Power transmission line external damage hidden danger positioning and grading evaluation method and device

Abstract

The invention relates to a power transmission line external damage hidden danger positioning and grading evaluation method and device. The method comprises the following steps: performing external damage hidden danger analysis on a regional image of a power transmission line, and determining at least one hidden danger and pixel coordinate information and feature information of each hidden danger; the feature information of the hidden danger comprises at least one of hidden danger depth information, hidden danger size, hidden danger shape and hidden danger type; for each hidden danger, determining a potential threat value of the hidden danger to the power transmission line based on geographical environment information in a preset range of the power transmission line and pixel coordinate information of the hidden danger; determining a feature threat value of the hidden danger to the power transmission line based on the feature information of the hidden danger; and determining the risk level of the hidden danger according to the potential threat value, the feature threat value and a preset risk assessment model. According to the method, potential threats are judged from the two aspects of geographic positions and features of hidden dangers, comprehensive analysis is carried out in combination with multi-source data, the comprehensiveness of external damage hidden danger assessment can be improved, and the accuracy of external damage hidden danger risk grading can also be improved.

Description

Technical Field

[0001] This application relates to the field of power technology, and in particular to a method and device for locating, classifying and assessing potential external damage hazards in transmission lines. Background Technology

[0002] With the rapid development of the power industry, the safety of transmission lines has received increasing attention. External damage hazards to transmission lines refer to potential threats posed by external objects or forces to transmission lines and related equipment, typically caused by factors such as construction machinery, vehicle collisions, and natural disasters. To ensure the stable operation of transmission lines, timely detection and handling of these hazards has become a crucial task for the power industry.

[0003] Traditional methods for detecting potential hazards rely heavily on manual inspections, which have drawbacks such as high labor costs, low detection efficiency, and slow response speed. Furthermore, traditional methods cannot provide accurate hazard location and comprehensive risk assessment, resulting in potential hazards not being discovered and effectively addressed in a timely manner, thus increasing the risk of transmission line failures.

[0004] Therefore, how to accurately locate and comprehensively assess the potential external damage to transmission lines is a technical problem that urgently needs to be solved. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, device, computer equipment, computer-readable storage medium, and computer program product for locating, classifying, and assessing external damage hazards of transmission lines, which can accurately locate and comprehensively assess the risks of external damage to transmission lines, thereby improving the response rate to such hazards.

[0006] Firstly, this application provides a method for locating and classifying potential external damage hazards in transmission lines, including:

[0007] External damage hazard analysis is performed on the regional images of the transmission line to identify at least one hazard and the pixel coordinates and feature information of each hazard. The feature information of the hazard includes at least one of the following: hazard depth, hazard size, hazard shape, and hazard type.

[0008] For each potential hazard, the potential threat value of the hazard to the transmission line is determined based on the geographical environment information within the preset range of the transmission line and the pixel coordinate information of the hazard.

[0009] Based on the characteristic information of the hidden danger, the characteristic threat value of the hidden danger to the transmission line is determined;

[0010] The risk level of a potential hazard is determined based on its potential threat value, characteristic threat value, and a pre-defined risk assessment model.

[0011] In one embodiment, an external damage hazard analysis is performed on a regional image of the transmission line to identify at least one hazard and the pixel coordinates and feature information of each hazard, including:

[0012] The area image of the transmission line is input into a preset hazard identification model to identify at least one hazard and the characteristic information of each hazard;

[0013] Edge detection is performed on the region image to obtain the edge contour image;

[0014] The edge contour image is compared with the preset hazard template image to determine the pixel coordinate information of each hazard.

[0015] In one embodiment, the characteristic information of the hazard includes hazard depth information, and the method further includes:

[0016] Use stereo vision technology or lidar technology to determine the depth information of potential hazards.

[0017] In one embodiment, based on geographical environment information within a preset range of the transmission line and pixel coordinate information of the potential hazard, the potential threat value of the hazard to the transmission line is determined, including:

[0018] Based on the geographical environment information and pixel coordinate information of the potential hazards within the preset range of the transmission line, the relative positional relationship between the potential hazards and the transmission line is determined.

[0019] Based on the relative positional relationship and the threat area of ​​the transmission line, the potential threat value of the hidden danger to the transmission line is determined; the threat area of ​​the transmission line is determined based on the characteristic information of the hidden danger and the safety requirements of the transmission line.

[0020] In one embodiment, the relative positional relationship includes the direction and / or distance between the hazard and the transmission line. Based on the relative positional relationship and the threat area of ​​the transmission line, the potential threat value of the hazard to the transmission line is determined, including:

[0021] Determine whether the hazard is located within the threat area of ​​the transmission line based on the direction and / or distance between the hazard and the transmission line;

[0022] If so, then a threat is identified, and the potential threat value of the hidden danger to the transmission line is determined to be the first value;

[0023] If not, then it is determined that there is no threat, and the potential threat value of the hidden danger to the transmission line is determined to be the second value.

[0024] In one embodiment, based on the characteristic information of the hazard, the characteristic threat value of the hazard to the transmission line is determined, including:

[0025] For each characteristic of a potential hazard, a quantitative threat value is determined based on each characteristic and the corresponding threat quantification model.

[0026] Based on the quantitative threat values ​​corresponding to each characteristic information of the hidden danger, the characteristic threat value of the hidden danger to the transmission line is determined.

[0027] In one embodiment, the risk level of a potential hazard is determined based on the potential threat value, the characteristic threat value, and a preset risk assessment model, including:

[0028] The overall threat value is determined by weighted summation of potential threat values ​​and characteristic threat values.

[0029] The risk level of a potential hazard is determined by comparing the overall threat value with the risk level threshold.

[0030] In one embodiment, the method further includes:

[0031] Determine the magnitude of the external force causing the potential hazard based on environmental factors.

[0032] Determine the external force threat value of a potential hazard based on the magnitude of the external force exerted upon it.

[0033] Accordingly, based on the potential threat value, characteristic threat value, and preset risk assessment model, the risk level of the hazard is determined, including:

[0034] The risk level of a potential hazard is determined based on the potential threat value, characteristic threat value, external threat value, and a pre-set risk assessment model.

[0035] In one embodiment, the method further includes:

[0036] Based on the alarm mechanism corresponding to the risk level of the hazard, a risk warning for the hazard is triggered.

[0037] Secondly, this application also provides a device for locating and classifying potential external damage hazards in transmission lines, comprising:

[0038] The first determination module is used to perform external damage hazard analysis on the regional image of the transmission line, and determine at least one hazard and the pixel coordinate information and feature information of each hazard; the feature information of the hazard includes at least one of the following: hazard depth information, hazard size, hazard shape and hazard type;

[0039] The second determination module is used to determine the potential threat value of each hidden danger to the transmission line based on the geographical environment information within the preset range of the transmission line and the pixel coordinate information of the hidden danger.

[0040] The third determination module is used to determine the characteristic threat value of the hidden danger to the transmission line based on the characteristic information of the hidden danger;

[0041] The fourth determination module is used to determine the risk level of a potential hazard based on the potential threat value, characteristic threat value, and a preset risk assessment model.

[0042] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method for locating and classifying potential hazards of external damage to transmission lines in the first aspect.

[0043] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, it implements the steps of the method for locating and classifying potential hazards of external damage to transmission lines as described in the first aspect.

[0044] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method for locating and classifying potential hazards of external damage to transmission lines as described in the first aspect.

[0045] The aforementioned method, device, computer equipment, storage medium, and computer program product for locating, classifying, and assessing external damage hazards to transmission lines analyze regional images of transmission lines to identify at least one hazard and its pixel coordinates and characteristic information. The characteristic information includes at least one of hazard depth, size, shape, and type. For each hazard, based on the geographical environment information within a preset range of the transmission line and the hazard's pixel coordinates, the potential threat value of the hazard to the transmission line is determined. Based on the hazard's characteristic information, the characteristic threat value of the hazard to the transmission line is determined. Based on the potential threat value, the characteristic threat value, and a preset risk assessment model, the risk level of the hazard is determined. In other words, this application's embodiments assess potential threats from both the geographical location and characteristics of the hazard, combine multi-source data for comprehensive analysis, and quantify the potential threat of the hazard to the transmission line. This provides foundational data for subsequent risk assessment, ensuring that the threat level of the hazard is accurately calculated. This not only improves the comprehensiveness of external damage hazard assessment but also enhances the accuracy of external damage hazard risk classification. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is an application environment diagram of the method for locating, classifying, and assessing external damage hazards to transmission lines in one embodiment;

[0048] Figure 2 This is a flowchart illustrating the method for locating and classifying potential external damage hazards to transmission lines in one embodiment.

[0049] Figure 3 This is a flowchart illustrating the method for locating and classifying potential external damage hazards to transmission lines in another embodiment;

[0050] Figure 4 This is a flowchart illustrating the method for locating and classifying potential external damage hazards to transmission lines in another embodiment;

[0051] Figure 5 This is a schematic diagram of the complete process of the method for locating, classifying, and assessing external damage hazards to transmission lines in one embodiment;

[0052] Figure 6 This is a structural block diagram of a device for locating and classifying potential external damage hazards to transmission lines in one embodiment;

[0053] Figure 7 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0055] The method for locating and classifying potential external damage hazards in transmission lines provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, one or more data acquisition devices 101 can be installed on or around the power transmission line for real-time monitoring and surveillance. These data acquisition devices 101 can include, but are not limited to, visual data acquisition devices, environmental data acquisition devices, and motion data acquisition devices. Visual data acquisition devices, also known as image acquisition devices, include cameras, monocular cameras, and binocular cameras. Environmental data acquisition devices include temperature and humidity sensors, meteorological monitoring equipment, and wind speed monitoring equipment. Motion data acquisition devices include visual cameras and accelerometers. The data acquisition devices 101 can communicate with a server 102 via a network to upload the real-time collected multi-source data to the server 102. This allows the server 102 to perform real-time online monitoring and risk warnings for potential external damage to the power transmission line based on the multi-source data. This multi-source data can include real-time monitoring data collected by various sensors. A data storage system can store the data that the server 102 needs to process. The data storage system can be integrated onto the server 102 or placed on a cloud or other network server. The server 102 can be implemented using a standalone server or a server cluster composed of multiple servers.

[0056] It should be noted that the method for locating and classifying potential external damage hazards to transmission lines provided in this application can be applied to cloud servers, and of course, it can also be applied to local monitoring terminals. For example, by setting up local monitoring terminals near transmission lines, various data acquisition devices can interact with the local monitoring terminals in real time, which can shorten the data transmission path, reduce the risks of data delay, data leakage, and data loss caused by data transmission, and improve the efficiency of risk warning. In addition, the cloud server can also communicate with the power grid control center to synchronously display information such as the real-time status of transmission lines, potential external damage hazards, and risk warnings on the display screen of the power grid control center system, so that the center personnel can monitor in real time.

[0057] In one exemplary embodiment, such as Figure 2 As shown, a method for locating and classifying potential external damage hazards in transmission lines is provided, and this method is applied to... Figure 1 Taking the server in the example, the explanation includes the following steps 201 to 204. Wherein:

[0058] Step 201: Perform external damage hazard analysis on the regional image of the transmission line to identify at least one hazard and the pixel coordinate information and feature information of each hazard.

[0059] The characteristic information of a hazard includes at least one of the following: hazard depth, hazard size, hazard shape, and hazard type.

[0060] For example, an image acquisition device, such as a camera, can be used to capture images of the power transmission line to obtain images of the area within a preset range around the power transmission line. The image acquisition device can acquire images of the area at a preset frequency and send the acquired images of the area to a server. The server can perform external damage hazard analysis on the area images of the power transmission line to determine whether there are any potential targets around the power transmission line that may cause damage to the power transmission line at the current time. These potential targets may include, but are not limited to, objects that may cause damage to the power transmission line, such as construction machinery, vehicles, and hydrogen balloons.

[0061] In one optional implementation, computer vision technology can be used for the automatic identification and classification of external damage hazards. For example, an area image of the transmission line can be input into a preset hazard identification model for automatic identification and classification, thereby determining whether there are external damage hazards (i.e., hazard targets) and the type of hazard. The preset hazard identification model can be any type of neural network model, such as convolutional neural networks, fully connected networks, attention mechanism networks, encoder networks, etc., and this application embodiment does not specifically limit it.

[0062] It should be noted that one or more potential hazards may exist near power transmission lines; therefore, one or more potential hazards may be identified from the regional image. For example, the aforementioned hazard identification network can further determine the pixel coordinates and / or feature information of each hazard, including at least one of the following: hazard depth, hazard size, hazard shape, and hazard type.

[0063] In another alternative implementation, if one or more hazards are identified in the regional image of the transmission line using a preset hazard identification model, image processing techniques can be employed to analyze the hazard in the regional image of the transmission line to obtain the pixel coordinate information and / or feature information of each hazard. For example, image processing techniques may include denoising, smoothing, edge detection, template matching, etc.

[0064] For example, the server can extract the pixel coordinate information of each potential hazard using algorithms such as edge detection and template matching to ensure high-precision extraction of hazard locations. For instance, edge detection can be performed on an area image of a power transmission line to obtain an edge contour image. This edge contour image is then compared with a preset hazard template image to determine the pixel coordinate information of each hazard. Edge detection algorithms, such as the Canny operator, are multi-stage algorithms that can be implemented through the following steps: First, Gaussian filtering is used to smooth the area image to remove noise. Next, the gradient value of each pixel is calculated to determine the edge strength in the area image, and the gradient image is processed to retain only local maxima and suppress non-edge points. Then, high and low thresholds are set, and potential edges are filtered and connected using a double-threshold method to finally extract the edge contour of the hazard, obtaining the edge contour image.

[0065] Next, a template matching algorithm is used to compare the similarity between the edge contour image and the hazard template image to pinpoint the specific location of the hazard. The hazard template image can include template images of different types of hazards. By comparing the similarity between the edge contour image and different hazard template images, the pixel coordinates of each hazard can be determined. Of course, a single area image can include multiple hazards of the same type, such as multiple construction machines.

[0066] For example, a template matching algorithm determines the best matching region by calculating the similarity between the input edge contour image and the hazard template image (e.g., using normalized cross-correlation). This may include the following steps: for each hazard, generating a hazard template image based on the hazard's characteristics (e.g., size, shape, etc.); using a sliding window method on the edge contour image to compare the template with each possible region; determining the similarity between the hazard template image and each image region of the edge contour image by calculating the normalized cross-correlation value or other similarity measure, and marking the specific location of the hazard at the position with the highest similarity.

[0067] In this example, edge detection is used to extract the edge information of the potential hazard, and template matching is combined to determine the pixel coordinate information of the potential hazard, which enables accurate location of the potential hazard.

[0068] In addition, for other characteristic information of potential hazards, image processing technology and / or other processing techniques can be used to analyze the regional images of the transmission line to obtain the characteristic information of each hazard. For example, for the hazard depth information, stereo vision technology and / or lidar technology can be used to estimate the depth of the hazard, determine the hazard depth information, and construct a correlation model between the hazard and the safe distance of the transmission line.

[0069] The following section introduces depth estimation based on stereo vision. Stereo vision obtains the depth information of potential hazards by calculating disparity maps. The disparity formula is shown in formula (1):

[0070] (1)

[0071] Where d is the depth of the hazard, f is the focal length of the camera, B is the baseline length between the two cameras, and Δx is the horizontal offset of the corresponding point of the same hazard target in the two images.

[0072] Stereo vision technology uses two cameras to capture the same scene from different angles, utilizing parallax to calculate the depth information of objects. In practical applications, stereo vision can be affected by factors such as lighting, viewing angle, and occlusion. Therefore, stereo matching optimization algorithms can be used to reduce parallax calculation errors and improve the accuracy of depth estimation. Stereo matching optimization algorithms improve 3D reconstruction results by reducing noise, handling occlusion, and maintaining edge continuity, thereby enhancing the quality of the parallax map and improving the accuracy of depth estimation.

[0073] The following section introduces depth estimation based on lidar technology. LiDAR obtains accurate 3D point cloud data by calculating the time difference of emitted light to generate depth information of potential hazards. LiDAR can generate high-precision 3D point cloud data, and through multiple scans, obtain detailed spatial structure of power transmission lines and their surrounding environment, providing depth information of potential hazards and their spatial relationship with power transmission lines.

[0074] It should be noted that a single technology can be used to determine the depth information of a hazard, or multiple technologies can be fused together. For example, the hazard depth information from lidar can be fused with the hazard depth information from stereo vision to further improve the accuracy of depth estimation. This is especially true in complex environments or in cases of occlusion, where fusing multi-source data can provide more accurate hazard location. Fusion methods can include, but are not limited to, averaging and weighted averaging.

[0075] Step 202: For each potential hazard, based on the geographical environment information within the preset range of the transmission line and the pixel coordinate information of the hazard, determine the potential threat value of the hazard to the transmission line.

[0076] For example, for each potential hazard, the potential threat to the power transmission line can be assessed by analyzing the relationship between the hazard and its surrounding geographical environment, including the relationship between the hazard and the power transmission line. The server can obtain geographical environment information within a preset range of the power transmission line and input the geographical environment information and the pixel coordinate information of the hazard into a preset threat analysis model for threat analysis to quantify the potential threat of the hazard to the power transmission line and obtain a potential threat value.

[0077] For example, spatial data of the transmission line and its surrounding environment can be obtained using a Geographic Information System (GIS), including but not limited to topography, landforms, vegetation distribution, buildings, and transportation routes. Of course, this spatial data can also be collected through remote sensing images (such as satellite imagery and aerial photography) or ground surveys (such as laser scanning and sensor data), and then processed and analyzed using GIS technology. By analyzing the geographic environment information and pixel coordinate information of potential hazards within a predetermined range of the transmission line using GIS, the relative positional relationship between the hazard and the transmission line can be analyzed to determine the potential threat posed by the hazard.

[0078] For each potential hazard, we can analyze its potential threat to the transmission line, thereby obtaining the potential threat value of each hazard to the transmission line.

[0079] Step 203: Based on the characteristic information of the hidden danger, determine the characteristic threat value of the hidden danger to the transmission line.

[0080] For example, the characteristic information of the hidden danger can be input into a preset threat quantification model for quantification processing to obtain the characteristic threat value of the hidden danger to the transmission line. When there are multiple characteristic information of the hidden danger, multiple characteristic threat values ​​can be obtained. Alternatively, the threat values ​​corresponding to each characteristic information can be weighted and summed to obtain a single characteristic threat value. For example, for each characteristic information of the hidden danger, based on each characteristic information and the corresponding threat quantification model, the quantified threat value corresponding to each characteristic information is determined. Then, based on the quantified threat values ​​corresponding to each characteristic information of the hidden danger, the characteristic threat value of the hidden danger to the transmission line is determined.

[0081] The preset threat quantification model can be a neural network model or a mathematical model. In the case of a mathematical model, different feature information can correspond to different threat quantification models, and feature information with the same attribute can correspond to the same threat quantification model. For example, a min-max normalization model or a threshold comparison model can be used.

[0082] Step 204: Determine the risk level of the hazard based on the potential threat value, characteristic threat value, and preset risk assessment model.

[0083] For example, the preset risk assessment model can be a risk assessment model based on the LEC (Job Condition Hazard Assessment) method, or a regression prediction model, or it can be dynamically adjusted based on the LEC assessment method and the regression prediction model. Taking the LEC assessment method as an example, by weighting and summing the potential threat value and the characteristic threat value, a comprehensive threat value can be obtained, which can be called the LEC value. According to the LEC value and the risk level threshold, the risk of the hidden danger can be divided into multiple risk levels, such as low risk, medium risk and high risk levels. That is, by comparing the comprehensive threat value and the risk level threshold, the risk level of the hidden danger can be determined. The regression prediction model dynamically adjusts the assessment standard and optimizes the risk prediction of hidden dangers by analyzing historical data. For example, the weight coefficients of the potential threat value and the characteristic threat value can be adjusted by regression prediction. The regression formula can be as shown in formula (2):

[0084] (2)

[0085] Where y represents the predicted risk level or overall threat value of the hazard. , ... The coefficients of the regression model, , ... These are the relevant input features.

[0086] For example, when implementing the LEC assessment method, key characteristic data of potential hazards are first collected, including factors such as the hazard's depth, location, external force influences, and environmental conditions. Based on this data, the LEC value of each hazard is calculated. During the data collection process, real-time and historical data are acquired through sensors, monitoring systems, and on-site inspections, and the LEC value of each hazard is automatically calculated and classified according to predetermined risk classification standards (such as low risk, medium risk, and high risk). For instance, when conducting risk assessments of hazards, the potential threat of a hazard to a transmission line can be comprehensively assessed based on factors such as its location, depth, size, shape, type, and geographical environment.

[0087] This process can be automated in the background, ensuring the real-time nature and accuracy of the assessment. Using the LEC assessment method, the potential threat of hazards can be quickly assessed, and timely responses can be taken based on the hazard's risk level. High-risk hazards will be prioritized for handling to ensure the safety of transmission lines.

[0088] For example, after determining the risk level of a potential hazard, a risk warning can be triggered based on the alarm mechanism corresponding to the risk level of the hazard, so as to eliminate the hazard in time before it damages the transmission line, and ensure the safe operation of the transmission line and the stable operation of the city's power supply.

[0089] In the aforementioned method for locating and classifying potential external damage hazards to transmission lines, external damage hazard analysis is performed on regional images of the transmission line to identify at least one hazard and its pixel coordinates and feature information. The feature information includes at least one of hazard depth, size, shape, and type. For each hazard, based on the geographical environment information within a preset range of the transmission line and the hazard's pixel coordinates, the potential threat value of the hazard to the transmission line is determined. Furthermore, based on the hazard's feature information, the characteristic threat value of the hazard to the transmission line is determined. Finally, based on the potential threat value, the characteristic threat value, and a preset risk assessment model, the risk level of the hazard is determined. In other words, this embodiment of the application judges the potential threat from both the geographical location and features of the hazard, combines multi-source data for comprehensive analysis, and quantifies the potential threat of the hazard to the transmission line, providing basic data for subsequent risk assessment and ensuring that the threat level of the hazard is accurately calculated. This not only improves the comprehensiveness of external damage hazard assessment but also enhances the accuracy of external damage hazard risk classification.

[0090] In one exemplary embodiment, such as Figure 3 As shown, step 202 above may include steps 301 to 302. Wherein:

[0091] Step 301: Based on the geographical environment information and pixel coordinate information of the hidden danger within the preset range of the transmission line, determine the relative positional relationship between the hidden danger and the transmission line.

[0092] The relative positional relationship can include the distance and / or direction between the potential hazard and the transmission line. For example, GIS technology can be used to obtain spatial data of the transmission channel and its surrounding environment to obtain geographical environmental information within a preset range of the transmission line. Then, by combining the geographical environmental information and the pixel coordinate information of the potential hazard, the distance and direction between the potential hazard and the transmission line can be analyzed.

[0093] Step 302: Based on the relative positional relationship and the threat area of ​​the transmission line, determine the potential threat value of the hidden danger to the transmission line.

[0094] The threat area of ​​a transmission line can be determined based on the characteristics of the potential hazard and the safety requirements of the transmission line.

[0095] For example, spatial analysis tools, combined with the safety standards and environmental conditions of transmission lines, can be used to determine whether a hazard is located within a potential threat area. This process includes the following aspects: Based on the safety requirements of the transmission line and the characteristic information of the hazard, such as hazard type, depth, and external force influence, a safety boundary is determined. Based on this safety boundary, the threat area of ​​the transmission line can be delineated. For example, a hazard within 3 meters of the transmission line may be considered high-risk, while a hazard further away is considered low-risk. GIS tools are used to analyze the spatial relationship between the hazard and the defined threat area to determine whether the hazard has entered the safety boundary, i.e., whether the hazard is located within the threat area. For example, spatial intersection functions (such as buffer zone analysis) can also be used to determine whether a hazard exists within the threat area.

[0096] For example, when quantifying potential threats based on threat regions, the server can determine whether a potential hazard is located within the threat region of the power transmission line based on the direction and / or distance between the hazard and the power transmission line. If the hazard is located within the threat region of the power transmission line, a threat is determined to exist, and the potential threat value of the hazard to the power transmission line is determined to be a first value, such as 1. If the hazard is not located within the threat region of the power transmission line, no threat is determined to exist, and the potential threat value of the hazard to the power transmission line is determined to be a second value, such as 0.

[0097] For example, the influence of the surrounding environment, such as meteorological conditions, soil type, and vegetation cover, can also be considered to assess whether these factors exacerbate the threat of the hazard. GIS technology can accomplish this analysis by integrating different spatial data (such as meteorological and topographical data). That is, based on the geographical environment information within the preset range of the transmission line and the pixel coordinate information of the hazard, the environmental characteristics around the transmission line can be determined, and the potential threat value of the hazard to the transmission line can be quantitatively determined based on the environmental characteristics; wherein, the geographical environment information may include the multiple spatial data mentioned above. Furthermore, a weighted sum of the first potential threat value determined based on the relative position relationship and the second potential threat value determined based on the environmental characteristics can be obtained to obtain a comprehensive potential threat value.

[0098] In this embodiment, by acquiring spatial data of the power transmission channel and its surrounding environment, the distance and direction between the hidden danger and the power transmission line are analyzed, and spatial analysis is used to determine whether the hidden danger is located in the potential threat area. This quantifies the potential threat of the hidden danger to the power transmission line, provides a reliable basis for subsequent classification, and improves the accuracy of the classification of external damage hidden dangers to the power transmission line.

[0099] In one exemplary embodiment, such as Figure 4 As shown, the above method also includes:

[0100] Step 401: Determine the magnitude of the external force of the hazard based on the environmental factors of the hazard.

[0101] For example, the magnitude of the external force on a potential hazard can be estimated based on factors such as the surrounding working environment, weather conditions, and construction machinery. For instance, by monitoring the dynamic load of construction machinery or vehicles with sensors and combining this with meteorological data (such as wind speed and temperature), the potential impact of external forces on the hazard can be determined.

[0102] Step 402: Determine the external force threat value of the hidden danger based on the magnitude of the external force.

[0103] For example, a threshold value for the external force of a potential hazard can be set. Based on the relationship between the external force of the potential hazard and the external force intensity threshold, the external force threat value of the potential hazard can be quantitatively determined. For example, when the external force of the potential hazard is greater than or equal to the external force intensity threshold, the external force threat value of the potential hazard is the first value, such as 1. When the external force of the potential hazard is less than the external force intensity threshold, the external force threat value of the potential hazard is the second value, such as 0.

[0104] Accordingly, determining the risk level of a hazard in step 204 above, based on the potential threat value, characteristic threat value, and preset risk assessment model, may include:

[0105] Step 403: Determine the risk level of the hazard based on the potential threat value, characteristic threat value, external force threat value, and preset risk assessment model.

[0106] For example, the potential threat value, characteristic threat value, and external force threat value can be weighted and summed based on the LEC assessment method to obtain the comprehensive threat value of the hidden danger to the transmission line. Then, based on the relationship between the comprehensive threat value and the risk level threshold, the risk level of the hidden danger can be determined.

[0107] In this embodiment, the potential threat of a hazard to a transmission line is comprehensively analyzed by considering three factors: the location of the hazard, the characteristics of the hazard, and the external force exerted on the hazard. This comprehensive analysis of the potential destructive impact of the hazard on the transmission line improves the accuracy of risk assessment for external damage hazards to the transmission line, provides a reliable basis for the subsequent elimination of the hazard, and enhances the operational safety of the transmission line.

[0108] In one optional embodiment, a complete process for locating and classifying potential external damage hazards in transmission lines is provided, such as... Figure 5 As shown, it includes the following steps:

[0109] Step 1: Use computer vision and image processing technologies to automatically detect potential external damage to power transmission lines and obtain their pixel coordinate information.

[0110] Image data of the power transmission line area (the aforementioned area image) is acquired through image acquisition equipment, and computer vision technology (such as convolutional neural networks) is used to automatically identify and classify external damage hazards, as well as image processing technology is used to determine the pixel coordinate information of the hazards.

[0111] Step 2: Obtain depth information of potential hazards through stereo vision and lidar data.

[0112] Stereo vision technology combined with LiDAR is used to acquire depth information of potential hazards in three-dimensional space. The stereo image is processed by the parallax method of computer vision to obtain the spatial location of the hazard; LiDAR provides high-precision depth information and generates three-dimensional point cloud data for further analysis of the spatial location and depth of the hazard.

[0113] Step 3: Use GIS technology to analyze the relative positional relationship between potential hazards and transmission lines.

[0114] GIS technology combines image data (such as pixel coordinates of potential hazards determined from image data) with geographic environmental information to calculate the relative position between potential hazards and transmission lines through spatial analysis models. Furthermore, GIS technology can provide spatial coordinate data of potential hazards and analyze the spatial relationships between potential hazards, transmission lines, and the surrounding environment based on geographic information, providing data support for hazard grading and assessment.

[0115] Step 4: Perform anomaly detection on the detected hidden dangers and set thresholds to quantify the threat of the hidden dangers.

[0116] For different parameters of potential hazards, such as type, depth, location, and external force, threshold ranges are set for relevant parameters. When any parameter of a hazard exceeds the corresponding set threshold, the anomaly handling process is initiated, entering the risk assessment stage (step 5). For example, if a hazard is located too close to a power transmission line, or its depth exceeds the depth threshold, the system automatically identifies it as a high-risk hazard. Then, based on the risk assessment results, the corresponding alarm mechanism is triggered, and on-site inspection and emergency response are conducted. It should be noted that the thresholds for different parameters can be fixed values ​​or dynamically adjusted based on real-time data.

[0117] For example, safety thresholds for different hazard parameters can be set based on the type of hazard and the safety requirements of the transmission line. For instance, a hazard might be considered high-risk if its depth exceeds 3 meters or its distance from the transmission line is less than 10 meters. The server can continuously monitor the relevant parameters of the hazard in real time using data acquisition equipment. Whenever a hazard's parameters exceed a predetermined threshold, it is automatically recorded and marked as abnormal, and different levels of risk handling procedures are automatically initiated based on the hazard's risk level. For severe anomalies, the emergency assessment and handling phase is prioritized. This process ensures that an emergency response procedure can be initiated immediately once a hazard exceeds the safety limit, effectively avoiding potential threats to the transmission line and improving response speed and accuracy.

[0118] Step 5: Combine multi-source data to construct a risk assessment system and classify the risks of potential hazards.

[0119] The multi-source data can include image data, depth data, and GIS data (the aforementioned geographic environmental information). Integrating this multi-source data allows for the construction of a comprehensive risk assessment system. This system categorizes hazards based on their characteristics, historical data, and risk assessment models. The categorization criteria include low, medium, and high risk levels, dynamically assessed based on factors such as the hazard's distance from the transmission line, its depth, the surrounding environment, and the intensity of external forces. Furthermore, the introduction of expert systems and historical data provides data support for hazard assessment, ensuring the reliability and real-time nature of the assessment results.

[0120] For example, potential threats are quantified based on multi-source data to obtain the threat value corresponding to each type of data. Then, the threat values ​​corresponding to each type of data are fused using a data fusion algorithm (such as the weighted average method) to assess the potential risk of the hidden danger and determine the risk level of the hidden danger. The fusion formula is shown in formula (3):

[0121] (3)

[0122] Where R is the overall threat value, I is the characteristic threat value of the hazard obtained from image data analysis, D is the deep threat value of the hazard obtained from deep data analysis, and G is the potential threat value of the hazard obtained from GIS data analysis. , and The weighting coefficients for the risks associated with each data source satisfy the following conditions: .

[0123] Image data can provide information such as the location, shape, size, and type of potential hazards. For example, determining the relative size and type of a hazard area in an image can yield its characteristic threat value. Depth data can assess the spatial relationship between a hazard and power transmission lines; the greater the depth, the greater the threat. Depth data reflects the proximity of the hazard to the power transmission line; greater depth indicates a higher potential threat. GIS data can provide information on the spatial relationship between a hazard and its surrounding environment, including the hazard's location, surrounding terrain, landforms, and other environmental factors. GIS data helps assess the geographical distribution of hazards and their relative position to power transmission lines. Weighting coefficients can be dynamically adjusted based on the actual situation. For example, if depth information is more important in certain areas, the weight of depth data can be increased; if the image data has high clarity, the weight of image data can be increased.

[0124] In other words, location parameters of potential hazards, such as pixel coordinates and relative positions, can be obtained first using image and GIS data. These parameters are then used to calculate the potential threat posed by the hazard to the transmission line. Subsequently, a weighted algorithm is used to assess the threat level of the hazard, taking into account its depth. For example, the closer the hazard is to the transmission line and the greater its depth, the more severe the threat. This process quantifies the potential threat of hazards to the transmission line, providing fundamental data for subsequent risk assessments and ensuring that the degree of threat is accurately calculated and assigned appropriate weights.

[0125] For example, multi-source data may also include external force data of potential hazards. Accordingly, analysis based on external force data of potential hazards can yield the external force threat value of potential hazards. By combining the characteristic threat value, deep threat value, potential threat value and external force threat value of potential hazards, the potential threat of potential hazards to transmission lines can be comprehensively assessed.

[0126] Furthermore, after quantifying the comprehensive threat value of the hidden danger to the transmission line, the risk level of the hidden danger, such as low risk, medium risk, or high risk, can be determined by comparing the relationship between the comprehensive threat value and multiple risk level thresholds.

[0127] For example, preprocessing can be performed on data from different sources. For image data, methods such as denoising, contrast enhancement, and color correction can improve the image quality of the region, ensuring that potential hazards are clearly visible. Image processing algorithms (such as histogram equalization and filtering) can remove noise and enhance image details. For depth data acquired by LiDAR or stereo vision, noise removal and error correction are performed. For example, filtering algorithms (such as median filtering and mean filtering) can remove outliers, ensuring the accuracy of the depth data. For GIS data, projection transformation and coordinate alignment are performed to ensure that spatial data from different sources are correctly aligned within the same coordinate system. Furthermore, GIS data needs to be cleaned to remove irrelevant information and standardize the data format.

[0128] It should be noted that during the hazard risk assessment process, real-time data stream processing can be used to dynamically detect hazards and adjust risk assessment strategies; real-time monitoring data can be received and updated to include information such as the depth and location of hazards; and hazard classification parameters can be adjusted based on real-time data. The status of hazards is continuously monitored through multiple data acquisition devices (such as environmental monitoring sensors, GPS positioning systems, LiDAR, cameras, etc.). The real-time data stream is transmitted to a central processing system or server for rapid analysis and processing.

[0129] The method provided in this application combines computer vision, image processing, stereo vision, lidar, and GIS technologies to achieve automatic detection, precise location, depth estimation, and risk assessment of external damage hazards to power transmission lines. Through multi-source data fusion and real-time dynamic assessment, it significantly improves the efficiency and accuracy of hazard detection, enabling timely discovery and response to potential threats. This method enhances the accuracy of hazard identification, reduces manual intervention, ensures the safety of power transmission lines, and provides a scientific basis for subsequent risk management and emergency response.

[0130] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0131] Based on the same inventive concept, this application also provides a device for locating and classifying external damage hazards of transmission lines to implement the aforementioned method for locating and classifying external damage hazards. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the device for locating and classifying external damage hazards of transmission lines provided below can be found in the limitations of the method for locating and classifying external damage hazards of transmission lines described above, and will not be repeated here.

[0132] In one exemplary embodiment, such as Figure 6 As shown, a device for locating and classifying potential external damage hazards in transmission lines is provided, comprising: a first determining module 601, a second determining module 602, a third determining module 603, and a fourth determining module 604, wherein:

[0133] The first determining module 601 is used to perform external damage hazard analysis on the regional image of the transmission line, and determine at least one hazard and the pixel coordinate information and feature information of each hazard; the feature information of the hazard includes at least one of the following: hazard depth information, hazard size, hazard shape and hazard type.

[0134] The second determining module 602 is used to determine the potential threat value of each hidden danger to the transmission line based on the geographical environment information within the preset range of the transmission line and the pixel coordinate information of the hidden danger.

[0135] The third determination module 603 is used to determine the characteristic threat value of the hidden danger to the transmission line based on the characteristic information of the hidden danger;

[0136] The fourth determination module 604 is used to determine the risk level of a potential hazard based on the potential threat value, characteristic threat value, and preset risk assessment model.

[0137] In one embodiment, the first determining module 601 includes:

[0138] The identification unit is used to input the regional image of the transmission line into the preset hidden danger identification model to identify at least one hidden danger and the feature information of each hidden danger;

[0139] The detection unit is used to perform edge detection on the region image to obtain the edge contour image;

[0140] The comparison unit is used to compare the similarity between the edge contour image and the preset hidden danger template image to determine the pixel coordinate information of each hidden danger.

[0141] In one embodiment, the characteristic information of the hazard includes hazard depth information, and the device further includes:

[0142] The fifth determination module is used to determine the depth information of potential hazards using stereo vision technology or lidar technology.

[0143] In one embodiment, the second determining module 602 includes:

[0144] The first determining unit is used to determine the relative positional relationship between the hidden danger and the transmission line based on the geographical environment information and the pixel coordinate information of the hidden danger within the preset range of the transmission line.

[0145] The second determining unit is used to determine the potential threat value of the hidden danger to the transmission line based on the relative positional relationship and the threat area of ​​the transmission line; the threat area of ​​the transmission line is determined based on the characteristic information of the hidden danger and the safety requirements of the transmission line.

[0146] In one embodiment, the relative positional relationship includes the direction and / or distance between the hazard and the transmission line. The second determining unit is specifically used to determine whether the hazard is located within the threat area of ​​the transmission line based on the direction and / or distance between the hazard and the transmission line. If so, it is determined that there is a threat, and the potential threat value of the hazard to the transmission line is determined to be a first value. If not, it is determined that there is no threat, and the potential threat value of the hazard to the transmission line is determined to be a second value.

[0147] In one embodiment, the third determining module 603 includes:

[0148] The third determining unit is used to determine the quantitative threat value corresponding to each feature information of the hidden danger based on each feature information and the corresponding threat quantification model.

[0149] The fourth determining unit is used to determine the characteristic threat value of the hidden danger to the transmission line based on the quantitative threat value corresponding to each characteristic information of the hidden danger.

[0150] In one embodiment, the fourth determining module 604 includes:

[0151] The fifth determining unit is used to perform a weighted summation of the potential threat value and the characteristic threat value to determine the comprehensive threat value;

[0152] The sixth determination unit is used to compare the comprehensive threat value and the risk level threshold to determine the risk level of the hidden danger.

[0153] In one embodiment, the device further includes:

[0154] The sixth determination module is used to determine the magnitude of the external force affecting the potential hazard based on environmental factors.

[0155] The seventh determination module is used to determine the external force threat value of a potential hazard based on the magnitude of the external force exerted on it.

[0156] The fourth determination module 604 is also used to determine the risk level of a potential hazard based on the potential threat value, characteristic threat value, external force threat value, and a preset risk assessment model.

[0157] In one embodiment, the device further includes:

[0158] The early warning module is used to trigger risk warnings for potential hazards based on the alarm mechanism corresponding to the risk level of the hazard.

[0159] Each module in the aforementioned power transmission line external damage hazard location and grading assessment device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0160] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs in the non-volatile storage media to run. The database stores multi-source sensor data collected by various data acquisition devices, as well as intermediate and final data generated during the hazard location and classification process. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for locating and classifying external damage hazards in transmission lines.

[0161] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0162] In one exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the transmission line external damage hazard location and grading assessment method in any of the above embodiments.

[0163] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the method for locating and classifying potential external damage hazards to transmission lines in any of the above embodiments.

[0164] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method for locating and classifying potential external damage hazards to transmission lines in any of the above embodiments.

[0165] It should be noted that the data involved in this application (including but not limited to data used for analysis, data stored, data displayed, etc.) are all information and data that have been fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0166] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0167] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0168] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for locating and grading external damage of a power transmission line, characterized in that, The method comprises: performing external damage hidden danger analysis on the regional image of the power transmission line to determine at least one hidden danger and pixel coordinate information and feature information of each hidden danger; the feature information of the hidden danger comprises at least one of hidden danger depth information, hidden danger size, hidden danger shape and hidden danger type; for each hidden danger, determining a potential threat value of the hidden danger to the power transmission line based on geographical environment information within a preset range of the power transmission line and the pixel coordinate information of the hidden danger; determining a feature threat value of the hidden danger to the power transmission line based on the feature information of the hidden danger; determining a risk level of the hidden danger according to the potential threat value, the feature threat value and a preset risk assessment model.

2. The method of claim 1, wherein, The external damage hidden danger analysis on the regional image of the power transmission line to determine at least one hidden danger and pixel coordinate information and feature information of each hidden danger comprises: inputting the regional image of the power transmission line into a preset hidden danger recognition model to determine at least one hidden danger and feature information of each hidden danger; performing edge detection on the regional image to obtain an edge contour image; comparing the edge contour image with a preset hidden danger template image to determine the pixel coordinate information of each hidden danger.

3. The method according to claim 1 or 2, characterized in that, The feature information of the hidden danger comprises hidden danger depth information, and the method further comprises: determining the hidden danger depth information of the hidden danger by using stereo vision technology or laser radar technology.

4. The method of claim 1, wherein, The determination of the potential threat value of the hidden danger to the power transmission line based on the geographical environment information within a preset range of the power transmission line and the pixel coordinate information of the hidden danger comprises: determining a relative position relationship between the hidden danger and the power transmission line based on the geographical environment information within a preset range of the power transmission line and the pixel coordinate information of the hidden danger; determining the potential threat value of the hidden danger to the power transmission line based on the relative position relationship and a threat area of the power transmission line; the threat area of the power transmission line is determined based on the feature information of the hidden danger and safety requirements of the power transmission line.

5. The method of claim 4, wherein, The relative position relationship comprises a direction and / or distance between the hidden danger and the power transmission line, and the determination of the potential threat value of the hidden danger to the power transmission line based on the relative position relationship and the threat area of the power transmission line comprises: determining whether the hidden danger is located in the threat area of the power transmission line according to the direction and / or distance between the hidden danger and the power transmission line; if yes, determining that there is a threat and determining that the potential threat value of the hidden danger to the power transmission line is a first value; if no, determining that there is no threat and determining that the potential threat value of the hidden danger to the power transmission line is a second value.

6. The method of claim 1, wherein, The determination of the feature threat value of the hidden danger to the power transmission line based on the feature information of the hidden danger comprises: for each feature information of the hidden danger, determining a quantized threat value corresponding to each feature information based on each feature information and a corresponding threat quantization model; determining the feature threat value of the hidden danger to the power transmission line based on the quantized threat values corresponding to each feature information of the hidden danger.

7. The method of claim 1, wherein, The method further comprises: determining an external force size of the hidden danger based on environmental factors of the hidden danger; determining an external force threat value of the hidden danger based on the external force size of the hidden danger; 8. The method of claim 1, wherein, Accordingly, the determining of the risk level of the hidden danger according to the potential threat value, the feature threat value and the preset risk assessment model comprises: determining the risk level of the hidden danger according to the potential threat value, the feature threat value, the external force threat value and the preset risk assessment model. The method further comprises: triggering a risk warning of the hidden danger according to an alarm mechanism corresponding to the risk level of the hidden danger. The device comprises:

9. The method of claim 1, wherein, a first determining module configured to analyze external damage hidden dangers of regional images of a power transmission line, determine at least one hidden danger and pixel coordinate information and feature information of each hidden danger, and the feature information of the hidden danger comprises at least one of hidden danger depth information, hidden danger size, hidden danger shape and hidden danger type; a second determining module configured to determine, for each hidden danger, a potential threat value of the hidden danger to the power transmission line based on geographical environment information within a preset range of the power transmission line and the pixel coordinate information of the hidden danger; 10. A device for locating and classifying potential external damage hazards in transmission lines, characterized in that, a third determining module configured to determine a feature threat value of the hidden danger to the power transmission line based on the feature information of the hidden danger; a fourth determining module configured to determine a risk level of the hidden danger according to the potential threat value, the feature threat value and a preset risk assessment model. ​ ​ ​

Images