Power transmission line tower aeolian vibration video analysis method and early warning device

Abstract

The invention provides a power transmission line tower aeolian vibration video analysis method and an early warning device, and relates to the technical field of power grids. According to the method, the video image of the power transmission line tower is framed to obtain the multi-frame video image, the position information of each key part of the target tower in the video image is determined, the time-frequency analysis is carried out, the vibration characteristics such as the amplitude-frequency characteristic, the time-frequency characteristic and the vibration dynamic characteristic are determined, and the comprehensive characteristic extraction of each key part of the target tower is realized. And then vibration analysis results such as the vibration type and the vibration intensity are obtained through analysis in combination with the inherent characteristics of the target tower, and aeolian vibration video analysis of the transmission line tower is achieved. The process does not need manual inspection, and the inspection efficiency of the power transmission line tower is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power grids, and in particular to a video analysis method and an early warning device for breeze vibration of a transmission line tower. Background Art

[0002] Transmission line towers are an important part of the power system, and ensuring their stability and safety is crucial to the reliable operation of the power system. Traditional tower inspections mainly rely on manual methods, including checking the tower body, foundation, connectors, crossarms, brackets, insulators, accessories and other parts for visible defects such as cracks.

[0003] Traditional manual inspection methods require a lot of manpower and time, especially in complex geographical conditions, where inspection work is more difficult and more costly. Traditional manual inspections have the problem of low inspection efficiency. Summary of the invention

[0004] The present invention provides a video analysis method and an early warning device for breeze vibration of a power transmission line tower, which can realize video analysis of breeze vibration of a power transmission line tower and improve the inspection efficiency of the power transmission line tower.

[0005] In a first aspect, the present invention provides a video analysis method for breeze vibration of a transmission line tower, the method comprising: acquiring video data of a target tower in the transmission line, and inherent characteristics of the target tower; performing frame processing on the video data of the target tower to obtain multiple frames of video images; identifying key parts of the target tower in each frame of video image to obtain key features of each frame of video image, the key features including position information of key parts of the target tower; performing time-frequency analysis based on the key features of each frame of video image to determine vibration characteristics of the target tower; the vibration characteristics include amplitude-frequency characteristics, time-frequency characteristics and vibration dynamic characteristics; based on the vibration characteristics of the target tower and the inherent characteristics of the tower, determining a vibration analysis result of the target tower, the vibration analysis result including a vibration type and a vibration intensity.

[0006] In a possible implementation, the inherent characteristics include the inherent frequency and the damping ratio, the amplitude-frequency characteristics include the main vibration frequency and the vibration amplitude distribution information, the time-frequency characteristics include the frequency distribution information and the non-stationary characteristics, and the vibration dynamic characteristics include the displacement peak value, the vibration velocity and the acceleration peak value; based on the key characteristics of each frame of the video image, the time-frequency analysis is performed to determine the vibration characteristics of the target tower, including: based on the key characteristics of each frame of the video image, the trajectory of each key part of the target tower is tracked to determine the vibration signal of each key part, and the vibration signal includes the vibration displacement of the key part at each moment; the vibration signal of each key part is Fourier transformed to obtain the frequency spectrum of each key part; based on the frequency spectrum of each key part, the main vibration frequency and the vibration amplitude distribution information are identified; the vibration signal of each key part is wavelet transformed to determine the frequency distribution information and the non-stationary characteristics of each key part; the displacement peak value of the vibration signal of each key part is extracted; based on the displacement peak value, the vibration velocity and the acceleration peak value are derived.

[0007] In a possible implementation, wavelet transform is performed on the vibration signal of each key part to determine the frequency distribution information and non-stationary characteristics of each key part, including: for the vibration signal of any key part, based on the frequency distribution information of the vibration signal, the wavelet basis function and the number of decomposition layers of the wavelet transform are determined; based on the wavelet basis and the number of decomposition layers, the vibration signal is subjected to wavelet transform to obtain the wavelet coefficients of each decomposition layer; based on the wavelet coefficients of each decomposition layer, the distribution of the wavelet coefficients of each decomposition layer and the change of the wavelet coefficients over time are determined; based on the distribution of the wavelet coefficients of each decomposition layer, the frequency distribution information of the vibration signal is determined; based on the change of the wavelet coefficients over time, the non-stationary characteristics of the vibration signal are determined.

[0008] In one possible implementation, video data of a target pole tower is framed to obtain multiple frames of video images, including: extracting multiple consecutive frames of video images from the video data; calculating an estimated value of the vibration frequency of the target pole tower based on the multiple consecutive frames of video images; determining a decomposition frame rate based on the estimated value of the vibration frequency of the target pole tower and a preset analysis accuracy; and based on the decomposition frame rate, frame-dividing the video data to obtain multiple frames of video images.

[0009] In a possible implementation, key parts of a target pole tower in each frame of video image are identified to obtain key features of each frame of video image, including: converting each frame of video image into a grayscale image to obtain multiple grayscale images; performing target detection on the multiple grayscale images to identify key parts of the target pole tower; performing feature point detection on the key parts on the multiple grayscale images to determine the position coordinates of each key part on each grayscale image; performing static and dynamic analysis on each key part based on the position coordinates of each key part on each grayscale image to determine the key parts in a static state and the key parts in a vibrating state; using the key parts in a static state on each grayscale image as a reference, determining the position information of the key parts in a vibrating state on each grayscale image; and determining key features based on the position information of each key part on each grayscale image.

[0010] In a possible implementation, based on the vibration characteristics of the target tower and the inherent characteristics of the tower, a vibration analysis result of the target tower is determined, including: based on the vibration characteristics of the target tower and the inherent characteristics of the tower, a comparison is made to determine the vibration type of the target tower, the vibration type including forced vibration, free vibration or resonance; based on the vibration type and the vibration characteristics, the vibration intensity of the target tower is determined.

[0011] In a possible implementation, after determining the vibration analysis result of the target tower based on the vibration characteristics of the target tower and the inherent characteristics of the tower, the method further includes: if the vibration type is resonance, determining a set frequency based on the natural frequency and the main vibration frequency; determining a target position of the shock-absorbing hammer based on the set frequency; and adjusting the position of the shock-absorbing hammer to the target position so that the vibration type of the target tower is changed from resonance to forced vibration.

[0012] In a possible implementation, after determining the vibration analysis result of the target tower based on the vibration characteristics of the target tower and the inherent characteristics of the tower, the method further includes: if the vibration type is forced vibration, determining the set damping force of the adjustable damper of the target tower and the set tension of the damping line at the transmission lines on both sides of the target tower based on the vibration intensity and the vibration characteristics; adjusting the damping force of the adjustable damper to the set damping force; and adjusting the tension of the damping line to the set tension.

[0013] In a possible implementation, the method also includes: acquiring wind data and vibration characteristics within a historical period; the wind data includes wind speed and wind direction; classifying the wind data and vibration characteristics within the historical period to obtain the vibration characteristics of the target tower under various wind data conditions; calculating the characteristic difference between the vibration characteristics of each key part of the target tower in the second time period and the vibration characteristics of the first time period under the same wind data conditions; wherein the first time period is the time period before the second time period in the historical period; if the characteristic difference of a key part is greater than a set threshold, the key part is determined to be in an abnormal state.

[0014] In a second aspect, an embodiment of the present invention provides a power transmission line tower breeze vibration early warning device, the early warning device comprising: a communication module, for acquiring video data of a target tower in a power transmission line, and inherent characteristics of the target tower; a processing module, for performing frame processing on the video data of the target tower to obtain multiple frames of video images; identifying key parts of the target tower in each frame of video image to obtain key features of each frame of video image, the key features including position information of key parts of the target tower; performing time-frequency analysis based on the key features of each frame of video image to determine the vibration characteristics of the target tower; the vibration characteristics include amplitude-frequency characteristics, time-frequency characteristics and vibration dynamic characteristics; based on the vibration characteristics of the target tower and the inherent characteristics of the tower, determining the vibration analysis results of the target tower, the vibration analysis results including vibration type and vibration intensity.

[0015] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, the memory storing a computer program, the processor being used to call and run the computer program stored in the memory to perform the steps of the method described in the first aspect and any possible implementation method of the first aspect.

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

[0017] The present invention provides a video analysis method and early warning device for breeze vibration of a transmission line pole tower. The present invention performs frame processing on a video image of a transmission line pole tower to obtain multiple frames of video images, determines the position information of key parts of a target pole tower in the video image, and performs time-frequency analysis to determine vibration characteristics such as amplitude-frequency characteristics, time-frequency characteristics, and vibration dynamic characteristics, thereby realizing comprehensive feature extraction of key parts of the target pole tower. After that, the inherent characteristics of the target pole tower are combined to analyze and obtain vibration analysis results such as vibration type and vibration intensity, thereby realizing video analysis of breeze vibration of a transmission line pole tower. This process does not require manual inspection, thereby improving the inspection efficiency of transmission line pole towers. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0019] Figure 1It is a flow chart of a method for video analysis of breeze vibration of a transmission line tower provided by an embodiment of the present invention;

[0020] Figure 2 The present invention is a schematic structural diagram of a power transmission line tower breeze vibration early warning device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may 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 prevent unnecessary details from obstructing the description of the present invention.

[0022] In the description of the present invention, unless otherwise specified, " / " means "or", for example, A / B can mean A or B. "And / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, "at least one" and "plurality" refer to two or more. The words "first", "second", etc. do not limit the quantity and execution order, and the words "first", "second", etc. do not limit them to be different.

[0023] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way 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 inclusions. 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 include other steps or modules that are not listed, or may optionally include other steps or modules that are inherent to these processes, methods, products or devices.

[0025] In order to make the purpose, technical solutions and advantages of the present invention more clear, 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, traditional manual inspection has the technical problem of low inspection efficiency.

[0027] In addition, traditional manual inspections only observe the appearance of each part of the tower and cannot determine the potential threats inside the tower. During the vibration of the tower, fatigue vibration may exist. There is no obvious change on the surface of the tower, but long-term breeze vibration is prone to fatigue damage. Fatigue damage caused by breeze vibration is usually not immediately reflected on the surface of the tower, so it is difficult to detect it in time through traditional inspection methods, thereby increasing the risk of tower collapse.

[0028] To solve this technical problem, Figure 1 As shown, an embodiment of the present invention provides a method for analyzing video of breeze vibration of a transmission line tower. The method includes steps S101-S104.

[0029] S101. Obtain video data of a target pole tower in a transmission line and inherent features of the target pole tower.

[0030] In some embodiments, the natural characteristics include natural frequency and damping ratio.

[0031] For example, the natural frequency is the frequency of the tower when it vibrates freely, which is an inherent property of the tower structure itself. If a frequency component close to the natural frequency appears in the vibration signal and the component is more prominent in the spectrum, it may be a sign of free vibration or resonance.

[0032] For example, the damping ratio reflects the speed at which energy is dissipated during vibration. In free vibration, the damping ratio affects the speed at which the amplitude decays. However, the damping ratio does not directly indicate the type of vibration and is used to evaluate vibration attenuation and stability.

[0033] In some embodiments, the target tower is any tower in a transmission line.

[0034] In some embodiments, the embodiments of the present invention can shoot a video of the target pole tower, periodically obtain video data of the target pole tower, obtain video data of multiple time periods, and analyze and process the video data of each time period to achieve breeze vibration analysis of the target pole tower.

[0035] S102: Perform frame processing on the video data of the target tower to obtain multiple frames of video images.

[0036] As a possible implementation manner, the embodiment of the present invention may perform frame processing on the video data based on steps S1021 - S1024 .

[0037] S1021. Extract multiple consecutive frames of video images from the video data.

[0038] S1022. Calculate an estimated value of the vibration frequency of the target tower based on the continuous multiple frames of video images.

[0039] S1023. Determine a decomposition frame rate based on the estimated value of the vibration frequency of the target tower and a preset analysis accuracy.

[0040] S1024: Divide the video data into frames based on the decomposition frame rate to obtain multiple frames of video images.

[0041] In this way, the embodiment of the present invention can adjust the frame frequency according to different vibration conditions of the tower, reduce memory overhead and improve the video analysis rate while ensuring the analysis accuracy.

[0042] S103, identifying key parts of the target tower in each frame of video image, and obtaining key features of each frame of video image.

[0043] In the embodiment of the present application, the key features include the position information of the key parts of the target tower.

[0044] In some embodiments, key parts of the tower include the tower body, foundation, connectors, cross arms, brackets, insulators and accessories.

[0045] As a possible implementation manner, step S103 may be specifically implemented as steps S1031 - S1036 .

[0046] S1031, converting each frame of video image into a grayscale image to obtain multiple grayscale images.

[0047] S1032: Perform target detection on multiple grayscale images to identify key parts of the target tower.

[0048] S1033, performing feature point detection on each key part on multiple grayscale images to determine the position coordinates of each key part on each grayscale image.

[0049] S1034. Based on the position coordinates of each key part on each grayscale image, a static and dynamic analysis is performed on each key part to determine the key parts in a static state and the key parts in a vibrating state.

[0050] S1035 . Determine the position information of the key parts in the vibration state on each grayscale image by taking the key parts in the static state on each grayscale image as a reference.

[0051] S1036: Determine key features based on the position information of each key part on each grayscale image.

[0052] S104: Perform time-frequency analysis based on key features of each frame of video image to determine vibration characteristics of the target tower.

[0053] In the embodiment of the present application, the vibration characteristics include amplitude-frequency characteristics, time-frequency characteristics and vibration dynamic characteristics.

[0054] In some embodiments, the amplitude-frequency feature includes vibration main frequency and vibration amplitude distribution information.

[0055] Exemplarily, the dominant frequency is the frequency component with the largest amplitude in the spectrum graph. If the dominant frequency is close to the natural frequency of the tower and the vibration signal persists (i.e., not transient), then it may be resonance. If the dominant frequency matches any known external driving force frequency, then it may be forced vibration.

[0056] Exemplarily, the vibration amplitude distribution information includes the relative strength of different frequency components. At resonance, the amplitude near the resonant frequency will increase significantly. In forced vibration, the amplitude of the main frequency will also be larger, but may not be as significant as at resonance.

[0057] In some embodiments, the time-frequency features include frequency distribution information and non-stationary characteristics.

[0058] Exemplarily, the frequency distribution information indicates the frequency distribution of the vibration signal over time. If the frequency of the vibration signal remains constant over a period of time and matches the frequency of the external driving force, it is likely to be forced vibration. If the frequency changes over time, but is close to the natural frequency and the amplitude increases significantly in a certain period of time, it may be resonance.

[0059] For example, if the vibration signal exhibits non-stationary characteristics, that is, the frequency, amplitude, etc. change significantly over time, it may be caused by complex external excitation or nonlinear factors within the system, such as the wind speed in the environment where the tower is located. In this case, a more detailed analysis is required to determine the type of vibration.

[0060] In some embodiments, the vibration dynamic characteristics include displacement peak, vibration velocity, and acceleration peak.

[0061] It should be noted that the embodiment of the present invention can use a vibration analysis algorithm to perform spectrum analysis and time-frequency analysis on the key features of each frame of video image, comprehensively analyze the vibration of the tower from the frequency domain and time domain, and conduct a risk assessment on the breeze vibration of the tower.

[0062] As a possible implementation manner, the embodiment of the present invention may determine the vibration characteristics of the target tower based on steps S1041 - S1044 .

[0063] S1041. Based on the key features of each frame of the video image, track the trajectory of each key part of the target tower to determine the vibration signal of each key part.

[0064] In some embodiments, the vibration signal includes the vibration displacement of the key parts at each moment.

[0065] S1042, performing Fourier transform on the vibration signal of each key part to obtain a frequency spectrum diagram of each key part.

[0066] Exemplarily, the embodiment of the present invention can perform Fourier transform on the vibration signal to obtain a frequency domain signal, and draw a spectrum diagram based on the frequency domain signal, wherein the horizontal axis of the spectrum diagram represents frequency and the vertical axis represents amplitude.

[0067] S1043. Based on the frequency spectrum of each key part, identify and obtain the main frequency and amplitude distribution information of vibration.

[0068] For example, the embodiment of the present invention can intuitively determine the intensity corresponding to each frequency band, that is, the amplitude, based on the spectrum diagram. Thus, the main vibration frequency with the largest intensity, that is, the largest amplitude, is identified. Combined with the amplitudes of other frequencies in the spectrum diagram, the vibration amplitude distribution information is obtained.

[0069] S1044. Perform wavelet transform on the vibration signals of each key part to determine the frequency distribution information and non-stationary characteristics of each key part.

[0070] Exemplarily, step S1044 may be specifically implemented as steps A1-A4.

[0071] A1. For the vibration signal of any key part, the wavelet basis function and the number of decomposition layers of the wavelet transform are determined based on the frequency distribution information of the vibration signal.

[0072] A2. Based on the wavelet basis and the number of decomposition layers, the vibration signal is subjected to wavelet transform to obtain the wavelet coefficients of each decomposition layer.

[0073] A3. Based on the wavelet coefficients of each decomposition layer, determine the distribution of the wavelet coefficients of each decomposition layer and the change of the wavelet coefficients over time.

[0074] A4. Based on the distribution of wavelet coefficients of each decomposition layer, determine the frequency distribution information of the vibration signal.

[0075] In some embodiments, each decomposition layer corresponds to a specific frequency range, and the distribution of wavelet coefficients represents the energy distribution of the vibration signal in different frequency bands, thereby obtaining frequency distribution information.

[0076] A5. Based on the change of wavelet coefficients over time, determine the non-stationary characteristics of the vibration signal.

[0077] It should be noted that, when observing the change of wavelet coefficients over time, the wavelet coefficients of non-stationary signals will show obvious changes on the time axis, while the wavelet coefficients of stationary signals are relatively stable. The multi-resolution characteristics of wavelet transform are used to analyze the frequency changes of signals on different time scales. This helps to identify non-stationary characteristics such as transient phenomena and frequency modulation in the vibration process.

[0078] Exemplarily, embodiments of the present invention may calculate statistics of wavelet coefficients, such as mean, variance, energy, etc., to quantify the degree of non-stationarity.

[0079] S1045. Extract the displacement peak value of the vibration signal of each key part.

[0080] S1046. Based on the displacement peak value, perform derivation to obtain the vibration velocity and acceleration peak value.

[0081] For example, in the embodiment of the present invention, the vibration displacement of each key part can be differentiated to obtain the vibration velocity, and the vibration velocity can be differentiated to obtain the acceleration, and then the acceleration peak value can be obtained.

[0082] S105: Determine a vibration analysis result of the target tower based on the vibration characteristics of the target tower and the inherent characteristics of the tower.

[0083] In the embodiment of the present application, the vibration analysis result includes the vibration type and the vibration intensity.

[0084] As a possible implementation manner, the embodiment of the present invention may determine the vibration analysis result based on steps S1051 - S1052 .

[0085] S1051. Based on the vibration characteristics of the target tower and the inherent characteristics of the tower, a comparison is performed to determine the vibration type of the target tower.

[0086] In some embodiments, the vibration type includes forced vibration, free vibration, or resonance.

[0087] For example, if the natural frequency of the tower mainly appears in the vibration signal, and there is no obvious external driving force, and the vibration gradually decays, that is, it is affected by damping, then it may be free vibration.

[0088] For example, if the main frequency of the vibration signal matches the frequency of the external driving force, and the vibration persists, that is, is not significantly affected by damping, it may be a forced vibration.

[0089] For example, if the amplitude of a frequency component in the vibration signal increases significantly, and the frequency is close to or equal to the natural frequency of the tower, and the vibration intensity and dynamic characteristics also increase significantly, such as displacement peak, vibration velocity, and acceleration peak, then it may be resonance.

[0090] For example, the embodiment of the present invention can compare the main vibration frequency and the natural frequency. If the main vibration frequency and the natural frequency are similar and the vibration duration is greater than a set threshold, it indicates that the vibration type of the tower is forced vibration or resonance.

[0091] After that, based on the displacement peak value, vibration velocity and acceleration peak value of the tower vibration, determine whether it is resonance. If the tower is resonant, appropriate measures should be taken immediately to get rid of the resonance of the tower.

[0092] If the main vibration frequency and natural frequency differ greatly, and the vibration duration is greater than the set threshold, it means that the vibration type of the tower is forced vibration.

[0093] If the pole tower is forced to vibrate, the change in the vibration amplitude of the pole tower is further detected. If the vibration amplitude gradually decreases, it means that the pole tower tends to vibrate freely.

[0094] If the vibration amplitude remains unchanged, or decreases slowly, or varies from time to time, it means that the wind force is strong and persistent. The vibration amplitude of the tower can be reduced by adjusting the damping force.

[0095] S1052: Determine the vibration intensity of the target tower based on the vibration type and vibration characteristics.

[0096] Exemplarily, after determining the vibration type, the present invention can comprehensively determine the vibration intensity through vibration amplitude distribution information, displacement peak value, vibration velocity and acceleration peak value.

[0097] For example, the embodiment of the present invention can classify the vibration intensity. The vibration intensity is classified based on the amplitude, speed and acceleration to obtain the parameters corresponding to each level of vibration intensity. The vibration intensity is determined based on the parameters corresponding to each level of vibration intensity.

[0098] The present invention provides a method for analyzing the video of breeze vibration of a transmission line tower. The method performs frame processing on the video image of the transmission line tower to obtain multiple frames of video images, determines the position information of each key part of the target tower in the video image, and performs time-frequency analysis to determine vibration characteristics such as amplitude-frequency characteristics, time-frequency characteristics, and vibration dynamic characteristics, thereby realizing comprehensive feature extraction of each key part of the target tower. After that, the inherent characteristics of the target tower are combined to analyze and obtain vibration analysis results such as vibration type and vibration intensity, thereby realizing the video analysis of breeze vibration of the transmission line tower. The process does not require manual inspection, thereby improving the inspection efficiency of the transmission line tower.

[0099] Optionally, the method for analyzing video of breeze vibration of a transmission line tower provided in an embodiment of the present invention further includes steps S201-S206 after step S105.

[0100] S201: If the vibration type is resonance, determine a set frequency based on the natural frequency and the main vibration frequency.

[0101] S202: Determine the target position of the anti-vibration hammer based on the set frequency.

[0102] S203, adjusting the position of the anti-vibration hammer to the target position, so that the vibration type of the target tower is changed from resonance to forced vibration.

[0103] In this way, the embodiment of the present invention can adjust the natural frequency of the target tower by adjusting the position of the anti-vibration hammer, so as to free the tower from the resonance state and reduce the influence of the tower vibration on the tower structure.

[0104] S204: If the vibration type is forced vibration, determine the set damping force of the adjustable damper of the target tower and the set tension of the damping line at the transmission lines on both sides of the target tower based on the vibration intensity and vibration characteristics.

[0105] S205: Adjust the damping force of the adjustable damper to a set damping force.

[0106] S206, adjusting the tension of the damping line to a set tension.

[0107] In this way, the embodiment of the present invention can adjust the vibration amplitude of the target tower by adjusting the damping force of the target tower, so that when the tower is affected by wind and forced to vibrate, the vibration amplitude under the same wind force level can be reduced, thereby improving the wind resistance of the tower and ensuring the reliability of the tower.

[0108] Optionally, the method for analyzing video of breeze vibration of a transmission line tower provided in an embodiment of the present invention further includes steps S301-S304 after step S105.

[0109] S301. Obtain wind data and vibration characteristics in a historical period.

[0110] In some embodiments, the wind data includes wind speed and wind direction.

[0111] S302: Classify the wind data and vibration characteristics in the historical period to obtain the vibration characteristics of the target tower under various wind data conditions.

[0112] S303, calculating the characteristic difference between the vibration characteristics of each key part of the target tower in the second period and the vibration characteristics of the first period under the same wind data conditions.

[0113] Among them, the first period is the period before the second period in the historical period.

[0114] S304: If the feature difference of a key part is greater than a set threshold, the key part is determined to be in an abnormal state.

[0115] For example, taking the crossarm of the target tower as an example, if the vibration amplitude of the crossarm in the current period is 30% higher than the vibration amplitude under the same wind force level N days ago, it means that the relevant position connected to the crossarm of the target tower may be damaged, causing the vibration amplitude of the crossarm to increase. In this case, it is determined that the crossarm at that location is abnormal, and the user is required to conduct an inspection test on the target tower to ensure the reliable operation of the tower and avoid power outages.

[0116] It should be understood that the order of execution of the steps in the above embodiment does not necessarily 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 on the implementation process of the embodiment of the present invention.

[0117] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0118] Figure 2 The schematic diagram of the structure of a power transmission line tower breeze vibration early warning device provided by an embodiment of the present invention is shown. The early warning device 400 includes a communication module 401 and a processing module 402 .

[0119] The communication module 401 is used to obtain the video data of the target tower in the transmission line and the inherent characteristics of the target tower;

[0120] The processing module 402 is used to perform frame processing on the video data of the target tower to obtain multiple frames of video images; identify the key parts of the target tower in each frame of video image to obtain the key features of each frame of video image, and the key features include the position information of the key parts of the target tower; based on the key features of each frame of video image, perform time-frequency analysis to determine the vibration characteristics of the target tower; the vibration characteristics include amplitude-frequency characteristics, time-frequency characteristics and vibration dynamic characteristics; based on the vibration characteristics of the target tower and the inherent characteristics of the tower, determine the vibration analysis results of the target tower, and the vibration analysis results include vibration type and vibration intensity.

[0121] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions 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 video analysis method for breeze vibration of a transmission line tower, characterized in that: include: Acquire video data of a target tower in a transmission line and inherent characteristics of the target tower; Performing frame processing on the video data of the target tower to obtain multiple frames of video images; Identify key parts of the target pole tower in each frame of video image to obtain key features of each frame of video image, wherein the key features include position information of key parts of the target pole tower; Based on the key features of each frame of the video image, a time-frequency analysis is performed to determine the vibration characteristics of the target tower; the vibration characteristics include amplitude-frequency characteristics, time-frequency characteristics and vibration dynamic characteristics; Based on the vibration characteristics of the target pole tower and the inherent characteristics of the target pole tower, a vibration analysis result of the target pole tower is determined, wherein the vibration analysis result includes a vibration type and a vibration intensity.

2. The method for video analysis of breeze vibration of power transmission line tower according to claim 1, characterized in that: The inherent characteristics include the natural frequency and the damping ratio, the amplitude-frequency characteristics include the main frequency of vibration and the distribution information of the vibration amplitude, the time-frequency characteristics include the frequency distribution information and the non-stationary characteristics, and the vibration dynamic characteristics include the displacement peak value, the vibration velocity and the acceleration peak value; The step of performing time-frequency analysis based on the key features of each frame of the video image to determine the vibration features of the target tower includes: Based on the key features of each frame of the video image, track the trajectory of each key part of the target tower to determine the vibration signal of each key part, wherein the vibration signal includes the vibration displacement of the key part at each moment; Performing Fourier transform on the vibration signals of the key parts to obtain frequency spectra of the key parts; Based on the frequency spectra of the key parts, the main vibration frequency and the vibration amplitude distribution information are identified; Performing wavelet transform on the vibration signals of each key part to determine the frequency distribution information and non-stationary characteristics of each key part; Extracting the displacement peak value of the vibration signal of each key part; Based on the displacement peak value, a derivative is performed to obtain the vibration velocity and acceleration peak value.

3. The method for analyzing the breeze vibration of a transmission line tower according to claim 2, characterized in that: The wavelet transform is performed on the vibration signals of the key parts to determine the frequency distribution information and non-stationary characteristics of the key parts, including: For the vibration signal of any key part, the wavelet basis function and the number of decomposition layers of the wavelet transform are determined based on the frequency distribution information of the vibration signal; Based on the wavelet basis and the number of decomposition layers, the vibration signal is subjected to wavelet transformation to obtain wavelet coefficients of each decomposition layer; Based on the wavelet coefficients of each decomposition layer, determine the distribution of the wavelet coefficients of each decomposition layer and the change of the wavelet coefficients over time; Based on the distribution of wavelet coefficients of each decomposition layer, the frequency distribution information of the vibration signal is determined; Based on the change of wavelet coefficients over time, the non-stationary characteristics of the vibration signal are determined.

4. The method for analyzing the breeze vibration of a transmission line tower according to claim 1, characterized in that: The step of performing frame processing on the video data of the target tower to obtain multiple frames of video images includes: Extracting a plurality of continuous frames of video images from the video data; Calculating an estimated value of the vibration frequency of the target tower based on the continuous multiple frames of video images; Determining a decomposition frame rate based on an estimated value of the vibration frequency of the target tower and a preset analysis accuracy; Based on the decomposed frame rate, the video data is framed to obtain the multiple frames of video images.

5. The method for analyzing the video of breeze vibration of a power transmission line tower according to claim 1, characterized in that: The identifying of the key parts of the target tower in each frame of video image to obtain the key features of each frame of video image includes: Convert each frame of the video image into a grayscale image to obtain a plurality of grayscale images; Performing target detection on the multiple grayscale images to identify key parts of the target tower; Performing feature point detection on each key part on the multiple grayscale images to determine the position coordinates of each key part on each grayscale image; Based on the position coordinates of each key part on each grayscale image, a static and dynamic analysis is performed on each key part to determine the key parts in a static state and the key parts in a vibrating state; Taking the key parts in the static state on each grayscale image as a reference, determining the position information of the key parts in the vibration state on each grayscale image; The key features are determined based on the position information of each key part on each grayscale image.

6. The method for analyzing the video of breeze vibration of a transmission line tower according to claim 1, characterized in that: The step of determining the vibration analysis result of the target tower based on the vibration characteristics of the target tower and the inherent characteristics of the target tower includes: Based on the vibration characteristics of the target pole tower and the inherent characteristics of the target pole tower, a comparison is performed to determine the vibration type of the target pole tower, wherein the vibration type includes forced vibration, free vibration or resonance; Based on the vibration type and the vibration characteristics, the vibration intensity of the target tower is determined.

7. The method for video analysis of breeze vibration of power transmission line tower according to claim 1, characterized in that: After determining the vibration analysis result of the target tower based on the vibration characteristics of the target tower and the inherent characteristics of the target tower, the method further includes: If the vibration type is resonance, determining a set frequency based on the natural frequency and the main vibration frequency; Based on the set frequency, determining a target position of the anti-vibration hammer; The position of the anti-vibration hammer is adjusted to the target position so that the vibration type of the target pole tower is changed from resonance to forced vibration.

8. The method for analyzing the breeze vibration video of a power transmission line tower according to any one of claims 1 to 7, characterized in that: After determining the vibration analysis result of the target tower based on the vibration characteristics of the target tower and the inherent characteristics of the target tower, the method further includes: If the vibration type is forced vibration, then based on the vibration intensity and the vibration characteristics, determine the set damping force of the adjustable damper of the target tower and the set tension of the damping line at the transmission lines on both sides of the target tower; adjusting the damping force of the adjustable damper to the set damping force; The tension of the damping wire is adjusted to the set tension.

9. The method for analyzing the breeze vibration video of a power transmission line tower according to any one of claims 1 to 7, characterized in that: The method further comprises: Acquiring wind data and vibration characteristics in a historical period; the wind data includes wind speed and wind direction; Classifying the wind data and vibration characteristics in the historical period to obtain the vibration characteristics of the target tower under various wind data conditions; Calculate the characteristic difference between the vibration characteristics of each key part of the target tower in the second period and the vibration characteristics of the first period under the same wind data conditions; wherein the first period is the period before the second period in the historical period; If the characteristic difference of a key part is greater than the set threshold, the key part is determined to be in an abnormal state.

10. A power transmission line tower breeze vibration early warning device, characterized in that: include: A communication module, used to obtain video data of a target tower in a transmission line and inherent characteristics of the target tower; A processing module, used for performing frame processing on the video data of the target tower to obtain multiple frames of video images; Identify key parts of the target pole tower in each frame of video image to obtain key features of each frame of video image, wherein the key features include position information of key parts of the target pole tower; perform time-frequency analysis based on the key features of each frame of video image to determine vibration features of the target pole tower; the vibration features include amplitude-frequency features, time-frequency features and vibration dynamic features; Based on the vibration characteristics of the target pole tower and the inherent characteristics of the pole tower, a vibration analysis result of the target pole tower is determined, wherein the vibration analysis result includes a vibration type and a vibration intensity.

Images