Transmission conductor galloping monitoring method and device adaptive to environmental change

Abstract

The invention provides a transmission conductor galloping monitoring method and device adaptive to environment change, and relates to the technical field of power grids. According to the method, the adaptive threshold value system is constructed, and the adaptive threshold value is determined based on the environment data of the current time period. After the galloping behavior of the transmission conductor is determined by the galloping behavior detection model, threshold judgment is performed on the galloping behavior based on the adaptive threshold, so that the transmission conductor galloping detection can be adaptive to environmental changes, and the accuracy of transmission conductor galloping monitoring is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power grids, and particularly to a method and device for monitoring the galloping of transmission lines adaptable to environmental changes. Background Art

[0002] The galloping of transmission lines is a common phenomenon in power systems, especially under harsh climate conditions such as strong winds and icing. Galloping not only affects the stable operation of the power system but may also lead to serious consequences such as wire damage and short circuits. Therefore, accurately monitoring the galloping behavior of transmission lines is crucial for ensuring the safe operation of the power system.

[0003] Traditional methods for monitoring the galloping of transmission lines usually use fixed thresholds to determine whether the galloping behavior exceeds the normal range. However, due to the variability of environmental conditions, environmental parameters such as temperature, humidity, wind speed, and wind direction are constantly changing. The fixed-threshold monitoring method cannot adapt to environmental changes and is difficult to accurately reflect the normal range of galloping behavior under different environmental conditions, resulting in inaccurate monitoring results and low reliability. Summary of the Invention

[0004] The present invention provides a method and device for monitoring the galloping of transmission lines adaptable to environmental changes, which can adapt to environmental changes in the transmission line area and improve the accuracy of monitoring the galloping of transmission lines.

[0005] In a first aspect, the present invention provides a method for monitoring the galloping of transmission lines adaptable to environmental changes, the method comprising: obtaining environmental data of the area where the transmission line is located at the current time period, and video data at the current time period; based on the environmental data and video data at the current time period, performing feature extraction to generate comprehensive features; based on the environmental data at the current time period and a preset adaptive adjustment model, determining an adaptive threshold system; the adaptive adjustment model is used to adjust the galloping monitoring threshold under different environments; based on the comprehensive features and a preset galloping behavior detection model, determining the galloping behavior of the transmission line; based on the galloping behavior of the transmission line and the adaptive threshold system, monitoring the galloping of the transmission line to obtain a galloping detection result.

[0006] In a possible implementation, the environmental data includes humidity, temperature, wind speed, wind direction, and ice coating thickness. Based on the environmental data and video data of the current period, feature extraction is performed to generate comprehensive features, including: performing frame splitting on the video data of the current period to obtain multiple video images; performing object detection on each video image to determine the positions of the spacer dampers in each video image; based on the positions of the spacer dampers in each video image, determining the dancing trajectory data of each spacer damper on the transmission line; based on the dancing trajectory data of each spacer damper on the transmission line, calculating the dancing displacement, dancing speed, and dancing acceleration of each spacer damper; and generating comprehensive features based on the environmental data of the current period, as well as the dancing trajectory data, dancing displacement, dancing speed, and dancing acceleration of each spacer damper.

[0007] In a possible implementation, before determining the adaptive threshold system based on the environmental data of the current period and the preset adaptive adjustment model, it further includes: obtaining the environmental data of each period in the historical period, as well as the dancing trajectory data of the spacer dampers on the transmission line in each period; performing feature extraction based on the environmental data and dancing trajectory data of each period to determine the clustering features of each period, where the clustering features include environmental features and dancing behavior features; performing clustering processing based on the clustering features of each period to obtain multiple clustering clusters, and each clustering cluster is a set of dancing behaviors under a certain environmental condition; calculating the statistical parameters of the dancing behavior features in each clustering cluster, where the statistical parameters include mean, standard deviation, and quantile; determining the threshold system corresponding to each clustering cluster based on the statistical parameters of the dancing behavior features in each clustering cluster; constructing a training sample with the environmental data of each period as the input and the threshold system corresponding to the environmental data of each period as the output; and training using gradient boosting trees based on the training sample to obtain the adaptive adjustment model.

[0008] In a possible implementation, training using gradient boosting trees based on the training sample to obtain the adaptive adjustment model includes: Step 1, initializing the decision tree model and setting the maximum number of iterations; Step 2, inputting the current sample into the current decision tree model to obtain an output vector; Step 3, calculating the residual vector between the output vector of the current decision tree model and the output vector of the current sample; Step 4, training a new decision tree with the input vector of the current sample as the input and the residual vector as the output; Step 5, performing model update based on the new decision tree and the current decision tree model to obtain an updated decision tree model; Step 6, if the number of iterations is greater than the maximum number of iterations, exit the iteration and use the updated decision tree model as the adaptive adjustment model; if the number of iterations is less than or equal to the maximum number of iterations, increment the number of iterations by one, and use the updated decision tree model as the current decision tree model in the next iteration process, and repeat Steps 2 to 6 for iterative training until the iteration process is exited.

[0009] In a possible implementation, before determining the galloping behavior of the transmission line based on the comprehensive features and a preset galloping behavior detection model, it further includes: obtaining the environmental data of each time period within the historical period and the video data of each time period; determining the galloping trajectory data of the spacer dampers of the transmission line in each time period based on the video data of each time period; generating the comprehensive features of each time period based on the environmental data of each time period and the galloping trajectory data of each time period; determining the galloping behavior of the transmission line in each time period based on the galloping trajectory data of each time period; generating training samples based on the comprehensive features and galloping behavior of each time period; and performing neural network training based on the training samples to obtain the galloping behavior detection model.

[0010] In a possible implementation, the galloping behavior includes the galloping amplitude and the galloping frequency; the adaptive threshold system includes an amplitude threshold and a frequency threshold; based on the galloping behavior of the transmission line and the adaptive threshold system, galloping monitoring is performed on the transmission line to obtain the galloping detection result, including: if the galloping amplitude is greater than the amplitude threshold and the galloping frequency is greater than the frequency threshold, it is determined that the galloping detection result is abnormal galloping; if the galloping amplitude is greater than the amplitude threshold and the galloping frequency is less than or equal to the frequency threshold, it is determined that the galloping detection result is large-amplitude galloping; if the galloping amplitude is less than or equal to the amplitude threshold and the galloping frequency is greater than the frequency threshold, it is determined that the galloping detection result is high-frequency galloping; if the galloping amplitude is less than or equal to the amplitude threshold and the galloping frequency is less than or equal to the frequency threshold, it is determined that the galloping detection result is normal galloping.

[0011] In a possible implementation, the method further includes: obtaining the predicted environmental data of the next time period of the current time period; performing feature extraction based on the environmental data of the next time period and the video data of the current time period to generate predicted features; determining the adaptive model parameters based on the environmental data of the next time period and a preset machine learning model; updating the galloping behavior detection model based on the adaptive model parameters to obtain an updated galloping behavior detection model; and predicting the galloping detection result of the next time period based on the predicted features and the updated galloping behavior detection model.

[0012] In a possible implementation, the method further includes: if the galloping detection result is normal galloping, keeping the normal inspection mode unchanged; if the galloping detection result is large-amplitude galloping, determining the anti-galloping plan as adding anti-galloping weights and spacer dampers; if the galloping detection result is high-frequency galloping, determining the anti-galloping plan as adding support structures for the transmission line; if the galloping detection result is abnormal galloping, recording the duration of the abnormal galloping, and if the duration of the abnormal galloping is greater than the set duration, determining the alternate line based on the location of the transmission line with abnormal galloping.

[0013] In a possible implementation, the method further includes: obtaining the galloping detection results of the transmission line during a historical period; based on the galloping detection results of the transmission line during the historical period, counting the abnormal frequencies at various positions of the transmission line; the abnormal frequencies include galloping abnormal frequencies, large-amplitude galloping frequencies, and high-frequency galloping frequencies; based on the abnormal frequencies at various positions, determining the positions of the transmission line to be overhauled; and generating an overhaul instruction based on the position coordinates of the positions to be overhauled and the types of the abnormal frequencies.

[0014] In a second aspect, an embodiment of the present invention provides a transmission line galloping monitoring device adaptable to environmental changes. The monitoring device includes: a communication module, configured to obtain the environmental data of the area where the transmission line is located during the current period, and the video data during the current period; a processing module, configured to perform feature extraction based on the environmental data and the video data during the current period to generate comprehensive features; determine an adaptive threshold system based on the environmental data during the current period and a preset adaptive adjustment model; the adaptive adjustment model is used to adjust the galloping monitoring thresholds in different environments; determine the galloping behavior of the transmission line based on the comprehensive features and a preset galloping behavior detection model; and perform galloping monitoring on the transmission line based on the galloping behavior of the transmission line and the adaptive threshold system to obtain galloping detection results.

[0015] In a third aspect, an embodiment of the present invention provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor is configured to call and run the computer program stored in the memory to execute the steps of the method described in the first aspect and any possible implementation manner in the first aspect.

[0016] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. The computer program, when executed by a processor, implements the steps of the method described in the first aspect and any possible implementation manner in the first aspect.

[0017] The present invention provides a transmission line galloping monitoring method and device adaptable to environmental changes. By constructing an adaptive threshold system and determining an adaptive threshold based on the environmental data during the current period, the present invention can, after the galloping behavior detection model determines the galloping behavior of the transmission line, perform threshold judgment on the galloping behavior based on the adaptive threshold, so as to achieve that the galloping detection of the transmission line can adapt to environmental changes and improve the accuracy of transmission line galloping monitoring. Description of the Drawings

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0019] Figure 1 FIG. is a schematic flowchart of a method for monitoring the galloping of a transmission line adaptable to environmental changes provided by an embodiment of the present invention;

[0020] Figure 2 FIG. is a schematic structural diagram of a device for monitoring the galloping of a transmission line adaptable to environmental changes provided by an embodiment of the present invention. Detailed Embodiments

[0021] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present invention. However, those skilled in the art should clearly understand that the present invention can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present invention.

[0022] In the description of the present invention, unless otherwise specified, " / " means "or". For example, A / B can represent A or B. The "and / or" herein is only a description of the association relationship of the associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, "at least one" and "multiple" mean two or more. The words such as "first" and "second" do not limit the quantity and execution order, and the words such as "first" and "second" do not necessarily limit being different.

[0023] In the embodiments of the present application, words such as "exemplary" or "for example" are used to represent examples, illustrations, or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, using words such as "exemplary" or "for example" aims to present relevant concepts in a specific manner for easy understanding.

[0024] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or modules is not limited to the listed steps or modules, but may optionally further include other unlisted steps or modules, or may optionally further include other steps or modules inherent to these processes, methods, products, or devices.

[0025] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will be described through specific embodiments in conjunction with the accompanying drawings of the present invention.

[0026] As described in the background art, during the detection of transmission line galloping, affected by environmental changes, the accuracy of galloping behavior detection is relatively low, which affects power safety.

[0027] To solve this technical problem, as Figure 1 shown, an embodiment of the present invention provides a method for monitoring the galloping of transmission lines that adapts to environmental changes. This method includes steps S101-S104.

[0028] S101. Obtain the environmental data of the area where the transmission line is located at the current time period, as well as the video data at the current time period.

[0029] In some embodiments, the environmental data includes humidity, temperature, wind speed, wind direction, and ice coating thickness.

[0030] Exemplarily, temperature changes can cause the expansion of the transmission line material, reduce the stiffness of the transmission line, and increase the galloping amplitude. In addition, temperature changes also affect the thermal stress of the transmission line, resulting in uneven stress distribution of the wire.

[0031] Exemplarily, a relatively high humidity can cause water droplets to condense on the surface of the transmission line, increase the weight and wind resistance of the transmission line, and increase the possibility of galloping. In addition, a relatively high humidity also increases the corrosion rate of the transmission line, reducing the stiffness and durability of the transmission line.

[0032] Exemplarily, when the wind speed is relatively high, the aerodynamic force on the transmission line is relatively large, the amplitude increases, and the vibration frequency also changes accordingly, increasing the risk of resonance and the accident rate.

[0033] Exemplarily, as the ice coating thickness increases, the weight of the transmission line increases, the wind resistance increases, the mechanical load on the tower increases, and the risk of power outage accidents increases.

[0034] Exemplarily, when the wind direction changes, the vibration mode of the transmission line changes, that is, the transmission line needs to be stressed in different directions, resulting in uneven stress and prone to torsional vibration of the transmission line, with a relatively high risk.

[0035] In some embodiments, the video data includes the video captured by a camera device installed on a transmission tower for the transmission wire. Among them, the video captured by the camera device contains the vibration video of the spacer dampers on the transmission wire.

[0036] S102. Based on the environmental data and video data of the current period, perform feature extraction to generate comprehensive features.

[0037] It should be noted that the embodiments of the present invention can analyze the video data to obtain the dancing trajectories of each spacer damper, combine the environmental data to generate comprehensive features, and comprehensively consider the influence of the dancing trajectories and environmental changes to improve the accuracy of dancing detection.

[0038] As a possible implementation, step S102 can be specifically implemented as steps S1021 - S1025.

[0039] S1021. Perform frame processing on the video data of the current period to obtain multiple frames of video images.

[0040] S1022. Perform object detection on each frame of the video image to determine the positions of each spacer damper in each frame of the video image.

[0041] S1023. Based on the positions of each spacer damper in each frame of the video image, determine the dancing trajectory data of each spacer damper on the transmission wire.

[0042] S1024. Based on the dancing trajectory data of each spacer damper on the transmission wire, calculate the dancing displacement, dancing speed, and dancing acceleration of each spacer damper.

[0043] S1025. Based on the environmental data of the current period, as well as the dancing trajectory data, dancing displacement, dancing speed, and dancing acceleration of each spacer damper, generate comprehensive features.

[0044] As a possible implementation, the embodiments of the present invention can combine the environmental data, dancing trajectory data, dancing displacement, dancing speed, and dancing acceleration to obtain comprehensive features.

[0045] S103. Based on the environmental data of the current period and a preset adaptive adjustment model, determine an adaptive threshold system.

[0046] In the embodiments of the present application, the adaptive adjustment model is used to adjust the dancing monitoring threshold under different environments.

[0047] In some embodiments, the adaptive adjustment model is obtained through cluster analysis and iterative training based on the environmental data and dancing trajectory data in the historical period.

[0048] As a possible implementation, the embodiments of the present invention can generate an environment vector based on the environmental data of the current period, and input the environment vector into an adaptive adjustment model to obtain an adaptive threshold system.

[0049] S104. Determine the galloping behavior of the transmission line based on the comprehensive features and a preset galloping behavior detection model.

[0050] In the embodiments of the present application, the galloping behavior detection model is used to detect the galloping behavior of the transmission line.

[0051] In some embodiments, the galloping behavior includes galloping amplitude and galloping frequency; the adaptive threshold system includes an amplitude threshold and a frequency threshold.

[0052] In some embodiments, the galloping behavior detection model is obtained by neural network training based on the environmental data and videos in the historical period.

[0053] As a possible implementation, the embodiments of the present invention can input the comprehensive features into the galloping behavior detection model to obtain the galloping behavior of the transmission line.

[0054] S105. Monitor the galloping of the transmission line based on the galloping behavior of the transmission line and the adaptive threshold system to obtain a galloping detection result.

[0055] The embodiments of the present invention can compare the detected galloping behavior with the adaptive threshold to determine the severity of the galloping behavior. Since the thresholds in the adaptive threshold system are dynamically adjusted according to the environmental parameters, the obtained galloping detection result can adapt to environmental changes and improve the accuracy of the galloping detection result.

[0056] As a possible implementation, step S105 can be specifically implemented as steps S1051 - S1054.

[0057] S1051. If the galloping amplitude is greater than the amplitude threshold and the galloping frequency is greater than the frequency threshold, determine that the galloping detection result is abnormal galloping.

[0058] S1052. If the galloping amplitude is greater than the amplitude threshold and the galloping frequency is less than or equal to the frequency threshold, determine that the galloping detection result is large - amplitude galloping.

[0059] S1053. If the galloping amplitude is less than or equal to the amplitude threshold and the galloping frequency is greater than the frequency threshold, determine that the galloping detection result is high - frequency galloping.

[0060] S1054. If the galloping amplitude is less than or equal to the amplitude threshold and the galloping frequency is less than or equal to the frequency threshold, determine that the galloping detection result is normal galloping.

[0061] The present invention provides a method for monitoring the galloping of transmission lines that adapts to environmental changes. By constructing an adaptive threshold system, an adaptive threshold is determined based on the environmental data of the current period. After the galloping behavior detection model determines the galloping behavior of the transmission line, a threshold judgment is made on the galloping behavior based on the adaptive threshold, so as to realize that the galloping detection of the transmission line can adapt to environmental changes and improve the accuracy of galloping monitoring of the transmission line.

[0062] Optionally, for the method for monitoring the galloping of transmission lines that adapts to environmental changes provided by the embodiments of the present invention, before step S103, steps S201-S207 are further included.

[0063] S201. Obtain the environmental data of each period within the historical period, as well as the galloping trajectory data of the spacer dampers of the transmission line in each period.

[0064] Exemplarily, the embodiments of the present invention can perform target detection on the video data of each period within the historical period to determine the galloping trajectory data of each spacer damper.

[0065] S202. Based on the environmental data and galloping trajectory data of each period, perform feature extraction to determine the clustering features of each period.

[0066] In some embodiments, the clustering features include environmental features and galloping behavior features.

[0067] Exemplarily, the environmental features include features such as humidity, temperature, wind speed, wind direction, and ice coating thickness.

[0068] Exemplarily, the galloping behavior features include galloping amplitude and galloping frequency.

[0069] Exemplarily, the galloping behavior features further include galloping displacement, galloping speed, and galloping acceleration.

[0070] S203. Based on the clustering features of each period, perform clustering processing to obtain multiple clustering clusters.

[0071] In some embodiments, each clustering cluster is a set of galloping behaviors under a certain environmental condition.

[0072] As a possible implementation manner, the embodiments of the present invention can classify based on each feature in the environmental features to obtain multiple clusters; then, count the multiple galloping behavior features corresponding to each cluster to form a clustering cluster. Each clustering cluster includes a set of galloping behaviors corresponding to a certain type of environmental feature.

[0073] S204. Calculate the statistical parameters of each galloping behavior feature in each clustering cluster.

[0074] In some embodiments, the statistical parameters include mean, standard deviation, and quantile.

[0075] Exemplarily, for each clustering cluster, embodiments of the present invention can calculate the mean, standard deviation, and quantiles of the dancing amplitudes in each dancing behavior in the clustering cluster, as well as the mean, standard deviation, and quantiles of the dancing frequencies.

[0076] S205. Determine the threshold system corresponding to each clustering cluster based on the statistical parameters of the dancing behavior characteristics in each clustering cluster.

[0077] Exemplarily, embodiments of the present invention can use the 95% quantile in the dancing amplitude samples in each clustering cluster as the amplitude threshold; and use the 95% quantile in the dancing frequency samples as the frequency threshold. In this way, it can be ensured that the probability of exceeding this threshold during the dancing of the transmission line is small and can be regarded as abnormal dancing.

[0078] S206. Construct training samples with the environmental data of each time period as the input and the threshold system corresponding to the environmental data of each time period as the output.

[0079] S207. Based on the training samples, use the gradient boosting tree for training to obtain an adaptive adjustment model.

[0080] Exemplarily, step S207 can be specifically implemented as steps one to six.

[0081] Step one: Initialize the decision tree model and set the maximum number of iterations.

[0082] Step two: Input the current sample into the current decision tree model to obtain an output vector.

[0083] Step three: Calculate the residual vector between the output vector of the current decision tree model and the output vector of the current sample.

[0084] Step four: Use the input vector of the current sample as the input and the residual vector as the output to train a new decision tree.

[0085] Step five: Based on the new decision tree and the current decision tree model, perform model update to obtain an updated decision tree model.

[0086] Step six: If the number of iterations is greater than the maximum number of iterations, exit the iteration and use the updated decision tree model as the adaptive adjustment model; if the number of iterations is less than or equal to the maximum number of iterations, increment the number of iterations by one and use the updated decision tree model as the current decision tree model in the next iteration process, and repeat steps two to six for iterative training until the iteration process is exited.

[0087] In this way, the embodiments of the present invention can determine the threshold system in each environment by clustering and analyzing the environmental data and the dancing trajectory data in the historical period, and train in combination with the gradient boosting tree model to establish a model between the environmental data and the adaptive threshold system, realizing the automatic adjustment of the dancing behavior threshold and improving the convenience and accuracy of the dancing behavior detection.

[0088] Optionally, before step S104, the method for monitoring the dancing of transmission lines adapting to environmental changes provided by the embodiments of the present invention further includes steps S301-S306.

[0089] S301. Obtain the environmental data of each time period in the historical period and the video data of each time period.

[0090] S302. Based on the video data of each time period, determine the dancing trajectory data of the spacer dampers of the transmission line in each time period.

[0091] Exemplarily, the embodiments of the present invention can perform frame-by-frame processing and object detection on the video data to determine the dancing trajectory data of each spacer damper in each time period.

[0092] S303. Generate the comprehensive features of each time period based on the environmental data of each time period and the dancing trajectory data of each time period.

[0093] S304. Determine the dancing behavior of the transmission line in each time period based on the dancing trajectory data of each time period.

[0094] Exemplarily, the embodiments of the present invention can perform statistics on the dancing trajectory data in each time period to obtain the maximum dancing amplitude and the fastest dancing frequency in each time period, and determine the dancing behavior in each time period.

[0095] S305. Generate training samples based on the comprehensive features and dancing behaviors of each time period.

[0096] Exemplarily, the embodiments of the present invention can use the comprehensive features of each time period as the input and the dancing behavior of each time period as the output to generate training samples.

[0097] S306. Perform neural network training based on the training samples to obtain a dancing behavior detection model.

[0098] In this way, the embodiments of the present invention can obtain a dancing behavior detection model through neural network training of the environmental data and the dancing trajectory data in the historical period, which is convenient for real-time dancing behavior detection and improves the accuracy of the dancing behavior detection.

[0099] Optionally, the method for monitoring the dancing of transmission lines adapting to environmental changes provided by the embodiments of the present invention further includes steps S401-S405.

[0100] S401. Obtain the predicted environmental data for the next time period of the current time period.

[0101] S402. Based on the environmental data of the next time period and the video data of the current time period, perform feature extraction to generate predicted features.

[0102] Exemplarily, embodiments of the present invention can combine the environmental data of the next time period and the video data of the current time period to generate predicted features.

[0103] S403. Based on the environmental data of the next time period and a preset machine learning model, determine the adaptive model parameters.

[0104] In some embodiments, the preset machine learning model is obtained through training and learning. Among them, the training samples of the preset machine learning model use environmental data as input and the model parameters of the dancing behavior detection model as output.

[0105] S404. Based on the adaptive model parameters, update the dancing behavior detection model to obtain an updated dancing behavior detection model.

[0106] S405. Based on the predicted features and the updated dancing behavior detection model, predict the dancing detection result for the next time period.

[0107] It should be noted that embodiments of the present invention perform neural network training on dancing behaviors in different environments to obtain dancing behavior detection models in different environments. In this way, the model parameters of the dancing behavior detection models in different environments can be obtained.

[0108] After that, using environmental data as input and the model parameters of the dancing behavior detection model corresponding to the environmental data as output for neural network training, a preset machine learning model is obtained. Thus, in different environments or when the environment changes, embodiments of the present invention can adaptively adjust the model parameters according to the environmental data, and then perform dancing behavior detection with a dancing behavior detection model that more conforms to the changed environment, ensuring the accuracy of transmission line dancing behavior detection.

[0109] Optionally, for the transmission line dancing monitoring method that adapts to environmental changes provided by embodiments of the present invention, after determining the dancing detection result, it further includes steps S501 - S504.

[0110] S501. If the dancing detection result is normal dancing, keep the normal inspection mode unchanged.

[0111] S502. If the dancing detection result is large - amplitude dancing, determine that the anti - dancing plan is to increase anti - dancing hammers and spacer dampers.

[0112] S503. If the dancing detection result is high-frequency dancing, determine that the anti-dancing plan is to add a support structure for the transmission line.

[0113] S504. If the dancing detection result is abnormal dancing, record the duration of the abnormal dancing. If the duration of the abnormal dancing is greater than the set duration, determine an alternative line based on the position of the transmission line with abnormal dancing.

[0114] In this way, the embodiments of the present invention can set corresponding anti-dancing measures for various abnormal dancing conditions, achieve the suppression of anti-dancing of the transmission line, and improve the safety and reliability of the transmission line.

[0115] Optionally, for the transmission line dancing monitoring method that adapts to environmental changes provided by the embodiments of the present invention, after determining the dancing detection result, steps S601 - S606 are further included.

[0116] S601. Obtain the dancing detection results of the transmission line in the historical period.

[0117] S602. Based on the dancing detection results of the transmission line in the historical period, count the abnormal frequencies at each position of the transmission line.

[0118] In some embodiments, the abnormal frequencies include abnormal dancing frequencies, large-amplitude dancing frequencies, and high-frequency dancing frequencies.

[0119] S603. Based on the abnormal frequencies at each position, determine the positions of the transmission line to be repaired.

[0120] S604. Generate a maintenance instruction based on the position coordinates of the position to be repaired and the type of abnormal frequency.

[0121] In this way, the embodiments of the present invention can count the abnormal frequencies at each position of the transmission line, achieve fault prediction for each position of the transmission line, and generate a maintenance instruction to prompt the user to strengthen inspection and ensure the safety of the transmission line.

[0122] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0123] The following is the device embodiment of the present invention. For the details not described in detail, reference can be made to the corresponding method embodiments above.

[0124] Figure 2 The structural schematic diagram of a transmission line dancing monitoring device that adapts to environmental changes provided by the embodiments of the present invention is shown. The dancing monitoring device 700 includes a communication module 701 and a processing module 702.

[0125] A communication module 701, configured to obtain environmental data of the area where the transmission wire is located in the current period, and video data of the current period;

[0126] A processing module 702, configured to perform feature extraction based on the environmental data and video data of the current period to generate comprehensive features; determine an adaptive threshold system based on the environmental data of the current period and a preset adaptive adjustment model; the adaptive adjustment model is used to adjust the dancing monitoring threshold in different environments; determine the dancing behavior of the transmission wire based on the comprehensive features and a preset dancing behavior detection model; perform dancing monitoring on the transmission wire based on the dancing behavior of the transmission wire and the adaptive threshold system to obtain a dancing detection result.

[0127] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for monitoring the galloping of a power transmission line that is adaptive to environmental changes, characterized in that: include: Obtaining environmental data of the area where the power transmission line is located during the current period, as well as video data of the current period; Based on the environmental data and video data of the current period, feature extraction is performed to generate comprehensive features; Based on the environmental data of the current period and a preset adaptive adjustment model, an adaptive threshold system is determined; the adaptive adjustment model is used to adjust the dancing monitoring threshold under different environments; Based on the comprehensive features and a preset dancing behavior detection model, determining the dancing behavior of the transmission line; Based on the dancing behavior of the power transmission line and the adaptive threshold system, the power transmission line is monitored for dancing to obtain a dancing detection result.

2. The method for monitoring the galloping of a power transmission line according to claim 1, characterized in that: The environmental data include humidity, temperature, wind speed, wind direction and ice thickness; The feature extraction based on the environmental data and video data of the current period to generate comprehensive features includes: Perform frame processing on the video data of the current period to obtain multiple frames of video images; Perform target detection on each frame of video image to determine the position of each spacer bar in each frame of video image; Based on the position of each spacer bar in each frame of video image, the dancing trajectory data of each spacer bar of the transmission line is determined; Based on the dancing trajectory data of each spacer bar of the transmission line, the dancing displacement, dancing speed and dancing acceleration of each spacer bar are calculated; The comprehensive features are generated based on the environmental data of the current time period, as well as the dancing trajectory data, dancing displacement, dancing speed and dancing acceleration of each spacer rod.

3. The method for monitoring the galloping of a power transmission line according to claim 1, characterized in that: Before determining the adaptive threshold system based on the environmental data of the current period and the preset adaptive adjustment model, the method further includes: Obtain environmental data for each period in the historical period, as well as dancing trajectory data of the spacer bars of the transmission line for each period; Based on the environmental data of each time period and the dancing trajectory data, feature extraction is performed to determine clustering features of each time period, wherein the clustering features include environmental features and dancing behavior features; Based on the clustering features of each time period, clustering processing is performed to obtain multiple clusters, each cluster being a set of dancing behaviors under a certain environmental condition; Calculating statistical parameters of each dancing behavior feature in each cluster, wherein the statistical parameters include mean, standard deviation and quantile; Based on the statistical parameters of the dancing behavior characteristics in each cluster, a threshold system corresponding to each cluster is determined; Taking the environmental data of each period as input and the threshold system corresponding to the environmental data of each period as output, a training sample is constructed; Based on the training samples, a gradient boosting tree is used to perform training to obtain the adaptive adjustment model.

4. The method for monitoring the galloping of a power transmission line according to claim 3, characterized in that: The step of training based on the training samples using a gradient boosting tree to obtain the adaptive adjustment model includes: Step 1: Initialize the decision tree model and set the maximum number of iterations; Step 2: Input the current sample into the current decision tree model to obtain the output vector; Step 3: Calculate the residual vector between the output vector of the current decision tree model and the output vector of the current sample; Step 4: Taking the input vector of the current sample as input and the residual vector as output, a new decision tree is trained; Step 5: Based on the new decision tree and the current decision tree model, the model is updated to obtain an updated decision tree model; Step 6. If the number of iterations is greater than the maximum number of iterations, exit the iteration and use the updated decision tree model as the adaptive adjustment model; if the number of iterations is less than or equal to the maximum number of iterations, increase the number of iterations by one and use the updated decision tree model as the current decision tree model in the next iteration process. Repeat steps 2 to 6 for iterative training until exiting the iteration process.

5. The method for monitoring the galloping of a power transmission line adaptive to environmental changes according to claim 1, characterized in that: Before determining the dancing behavior of the transmission line based on the comprehensive features and the preset dancing behavior detection model, the method further includes: Obtain environmental data for each period of the historical period, as well as video data for each period; Based on the video data of each time period, the dancing trajectory data of the spacer rod of the transmission line in each time period is determined; Generate comprehensive features of each time period based on the environmental data of each time period and the dancing trajectory data of each time period; Based on the dancing trajectory data of each period, the dancing behavior of the transmission line in each period is determined; Generate training samples based on the comprehensive characteristics and dancing behaviors of each time period; Based on the training samples, neural network training is performed to obtain a dancing behavior detection model.

6. The method for monitoring the galloping of a power transmission line adaptive to environmental changes according to claim 1, characterized in that: The dancing behavior includes dancing amplitude and dancing frequency; the adaptive threshold system includes amplitude threshold and frequency threshold; The dancing behavior of the power transmission line and the adaptive threshold system are used to monitor the dancing of the power transmission line to obtain the dancing detection result, including: If the dancing amplitude is greater than the amplitude threshold, and the dancing frequency is greater than the frequency threshold, then the dancing detection result is determined to be abnormal dancing; If the dancing amplitude is greater than the amplitude threshold and the dancing frequency is less than or equal to the frequency threshold, the dancing detection result is determined to be large-amplitude dancing; If the dancing amplitude is less than or equal to the amplitude threshold, and the dancing frequency is greater than the frequency threshold, then the dancing detection result is determined to be high-frequency dancing; If the dancing amplitude is less than or equal to the amplitude threshold, and the dancing frequency is less than or equal to the frequency threshold, then the dancing detection result is determined to be normal dancing.

7. The method for monitoring the galloping of a power transmission line according to claim 1, characterized in that: The method further comprises: Obtain the predicted environmental data for the next period of the current period; Based on the environmental data of the next period and the video data of the current period, feature extraction is performed to generate prediction features; Determining adaptive model parameters based on the environmental data of the next period and a preset machine learning model; Based on the adaptive model parameters, the dancing behavior detection model is updated to obtain an updated dancing behavior detection model; Based on the prediction features and the updated dancing behavior detection model, the dancing detection result for the next time period is predicted.

8. The method for monitoring the galloping of a power transmission line adaptive to environmental changes according to any one of claims 1 to 7, characterized in that: The method further comprises: If the dancing detection result is that the dancing is normal, the normal inspection mode is maintained unchanged; If the dancing detection result is large-amplitude dancing, the anti-dancing plan is to add anti-dancing hammers and spacer bars; If the dancing detection result is high-frequency dancing, the anti-dancing plan is to add a supporting structure for the transmission line; If the dancing detection result is abnormal dancing, the duration of the abnormal dancing is recorded. If the duration of the abnormal dancing is greater than the set duration, a backup line is determined based on the position of the transmission wire with the abnormal dancing.

9. The method for monitoring the galloping of a power transmission line adaptive to environmental changes according to claim 1, characterized in that: The method further comprises: Obtain the transmission line galloping detection results in the historical period; Based on the dancing detection results of the power transmission line in the historical period, the abnormal frequency at each position of the power transmission line is counted; the abnormal frequency includes abnormal dancing frequency, large-amplitude dancing frequency and high-frequency dancing frequency; Determining the position of the transmission line to be inspected based on the abnormal frequency at each position; A maintenance instruction is generated based on the location coordinates of the location to be maintained and the type of abnormal frequency.

10. A transmission line dancing monitoring device that is adaptive to environmental changes, characterized in that: include: A communication module, used to obtain environmental data of the area where the power transmission line is located during the current period, and video data of the current period; A processing module, used for extracting features and generating comprehensive features based on environmental data and video data of the current period; Based on the environmental data of the current period and a preset adaptive adjustment model, an adaptive threshold system is determined; the adaptive adjustment model is used to adjust the dancing monitoring threshold under different environments; Based on the comprehensive features and a preset dancing behavior detection model, determining the dancing behavior of the transmission line; Based on the dancing behavior of the power transmission line and the adaptive threshold system, the power transmission line is monitored for dancing to obtain a dancing detection result.

Images