includes a parallel ghost convolution layer GhostConv and a depth-separable convolution layer DWConv. The depth-separable convolution layer DWConv is connected to the terminal fusion layer Add via the convolution layer Conv. The ghost convolution layer GhostConv is connected to the terminal fusion layer Add via another depth-separable convolution layer DWConv and another ghost convolution layer GhostConv.

8. The method for measuring fault location of a power transmission line according to claim 7, characterized in that: In step 8, the calculation to obtain the position of the line fault point includes: 1) Calculate the wave velocity of the zero mode or line mode component corresponding to the fault traveling wave of the line according to the parameters of the transmission line , the calculation formula is: ；（12） In the formula , They are the inductance and capacitance of the line per unit length under the same phase sequence respectively; 2) According to the principle of double-terminal traveling wave ranging, the location of the fault on the line is assumed to be point F, and the time of the fault is recorded as , the fault traveling wave propagates from point F to points M and N at the left and right ends of the line, where M is the left end point of the line and N is the right end point of the line; The time when the initial wave head of the fault traveling wave reaches point M is recorded as The time when it reaches point N is recorded as , then: ；（13） ；（14） ；（15） In the formula Indicates the distance from point F to point M; 3) For the mixed lines of overhead lines and cable lines, normalization is performed, and the cable lines are equivalent to overhead lines of corresponding lengths. The wave velocities of traveling waves in overhead lines and cable lines are expressed as , It means that the calculation formula for the wave speed conversion of different lines is: ；（16） In the formula is the normalized equivalent overhead line length of the cable, Indicates the length of cables in the distribution network.

9. The system of the power transmission line fault location method according to claim 1 or 2 or 3 or 4 or 6 or 7 or 8, characterized in that: The system comprises: Traveling wave generation module: used to simulate and obtain the three-phase fault transient voltage signal at a sampling rate of 10MHz after a line fault occurs, and output the fault voltage waveform; Fault voltage waveform detection module: used to process the fault voltage waveform diagram to obtain the fault voltage waveform detection diagram with a boundary box, the fault target probability and the fault initial time range of the traveling wave body; Phase mode conversion module: used to convert the three-phase fault transient voltage signal within the initial time range of the fault into the corresponding line mode component through the Karenberg transformation matrix; ICCEMDAN algorithm module: used to decompose the fault characteristics of the line mode components within a given time range through the ICCEMDAN algorithm to obtain the corresponding first-order intrinsic mode function components; NTEO algorithm module: used to enhance the fault characteristics of the first-order intrinsic mode function components within a given time range through the NTEO algorithm to obtain the corresponding energy spectrum data, as well as the fault traveling wave energy spectrum diagram or the amplified traveling wave energy spectrum diagram; Traveling wave energy spectrum detection module: used to pass the line mode components within the initial time range of the fault through the ICCEMDAN algorithm module and the NTEO algorithm module respectively, to obtain the fault traveling wave energy spectrum detection diagram with a bounding box, the fault target probability and the fault reduction time range of the traveling wave body; then filter the energy spectrum data within the fault reduction time range to obtain the enlarged traveling wave energy spectrum detection diagram with a bounding box, the fault target probability and the accurate arrival time of the traveling wave head; Line fault point calculation module: used to integrate the accurate arrival time of the traveling wave heads at both ends of the line, that is, the time corresponding to the maximum point in the energy spectrum diagram, and calculate the accurate fault point location of the line.

Images