Distributed optical fiber vibration detection method and system for power transmission lines based on CNN

Through the CNN-based method, power supply areas are divided and adaptive sampling are carried out on the transmission line, and optical fiber vibration prediction model is constructed, which solves the problem of untargeted vibration signals in different power supply areas in the prior art, and improves detection efficiency and accuracy.

CN118817062BActive Publication Date: 2024-11-15STATE GRID GANSU ELECTRIC POWER CO LANZHOU POWER SUPPLY CO
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411304701.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-19
Publication Date
2024-11-15
Estimated Expiration
2044-09-19

AI Technical Summary

Technical Problem

The prior art lacks targetedness in the acquisition of vibration signals in different power supply areas on the transmission line, resulting in low detection efficiency, high power supply areas may miss inspection, and low power supply areas waste resources.

Method used

The distributed optical fiber vibration detection method for transmission lines based on CNN, by dividing power supply areas, calculating importance index and historical accident frequency, adaptively adjusting the resampling frequency, and constructing an optical fiber vibration prediction model to realize an adaptive sampling strategy for different regions.

Benefits of technology

It improves the pertinence and efficiency of detection, ensures the detection quality of high power supply areas, reduces resource waste in low power supply areas, realizes balanced and optimized configuration of detection resources, and enhances the system's real-time response capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118817062B_ABST
    Figure CN118817062B_ABST
Patent Text Reader

Abstract

The present application discloses a distributed optical fiber vibration detection method and system for power transmission lines based on CNN, which relates to the technical field of optical fiber vibration detection. The power transmission lines are divided into n1 power supply areas according to their voltage categories; for each power supply area, the voltage category, the power transmission capacity index and the power reliability index are obtained, and the importance index of the power transmission line is calculated; for each power supply area, the number of optical fiber vibration accidents is obtained, the historical accident frequency index is calculated, and the optical fiber vibration detection intensity is calculated according to the transmission line importance index and the historical accident frequency index; the original vibration signal is obtained, and a resampling frequency is calculated according to the optical fiber vibration detection intensity, and the original vibration signal is resampled using the resampling frequency to obtain a resampled vibration signal; a training sample is constructed using the resampled vibration signal, and a CNN model is constructed to obtain an optical fiber vibration prediction model for training, and for each power supply area, the optical fiber vibration prediction model is used to perform vibration detection on the power supply area.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of optical fiber vibration detection, and in particular to a CNN-based distributed optical fiber vibration detection method and system for power transmission lines. Background Art

[0002] The safe operation of transmission lines is crucial to the power system. More than 70% of transmission line failures are caused by external forces, such as lightning strikes, icing, wind deflection, tree toppling, and human damage. Traditional line fault alarms mainly rely on electrical quantity reflections such as line protection device action information and fault recording.

[0003] The Chinese patent with the publication number CN114325249A discloses a fault detection system based on optical fiber sensing technology for power substations, including: GIS discharge distributed positioning technology using phase-sensitive optical time domain reflection technology, distributed optical fiber vibration detection system based on GIS internal discharge, continuous optical fiber is arranged inside the GIS device, and the output signal of the optical fiber is measured based on phase-sensitive optical time domain reflection technology, and GIS discharge distributed positioning technology is adopted: that is, the signal characteristic technology of the distributed optical fiber vibration detection system caused by GIS internal discharge is measured: by studying the factors affecting the signal-to-noise ratio, sensitivity, spatial resolution, positioning accuracy, and sampling rate of the distributed optical fiber positioning system, the influence of the light source signal parameters, optoelectronic device parameters, signal detection and post-processing methods, and optical fiber layout schemes in the system on the above performance indicators is mastered; optical fiber data sensing technology is used and combined with the DAS fault detection system to judge abnormal conditions and issue warnings at the fastest speed. The distributed optical fiber is a special optical fiber sensor, which is mainly used for distributed measurement of parameters such as temperature and strain in a wide range. Its basic working principle is to use the fact that when light is transmitted in the optical fiber, various linear and nonlinear scattering will be generated due to the fluctuation of the core refractive index or external effects.

[0004] The existing technology adopts a unified signal collection strategy for vibration signals in different power supply areas on the transmission line, without considering the risk differences in different areas. The collection of optical fiber vibration signals lacks specificity. High-power supply areas may be missed due to insufficient sampling frequency, while low-power supply areas waste too many sampling resources, and the overall detection efficiency is low. Summary of the invention

[0005] The present application aims to solve at least one of the technical problems in the related art to a certain extent. To this end, one purpose of the present application is to propose a distributed optical fiber vibration detection method and system for power transmission lines based on CNN, which improves the pertinence of optical fiber vibration signal detection in different power supply areas.

[0006] One aspect of the present application provides a distributed optical fiber vibration detection method for a power transmission line based on CNN, comprising:

[0007] Step S100: Divide the transmission line into n1 power supply areas according to its voltage category, and each power supply area corresponds to a section of optical fiber link;

[0008] Step S200: For each power supply area, the voltage category, power transmission capacity index and power reliability index of the power supply area are obtained, and the power transmission line importance index of the power supply area is calculated;

[0009] Step S300: For each power supply area, the number of optical fiber vibration accidents in the history is obtained, and the historical accident frequency index is calculated. According to the importance index of the power transmission line in the power supply area and the historical accident frequency index, the optical fiber vibration detection intensity of the power supply area is calculated;

[0010] Step S400: obtaining the original vibration signal of each power supply area, calculating the resampling frequency according to the optical fiber vibration detection strength, and resampling the original vibration signal using the resampling frequency to obtain a resampled vibration signal;

[0011] Step S500: construct training samples using resampled vibration signals, construct a CNN model and train it to obtain an optical fiber vibration prediction model. For each power supply area, calculate its resampling frequency, and use the optical fiber vibration prediction model to perform vibration detection on the power supply area.

[0012] Furthermore, the specific method of dividing the power transmission line into n1 power supply areas according to the voltage category, and each power supply area corresponds to a section of the optical fiber link is:

[0013] Step S110: Obtain the spatial coordinates of all towers on the transmission line and the voltage of the corresponding transmission line. The spatial coordinates of the i-th tower are , the corresponding voltage is ;

[0014] Step S120: setting a voltage category classification threshold, wherein the voltage category classification threshold includes a first classification threshold, a second classification threshold, and a third classification threshold;

[0015] Step S130: quantify the voltage of the transmission line into voltage categories according to the voltage category classification threshold. When the voltage of the transmission line is less than or equal to the first classification threshold, the voltage category ; When the voltage of the transmission line is greater than the first division threshold and less than or equal to the second division threshold, the voltage category ; When the voltage of the transmission line is greater than the second division threshold and less than or equal to the third division threshold, the voltage category ; When the voltage of the transmission line is greater than the third division threshold, the voltage category ;

[0016] Step S140: Divide the power supply area of ​​the transmission line according to the voltage classification threshold, and Separately divided into power supply areas , the power supply area Join the power supply area set; start from the second tower and judge each tower With the previous tower Are the voltage categories the same? ≥2, when the tower The voltage category is the same as the previous tower When the voltage categories are the same, the tower Divide to the previous tower In the same power supply area; when the tower The voltage category is the same as the previous tower When the voltage category is different, the tower Divide into new power supply areas, and add the new power supply areas to the power supply area set; repeat the above process until the division of power supply areas of all towers is completed;

[0017] Step S150: For each power supply area, the minimum and maximum spatial coordinates of the pole tower in the power supply area are obtained, the minimum value of the pole tower spatial coordinates is used as the starting coordinates of the optical fiber link in the power supply area, and the maximum value of the pole tower spatial coordinates is used as the end coordinates of the optical fiber link in the power supply area.

[0018] Furthermore, for each power supply area, the voltage category, transmission capacity index and power reliability index of the power supply area are obtained, and the specific method for calculating the importance index of the power transmission line of the power supply area is:

[0019] Step S210: For each power supply area, obtain its voltage category , Indicates the voltage category of the ath power supply area;

[0020] Step S220: For each power supply area, count the total number of power transmission lines in the power supply area. , measuring the current on each transmission line and voltage , calculate the actual transmission power of each transmission line , perform weighted summation on the transmission power of all transmission lines in the power supply area to obtain the comprehensive transmission power ;

[0021] Step S230: Obtain the rated transmission power of each power supply area , the ratio of the comprehensive transmission power to the rated transmission power Compare with 1 and take the minimum value between the two as the transmission capacity index ;

[0022] Step S240: For each power supply area, calculate the power reliability index of the power supply area according to whether the transmission line to which the power supply area belongs contains important load types. ;

[0023] Step S250: Using the voltage category of each power supply area , Transmission Capacity Index , Power reliability index Calculate the importance index of the transmission line in the power supply area .

[0024] Furthermore, for each power supply area, the number of optical fiber vibration accidents in the history is obtained, and the historical accident frequency index is calculated. According to the importance index of the power transmission line and the historical accident frequency index of the power supply area, the specific method for calculating the optical fiber vibration detection strength of the power supply area is:

[0025] Step S310: extract all the optical fiber vibration accident records that occurred according to the operation and maintenance records of the transmission line, associate the optical fiber vibration accident records with the corresponding power supply areas, and obtain the number of optical fiber vibration accidents in each power supply area within the historical time length T;

[0026] Step S320: Obtain the length of optical fiber in each power supply area , multiply the fiber length by the historical time T to obtain the product The ratio of the number of optical fiber vibration accidents in the power supply area to the product is used as the historical accident frequency index of the power supply area. ;

[0027] Step S330: weighted sum of the importance index of the power transmission line and the historical accident frequency index of each power supply area to obtain the optical fiber vibration detection intensity of the power supply area .

[0028] Furthermore, the specific method of obtaining the original vibration signal of each power supply area, calculating the resampling frequency according to the optical fiber vibration detection strength, and resampling the original vibration signal using the resampling frequency to obtain the resampled vibration signal is:

[0029] Step S410: For each power supply area, according to the starting point coordinates and the end point coordinates of the corresponding optical fiber link, the original vibration signals of the same sampling point on the optical fiber link in the power supply area at different times are obtained, and the vibration signals of all the sampling points constitute an original vibration signal set;

[0030] The original vibration signal of the hth sampling point is: ,in, is the Mth original vibration signal of the optical fiber link, and M is the total number of original vibration signals;

[0031] Step S420: Obtaining a reference sampling frequency Maximum value of optical fiber vibration detection force in the power supply area According to the maximum value of the optical fiber vibration detection intensity, the optical fiber vibration detection intensity of the a-th power supply area is normalized to obtain the normalized basis value , multiply the normalized basis value by the base sampling frequency to get the resampling frequency ;

[0032] Step S430: resampling the original vibration signal using the resampling frequency to obtain a resampled vibration signal;

[0033] The resampled vibration signal is ,in, is the mth resampled vibration signal, and m is the total number of resampled vibration signals.

[0034] Furthermore, the specific method of resampling the original vibration signal using the resampling frequency to obtain the resampled vibration signal is:

[0035] Step S431: Obtaining the original sampling frequency according to the hardware setting of the distributed optical fiber vibration sensor , the ratio of the resampling frequency to the original sampling frequency As the resampling factor θ1, when θ1>1, the original vibration signal is upsampled; when θ1<1, the original vibration signal is downsampled; when θ1=1, the original vibration signal is resampled at the resampling frequency;

[0036] Step S432: The original sampling time corresponding to the original vibration signal is ,in, is the Mth original sampling time, the jth original sampling time ;

[0037] Step S433: The resampling time corresponding to the resampled vibration signal is ,in, is the mth resampling moment, Resampling time ;

[0038] Step S434: For the resampling time , find from the original sampling time Two adjacent original sampling moments and ,satisfy ≤ < , linear interpolation is used to calculate the resampling time Resampled vibration signal ;

[0039] Step S435: Calculate and obtain the resampled vibration signals at all resampled moments.

[0040] Furthermore, the specific method of constructing training samples using resampled vibration signals, constructing a CNN model and training to obtain an optical fiber vibration prediction model, calculating the resampling frequency for each power supply area, and using the optical fiber vibration prediction model to perform vibration detection on the power supply area is as follows:

[0041] Step S510: extracting Y resampled vibration samples from the resampled vibration signal using a sliding window method, and marking whether an optical fiber vibration accident has occurred within a historical time range corresponding to the resampled vibration samples of the power supply area according to the optical fiber vibration accident records associated with each power supply area, and obtaining the marked resampled vibration samples as training samples;

[0042] Step S520: construct a CNN model, the CNN model includes an input layer, a convolution layer, a pooling layer, a fully connected layer and an output layer, the input layer inputs the resampled vibration sample, the convolution layer uses a one-dimensional convolution kernel, the pooling layer selects a one-dimensional maximum pooling layer, and the last fully connected layer is connected to the output layer. The output layer contains a neuron and uses a Sigmoid function to output the probability of an optical fiber vibration accident.

[0043] Step S530: Select binary cross entropy as the loss function for training the CNN model and use the Adam optimization algorithm for optimization;

[0044] Step S540: using the resampled vibration sample as input data, and using whether an optical fiber vibration accident has occurred within the historical time range corresponding to the resampled vibration sample as output data, outputting 0 if no optical fiber vibration accident has occurred, and outputting 1 if an optical fiber vibration accident has occurred;

[0045] Step S550: taking accurate prediction of whether an optical fiber vibration accident occurs as a prediction target and minimizing the loss function as a training target, and when the loss function reaches convergence, stopping the training to obtain a trained optical fiber vibration prediction model;

[0046] Step S560: For the power supply area that needs to perform optical fiber vibration detection, obtain its real-time original vibration signal, calculate its resampling frequency and resample the real-time original vibration signal to obtain a real-time resampled vibration signal, and use the optical fiber vibration prediction model to predict whether there are optical fiber vibration accidents on different optical fiber links in the power supply area.

[0047] One aspect of the present application provides a CNN-based distributed optical fiber vibration detection system for power transmission lines, comprising:

[0048] A power supply area division module is used to divide the power transmission line into n1 power supply areas according to its voltage category, and each power supply area corresponds to a section of optical fiber link;

[0049] An importance index calculation module is used to obtain, for each power supply area, the voltage category, transmission capacity index and power reliability index of the power supply area, and calculate the importance index of the power transmission line in the power supply area;

[0050] The sampling basis calculation module is used to obtain the number of optical fiber vibration accidents in the historical time for each power supply area, calculate the historical accident frequency index, and calculate the optical fiber vibration detection intensity of the power supply area according to the power transmission line importance index and the historical accident frequency index of the power supply area;

[0051] A vibration signal sampling module is used to obtain the original vibration signal of each power supply area, calculate the resampling frequency according to the optical fiber vibration detection strength, and resample the original vibration signal using the resampling frequency to obtain a resampled vibration signal;

[0052] The optical fiber vibration detection module is used to construct training samples using resampled vibration signals, build a CNN model and train it to obtain an optical fiber vibration prediction model. For each power supply area, its resampling frequency is calculated, and the optical fiber vibration prediction model is used to perform vibration detection on the power supply area.

[0053] One aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in a distributed optical fiber vibration detection method for a power transmission line based on CNN are implemented.

[0054] One aspect of the present application provides a readable storage medium storing a computer program, wherein the computer program is suitable for loading by a processor to execute the steps in a CNN-based distributed optical fiber vibration detection method for power transmission lines.

[0055] Compared with the prior art, the CNN-based distributed optical fiber vibration detection method and system for power transmission lines proposed in this application have the following advantages:

[0056] By dividing the transmission lines into power supply areas and adopting an adaptive sampling strategy for different power supply areas, and by calculating the resampling frequencies of different power supply areas, the present application can reduce resource waste in low power supply areas while ensuring the detection quality in high power supply areas, thereby improving the detection efficiency as a whole and achieving a balanced and optimal configuration of detection resources.

[0057] This application fully explores and utilizes the characteristics and laws of vibration signals in different power supply areas, and combines prior knowledge such as voltage category, transmission line importance index, and historical accident frequency index of the power supply area to construct a fiber vibration prediction model for different power supply areas. Compared with a unified detection method, this application can more accurately capture the key signal patterns of each power supply area, greatly improving the pertinence and effectiveness of detection.

[0058] This patent can optimize the detection strategy in real time according to the dynamic changes of the power supply area by adaptively adjusting the resampling frequency, enhance the real-time response capability and adaptability of the system, and make the detection process more flexible and intelligent. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A method flow chart of a distributed optical fiber vibration detection method for power transmission lines based on CNN provided in this application;

[0060] Figure 2 Functional module diagram of the CNN-based distributed optical fiber vibration detection system for power transmission lines provided in this application;

[0061] Figure 3 A schematic diagram of the structure of an electronic device provided in this application;

[0062] Figure 4 It is a schematic diagram of the structure of a readable storage medium provided by this application. DETAILED DESCRIPTION

[0063] In order to better understand the present application, various aspects of the present application will be described in more detail with reference to the accompanying drawings. It should be understood that these detailed descriptions are only descriptions of exemplary embodiments of the present application and do not limit the scope of the present application in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0064] In the accompanying drawings, the size, dimensions and shapes of the elements have been slightly adjusted for ease of illustration. The drawings are for illustration only and are not strictly drawn to scale. As used herein, the terms "substantially", "approximately" and similar terms are used as terms of approximation, not as terms of degree, and are intended to illustrate the inherent deviations in measurements or calculations that will be recognized by those of ordinary skill in the art. In addition, in this application, the order in which the steps are described does not necessarily represent the order in which these processes occur in actual operation, unless otherwise specified or can be derived from the context.

[0065] It should also be understood that expressions such as "including", "comprising", "having", "containing" and / or "comprising" are open rather than closed expressions in this specification, which indicate the presence of the stated features, elements and / or components, but do not exclude the presence of one or more other features, elements, components and / or combinations thereof. In addition, when expressions such as "at least one of..." appear after a list of listed features, they modify the entire list of features rather than just the individual elements in the list. In addition, when describing embodiments of the present application, "may" is used to mean "one or more embodiments of the present application". And, the term "exemplary" is intended to refer to an example or illustration.

[0066] Unless otherwise defined, all words (including engineering terms and scientific and technological terms) used in this article have the same meaning as those commonly understood by ordinary technicians in the field to which this application belongs. It should also be understood that unless there is a clear explanation in this application, words defined in commonly used dictionaries should be interpreted as having the same meaning as their meaning in the context of the relevant technology, and should not be interpreted in an idealized or overly formal sense.

[0067] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0068] Example 1

[0069] like Figure 1 As shown, the distributed optical fiber vibration detection method for power transmission lines based on CNN provided in this application includes:

[0070] Step S100: Divide the transmission line into n1 power supply areas according to its voltage category, and each power supply area corresponds to a section of optical fiber link;

[0071] The specific method of dividing the transmission line into n1 power supply areas according to the voltage category, and each power supply area corresponds to a section of the optical fiber link is as follows:

[0072] Step S110: Obtain the spatial coordinates of all towers on the transmission line and the voltage of the corresponding transmission line. The spatial coordinates of the i-th tower are , the corresponding voltage is ;

[0073] Step S120: setting a voltage category classification threshold, wherein the voltage category classification threshold includes a first classification threshold, a second classification threshold, and a third classification threshold;

[0074] The first division threshold is 110 kV, the second division threshold is 220 kV, and the third division threshold is 330 kV;

[0075] Step S130: quantify the voltage of the transmission line into voltage categories according to the voltage category classification threshold. When the voltage of the transmission line is less than or equal to the first classification threshold, the voltage category ; When the voltage of the transmission line is greater than the first division threshold and less than or equal to the second division threshold, the voltage category ; When the voltage of the transmission line is greater than the second division threshold and less than or equal to the third division threshold, the voltage category ; When the voltage of the transmission line is greater than the third division threshold, the voltage category ;

[0076] Step S140: Divide the power supply area of ​​the transmission line according to the voltage classification threshold, and Separately divided into power supply areas , the power supply area Join the power supply area set; start from the second tower and judge each tower With the previous tower Are the voltage categories the same? ≥2, when the tower The voltage category is the same as the previous tower When the voltage categories are the same, the tower Divide to the previous tower In the same power supply area; when the tower The voltage category is the same as the previous tower When the voltage category is different, the tower Divide into new power supply areas, and add the new power supply areas to the power supply area set; repeat the above process until the division of power supply areas of all towers is completed;

[0077] Step S150: For each power supply area, the minimum and maximum values ​​of the pole tower spatial coordinates in the power supply area are obtained, the minimum value of the pole tower spatial coordinates is used as the starting point coordinates of the optical fiber link in the power supply area, and the maximum value of the pole tower spatial coordinates is used as the end point coordinates of the optical fiber link in the power supply area;

[0078] In order to refine the sampling frequency of vibration signals in different areas, the transmission lines are divided into different power supply areas according to voltage categories. This step divides the transmission lines into multiple power supply areas according to voltage categories, providing a basic unit for subsequent importance index calculation and optical fiber vibration data analysis.

[0079] Step S200: For each power supply area, the voltage category, power transmission capacity index and power reliability index of the power supply area are obtained, and the power transmission line importance index of the power supply area is calculated;

[0080] The specific method of obtaining the voltage category, transmission capacity index and power reliability index of each power supply area and calculating the importance index of the power transmission line of the power supply area is as follows:

[0081] Step S210: For each power supply area, obtain its voltage category , Indicates the voltage category of the ath power supply area;

[0082] As can be seen from step S100, the power supply area of ​​the transmission line is divided according to the voltage category of each tower. Once the voltage categories of two adjacent towers are inconsistent, they are divided into two power supply areas. Therefore, the voltage category of the transmission line in each power supply area is the same.

[0083] Step S220: For each power supply area, count the total number of power transmission lines in the power supply area. , measuring the current on each transmission line and voltage , calculate the actual transmission power of each transmission line , perform weighted summation on the transmission power of all transmission lines in the power supply area to obtain the comprehensive transmission power ;

[0084] The actual transmission power of each transmission line The calculation formula is: ,in, represents the voltage on the kth transmission line in the ath power supply area, represents the current on the kth transmission line in the ath power supply area, Indicates the power factor between current and voltage;

[0085] The power factor represents the phase difference between current and voltage and is measured using a power factor meter;

[0086] The power factor between current and voltage of transmission lines with different types of power loads is different. Generally, the power factor under industrial loads ranges from 0.85 to 0.95, the power factor under commercial loads ranges from 0.90 to 0.98, and the power factor under residential loads ranges from 0.80 to 0.90.

[0087] The integrated transmission power The calculation formula is: ,in, is the comprehensive transmission power of the ath power supply area, is the weight coefficient of the kth transmission line, is the actual transmission power of the kth transmission line, k∈{1,2,...,};

[0088] The weight coefficient of the transmission line is set by a person skilled in the art according to the operating status of different transmission lines;

[0089] Step S230: Obtain the rated transmission power of each power supply area , the ratio of the comprehensive transmission power to the rated transmission power Compare with 1 and take the minimum value between the two as the transmission capacity index ;

[0090] The calculation formula of the transmission capacity index is: ,in, is the rated transmission power of the ath power supply area, The function represents the minimum value;

[0091] The rated transmission power of the power supply area is the average of the rated transmission powers of all the transmission lines in each power supply area, and the rated transmission power of the transmission line is obtained from the design document of the transmission line;

[0092] Step S240: For each power supply area, calculate the power reliability index of the power supply area according to whether the transmission line to which the power supply area belongs contains important load types. ;

[0093] The calculation formula of the power reliability index is: ,in, Indicates whether the ath power supply area contains the βth type of important load. If so, Equal to 1, if not included is equal to 0, Indicates the weight coefficients of different important load types, and sum() represents the summation function;

[0094] The weight coefficients of the different important load types are set by those skilled in the art according to the importance priority of the important load types;

[0095] The important load types include hospital load, government agency load, transportation hub load, and factory load;

[0096] Step S250: Using the voltage category of each power supply area , Transmission Capacity Index , Power reliability index Calculate the importance index of the transmission line in the power supply area ;

[0097] The calculation formula of the transmission line importance index is: ,in, , and are the weight coefficients of voltage category, transmission capacity index and power reliability index, ;

[0098] The weight coefficients of the voltage category, transmission capacity index and power reliability index are set by those skilled in the art according to actual needs and experience;

[0099] This step comprehensively utilizes the voltage category, transmission capacity index and power reliability index of the power supply area to calculate the transmission line importance index, which is an influencing factor reflecting the risk level of different power supply areas.

[0100] Step S300: For each power supply area, the number of optical fiber vibration accidents in the history is obtained, and the historical accident frequency index is calculated. According to the importance index of the power transmission line in the power supply area and the historical accident frequency index, the optical fiber vibration detection intensity of the power supply area is calculated;

[0101] For each power supply area, the number of optical fiber vibration accidents in the history is obtained, and the historical accident frequency index is calculated. According to the importance index of the power transmission line and the historical accident frequency index of the power supply area, the specific method for calculating the optical fiber vibration detection strength of the power supply area is:

[0102] Step S310: extract all the optical fiber vibration accident records that occurred according to the operation and maintenance records of the transmission line, associate the optical fiber vibration accident records with the corresponding power supply areas, and obtain the number of optical fiber vibration accidents in each power supply area within the historical period;

[0103] Step S320: Obtain the length of optical fiber in each power supply area , multiply the fiber length by the historical time T to obtain the product The ratio of the number of optical fiber vibration accidents in the power supply area to the product is used as the historical accident frequency index of the power supply area. ;

[0104] The calculation formula of the historical accident frequency index is: ,in, is the number of optical fiber vibration accidents that occurred in the a-th power supply area within the historical time length T;

[0105] The optical fiber length in the power supply area is obtained according to the route length between the starting point coordinates and the end point coordinates of the optical fiber link in the power supply area;

[0106] The historical accident frequency index reflects the frequency of optical fiber vibration accidents in each power supply area in the historical period;

[0107] Step S330: weighted sum of the importance index of the power transmission line and the historical accident frequency index of each power supply area to obtain the optical fiber vibration detection intensity of the power supply area ;

[0108] The calculation formula of the optical fiber vibration detection strength is: ,in, , are the weight coefficients of the transmission line importance index and the historical accident frequency index respectively;

[0109] The weight coefficients of the transmission line importance index and the historical accident frequency index are determined by those skilled in the art according to actual needs. + =1;

[0110] when When it is larger, the transmission line importance index has a greater impact on the sampling rate; when When is larger, the historical accident frequency index has a greater impact on the sampling rate.

[0111] This step calculates the optical fiber vibration detection strength of each power supply area through the transmission line importance index and historical accident frequency index of the power supply area. The optical fiber vibration detection strength is the basis for determining the sampling frequency of the vibration signal. The transmission line importance index and historical accident frequency index of different power supply areas are different, so their optical fiber vibration detection strength is different, and thus the subsequent calculated resampling frequency is different. The calculation of the optical fiber vibration detection strength plays an important role in implementing different sampling strategies according to different power supply areas.

[0112] Step S400: obtaining the original vibration signal of each power supply area, calculating the resampling frequency according to the optical fiber vibration detection strength, and resampling the original vibration signal using the resampling frequency to obtain a resampled vibration signal;

[0113] The original vibration signal is a vibration signal of each power supply area in the historical time;

[0114] The specific method of obtaining the original vibration signal of each power supply area, calculating the resampling frequency according to the optical fiber vibration detection strength, and resampling the original vibration signal using the resampling frequency to obtain the resampled vibration signal is as follows:

[0115] Step S410: For each power supply area, according to the starting point coordinates and the end point coordinates of the corresponding optical fiber link, the original vibration signals of the same sampling point on the optical fiber link in the power supply area at different times are obtained, and the vibration signals of all the sampling points constitute an original vibration signal set;

[0116] The original vibration signal of the hth sampling point is: ,in, is the Mth original vibration signal of the optical fiber link, and M is the total number of original vibration signals;

[0117] The original vibration signal is collected by a distributed optical fiber vibration sensor arranged in the power supply area;

[0118] Step S420: Obtaining a reference sampling frequency Maximum value of optical fiber vibration detection force in the power supply area According to the maximum value of the optical fiber vibration detection intensity, the optical fiber vibration detection intensity of the a-th power supply area is normalized to obtain the normalized basis value , multiply the normalized basis value by the base sampling frequency to get the resampling frequency ;

[0119] The calculation formula of the resampling frequency is: ;

[0120] The reference sampling frequency represents the standard sampling frequency when the power supply area is at a general risk level, and is set by those skilled in the art based on experience;

[0121] Step S430: resampling the original vibration signal using the resampling frequency to obtain a resampled vibration signal;

[0122] The resampled vibration signal is ,in, is the mth resampled vibration signal, and m is the total number of resampled vibration signals;

[0123] The specific method of resampling the original vibration signal using the resampling frequency to obtain the resampled vibration signal is:

[0124] Step S431: Obtaining the original sampling frequency according to the hardware setting of the distributed optical fiber vibration sensor , the ratio of the resampling frequency to the original sampling frequency As the resampling factor θ1, when θ1>1, the original vibration signal is upsampled; when θ1<1, the original vibration signal is downsampled; when θ1=1, the original vibration signal is resampled at the resampling frequency;

[0125] Step S432: The original sampling time corresponding to the original vibration signal is ,in, is the Mth original sampling time, the jth original sampling time ;

[0126] Step S433: The resampling time corresponding to the resampled vibration signal is ,in, is the mth resampling moment, Resampling time ;

[0127] Step S434: For the resampling time , find from the original sampling time Two adjacent original sampling moments and ,satisfy ≤ < , linear interpolation is used to calculate the resampling time Resampled vibration signal ;

[0128] The linear interpolation method is used to calculate the resampling time The calculation formula of the resampled vibration signal is: ,in, , are adjacent original sampling moments and The original vibration signal;

[0129] Step S435: Calculate and obtain the resampled vibration signals at all resampled moments;

[0130] The original sampling frequency is the sampling frequency of the distributed optical fiber vibration sensor;

[0131] This step calculates the corresponding resampling frequency according to the different optical fiber vibration detection strengths in different power supply areas, implements different sampling strategies for different power supply areas, and realizes a targeted sampling mechanism for different power supply areas.

[0132] Step S500: construct training samples using resampled vibration signals, construct a CNN model and train it to obtain an optical fiber vibration prediction model. For each power supply area, calculate its resampling frequency, and use the optical fiber vibration prediction model to perform vibration detection on the power supply area.

[0133] The specific method of constructing training samples using resampled vibration signals, constructing a CNN model and training to obtain an optical fiber vibration prediction model, calculating the resampling frequency for each power supply area, and using the optical fiber vibration prediction model to perform vibration detection on the power supply area is as follows:

[0134] Step S510: extracting Y resampled vibration samples from the resampled vibration signal using a sliding window method, and marking whether an optical fiber vibration accident has occurred within a historical time range corresponding to the resampled vibration samples of the power supply area according to the optical fiber vibration accident records associated with each power supply area, and obtaining the marked resampled vibration samples as training samples;

[0135] Step S520: construct a CNN model, the CNN model includes an input layer, a convolution layer, a pooling layer, a fully connected layer and an output layer, the input layer inputs the resampled vibration sample, the convolution layer uses a one-dimensional convolution kernel, the pooling layer selects a one-dimensional maximum pooling layer, and the last fully connected layer is connected to the output layer. The output layer contains a neuron and uses a Sigmoid function to output the probability of an optical fiber vibration accident.

[0136] The convolution layer extracts a feature map of the resampled vibration sample, and the convolution layer uses multiple convolution layers, each layer using convolution kernels of different numbers and sizes;

[0137] The pooling layer is used to reduce the size of the feature map of the resampled vibration samples;

[0138] The fully connected layer includes one or more fully connected layers;

[0139] After multiple convolutions and pooling, the feature maps extracted by the convolution layer and the pooling layer are flattened and sent to the fully connected layer to achieve nonlinear combination of features;

[0140] Step S530: Select binary cross entropy as the loss function for training the CNN model and use the Adam optimization algorithm for optimization;

[0141] Step S540: using the resampled vibration sample as input data, and using whether an optical fiber vibration accident has occurred within the historical time range corresponding to the resampled vibration sample as output data, outputting 0 if no optical fiber vibration accident has occurred, and outputting 1 if an optical fiber vibration accident has occurred;

[0142] Step S550: taking accurate prediction of whether an optical fiber vibration accident occurs as a prediction target and minimizing the loss function as a training target, and when the loss function reaches convergence, stopping the training to obtain a trained optical fiber vibration prediction model;

[0143] Step S560: For the power supply area that needs to perform optical fiber vibration detection, obtain its real-time original vibration signal, calculate its resampling frequency and resample the real-time original vibration signal to obtain a real-time resampled vibration signal, and use the optical fiber vibration prediction model to predict whether there are optical fiber vibration accidents on different optical fiber links in the power supply area.

[0144] Transmission lines in high-risk areas are of high importance, so higher resampling frequencies are required. Low-power supply areas do not require excessively high-frequency sampling and testing. Different sampling mechanisms are used for different areas.

[0145] The CNN-based optical fiber vibration prediction model takes the resampled vibration signal as input and outputs the vibration detection results of different sampling points in different power supply areas. Due to the different sampling mechanisms in different areas, the frequency of using the optical fiber vibration prediction model for optical fiber vibration accident detection in different power supply areas is different. Targeted vibration detection realizes the balanced and optimized configuration of detection resources.

[0146] Example 2

[0147] like Figure 2 As shown, the distributed optical fiber vibration detection system for power transmission lines based on CNN provided by the present application includes:

[0148] A power supply area division module is used to divide the power transmission line into n1 power supply areas according to its voltage category, and each power supply area corresponds to a section of optical fiber link;

[0149] An importance index calculation module is used to obtain, for each power supply area, the voltage category, transmission capacity index and power reliability index of the power supply area, and calculate the importance index of the power transmission line in the power supply area;

[0150] The sampling basis calculation module is used to obtain the number of optical fiber vibration accidents in the historical time for each power supply area, calculate the historical accident frequency index, and calculate the optical fiber vibration detection intensity of the power supply area according to the power transmission line importance index and the historical accident frequency index of the power supply area;

[0151] A vibration signal sampling module is used to obtain the original vibration signal of each power supply area, calculate the resampling frequency according to the optical fiber vibration detection strength, and resample the original vibration signal using the resampling frequency to obtain a resampled vibration signal;

[0152] The optical fiber vibration detection module is used to construct training samples using resampled vibration signals, build a CNN model and train it to obtain an optical fiber vibration prediction model. For each power supply area, its resampling frequency is calculated, and the optical fiber vibration prediction model is used to perform vibration detection on the power supply area.

[0153] Example 3

[0154] Figure 3 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 3 As shown, according to another aspect of the present application, an electronic device is also provided. The electronic device may include one or more processors and one or more memories. The memories store computer readable codes, and when the computer readable codes are run by one or more processors, the distributed optical fiber vibration detection method for power transmission lines based on CNN as described above may be executed.

[0155] The method or system according to the embodiment of the present application can also be used by Figure 3 The electronic device architecture shown in FIG. Figure 3 As shown, the electronic device may include a bus, one or more CPUs, a read-only memory (ROM), a random access memory (RAM), a communication port connected to a network, an input / output component, a hard disk, etc. A storage device in the electronic device, such as a ROM or a hard disk, may store the CNN-based distributed optical fiber vibration detection method for a power transmission line provided in the present application. The CNN-based distributed optical fiber vibration detection method for power transmission lines may, for example, include: dividing the power transmission line into n1 power supply areas according to its voltage category, each power supply area corresponds to a section of optical fiber link; for each power supply area, obtaining the voltage category, transmission capacity index and power reliability index of the power supply area, and calculating the importance index of the power supply area's transmission line; for each power supply area, obtaining the number of optical fiber vibration accidents in its history, calculating the historical accident frequency index, and calculating the optical fiber vibration detection strength of the power supply area according to the transmission line importance index and the historical accident frequency index of the power supply area; obtaining the original vibration signal of each power supply area, calculating the resampling frequency according to the optical fiber vibration detection strength, and resampling the original vibration signal using the resampling frequency to obtain a resampled vibration signal; constructing training samples using the resampled vibration signal, constructing a CNN model and training to obtain an optical fiber vibration prediction model, calculating the resampling frequency for each power supply area, and using the optical fiber vibration prediction model to perform vibration detection on the power supply area. Furthermore, the electronic device may also include a user interface. Of course, Figure 3 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 3 One or more components of an electronic device are shown.

[0156] Example 4

[0157] Figure 4 Schematic diagram of a readable storage medium structure provided by an embodiment of the present application. Figure 4 As shown, it is a readable storage medium according to an embodiment of the present application. Computer-readable instructions are stored on the computer-readable storage medium. When the computer-readable instructions are executed by the processor, the distributed optical fiber vibration detection method for power transmission lines based on CNN according to the embodiment of the present application described with reference to the above figures can be executed. The storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache). Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0158] In addition, according to an embodiment of the present application, the process described above with reference to the flowchart may be implemented as a computer software program. For example, the present application provides a non-temporary machine-readable storage medium, which stores machine-readable instructions, and the machine-readable instructions can be executed by a processor to execute instructions corresponding to the method steps provided in the present application, for example: dividing the transmission line into n1 power supply areas according to its voltage category, each power supply area corresponding to a section of optical fiber link; for each power supply area, obtaining the voltage category, transmission capacity index and power reliability index of the power supply area, and calculating the transmission line importance index of the power supply area; for each power supply area, obtaining the number of optical fiber vibration accidents in its historical time, calculating the historical accident frequency index, and calculating the optical fiber vibration detection strength of the power supply area according to the transmission line importance index and the historical accident frequency index of the power supply area; obtaining the original vibration signal of each power supply area, calculating the resampling frequency according to the optical fiber vibration detection strength, and resampling the original vibration signal using the resampling frequency to obtain a resampled vibration signal; constructing training samples using the resampled vibration signals, constructing a CNN model and training to obtain an optical fiber vibration prediction model, for each power supply area, calculating its resampling frequency, and performing vibration detection on the power supply area using the optical fiber vibration prediction model. When the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present application are performed.

[0159] The methods, apparatuses, and devices of the present application may be implemented in many ways. For example, the methods, apparatuses, and devices of the present application may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present application are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present application may also be implemented as programs recorded in a recording medium, which include machine-readable instructions for implementing the method according to the present application. Therefore, the present application also covers recording media storing programs for executing the method according to the present application.

[0160] In addition, the parts of the above-mentioned technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0161] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A distributed optical fiber vibration detection method for power transmission lines based on CNN, characterized in that: include: The transmission line is divided into n1 power supply areas according to its voltage category, and each power supply area corresponds to a section of optical fiber link; For each power supply area, the voltage category, transmission capacity index and power reliability index of the power supply area are obtained, and the importance index of the power transmission line of the power supply area is calculated; For each power supply area, the number of optical fiber vibration accidents in its history is obtained, and the historical accident frequency index is calculated. According to the importance index of the power transmission line and the historical accident frequency index of the power supply area, the optical fiber vibration detection intensity of the power supply area is calculated; The original vibration signal of each power supply area is obtained, a resampling frequency is calculated according to the optical fiber vibration detection strength, and the original vibration signal is resampled using the resampling frequency to obtain a resampled vibration signal; The resampled vibration signals are used to construct training samples, and a CNN model is built and trained to obtain a fiber vibration prediction model. For each power supply area, its resampling frequency is calculated, and the fiber vibration prediction model is used to perform vibration detection on the power supply area.

2. The CNN-based distributed optical fiber vibration detection method for power transmission lines according to claim 1, characterized in that: The specific method of dividing the transmission line into n1 power supply areas according to the voltage category, and each power supply area corresponds to a section of the optical fiber link is as follows: Get the spatial coordinates of all towers on the transmission line and the voltage of the corresponding transmission line. The spatial coordinates of the i-th tower are: , the corresponding voltage is ; Setting a voltage category division threshold, wherein the voltage category division threshold includes a first division threshold, a second division threshold, and a third division threshold; The voltage of the transmission line is quantified into voltage categories according to the voltage category classification threshold. When the voltage of the transmission line is less than or equal to the first classification threshold, the voltage category ; When the voltage of the transmission line is greater than the first division threshold and less than or equal to the second division threshold, the voltage category ; When the voltage of the transmission line is greater than the second division threshold and less than or equal to the third division threshold, the voltage category ; When the voltage of the transmission line is greater than the third division threshold, the voltage category ; The power supply area of ​​the transmission line is divided according to the voltage category threshold. Separately divided into power supply areas , the power supply area Join the power supply area collection; Starting from the second tower, judge each tower With the previous tower Are the voltage categories the same? ≥2, when the tower The voltage category is the same as the previous tower When the voltage categories are the same, the tower Divide to the previous tower In the same power supply area; when the tower The voltage category is the same as the previous tower When the voltage category is different, the tower Divide into a new power supply area, and add the new power supply area to the power supply area set; Until the division of power supply areas of all towers is completed; For each power supply area, the minimum and maximum values ​​of the pole tower spatial coordinates in the power supply area are obtained, the minimum value of the pole tower spatial coordinates is used as the starting point coordinates of the optical fiber link in the power supply area, and the maximum value of the pole tower spatial coordinates is used as the end point coordinates of the optical fiber link in the power supply area.

3. The CNN-based distributed optical fiber vibration detection method for power transmission lines according to claim 2, characterized in that: The specific method of obtaining the voltage category, transmission capacity index and power reliability index of each power supply area and calculating the importance index of the power transmission line of the power supply area is as follows: For each power supply area, get its voltage category , Indicates the voltage category of the ath power supply area; For each power supply area, count the total number of power transmission lines in the power supply area , measuring the current on each transmission line and voltage , calculate the actual transmission power of each transmission line , perform weighted summation on the transmission power of all transmission lines in the power supply area to obtain the comprehensive transmission power ; Get the rated transmission power of each power supply area , the ratio of the comprehensive transmission power to the rated transmission power Compare with 1 and take the minimum value between the two as the transmission capacity index ; For each power supply area, the power reliability index of the power supply area is calculated according to whether the transmission line to which the power supply area belongs contains important load types. ; Utilize the voltage category of each power supply area , Transmission Capacity Index , Power reliability index Calculate the importance index of the transmission line in the power supply area .

4. The CNN-based distributed optical fiber vibration detection method for power transmission lines according to claim 3, characterized in that: For each power supply area, the number of optical fiber vibration accidents in the history is obtained, and the historical accident frequency index is calculated. According to the importance index of the power transmission line and the historical accident frequency index of the power supply area, the specific method for calculating the optical fiber vibration detection strength of the power supply area is: According to the operation and maintenance records of the transmission lines, all the records of optical fiber vibration accidents are extracted, and the records of optical fiber vibration accidents are associated with the corresponding power supply areas to obtain the number of optical fiber vibration accidents in each power supply area within the historical time length T; Get the fiber length in each power supply area , multiply the fiber length by the historical time T to obtain the product The ratio of the number of optical fiber vibration accidents in the power supply area to the product is used as the historical accident frequency index of the power supply area. ; The optical fiber vibration detection intensity of each power supply area is obtained by weighted summing the transmission line importance index and the historical accident frequency index of each power supply area. .

5. The CNN-based distributed optical fiber vibration detection method for power transmission lines according to claim 4, characterized in that: The specific method of obtaining the original vibration signal of each power supply area, calculating the resampling frequency according to the optical fiber vibration detection strength, and resampling the original vibration signal using the resampling frequency to obtain the resampled vibration signal is as follows: For each power supply area, according to the starting point coordinates and the end point coordinates of the corresponding optical fiber link, the original vibration signals of the same sampling point on the optical fiber link in the power supply area at different times are obtained, and the vibration signals of all sampling points constitute the original vibration signal set; The original vibration signal of the hth sampling point is: ,in, is the Mth original vibration signal of the optical fiber link, and M is the total number of original vibration signals; Get the base sampling frequency Maximum value of optical fiber vibration detection force in the power supply area According to the maximum value of the optical fiber vibration detection intensity, the optical fiber vibration detection intensity of the a-th power supply area is normalized to obtain the normalized basis value , multiply the normalized basis value by the base sampling frequency to get the resampling frequency ; Resampling the original vibration signal using the resampling frequency to obtain a resampled vibration signal; The resampled vibration signal is ,in, is the mth resampled vibration signal, and m is the total number of resampled vibration signals.

6. The CNN-based distributed optical fiber vibration detection method for power transmission lines according to claim 5, characterized in that: The specific method of resampling the original vibration signal using the resampling frequency to obtain the resampled vibration signal is: The original sampling frequency is obtained according to the hardware settings of the distributed optical fiber vibration sensor , the ratio of the resampling frequency to the original sampling frequency As the resampling factor θ1, when θ1>1, the original vibration signal is upsampled; when θ1<1, the original vibration signal is downsampled; when θ1=1, the original vibration signal is resampled at the resampling frequency; The original sampling time corresponding to the original vibration signal is ,in, is the Mth original sampling time, the jth original sampling time ; The resampling time corresponding to the resampled vibration signal is ,in, is the mth resampling moment, Resampling time ; For the resampling time , find from the original sampling time Two adjacent original sampling moments and ,satisfy ≤ < , linear interpolation is used to calculate the resampling time Resampled vibration signal ; The resampled vibration signals at all resampled moments are calculated.

7. The CNN-based distributed optical fiber vibration detection method for power transmission lines according to claim 6, characterized in that: The specific method of constructing training samples using resampled vibration signals, constructing a CNN model and training to obtain an optical fiber vibration prediction model, calculating the resampling frequency for each power supply area, and using the optical fiber vibration prediction model to perform vibration detection on the power supply area is as follows: A sliding window method is used to extract Y resampled vibration samples from the resampled vibration signal, and according to the optical fiber vibration accident records associated with each power supply area, whether an optical fiber vibration accident has occurred within the historical time range corresponding to the resampled vibration samples of the power supply area is marked, and the marked resampled vibration samples are obtained as training samples; Construct a CNN model, wherein the CNN model includes an input layer, a convolution layer, a pooling layer, a fully connected layer and an output layer, wherein the input layer inputs a resampled vibration sample, the convolution layer uses a one-dimensional convolution kernel, the pooling layer selects a one-dimensional maximum pooling layer, and the last fully connected layer is connected to the output layer. The output layer contains a neuron and uses a Sigmoid function to output the probability of an optical fiber vibration accident occurring; Select binary cross entropy as the loss function for training the CNN model and use the Adam optimization algorithm for optimization; The resampled vibration sample is used as input data, and whether a fiber vibration accident has occurred within the historical time range corresponding to the resampled vibration sample is used as output data. If there is no fiber vibration accident, the output is 0, and if there is a fiber vibration accident, the output is 1; The prediction goal is to accurately predict whether a fiber vibration accident will occur, and the training goal is to minimize the loss function. When the loss function reaches convergence, the training is stopped to obtain a trained fiber vibration prediction model. For the power supply area that needs to perform fiber optic vibration detection, the real-time original vibration signal is obtained, the resampling frequency is calculated and the real-time original vibration signal is resampled to obtain the real-time resampled vibration signal, and the fiber optic vibration prediction model is used to predict whether there are fiber optic vibration accidents on different fiber optic links in the power supply area.

8. A distributed optical fiber vibration detection system for power transmission lines based on CNN, which is used to implement the distributed optical fiber vibration detection method for power transmission lines based on CNN as described in any one of claims 1 to 7, characterized in that: include: A power supply area division module is used to divide the power transmission line into n1 power supply areas according to its voltage category, and each power supply area corresponds to a section of optical fiber link; An importance index calculation module is used to obtain, for each power supply area, the voltage category, transmission capacity index and power reliability index of the power supply area, and calculate the importance index of the power transmission line in the power supply area; The sampling basis calculation module is used to obtain the number of optical fiber vibration accidents in the historical time for each power supply area, calculate the historical accident frequency index, and calculate the optical fiber vibration detection intensity of the power supply area according to the power transmission line importance index and the historical accident frequency index of the power supply area; A vibration signal sampling module is used to obtain the original vibration signal of each power supply area, calculate the resampling frequency according to the optical fiber vibration detection strength, and resample the original vibration signal using the resampling frequency to obtain a resampled vibration signal; The optical fiber vibration detection module is used to construct training samples using resampled vibration signals, build a CNN model and train it to obtain an optical fiber vibration prediction model. For each power supply area, its resampling frequency is calculated, and the optical fiber vibration prediction model is used to perform vibration detection on the power supply area.

9. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the CNN-based distributed optical fiber vibration detection method for power transmission lines as described in any one of claims 1 to 7 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor to execute the steps in the CNN-based distributed optical fiber vibration detection method for power transmission lines as described in any one of claims 1 to 7.