Overhead distribution line external damage hidden danger point detection method and device based on video analysis

Abstract

The invention discloses a video analysis-based overhead distribution line external damage hidden danger point detection method and device, and proposes the analysis of meteorological data, and obtains the meteorological influence data having an influence on a power line; and analyzing the dynamic interference data of the influence of the interferent on the power line under the condition of the meteorological influence data. Interferent and meteorological influence are considered at the same time, and the influence of meteorological conditions and high-interference environment on external damage hidden danger point detection is overcome. By extracting characteristic parameters, the external damage hidden danger probability of the suspected external damage hidden danger point under the weather influence data and the dynamic interference data under the time condition is analyzed, the external damage hidden danger probability is matched with the corresponding overhead distribution line external damage hidden danger point, and if the probability is larger than a certain threshold value, the overhead distribution line external damage hidden danger point is determined. If yes, the suspected external damage hidden danger point is the external damage hidden danger point on the distribution line, so that detection is completed.

Description

Technical Field

[0001] The present invention relates to the technical field of detection of external damage potential points of overhead distribution lines, and in particular to a method and device for detecting external damage potential points of overhead distribution lines based on video analysis. Background Art

[0002] Line inspection refers to the work of staff using their eyes or telescopes and other tools and instruments to observe, inspect and measure the various components of the transmission line. The purpose is to grasp the operating status of the line, promptly discover equipment defects and problems that threaten the safety of the line. Due to the wide distribution of overhead lines in urban areas, complex traffic conditions, and the long-term operation of lines under the open air, they are often affected by the surrounding environment and weather changes, and there is a high risk of external damage. In order to further respond to the requirements of digitalization of power grid operation and maintenance, realize fine monitoring of the operation and maintenance status of lines in special sections, and better reduce line tripping caused by external damage to the urban network, tree obstacles in the channel, and quality problems of the equipment itself, an efficient and intelligent visual channel intelligent early warning method for external damage of overhead distribution lines is needed.

[0003] According to the data table of overhead distribution line faults and tripping that have occurred between 2021 and 2024, overhead distribution line faults and tripping can be roughly divided into four categories: the first category is faults caused by defects in the equipment itself; the second category is line faults caused by external force damage, including mechanical construction, tree planting, drone damage, etc.; the third category is faults caused by natural factors, such as strong winds, lightning strikes, etc.; the fourth category is faults caused by other reasons.

[0004] From the perspective of the types of damage to overhead distribution lines, they can be divided into human factors and natural factors. Human factors include mechanical construction, construction, fire, foreign objects and other factors, while natural factors are mainly caused by strong winds, thunderstorms, floods and other disasters. According to statistical data, external force damage accounts for a large proportion of the causes of line failures.

[0005] Among the reasons for line tripping, most cases are caused by external force damage, and external force damage will cause the scope of power outage to expand, making it difficult to quickly determine the cause of the tripping, causing a relatively long power outage, which is very likely to cause user complaints and public opinion events. At the same time, most external force damage is short-term, and traditional monitoring devices and inspections are difficult to find evidence of damage. With the gradual expansion of the scope of overhead distribution line laying, the frequency of external force damage has gradually increased, and the negative impact on the quality of power grid operation has also become increasingly greater.

[0006] At present, the method adopted is to install an early warning system device equipped with intelligent video analysis technology in areas where potential damage points often occur outside the overhead distribution lines. This device can monitor foreign objects in the area in a dynamic real-time video monitoring and early warning mode, and provide timely feedback to the terminal.

[0007] However, under meteorological conditions and high-interference environments, it is difficult to identify abnormal behaviors from videos, and the detection results are disturbed, resulting in large errors. Summary of the invention

[0008] Based on the problems raised by the above background technology, the purpose of the present invention is to provide a method and equipment for detecting external damage potential points of overhead distribution lines based on video analysis, which solves the problem that it is difficult to identify abnormal behavior from the video under meteorological conditions and high interference environments, and the detection results are interfered with, resulting in large errors.

[0009] The present invention is achieved through the following technical solutions:

[0010] The first aspect of the present invention provides a method for detecting external damage potential points of overhead distribution lines based on video analysis, comprising the following steps:

[0011] Step S1, obtaining an overhead distribution line monitoring video, extracting power lines from the overhead distribution line monitoring video, and performing external damage potential point detection on the power lines to obtain suspected external damage potential points;

[0012] Step S2, acquiring meteorological data, performing meteorological analysis on the meteorological data to obtain meteorological impact data, and performing dynamic interference analysis on the overhead distribution line monitoring video based on the meteorological impact data to obtain dynamic interference data under the meteorological impact data;

[0013] Step S3, constructing an external failure hidden danger detection model, and using the external failure hidden danger detection model to detect the external failure hidden danger probability of the suspected external failure hidden danger point under the meteorological influence data and the dynamic interference data;

[0014] Step S4: comprehensively consider the external failure hidden danger probability and the external failure hidden danger point of the overhead distribution line to generate the external failure hidden danger point of the overhead distribution line.

[0015] In the above technical solution, the monitoring video of the overhead distribution line is first processed, the power lines are extracted from the monitoring video of the overhead distribution line, and the initial external damage potential points of the extracted power lines are detected to obtain suspected external damage potential points.

[0016] Since detection is susceptible to interference under weather conditions such as strong winds, it is proposed to analyze meteorological data to obtain meteorological impact data on power lines. At the same time, there are interference objects, such as trees and foreign objects, which hit the power lines and cause hidden dangers of external damage to the power lines. Interference objects will also be affected by strong winds and other weather conditions. Therefore, it is necessary to analyze the dynamic interference data of the interference objects on the power lines under the conditions of meteorological impact data. The simultaneous consideration of interference objects and meteorological influences overcomes the influence of meteorological conditions and high interference environments on the detection of external damage risk points.

[0017] An external failure hazard detection model is constructed. By extracting characteristic parameters, the probability of external failure hazards of suspected external failure hazard points under time conditions under meteorological influence data and dynamic interference data is analyzed, and the probability of external failure hazards is matched with the corresponding external failure hazard points of overhead distribution lines. If the probability is greater than a certain threshold, the suspected external failure hazard point is the external failure hazard point on the distribution line, thus completing the detection.

[0018] In an optional embodiment, extracting power lines from the overhead distribution line monitoring video and detecting external damage potential points on the power lines includes the following steps:

[0019] Step S11, filtering the overhead distribution line monitoring video frame by frame to obtain a plurality of frames of overhead distribution line point cloud images;

[0020] Step S12, extracting point clouds from each frame of the overhead distribution line point cloud image, and dividing the extracted point clouds into line point clouds and obstacle point clouds;

[0021] Step S13, performing curve fitting on the line point cloud according to the structural characteristics of the overhead distribution line to obtain a power line point cloud;

[0022] Step S14, traversing the power line point cloud, performing safety distance judgment between the power line point cloud and the obstacle point cloud, and determining suspected external damage potential points according to the safety distance judgment result.

[0023] In an optional embodiment, obtaining meteorological data and performing meteorological analysis on the meteorological data comprises the following steps:

[0024] Step S21, obtaining wind direction data and wind speed data within a monitoring period through a wind speed monitoring device;

[0025] Step S22, combining the wind direction data in the monitoring period with the corresponding wind speed data at intervals to perform vector decomposition to obtain the pulsating wind speed;

[0026] Step S23, calculating the average speed of the wind speed data during the monitoring period to obtain the average wind speed;

[0027] Step S24: Calculate the meteorological impact data at each time point within the monitoring period based on the average wind speed and the pulsating wind speed.

[0028] In an optional embodiment, performing dynamic interference analysis on the overhead distribution line monitoring video based on the meteorological impact data comprises the following steps:

[0029] Step S25, extracting an obstacle point cloud of interference objects from the overhead distribution line monitoring video, and determining the boundary of the obstacle point cloud;

[0030] Step S26, calculating the interval distance between the boundary of the obstacle point cloud and the wind speed monitoring device;

[0031] Step S27, performing wind field simulation on the meteorological impact data at each time point in the monitoring period based on the interval distance, to obtain the impact parameters at each time point in the monitoring period;

[0032] Step S28: Calculate the motion state of the obstacle point cloud under the influencing parameters at each time point in the monitoring period to obtain dynamic interference data.

[0033] In an optional embodiment, building an external damage hidden danger detection model includes:

[0034] Constructing a feature node layer, the feature node layer includes a forward feature node layer and a reverse feature node layer, using the forward feature node layer to detect the external failure transformation characteristics of the suspected external failure potential point in the forward time sequence; using the reverse feature node layer to detect the external failure transformation characteristics of the suspected external failure potential point in the reverse time sequence;

[0035] Constructing an enhanced node layer, the enhanced node layer comprising a forward enhanced node layer and a reverse enhanced node layer, using the forward enhanced node layer to detect the association characteristics of the suspected external failure potential point with the meteorological impact data and the dynamic interference data in a forward time sequence; using the reverse enhanced node layer to detect the association characteristics of the suspected external failure potential point with the meteorological impact data and the dynamic interference data in a reverse time sequence;

[0036] A connection matrix is ​​constructed, and the external transformation features output by the feature node layer are connected and combined with the associated features output by the enhancement node layer through the connection matrix.

[0037] In an optional embodiment, using the external failure hidden danger detection model to detect the external failure hidden danger probability of the suspected external failure hidden danger point under the meteorological influence data and the dynamic interference data includes the following steps:

[0038] Step S31, setting the power line point cloud including the suspected external damage potential point as a suspected external damage potential area;

[0039] Step S32, using the feature node layer of the external failure hidden danger detection model to perform forward and reverse time series detection on the suspected external failure hidden danger area to obtain external failure transformation features;

[0040] Step S33: using the enhanced node layer of the external damage hidden danger detection model to detect the correlation characteristics of the meteorological impact data and the dynamic interference data with the suspected external damage hidden danger area;

[0041] Step S34: connect and combine the external transformation feature and the associated feature to obtain a combined feature, and multiply the combined feature by a connection matrix to obtain an output matrix;

[0042] Step S35, solving the output matrix to obtain the probability of external damage risk.

[0043] In an optional embodiment, using the enhanced node layer of the external damage hidden danger detection model to detect the correlation characteristics of the meteorological impact data and the dynamic interference data with the suspected external damage hidden danger area includes the following steps:

[0044] In an optional embodiment, using the enhanced node layer of the external damage hidden danger detection model to detect the correlation characteristics of the meteorological impact data and the dynamic interference data on the suspected external damage hidden danger area in the forward time sequence and the reverse time sequence includes the following steps:

[0045] Extracting a boundary tangent from the suspected external failure potential area, calculating the displacement of the suspected external failure potential area in the direction of the boundary tangent under the influence of the meteorological impact data at a specific time sequence, and performing a force analysis on the suspected external failure potential area based on the displacement to obtain meteorological impact characteristics;

[0046] Calculate the boundary area between the obstacle point cloud and the suspected external failure potential area, calculate the stress condition of the boundary area under the influence of the meteorological influence data in a specific time sequence under the influence of the dynamic interference data in the boundary tangent direction, and obtain the interference influence feature;

[0047] The meteorological influence feature is associated and combined with the interference influence feature to obtain an associated feature.

[0048] The second aspect of the present invention provides a system for detecting external damage potential points of overhead distribution lines based on video analysis, comprising:

[0049] A suspected calculation module is used to obtain an overhead distribution line monitoring video, extract power lines from the overhead distribution line monitoring video, and perform external damage potential point detection on the power lines to obtain suspected external damage potential points;

[0050] An interference calculation module is used to obtain meteorological data, perform meteorological analysis on the meteorological data to obtain meteorological impact data, and perform dynamic interference analysis on the overhead distribution line monitoring video based on the meteorological impact data to obtain dynamic interference data under the meteorological impact data;

[0051] A probability calculation module is used to construct an external failure hidden danger detection model, and use the external failure hidden danger detection model to detect the external failure hidden danger probability of the suspected external failure hidden danger point under the meteorological influence data and the dynamic interference data;

[0052] The hidden danger point confirmation module is used to comprehensively consider the external failure hidden danger probability and the suspected external failure hidden danger point to generate the external failure hidden danger point of the overhead distribution line.

[0053] A third aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for detecting external damage potential points of overhead distribution lines based on video analysis is implemented.

[0054] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for detecting external damage potential points of overhead distribution lines based on video analysis.

[0055] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0056] It proposes to analyze meteorological data to obtain meteorological impact data on power lines; analyze dynamic interference data of interference on power lines under the condition of meteorological impact data. The simultaneous consideration of interference and meteorological impact overcomes the influence of meteorological conditions and high interference environment on the detection of external damage potential points. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative work. In the drawings:

[0058] Figure 1 A schematic diagram of a flow chart of a method for detecting external damage potential points of overhead distribution lines based on video analysis provided in Embodiment 1 of the present invention;

[0059] Figure 2 A schematic diagram of the structure of a system for detecting external damage potential points of overhead distribution lines based on video analysis provided in Embodiment 2 of the present invention;

[0060] Figure 3 A schematic diagram of the structure of an electronic device provided in Example 3 of the present invention. DETAILED DESCRIPTION

[0061] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0062] Example 1

[0063] Figure 1 A schematic diagram of a flow chart of a method for detecting external damage potential points of overhead distribution lines based on video analysis provided in Example 1 of the present invention, as shown in FIG. Figure 1 As shown, the method for detecting external damage potential points of overhead distribution lines based on video analysis includes the following steps:

[0064] Step S1, obtaining an overhead distribution line monitoring video, extracting power lines from the overhead distribution line monitoring video, and performing external damage potential point detection on the power lines to obtain suspected external damage potential points;

[0065] Step S2, acquiring meteorological data, performing meteorological analysis on the meteorological data to obtain meteorological impact data, and performing dynamic interference analysis on the overhead distribution line monitoring video based on the meteorological impact data to obtain dynamic interference data under the meteorological impact data;

[0066] Step S3, constructing an external failure hidden danger detection model, and using the external failure hidden danger detection model to detect the external failure hidden danger probability of the suspected external failure hidden danger point under the meteorological influence data and the dynamic interference data;

[0067] Step S4: generating external failure potential points of overhead distribution lines by comprehensively considering the external failure potential probability and the suspected external failure potential points.

[0068] It should be noted that, due to meteorological conditions and high interference environments, it is difficult to identify abnormal behavior from the video, and the detection results are interfered with, resulting in large errors. In response to the above problems, an embodiment of the present invention proposes a method for detecting external damage potential points of overhead distribution lines based on video analysis. In this method, the monitoring video of the overhead distribution line is first processed, and the power line is extracted from the monitoring video of the overhead distribution line. The extracted power line is initially detected for external damage potential points to obtain suspected external damage potential points.

[0069] Since detection is susceptible to interference under weather conditions such as strong winds, it is proposed to analyze meteorological data to obtain meteorological impact data on power lines. At the same time, there are interference objects, such as trees and foreign objects, which hit the power lines and cause hidden dangers of external damage to the power lines. Interference objects will also be affected by strong winds and other weather conditions. Therefore, it is necessary to analyze the dynamic interference data of the interference objects on the power lines under the conditions of meteorological impact data. The simultaneous consideration of interference objects and meteorological influences overcomes the influence of meteorological conditions and high interference environments on the detection of external damage risk points.

[0070] An external failure hazard detection model is constructed. By extracting characteristic parameters, the probability of external failure hazards of suspected external failure hazard points under time conditions under meteorological influence data and dynamic interference data is analyzed, and the probability of external failure hazards is matched with the corresponding external failure hazard points of overhead distribution lines. If the probability is greater than a certain threshold, the suspected external failure hazard point is the external failure hazard point on the distribution line, thus completing the detection.

[0071] In an optional embodiment, extracting power lines from the overhead distribution line monitoring video and detecting external damage potential points on the power lines includes the following steps:

[0072] Step S11, filtering the overhead distribution line monitoring video frame by frame to obtain a plurality of frames of overhead distribution line point cloud images;

[0073] Step S12, extracting point clouds from each frame of the overhead distribution line point cloud image, and dividing the extracted point clouds into line point clouds and obstacle point clouds;

[0074] Step S13, performing curve fitting on the line point cloud according to the structural characteristics of the overhead distribution line to obtain a power line point cloud;

[0075] Step S14, traversing the power line point cloud, performing safety distance judgment between the power line point cloud and the obstacle point cloud, and determining suspected external damage potential points according to the safety distance judgment result.

[0076] It should be noted that the purpose of filtering the overhead distribution line monitoring video frame by frame is to reduce noise and interference and improve the accuracy of subsequent point cloud extraction. The point cloud data acquired by the laser radar sometimes receives the echo signal incorrectly, resulting in some inevitable outliers, which have a great impact on the imaging, segmentation and subsequent target recognition of the point cloud. In this embodiment, statistical filtering is used to perform statistical analysis on each point cloud and its neighborhood, and points exceeding the distance threshold are regarded as outliers and eliminated.

[0077] After completing the statistical filtering, the point cloud data is filtered for cloth simulation to obtain the elevation data, and the ground point cloud is removed based on the elevation data. The purpose of this step is to extract accurate line point clouds. At the same time, it is to avoid the subsequent interference detection of interference objects, and the ground point cloud is used as part of the line point cloud, which will increase the intersection area and inaccurate analysis of its force situation.

[0078] In an optional embodiment, obtaining meteorological data and performing meteorological analysis on the meteorological data comprises the following steps:

[0079] Step S21, obtaining wind direction data and wind speed data within a monitoring period through a wind speed monitoring device;

[0080] Step S22, combining the wind direction data in the monitoring period with the corresponding wind speed data at intervals to perform vector decomposition to obtain the pulsating wind speed;

[0081] Step S23, calculating the average speed of the wind speed data during the monitoring period to obtain the average wind speed;

[0082] Step S24: Calculate the meteorological impact data at each time point within the monitoring period based on the average wind speed and the pulsating wind speed.

[0083] It should be noted that, according to the wind direction data, the wind speed data is vector decomposed, wherein the process of vector decomposition is to obtain the tangent and tangent point of the power line point cloud, take the tangent point as the center, and decompose the wind speed data vector into the pulsating wind speed perpendicular to the tangent. Specifically, the decomposition process is as follows:

[0084]

[0085] Where v(t) is the fluctuating wind speed perpendicular to the tangent line of the power line point cloud at time t, u n (t) is the north wind speed, u e (t) is the east wind speed, U n is the average northerly wind speed during the monitoring period, U e is the average eastward wind speed during the monitoring period.

[0086] In an optional embodiment, performing dynamic interference analysis on the overhead distribution line monitoring video based on the meteorological impact data comprises the following steps:

[0087] Step S25, extracting an obstacle point cloud of interference objects from the overhead distribution line monitoring video, and determining the boundary of the obstacle point cloud;

[0088] Step S26, calculating the interval distance between the boundary of the obstacle point cloud and the wind speed monitoring device;

[0089] Step S27, performing wind field simulation on the meteorological impact data at each time point in the monitoring period based on the interval distance, to obtain the impact parameters at each time point in the monitoring period;

[0090] Step S28: Calculate the motion state of the obstacle point cloud under the influencing parameters at each time point in the monitoring period to obtain dynamic interference data.

[0091] It should be noted that the pulsating wind speed in the tangent direction of the wind field perpendicular to the power line point cloud will change with the spatial distance relationship, and there is a certain interval distance between the obstacle point cloud and the power line point cloud. Therefore, it is necessary to first perform a transformation analysis of the pulsating wind speed in space. The process is as follows:

[0092]

[0093] D v =exp(-c*d)

[0094] Among them, R is the turbulence intensity, T is the monitoring period, G T is the gust factor, D v is the turbulence integral scale, c is the parameter to be fitted, and d is the distance between the boundary of the obstacle point cloud and the wind speed monitoring device.

[0095] The calculation of the obstacle point cloud shows the dynamic interference of the power lines under the influence of wind, which is beneficial for subsequent analysis.

[0096] In an optional embodiment, building an external damage hidden danger detection model includes:

[0097] Constructing a feature node layer, the feature node layer includes a forward feature node layer and a reverse feature node layer, using the forward feature node layer to detect the external failure transformation characteristics of the suspected external failure potential point in the forward time sequence; using the reverse feature node layer to detect the external failure transformation characteristics of the suspected external failure potential point in the reverse time sequence;

[0098] Constructing an enhanced node layer, the enhanced node layer comprising a forward enhanced node layer and a reverse enhanced node layer, using the forward enhanced node layer to detect the association characteristics of the suspected external failure potential point with the meteorological impact data and the dynamic interference data in a forward time sequence; using the reverse enhanced node layer to detect the association characteristics of the suspected external failure potential point with the meteorological impact data and the dynamic interference data in a reverse time sequence;

[0099] A connection matrix is ​​constructed, and the external transformation features output by the feature node layer are connected and combined with the associated features output by the enhancement node layer through the connection matrix.

[0100] In an optional embodiment, using the external failure hidden danger detection model to detect the external failure hidden danger probability of the suspected external failure hidden danger point under the meteorological influence data and the dynamic interference data includes the following steps:

[0101] Step S31, setting the power line point cloud including the suspected external damage potential point as a suspected external damage potential area;

[0102] Step S32, using the feature node layer of the external failure hidden danger detection model to perform forward time series and reverse time series detection on the suspected external failure hidden danger area to obtain external failure transformation features;

[0103] Step S33, using the enhanced node layer of the external damage hidden danger detection model to detect the correlation characteristics of the meteorological impact data and the dynamic interference data with the suspected external damage hidden danger area in the forward time sequence and the reverse time sequence;

[0104] Step S34: connect and combine the external transformation feature and the associated feature to obtain a combined feature, and multiply the combined feature by a connection matrix to obtain an output matrix;

[0105] Step S35, solving the output matrix to obtain the probability of external damage risk.

[0106] In an optional embodiment, using the enhanced node layer of the external damage hidden danger detection model to detect the correlation characteristics of the meteorological impact data and the dynamic interference data on the suspected external damage hidden danger area in the forward time sequence and the reverse time sequence includes the following steps:

[0107] Extracting a boundary tangent from the suspected external failure potential area, calculating the displacement of the suspected external failure potential area in the direction of the boundary tangent under the influence of the meteorological impact data at a specific time sequence, and performing a force analysis on the suspected external failure potential area based on the displacement to obtain meteorological impact characteristics;

[0108] Calculate the boundary area between the obstacle point cloud and the suspected external failure potential area, calculate the stress condition of the boundary area under the influence of the meteorological influence data in a specific time sequence under the influence of the dynamic interference data in the boundary tangent direction, and obtain the interference influence feature;

[0109] The meteorological influence feature is associated and combined with the interference influence feature to obtain an associated feature.

[0110] Example 2

[0111] Figure 2 The schematic diagram of the structure of the overhead distribution line external damage potential point detection system based on video analysis provided in Example 2 of the present invention is as follows: Figure 2 As shown in the figure, the overhead distribution line external damage potential point detection system based on video analysis includes:

[0112] A suspected calculation module is used to obtain an overhead distribution line monitoring video, extract power lines from the overhead distribution line monitoring video, and perform external damage potential point detection on the power lines to obtain suspected external damage potential points;

[0113] An interference calculation module is used to obtain meteorological data, perform meteorological analysis on the meteorological data to obtain meteorological impact data, and perform dynamic interference analysis on the overhead distribution line monitoring video based on the meteorological impact data to obtain dynamic interference data under the meteorological impact data;

[0114] A probability calculation module is used to construct an external failure hidden danger detection model, and use the external failure hidden danger detection model to detect the external failure hidden danger probability of the suspected external failure hidden danger point under the meteorological influence data and the dynamic interference data;

[0115] The hidden danger point confirmation module is used to comprehensively consider the external failure hidden danger probability and the suspected external failure hidden danger point to generate the external failure hidden danger point of the overhead distribution line.

[0116] Example 3

[0117] Figure 3 A schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention is shown in FIG. Figure 3 As shown, the electronic device includes a processor 21, a memory 22, an input device 23 and an output device 24; the number of processors 21 in the computer device can be one or more. Figure 3 A processor 21 is taken as an example; the processor 21, the memory 22, the input device 23 and the output device 24 in the electronic device can be connected by a bus or other means. Figure 3 The example of connecting through bus is taken in the following.

[0118] The memory 22 is a computer-readable storage medium that can be used to store software programs, computer executable programs, and modules. The processor 21 executes various functional applications and data processing of the electronic device by running the software programs, instructions, and modules stored in the memory 22, that is, the method for detecting external damage potential points of overhead distribution lines based on video analysis of Example 1 is implemented.

[0119] The memory 22 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 22 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 22 may further include a memory remotely arranged relative to the processor 21, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0120] The input device 23 can be used to receive the ID and password input by the user, etc. The output device 24 is used to output the network configuration page.

[0121] Example 4

[0122] Embodiment 4 of the present invention further provides a computer-readable storage medium, wherein the computer-executable instructions, when executed by a computer processor, are used to implement the method for detecting external damage potential points of overhead distribution lines based on video analysis as provided in Embodiment 1.

[0123] An embodiment of the present invention provides a storage medium containing computer executable instructions, and its computer executable instructions are not limited to the method operations provided in Example 1, and can also execute related operations in the method for detecting external failure potential points of overhead distribution lines based on video analysis provided in any embodiment of the present invention.

[0124] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for detecting external damage potential points of overhead distribution lines based on video analysis, characterized in that: The steps include: Step S1, obtaining an overhead distribution line monitoring video, extracting power lines from the overhead distribution line monitoring video, and performing external damage potential point detection on the power lines to obtain suspected external damage potential points; Step S2, acquiring meteorological data, performing meteorological analysis on the meteorological data to obtain meteorological impact data, and performing dynamic interference analysis on the overhead distribution line monitoring video based on the meteorological impact data to obtain dynamic interference data under the meteorological impact data; Step S3, constructing an external failure hidden danger detection model, and using the external failure hidden danger detection model to detect the external failure hidden danger probability of the suspected external failure hidden danger point under the meteorological influence data and the dynamic interference data; Step S4: generating external failure potential points of overhead distribution lines by comprehensively considering the external failure potential probability and the suspected external failure potential points.

2. The method for detecting external damage potential points of overhead distribution lines based on video analysis according to claim 1 is characterized in that: Extracting power lines from the overhead distribution line monitoring video and detecting external damage potential points on the power lines includes the following steps: Step S11, filtering the overhead distribution line monitoring video frame by frame to obtain a plurality of frames of overhead distribution line point cloud images; Step S12, extracting point clouds from each frame of the overhead distribution line point cloud image, and dividing the extracted point clouds into line point clouds and obstacle point clouds; Step S13, performing curve fitting on the line point cloud according to the structural characteristics of the overhead distribution line to obtain a power line point cloud; Step S14, traversing the power line point cloud, performing safety distance judgment between the power line point cloud and the obstacle point cloud, and determining suspected external damage potential points according to the safety distance judgment result.

3. The method for detecting external damage potential points of overhead distribution lines based on video analysis according to claim 1 is characterized in that: Acquiring meteorological data and performing meteorological analysis on the meteorological data comprises the following steps: Step S21, obtaining wind direction data and wind speed data within a monitoring period through a wind speed monitoring device; Step S22, combining the wind direction data in the monitoring period with the corresponding wind speed data at intervals to perform vector decomposition to obtain the pulsating wind speed; Step S23, calculating the average speed of the wind speed data during the monitoring period to obtain the average wind speed; Step S24: Calculate the meteorological impact data at each time point within the monitoring period based on the average wind speed and the pulsating wind speed.

4. The method for detecting external damage potential points of overhead distribution lines based on video analysis according to claim 3 is characterized in that: Performing dynamic interference analysis on the overhead distribution line monitoring video based on the meteorological impact data includes the following steps: Step S25, extracting an obstacle point cloud of interference objects from the overhead distribution line monitoring video, and determining a boundary of the obstacle point cloud; Step S26, calculating the interval distance between the boundary of the obstacle point cloud and the wind speed monitoring device; Step S27, performing wind field simulation on the meteorological impact data at each time point in the monitoring period based on the interval distance, to obtain the impact parameters at each time point in the monitoring period; Step S28: Calculate the motion state of the obstacle point cloud under the influencing parameters at each time point in the monitoring period to obtain dynamic interference data.

5. The method for detecting external damage potential points of overhead distribution lines based on video analysis according to claim 1 is characterized in that: Construct an external damage risk detection model, including: Constructing a feature node layer, the feature node layer includes a forward feature node layer and a reverse feature node layer, using the forward feature node layer to detect the external failure transformation characteristics of the suspected external failure potential point in the forward time sequence; using the reverse feature node layer to detect the external failure transformation characteristics of the suspected external failure potential point in the reverse time sequence; Constructing an enhanced node layer, the enhanced node layer comprising a forward enhanced node layer and a reverse enhanced node layer, using the forward enhanced node layer to detect the association characteristics of the suspected external failure potential point with the meteorological impact data and the dynamic interference data in a forward time sequence; using the reverse enhanced node layer to detect the association characteristics of the suspected external failure potential point with the meteorological impact data and the dynamic interference data in a reverse time sequence; A connection matrix is ​​constructed, and the external transformation features output by the feature node layer are connected and combined with the associated features output by the enhancement node layer through the connection matrix.

6. The method for detecting external damage potential points of overhead distribution lines based on video analysis according to claim 5 is characterized in that: Using the external failure hidden danger detection model to detect the external failure hidden danger probability of the suspected external failure hidden danger point under the meteorological influence data and the dynamic interference data includes the following steps: Step S31, setting the power line point cloud including the suspected external damage potential point as a suspected external damage potential area; Step S32, using the feature node layer of the external failure hidden danger detection model to perform forward and reverse time series detection on the suspected external failure hidden danger area to obtain external failure transformation features; Step S33: using the enhanced node layer of the external damage hidden danger detection model to detect the correlation characteristics of the meteorological impact data and the dynamic interference data with the suspected external damage hidden danger area; Step S34: connect and combine the external transformation feature and the associated feature to obtain a combined feature, and multiply the combined feature by a connection matrix to obtain an output matrix; Step S35, solving the output matrix to obtain the probability of external damage risk.

7. The method for detecting external damage potential points of overhead distribution lines based on video analysis according to claim 6 is characterized in that: Detecting the correlation characteristics of the meteorological impact data and the dynamic interference data on the suspected external damage potential area in the forward time sequence and the reverse time sequence using the enhanced node layer of the external damage potential detection model includes the following steps: Extracting a boundary tangent from the suspected external failure potential area, calculating the displacement of the suspected external failure potential area in the direction of the boundary tangent under the influence of the meteorological impact data at a specific time sequence, and performing a force analysis on the suspected external failure potential area based on the displacement to obtain meteorological impact characteristics; Calculate the boundary area between the obstacle point cloud and the suspected external failure potential area, calculate the stress condition of the boundary area under the influence of the meteorological influence data in a specific time sequence under the influence of the dynamic interference data in the boundary tangent direction, and obtain the interference influence feature; The meteorological influence feature is associated and combined with the interference influence feature to obtain an associated feature.

8. The overhead distribution line external damage potential point detection system based on video analysis is characterized by: include: A suspected calculation module is used to obtain an overhead distribution line monitoring video, extract power lines from the overhead distribution line monitoring video, and perform external damage potential point detection on the power lines to obtain suspected external damage potential points; An interference calculation module is used to obtain meteorological data, perform meteorological analysis on the meteorological data to obtain meteorological impact data, and perform dynamic interference analysis on the overhead distribution line monitoring video based on the meteorological impact data to obtain dynamic interference data under the meteorological impact data; A probability calculation module is used to construct an external failure hidden danger detection model, and use the external failure hidden danger detection model to detect the external failure hidden danger probability of the suspected external failure hidden danger point under the meteorological influence data and the dynamic interference data; The hidden danger point confirmation module is used to comprehensively consider the external failure hidden danger probability and the suspected external failure hidden danger point to generate the external failure hidden danger point of the overhead distribution line.

9. An electronic device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method for detecting external damage potential points of overhead distribution lines based on video analysis as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for detecting external damage potential points of overhead distribution lines based on video analysis as described in any one of claims 1 to 7 is implemented.

Images