Automatic inspection method for overhead transmission line and related product
Through the lightweight point cloud segmentation network and point cloud thinning algorithm, combined with the concept of central axis, the problem of low patrol efficiency of overhead transmission lines is solved, and fast and efficient patrol results identification and safety evaluation are achieved.
Patent Information
- Application Number
- CN202410950794.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-16
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-07-16
AI Technical Summary
The inspection methods of existing overhead transmission lines rely on manual surveys, resulting in low patrol efficiency, especially in areas with wide and complex environments across regions, and the huge amount of data collected by drones usually use full amount comparison, resulting in low efficiency.
A lightweight transmission line point cloud segmentation network is used to classify classified point cloud data, combining point cloud dilution algorithm and central axis concepts to reduce point cloud density and improve patrol efficiency.
It has achieved rapid classification and efficient patrol inspection, improved the efficiency of overhead transmission lines, and can quickly identify power lines and land objects to ensure the accuracy and safety of patrol results.
Smart Images

Figure CN118941986A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of circuit inspection technology, and in particular to an automatic inspection method for overhead power transmission lines and related products. Background Art
[0002] Overhead transmission lines are composed of towers and power lines. Towers are used as support for power lines to lift power lines and transmit electricity. As an important part of the power transmission system, overhead transmission lines have many safety management rules, such as prohibiting the stacking of items underneath. Therefore, regular inspections of overhead transmission lines are essential.
[0003] Existing inspection methods for overhead power transmission lines still rely on manual inspections, which are conducted by technicians on-site. However, for overhead power transmission lines that span a wide range of regions and have different and complex on-site environments in different regions, manual inspections will lead to low inspection efficiency.
[0004] Therefore, how to improve the inspection efficiency is a problem that technical personnel in this field need to solve urgently. Summary of the invention
[0005] Based on the above problems, the present application provides an automatic inspection method and related products for overhead transmission lines, introduces an FPS network capable of rapid classification, and reduces the point cloud density through a point cloud thinning algorithm and the concept of a central axis, thereby improving inspection efficiency.
[0006] In a first aspect, an embodiment of the present application provides an automatic inspection method for an overhead transmission line, comprising:
[0007] Acquire the point cloud data to be classified corresponding to the area to be inspected; the area to be inspected has ground objects and power lines;
[0008] Classifying the point cloud data to be classified using a lightweight power transmission line point cloud segmentation network, and obtaining a first point cloud data set corresponding to the ground object and a second point cloud data set corresponding to the power line;
[0009] Processing the first point cloud data set based on a point cloud thinning algorithm to obtain a first comparison data set;
[0010] Determine the central axis point set data of the power line based on the second point cloud data set;
[0011] The distance between each point in the first comparison data set and each point in the central axis point set data is calculated, and compared with the preset safety distance to determine the inspection result.
[0012] Optionally, the step of obtaining the point cloud data to be classified corresponding to the area to be inspected includes:
[0013] Obtain the point cloud data to be processed corresponding to the area to be inspected;
[0014] The point cloud data to be processed is completed based on a point cloud completion algorithm to obtain point cloud data to be classified.
[0015] Optionally, the step of completing the point cloud data to be processed based on a point cloud completion algorithm and obtaining the point cloud data to be classified includes:
[0016] Based on the linear interpolation algorithm and the quadratic curve model, the missing point cloud data corresponding to the power lines are completed, and the point cloud data to be classified is obtained.
[0017] Optionally, the processing the first point cloud data set based on a point cloud thinning algorithm to obtain a first comparison data set includes:
[0018] Divide a preset number of network blocks with the same spatial size based on the first point cloud data set;
[0019] Determine the center point location corresponding to each network block;
[0020] Determine, from among all the network blocks, a network block whose distance from the center point to the power line exceeds a first preset distance as a target network block;
[0021] Randomly delete half of the point cloud data corresponding to the target network block, and integrate the remaining point cloud data to obtain a first comparison data set.
[0022] Optionally, determining the central axis point set data of the power line based on the second point cloud data set includes:
[0023] Converting the second point cloud data set based on a spline curve interpolation algorithm to obtain dense and smooth point cloud data;
[0024] The central axis point set data of the power line is determined based on the smoothed point cloud data.
[0025] Optionally, the method further includes:
[0026] Evaluate the inspection results based on the fuzzy comprehensive evaluation method and obtain a comprehensive evaluation result;
[0027] The comprehensive evaluation result is compared with a preset evaluation table to determine whether the clearance of the area to be inspected is in a safe state.
[0028] Optionally, the inspection result is evaluated based on a fuzzy comprehensive evaluation method to obtain a comprehensive evaluation result, including:
[0029] Determining clearance safety influencing factors based on the inspection results;
[0030] Calculating the membership degree of the clearance safety influencing factors and obtaining the calculation results;
[0031] The calculation results are normalized to obtain the comprehensive evaluation results.
[0032] In a second aspect, an embodiment of the present application provides an automatic inspection device for an overhead power transmission line, comprising:
[0033] An acquisition module is used to acquire the point cloud data to be classified corresponding to the area to be inspected; the area to be inspected has ground objects and power lines;
[0034] A classification module, used to classify the point cloud data to be classified using a lightweight power transmission line point cloud segmentation network, and obtain a first point cloud data set corresponding to the ground object and a second point cloud data set corresponding to the power line;
[0035] A first processing module, used for processing the first point cloud data set based on a point cloud thinning algorithm to obtain a first comparison data set;
[0036] A second processing module, used for determining the central axis point set data of the power line based on the second point cloud data set;
[0037] The detection module is used to calculate the distance between each point in the first comparison data set and each point in the central axis point set data, and compare it with the preset safety distance to determine the inspection result.
[0038] In a third aspect, an embodiment of the present application provides an automatic inspection device for overhead power transmission lines, including:
[0039] Memory for storing computer programs;
[0040] A processor is used to implement the steps of the automatic inspection method of overhead power transmission lines as described above when executing the computer program.
[0041] In a fourth aspect, an embodiment of the present application provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the automatic inspection method of overhead transmission lines as described above are implemented.
[0042] It can be seen from the above technical solutions that compared with the prior art, the present application has the following advantages:
[0043] The present application first obtains the point cloud data to be classified corresponding to the area to be inspected. Among them, there are land objects and power lines in the area to be inspected. Then, the point cloud data to be classified is classified using a lightweight transmission line point cloud segmentation network, and a first point cloud data set corresponding to the land objects and a second point cloud data set corresponding to the power lines are obtained. Finally, the first point cloud data set is processed based on the point cloud thinning algorithm, and a first comparison data set is obtained. The central axis point set data of the power line is determined based on the second point cloud data set, and the distance between each point in the first comparison data set and each point in the central axis point set data is calculated, and compared with the preset safety distance to determine the inspection result. In this way, the embodiment of the present application introduces an FPS network that can be quickly classified, and reduces the point cloud density through the point cloud thinning algorithm and the concept of the central axis, thereby improving the inspection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] Figure 1 A flowchart of an automatic inspection method for overhead power transmission lines provided in an embodiment of the present application;
[0045] Figure 2 A schematic diagram of the architecture of an FPS network for fast segmentation of an overhead power transmission line point cloud scene provided in an embodiment of the present application;
[0046] Figure 3 A schematic structural diagram of an automatic inspection device for overhead power lines provided in an embodiment of the present application. DETAILED DESCRIPTION
[0047] As mentioned above, the existing inspection methods for overhead transmission lines have the problem of low inspection efficiency. Specifically, the existing inspection methods for overhead transmission lines still rely on manual inspections, which are conducted by technicians on-site. However, in the face of overhead transmission lines that span a wide range of domains and have different and complex on-site environments in different regions, in order to ensure the quality of inspections, technicians need to carefully inspect the overhead transmission lines in each area, resulting in low inspection efficiency. In addition, the existing technology also uses drones to inspect overhead transmission lines. Compared with manual inspections, drones can go to places that personnel cannot reach, and the data collected is also huge. However, in the face of huge amounts of collected data, the existing technology usually uses a full comparison method to determine the inspection results, which also leads to the problem of low inspection efficiency.
[0048] In order to solve the above problems, an embodiment of the present application provides an automatic inspection method for overhead transmission lines, including: first, obtaining point cloud data to be classified corresponding to the area to be inspected. There are land objects and power lines in the area to be inspected. Then, a lightweight transmission line point cloud segmentation network is used to classify the point cloud data to be classified, and a first point cloud data set corresponding to the land objects and a second point cloud data set corresponding to the power lines are obtained. Finally, the first point cloud data set is processed based on a point cloud thinning algorithm, and a first comparison data set is obtained. The central axis point set data of the power line is determined based on the second point cloud data set, and the distance between each point in the first comparison data set and each point in the central axis point set data is calculated, and compared with the preset safety distance to determine the inspection result.
[0049] In this way, the embodiment of the present application introduces an FPS network that can quickly classify, and reduces the point cloud density through a point cloud thinning algorithm and the concept of a central axis, thereby improving inspection efficiency.
[0050] It should be noted that the automatic inspection method for overhead power transmission lines and related products provided by the present application can be applied to the field of circuit inspection technology. The above is only an example and does not limit the application field of the automatic inspection method for overhead power transmission lines and related products provided by the present application.
[0051] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0052] Figure 1 A flowchart of an automatic inspection method for overhead power transmission lines provided in an embodiment of the present application. Figure 1 As shown, an automatic inspection method for overhead transmission lines provided in an embodiment of the present application may include:
[0053] S101: Acquire point cloud data to be classified corresponding to the area to be inspected; the area to be inspected has ground objects and power lines.
[0054] In practical applications, rapid inspection of transmission lines is the basic guarantee for ensuring the safety of the line network. With the increasing pressure of line inspection brought by the transmission network, and in order to better ensure the safety of inspection personnel, drone inspection technology has been more widely used. The embodiment of the present application adopts a drone for data collection, and after the drone uploads the collected data to the system, the server calculates the inspection results based on the collected data. Specifically, the drone is equipped with a camera, which can run according to the route formulated by the technician and collect data through the camera. The location of each tower and the mounting form of the power line on the tower are recorded. The technician can determine the area to be inspected according to the record and formulate an inspection route for the drone for the area. It should be noted that in order to ensure the effectiveness of the inspection and determine the clearance safety of the power line, there must be objects and power lines in the area to be inspected. When the drone flies on the inspection route, it can collect point cloud data (point cloud data to be classified) in the area to be inspected through the camera carried by the drone and upload it. In addition, since the power line is continuous, the tower is more suitable as a mark to distinguish the geographical location. Therefore, when dividing the area to be inspected, the area between two towers is often used as an area to be inspected. It is understandable that the area to be inspected usually also includes electric towers. The point cloud data to be classified corresponding to the area to be inspected obtained by the drone includes point cloud data of ground objects, point cloud data of power lines, point cloud data of electric towers and point cloud data of other categories (such as birds, etc.).
[0055] In addition, since the methods for obtaining the point cloud data to be classified are not the same, the embodiment of the present application can illustrate a possible acquisition method.
[0056] In one case, the step of obtaining the point cloud data to be classified corresponding to the area to be inspected includes:
[0057] Obtain the point cloud data to be processed corresponding to the area to be inspected;
[0058] The point cloud data to be processed is completed based on a point cloud completion algorithm to obtain point cloud data to be classified.
[0059] In actual applications, when the drone uses a laser radar or camera to scan the point cloud of the area to be inspected, it will be interfered by factors such as weather, environment, and electromagnetic signals, resulting in the problem of missing point cloud data. Therefore, the embodiment of the present application needs to complete the missing point cloud data. Specifically, the embodiment of the present application assumes that the point cloud data collected by the drone is missing. After the drone uploads these point cloud data (point cloud data to be processed), the server needs to complete these point cloud data to be processed through a point cloud completion algorithm based on the application of quadratic functions and symmetry principles, and then obtain the point cloud data to be classified.
[0060] In addition, since the methods for completing the point cloud data to be processed are different, the embodiment of the present application can illustrate a possible completion method.
[0061] In one case, the step of completing the point cloud data to be processed based on a point cloud completion algorithm and obtaining the point cloud data to be classified includes:
[0062] Based on the linear interpolation algorithm and the quadratic curve model, the missing point cloud data corresponding to the power lines are completed, and the point cloud data to be classified is obtained.
[0063] In practical applications, taking the case where there are objects, power lines and electric towers in the area to be inspected as an example, the point cloud data that needs to be supplemented is the point cloud data missing from the power lines and electric towers. Therefore, the server needs to first perform a preliminary classification on the acquired point cloud data to be processed, and determine the point cloud data corresponding to the power lines and the point cloud data corresponding to the electric towers. The embodiment of the present application provides a lightweight point cloud (Fast Powerline Segmentation, FPS) network for fast segmentation of overhead transmission line scenes, which can complete the classification of point cloud data in a relatively short time. For the completion of the point cloud data corresponding to the power lines, the distance between adjacent power line points is first calculated, and if it exceeds the set threshold, it is marked as a breakpoint. It can be understood that, assuming that there are multiple parallel power lines between two electric towers, then a coordinate system is established with the power lines parallel to the X-axis, then the distance between two points with the same X coordinate on two adjacent power lines should be within a certain range, so a threshold can be set, and if the distance between the two points exceeds the set threshold, it is marked as a breakpoint. Then, the two points near the breakpoint are connected to a straight line, and a straight line is fitted according to the coordinates of the two points, as shown in the following formula (1):
[0064]
[0065] Where (X1, Y1, Z1) and (X2, Y2, Z2) are two known adjacent break points, t represents the parameters of the three-dimensional straight line equation, and (x, y, z) represents the coordinate points generated near the break points. Finally, equally spaced values are taken between the three-dimensional coordinates (X1, Y1, Z1) and (X2, Y2, Z2), and interpolation calculations are performed to obtain a total of i coordinate points, that is, i interpolation points between the break points, to achieve rapid completion of partially missing power lines. According to this method, the point cloud data completion of the power lines in the area to be inspected is realized, and complete power line point cloud data is obtained. For the completion of the point cloud data corresponding to the power tower, the completion of the locally missing point cloud data of the power tower is carried out based on the principle of symmetry on both sides of the power tower. Specifically, the three-dimensional data of the power tower point cloud is first read, and then the height of the point cloud is calculated and divided into several parts according to the height difference. Taking the average division into 100 parts as an example, the number of points in each height interval is counted, and the center point (x mean,y mean ,z mean ), the calculation formula is as follows:
[0066]
[0067] In the formula, n represents the total number of point clouds in the interval, and j represents the sequence number of the point cloud in the interval. After the interval is divided proportionally according to the height, the center point of the set calculated for the interval with missing point clouds may be offset from the actual position, so it is necessary to use negative feedback to perform fine-tuning so that the center of the actual point cloud can gradually restore the actual position. Specifically, first set the slope and intercept of the initial straight line in combination with the center points of the upper and lower adjacent partitions, and define the maximum number of iterations. During the iteration process, the straight line is continuously fitted, and the fitting error of each point is calculated. According to the fitting error, the slope and intercept are adjusted by negative feedback. If the error is greater than 0, reduce the values of the slope and intercept so that the fitted straight line result is closer to the overall center point set in the global range, and finally determine the symmetry line of the tower. Then refer to the symmetry line to complete the missing point cloud of the local tower. Assume that the coordinates of the two symmetrical points are (x j ,y j , z j ) and (x' j , y' j , z' j ), and the coordinates of the two points satisfy the following formula:
[0068] 2*x mean =x j +x′ j (5)
[0069] 2*y mean =y j +y′ j (6)
[0070] z j = z′ j (7)
[0071] Then the coordinates of the symmetric point (x' j , y' j , z' j ) can be determined as:
[0072] x' j =2*x mean -x j (8)
[0073] y' j =2*y mean -y j (9)
[0074] z' j =z j (10)
[0075] Based on this, the missing point cloud data of the power tower is completed, and the complete point cloud data of the power tower is obtained. The complete point cloud data of the power line, the complete point cloud data of the power tower, and the point cloud data of the ground objects are integrated to obtain the point cloud data to be classified.
[0076] S102: Classifying the point cloud data to be classified using a lightweight power transmission line point cloud segmentation network, and obtaining a first point cloud data set corresponding to the ground feature and a second point cloud data set corresponding to the power line.
[0077] In practical applications, the real-time nature of inspection tasks and the generalization capability of deep learning network migration are taken into consideration. To improve inspection efficiency, the embodiment of the present application has undergone multiple speed tests, adjusted the number of network nodes, and designed an FPS network specifically for fast segmentation of overhead transmission line point cloud scenes. Figure 2 A schematic diagram of the architecture of an FPS network for fast segmentation of overhead power line point cloud scenes provided in an embodiment of the present application. Figure 2As shown in the figure, the network extracts features and classifies the input point cloud data to be classified through multiple fully connected layers. (N,6)-xyz&rgb indicates that the network input includes 6-dimensional point cloud data to be classified, including 3-dimensional spatial coordinates and 3-dimensional color information. The output of the network is the probability of each point cloud data corresponding to each category. Specifically, according to the main focus of power line inspection, three categories are set for the network, including power lines, ground objects and electric towers. The input layer receives 6-dimensional point cloud data to be classified. The original coordinate system is converted into the local coordinate system where a single test set is located through a decentralized operation, further highlighting the height difference between the wires, towers and the ground, so that the network can learn more features. First, the first fully connected layer (FC1) maps the input data to a 64-dimensional feature space, and the ReLU activation function performs a nonlinear transformation on the output of the first layer. Then, the second fully connected layer (FC2) maps the output of the first layer to a 64-dimensional feature space, and the ReLU activation function performs a nonlinear transformation on the output of the second layer. Finally, the output of the second layer is mapped to the probability distribution of the three categories by the third fully connected layer (FC3), and the output layer outputs the probability that the point cloud data to be classified belongs to each category. The network is set to determine that the point cloud data to be classified belongs to a certain category when the probability exceeds the preset threshold. In this way, the FPS network for rapid segmentation of the point cloud scene of the overhead transmission line quickly classifies the point cloud data to be classified, and the point cloud data corresponding to the ground object is classified as the first point cloud data set, the point cloud data corresponding to the power line is classified as the second point cloud data set, and the point cloud data corresponding to the electric tower is classified as the third point cloud data set. In addition, for the training of the FPS network for rapid segmentation of the point cloud scene of the overhead transmission line, an embodiment of the present application provides a training method. Specifically, a large amount of training data (point cloud data of power lines, point cloud data of electric towers, and point cloud data of ground objects) is first provided, and the training data is divided into small batches for training. The number of each batch and the number of training repetitions are set by the technician, for example, 32 per batch, 500 epochs per training, etc. The data loading function set in the code is used to receive point cloud data and convert the data into tensor form. A custom data set function is set to encapsulate the data set, and the length of the data set and the data acquisition method are defined. A point cloud classification model function is set to define the structure of the network, including three fully connected layers and a ReLU activation function. The training function is used to train the model and save the model parameters with better results. The cross entropy loss function is used to measure the difference between the network output result and the true label, and the Adam optimizer is used to update the network parameters, thereby realizing network training and obtaining the FPS network for fast segmentation of the overhead transmission line point cloud scene in the embodiment of the present application.
[0078] S103: Processing the first point cloud data set based on a point cloud thinning algorithm to obtain a first comparison data set.
[0079] In practical applications, the FPS network that quickly segments the point cloud scene of the overhead transmission line classifies the point cloud data to be classified to obtain the first point cloud data set corresponding to the ground object, the second point cloud data set corresponding to the power line, and the third point cloud data set corresponding to the tower. It can be understood that the point cloud data in the data set is huge. If calculations are performed based on this, the calculation process will be relatively long, thereby reducing the inspection efficiency. To this end, the embodiment of the present application provides a method for reducing the point cloud density to reduce the amount of calculation and improve the inspection efficiency. Specifically, for the first point cloud data set corresponding to the ground object, the embodiment of the present application processes it based on the point cloud thinning algorithm. Since the present application mainly considers the clearance safety of the overhead transmission line, the closer the ground object is to the power line, the higher the impact will be. The server can divide the ground objects by height and set a threshold. The ground objects above a certain height are regarded as key calculation targets and are not processed; the ground objects below a certain height are regarded as non-key calculation targets and point cloud thinning is performed.
[0080] In addition, since the methods for processing the first point cloud data set are not the same, the embodiment of the present application can illustrate a possible processing method.
[0081] In one case, S103: processing the first point cloud data set based on a point cloud thinning algorithm to obtain a first comparison data set may specifically include:
[0082] Divide a preset number of network blocks with the same spatial size based on the first point cloud data set;
[0083] Determine the center point location corresponding to each network block;
[0084] Determine, from among all the network blocks, a network block whose distance from the center point to the power line exceeds a first preset distance as a target network block;
[0085] Randomly delete half of the point cloud data corresponding to the target network block, and integrate the remaining point cloud data to obtain a first comparison data set.
[0086] In practical applications, when performing point cloud thinning, the server can evenly divide the spatial position of the first point cloud data set into several grid blocks of the same size. The number of grid blocks can be 500 or other numbers. It can be understood that the divided grid blocks are small cuboids stacked together. These small cuboids are stacked together to form a large cuboid, whose upper surface is flush with the lower surface of the power line, and the lower surface is flush with the lowest point in the first point cloud data set. Taking the number of grid blocks as 500 as an example, define the divide_into_blocks(data_set,num_blocks=500) function, first calculate the size of the first point cloud data set, and divide it into blocks using list derivation. Then traverse the corresponding point cloud position in each grid block and calculate the center point position. The np.mean function is used to calculate the average value in each direction, determine the center point of the grid block, and axis=0 means that the mean is calculated according to the column and the average operation is performed on each column, and the following expression is obtained:
[0087]
[0088] Then, we traverse and calculate the Euclidean distance from the center point to each point in the second data set, store them in the table, and finally return the minimum distance in the list. The expression is as follows:
[0089]
[0090] In summary, P is the set of coordinate points in the second data set; axis represents the point cloud number of the center point; m represents the number of point clouds; q i Represents the point cloud number in the grid area; p k The point cloud number of the second dataset corresponding to the power line. The technician sets a threshold (usually 30 meters), and randomly deletes half of the data points from the grid block whose distance to the power line is greater than the threshold. In this way, the remaining point cloud data are integrated to form a new dataset for comparison, namely the first comparison dataset.
[0091] S104: Determine the central axis point set data of the power line based on the second point cloud data set.
[0092] In actual applications, there are multiple power lines mounted between two power towers, and the second point cloud data set includes all the point cloud data of these power lines. It is understandable that these data are huge, and if calculations are performed based on this, the calculation process will be relatively long, thereby reducing the inspection efficiency. To this end, the embodiment of the present application provides a method for reducing the point cloud density to reduce the amount of calculation and improve the inspection efficiency. Specifically, for the second point cloud data set corresponding to the power lines, the embodiment of the present application fits the multiple power lines between adjacent power towers into a central axis of power lines with similar curvature, and calculates based on the central axis point set data of the power lines and the above-mentioned first comparison data set, so as to achieve the purpose of reducing the point cloud density and improving the inspection efficiency.
[0093] In addition, since the methods for processing the second point cloud data set are not the same, the embodiment of the present application can illustrate a possible processing method.
[0094] In one case, S104: determining the central axis point set data of the power line based on the second point cloud data set may specifically include:
[0095] Converting the second point cloud data set based on a spline curve interpolation algorithm to obtain dense and smooth point cloud data;
[0096] The central axis point set data of the power line is determined based on the smoothed point cloud data.
[0097] In practical applications, the towers are connected by multiple power lines. Clearance detection needs to ensure that there are no hidden dangers of ground objects within the clearance range of each power line. However, if each power line is detected, it will inevitably affect the computing efficiency. In order to improve the computing efficiency, several power lines between the two towers are reasonably fitted into a power line central axis. Through the combination of interpolation and coordinate operations, the point cloud data of the power line is converted into the point set data of the central axis of the power line. Specifically, the server first calculates the average value of the coordinates of every two points in the second point cloud data set corresponding to the power line, and then obtains the midpoint, and converts the point cloud data in the second point cloud data set into more dense and smooth point cloud data through spline interpolation. The number of spline interpolation, smoothness, etc. are set by technicians. Generally, the number of interpolation k=3 and the smoothness s is 0. Set a t to represent the generation of a numerical sequence from 0 to 1. The number of elements in the sequence is the same as the number of discrete points on the power line (the number of coordinate point cloud data in the second point cloud data set) to calculate the points on the central axis. Then, the index position of the linear interpolation is calculated according to t. Specifically, by multiplying t by the number of points of the discrete curve and taking the integer part, the coordinates of the central axis (x, y) of the point at the corresponding index position on each curve are calculated according to the parameter t from the index sequence of the corresponding curve coordinates, as shown in the following expression (13):
[0098] n(x,y)=[t·num] (13)
[0099] Where n(x,y) is the index sequence of the corresponding curve coordinates, and num is the number of points of the discrete curve. Finally, by averaging these points, we get the virtual point on the central axis of the power line at each position, and adjust the parameter position by linear interpolation to make the virtual point more consistent with the actual wire point arc sag, so as to achieve the fitting of multiple power lines, and get the central axis point set data as the data set for subsequent calculation with the first comparison data set.
[0100] S105: Calculate the distance between each point in the first comparison data set and each point in the central axis point set data, and compare with a preset safety distance to determine an inspection result.
[0101] In practical applications, regarding the clearance detection of the transmission line neighborhood, the safety distance of 500kv in the overhead transmission line operation regulations is 8.5m, and the distances from the central axis of the power line to the single-strand power line are generally 18m and 12m respectively. Therefore, when the server uses the power central axis as a reference for clearance inspection, the safety distance can be adjusted appropriately, and the recommended value is between 8.5m-26.5m. In this way, when setting 10m as the preset safety distance, the server can first make a circle perpendicular to the power line with each point on the central axis as the center, and then form a cylinder with a radius of 10m from these circles. Then traverse each point cloud data in the first comparison data set, calculate the distance between each point and each point in the central axis point set data, and realize the retrieval of the central axis neighborhood space. When there is a point in the first comparison data set with a distance from a point in the central axis point set data that is less than or equal to 10m, the inspection result of the point within the safe range around the power line is obtained. That is, when the presence of ground objects around the power line is detected, the algorithm automatically alarms when the distance does not meet the safety requirements in the specification, as shown in formula (14):
[0102]
[0103] Where P′ mid (x′ mid ,y′ mid ,z′ mid ) represents the point on the central axis of the power line, f represents the surrounding ground objects, and r represents the neighborhood search radius.
[0104] In addition, since the processing methods of the inspection results are not the same, the embodiment of the present application can illustrate a possible processing method.
[0105] In one embodiment, the method further comprises:
[0106] Evaluate the inspection results based on the fuzzy comprehensive evaluation method and obtain a comprehensive evaluation result;
[0107] The comprehensive evaluation result is compared with a preset evaluation table to determine whether the clearance of the area to be inspected is in a safe state.
[0108] In practical applications, whether the ground object is within the safety range of the power line is the inspection result obtained by the above method. The embodiment of the present application also provides an overhead power transmission line clearance safety evaluation system based on the fuzzy comprehensive evaluation method, and further clearance safety evaluation is triggered when the ground object is within the safety range of the power line. Specifically, there are many types of ground objects, such as trees, three-span buildings, and surrounding scene power grids. Different types have different degrees of influence on the clearance safety of transmission lines. Therefore, the above inspection results can be further evaluated by the fuzzy comprehensive evaluation method, and a numerical comprehensive evaluation result can be obtained, such as 1, 2, and 10. The preset evaluation table is used to indicate the clearance safety situation corresponding to different values. Taking levels 1 to 3 as an example, the higher the level, the lower the safety level of the circuit line, and each level has its corresponding comprehensive evaluation result numerical range. Compare the comprehensive evaluation result with the preset evaluation table. If the value corresponding to level 3 is 8-10, and the value of the comprehensive evaluation result is determined by calculation to be 9.1, the clearance safety status of the area to be inspected determined and returned by the server is level 3. If level 3 is predefined as an unsafe state, the server will also warn that the inspection area is clear and in an unsafe state.
[0109] In addition, since the methods for evaluating the inspection results are not the same, the embodiments of the present application can illustrate a possible evaluation method.
[0110] In one case, the inspection result is evaluated based on the fuzzy comprehensive evaluation method to obtain a comprehensive evaluation result, including:
[0111] Determining clearance safety influencing factors based on the inspection results;
[0112] Calculating the membership degree of the clearance safety influencing factors and obtaining the calculation results;
[0113] The calculation results are normalized to obtain the comprehensive evaluation results.
[0114] In practical applications, the overhead transmission line clearance safety evaluation system based on the fuzzy comprehensive evaluation method mainly includes the following steps. Specifically, first determine the clearance safety influencing factors, input the tree growth height, three-span buildings, and the nearest distance of the surrounding scene power grid. Then establish a fuzzy evaluation matrix (weight vector matrix A) for each safety influencing factor. Among them, the elements in the matrix represent the membership of calcium elements at different levels. The determination of membership can be obtained through expert opinions, on-site surveys or historical data, and the sum of weight vectors needs to be equal to 1. Then, obtain the evaluation situation corresponding to each indicator, and construct the weight judgment matrix R by combining the above-mentioned various algorithm analysis in the evaluation process, and calculate the membership of matrix A and matrix R (matrix cross multiplication) to obtain the calculation results of each scheme. Finally, normalize the membership calculation results, compare the obtained comprehensive score with the evaluation table, and obtain the comprehensive evaluation results to determine whether the state of the power grid clearance in the area is safe.
[0115] In summary, the present application first obtains the point cloud data to be classified corresponding to the area to be inspected. Among them, there are land objects and power lines in the area to be inspected. Then, the point cloud data to be classified is classified using a lightweight transmission line point cloud segmentation network, and a first point cloud data set corresponding to the land objects and a second point cloud data set corresponding to the power lines are obtained. Finally, the first point cloud data set is processed based on the point cloud thinning algorithm, and a first comparison data set is obtained. The central axis point set data of the power line is determined based on the second point cloud data set, and the distance between each point in the first comparison data set and each point in the central axis point set data is calculated, and compared with the preset safety distance to determine the inspection result. In this way, the embodiment of the present application introduces an FPS network that can be quickly classified, and reduces the point cloud density through the point cloud thinning algorithm and the concept of the central axis, thereby improving the inspection efficiency.
[0116] Based on the automatic inspection method of an overhead power transmission line provided in the above embodiment, the embodiment of the present application further provides an automatic inspection device of an overhead power transmission line. The automatic inspection device of an overhead power transmission line is described below in combination with the embodiments and drawings.
[0117] Figure 3 A schematic diagram of the structure of an automatic inspection device for overhead power transmission lines provided in an embodiment of the present application. Figure 3 As shown, the automatic inspection device 300 for overhead power transmission lines provided in the embodiment of the present application includes:
[0118] The acquisition module 301 is used to acquire the point cloud data to be classified corresponding to the area to be inspected; the area to be inspected has ground objects and power lines;
[0119] A classification module 302, used to classify the point cloud data to be classified using a lightweight power transmission line point cloud segmentation network, and obtain a first point cloud data set corresponding to the ground object and a second point cloud data set corresponding to the power line;
[0120] A first processing module 303, configured to process the first point cloud data set based on a point cloud thinning algorithm to obtain a first comparison data set;
[0121] A second processing module 304 is used to determine the central axis point set data of the power line based on the second point cloud data set;
[0122] The detection module 305 is used to calculate the distance between each point in the first comparison data set and each point in the central axis point set data, and compare it with the preset safety distance to determine the inspection result.
[0123] As an implementation method, with respect to how to obtain the point cloud data to be classified corresponding to the area to be inspected, the acquisition module 301 includes: an acquisition submodule and a completion module;
[0124] The acquisition submodule is used to obtain the point cloud data to be processed corresponding to the area to be inspected;
[0125] The completion module is used to complete the point cloud data to be processed based on a point cloud completion algorithm and obtain point cloud data to be classified.
[0126] In the first implementation mode, regarding how to complete the point cloud data to be processed, the completion module is specifically used for:
[0127] Based on the linear interpolation algorithm and the quadratic curve model, the missing point cloud data corresponding to the power lines are completed, and the point cloud data to be classified is obtained.
[0128] As an implementation manner, regarding how to process the first point cloud data set, the first processing module 303 is specifically used to:
[0129] Divide a preset number of network blocks of the same spatial size based on the first point cloud data set;
[0130] Determine the center point location corresponding to each network block;
[0131] Determine, from among all the network blocks, a network block whose distance from the center point to the power line exceeds a first preset distance as a target network block;
[0132] Randomly delete half of the point cloud data corresponding to the target network block, and integrate the remaining point cloud data to obtain a first comparison data set.
[0133] As an implementation manner, regarding how to process the second point cloud data set, the second processing module 304 is specifically used to:
[0134] Converting the second point cloud data set based on a spline curve interpolation algorithm to obtain dense and smooth point cloud data;
[0135] The central axis point set data of the power line is determined based on the smoothed point cloud data.
[0136] As an implementation method, regarding how to perform the evaluation, the automatic inspection device 300 for overhead power transmission lines further includes: an evaluation module;
[0137] An evaluation module, used to evaluate the inspection results based on a fuzzy comprehensive evaluation method and obtain a comprehensive evaluation result;
[0138] The comprehensive evaluation result is compared with a preset evaluation table to determine whether the clearance of the area to be inspected is in a safe state.
[0139] As an implementation method, regarding how to evaluate the inspection results based on the fuzzy comprehensive evaluation method, the above evaluation module is specifically used for:
[0140] Determining clearance safety influencing factors based on the inspection results;
[0141] Calculating the membership degree of the clearance safety influencing factors and obtaining the calculation results;
[0142] The calculation results are normalized to obtain the comprehensive evaluation results.
[0143] In summary, the present application first obtains the point cloud data to be classified corresponding to the area to be inspected. Among them, there are land objects and power lines in the area to be inspected. Then, the point cloud data to be classified is classified using a lightweight transmission line point cloud segmentation network, and a first point cloud data set corresponding to the land objects and a second point cloud data set corresponding to the power lines are obtained. Finally, the first point cloud data set is processed based on the point cloud thinning algorithm, and a first comparison data set is obtained. The central axis point set data of the power line is determined based on the second point cloud data set, and the distance between each point in the first comparison data set and each point in the central axis point set data is calculated, and compared with the preset safety distance to determine the inspection result. In this way, the embodiment of the present application introduces an FPS network that can be quickly classified, and reduces the point cloud density through the point cloud thinning algorithm and the concept of the central axis, thereby improving the inspection efficiency.
[0144] In addition, the embodiment of the present application also provides an automatic inspection device for overhead power transmission lines, including:
[0145] Memory for storing computer programs;
[0146] A processor is used to implement the steps of the automatic inspection method of overhead power transmission lines as described above when executing the computer program.
[0147] In addition, an embodiment of the present application further provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the automatic inspection method of overhead transmission lines as described above are implemented.
[0148] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. An automatic inspection method for overhead transmission lines, It is characterized in that The method comprises: Acquire the point cloud data to be classified corresponding to the area to be inspected; the area to be inspected has ground objects and power lines; Classifying the point cloud data to be classified using a lightweight power transmission line point cloud segmentation network, and obtaining a first point cloud data set corresponding to the ground object and a second point cloud data set corresponding to the power line; Processing the first point cloud data set based on a point cloud thinning algorithm to obtain a first comparison data set; Determine the central axis point set data of the power line based on the second point cloud data set; The distance between each point in the first comparison data set and each point in the central axis point set data is calculated, and compared with the preset safety distance to determine the inspection result.
2. The method according to claim 1, It is characterized in that The step of obtaining the point cloud data to be classified corresponding to the area to be inspected includes: Obtain the point cloud data to be processed corresponding to the area to be inspected; The point cloud data to be processed is completed based on a point cloud completion algorithm to obtain point cloud data to be classified.
3. The method according to claim 1, It is characterized in that The step of completing the point cloud data to be processed based on a point cloud completion algorithm and obtaining the point cloud data to be classified includes: Based on the linear interpolation algorithm and the quadratic curve model, the missing point cloud data corresponding to the power lines are completed, and the point cloud data to be classified is obtained.
4. The method according to claim 1, It is characterized in that The step of processing the first point cloud data set based on a point cloud thinning algorithm to obtain a first comparison data set includes: Divide a preset number of network blocks of the same spatial size based on the first point cloud data set; Determine the center point location corresponding to each network block; Determine, from among all the network blocks, a network block whose distance from the center point to the power line exceeds a first preset distance as a target network block; Randomly delete half of the point cloud data corresponding to the target network block, and integrate the remaining point cloud data to obtain a first comparison data set.
5. The method according to claim 1, It is characterized in that The determining the central axis point set data of the power line based on the second point cloud data set includes: Converting the second point cloud data set based on a spline curve interpolation algorithm to obtain dense and smooth point cloud data; The central axis point set data of the power line is determined based on the smoothed point cloud data.
6. The method according to claim 1, It is characterized in that The method further comprises: Evaluate the inspection results based on the fuzzy comprehensive evaluation method and obtain a comprehensive evaluation result; The comprehensive evaluation result is compared with a preset evaluation table to determine whether the clearance of the area to be inspected is in a safe state.
7. The method according to claim 6, It is characterized in that The inspection results are evaluated based on the fuzzy comprehensive evaluation method to obtain a comprehensive evaluation result, including: Determining clearance safety influencing factors based on the inspection results; Calculating the membership degree of the clearance safety influencing factors and obtaining the calculation results; The calculation results are normalized to obtain the comprehensive evaluation results.
8. An automatic inspection device for overhead power transmission lines, It is characterized in that include: An acquisition module is used to obtain the point cloud data to be classified corresponding to the area to be inspected; There are ground objects and power lines in the area to be inspected; A classification module, used to classify the point cloud data to be classified using a lightweight power transmission line point cloud segmentation network, and obtain a first point cloud data set corresponding to the ground object and a second point cloud data set corresponding to the power line; A first processing module, used for processing the first point cloud data set based on a point cloud thinning algorithm to obtain a first comparison data set; A second processing module, used for determining the central axis point set data of the power line based on the second point cloud data set; The detection module is used to calculate the distance between each point in the first comparison data set and each point in the central axis point set data, and compare it with the preset safety distance to determine the inspection result.
9. An automatic inspection device for overhead power transmission lines, It is characterized in that include: Memory for storing computer programs; A processor, configured to implement the steps of the automatic inspection method for overhead power transmission lines as claimed in any one of claims 1 to 7 when executing the computer program.
10. A readable storage medium, It is characterized in that The readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the automatic inspection method for overhead transmission lines according to any one of claims 1 to 7 are implemented.
Citation Information
Patent Citations
Catenary support facility laser point cloud full-automatic extraction method considering spatial relationship
CN114897777A
Electric power inspection ground feature classification method based on three-dimensional point cloud and storage medium
CN116052023A
Point cloud-based suburban power transmission line network tree obstacle positioning and removing method
CN117409336A
Safety assessment method, device, equipment and medium for ultrahigh-pressure maintenance operation personnel
CN117788902A
Power transmission line tree obstacle hidden danger detection and prediction method and system
CN118298292A
Cited By
Overhead line safety information display method, device, equipment and medium
CN119599438A
