Airborne laser radar assisted power transmission line state monitoring and evaluation method

Abstract

The invention relates to the technical field of laser radars, in particular to an airborne laser radar assisted power transmission line state monitoring and evaluation method, which specifically comprises the following steps: acquiring point cloud data and an aircraft position; the collected point cloud data are preprocessed; extracting geometric features of the power transmission line, calculating roughness of the surface of the power transmission line, and obtaining salt mist concentration; establishing a corrosion identification model, and judging the corrosion degree of the power transmission line; the trained corrosion identification model is applied to offshore power transmission line monitoring, and a closed loop is completed; according to the method, the corrosion degree of the offshore power transmission line is analyzed by combining the geometrical characteristics, the roughness and the salt mist concentration, and the condition of the power transmission line can be known more accurately and comprehensively.

Description

Technical Field

[0001] The present invention relates to the field of laser radar technology, and in particular to a method for monitoring and evaluating the state of a power transmission line assisted by an airborne laser radar. Background Art

[0002] Traditional transmission line inspections mainly rely on manual labor. Inspectors need to walk along the transmission line corridors or use transportation to inspect. This method is labor-intensive, inefficient, and severely restricted by geographical and climatic conditions. Inspectors may find it difficult to reach certain key parts of the transmission line, making it impossible to discover potential hidden dangers in a timely manner. In addition, manual inspections often cannot be carried out normally in bad weather, which may lead to untimely and incomplete acquisition of transmission line status information.

[0003] Laser Ranging and Detecting (LiDAR) is an active optical remote sensing technology with the characteristics of high precision and high resolution. It can quickly obtain three-dimensional models of large-area terrain and objects. Compared with ground monitoring, airborne laser radar can fly quickly along the transmission line corridor and cover longer line sections at one time, which greatly improves the monitoring efficiency and can obtain a large amount of transmission line data in a short time. Moreover, the airborne platform can flexibly adjust the flight route and altitude to adapt to the monitoring needs of different terrains and transmission line directions.

[0004] Offshore transmission lines are more susceptible to corrosion than land transmission lines due to the higher concentration of salt spray in the air. Therefore, operation and maintenance personnel need to have a specific judgment on the degree of corrosion of the transmission lines in order to inspect and repair the offshore transmission lines. Summary of the invention

[0005] In view of the above-mentioned shortcomings of the prior art, the present invention provides an airborne laser radar-assisted transmission line status monitoring and evaluation method, which can effectively solve the problems mentioned in the prior art.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: The present invention provides an airborne laser radar-assisted transmission line status monitoring and evaluation method, comprising the following steps: Step 1, using airborne laser radar equipment to perform three-dimensional scanning of offshore transmission lines and their surrounding environment to obtain point cloud data and aircraft positions; Step 2, transmitting the collected point cloud data to a ground data processing center for preprocessing; Step 3, based on the preprocessed point cloud data, extracting the geometric features of the transmission line; and analyzing the distance changes between adjacent points in the point cloud data to calculate the roughness of the transmission line surface; Finally, using the intensity information of the laser radar to obtain the salt spray concentration at sea at that time; Step 4, using the extracted geometric features, roughness and salt spray concentration of the transmission line as input, establishing a corrosion recognition model, and judging the degree of corrosion of the transmission line; Step 5, applying the trained corrosion recognition model to offshore transmission line monitoring, collecting point cloud data of the transmission line in real time through the laser radar, extracting features and inputting them into the corrosion recognition model, realizing real-time recognition and monitoring of the degree of corrosion of the transmission line, and completing a closed loop.

[0007] Preferably, step 2 specifically includes: step 2.1, performing noise reduction processing on the point cloud data, for each point in the point cloud data , calculate its local density , define a radius r, and count the number of points within the radius r to represent the local density , the formula is: ; where X is the indicator function, For point To adjacent point The distance between When X=1, otherwise X=0; find all local densities greater than point , forming a set , ; Calculation point To Collection The distance of a point , then point To a local density greater than The average distance of the points The calculation formula is: ; where m is the set The number of midpoints; defines the denoising metric: ;in, It is the maximum value of the local density of all points in the point cloud; set the denoising threshold ,when When Mark as noise points and remove them; Step 2.2: Perform straight-through filtering on the denoised point cloud data. , extract its coordinate value on the Z axis , set the threshold range in the Z-axis direction ,judge Whether the threshold conditions are met, that is: ; If the conditions are met, the points in the point cloud data are retained , add it to the new filtered point cloud data set; if the condition is not met, the point in the point cloud data is discarded , continue to process the next point; after traversing all the points, the new point cloud data set contains the points retained after the straight-through filtering, that is, the transmission line point cloud within the threshold range.

[0008] Preferably, in step 3, the geometric features of the transmission line are extracted based on the preprocessed point cloud data, specifically including: adaptively dividing the point cloud data of the transmission line into multiple local areas using a density clustering algorithm according to the density distribution of the point cloud data, and the divided area set is , for each region , calculate its point cloud density and the average spacing , calculate the cloud density The formula is: ;in is the number of points in the region, is the volume of the region; the average spacing It is obtained by calculating the average distance between points in the region. and Two points in the area, point and The Euclidean distance between for: ; then the average spacing for: ;in, Indicates from The number of combinations of selecting 2 elements; extracting local areas The characteristics of each local area In the local area, a local geometric graph is constructed, and the points in the area are taken as nodes of the graph. The edge weight between two points is the Euclidean distance between the nodes. The Laplace matrix of the graph is calculated. , whose elements The definition of is: hour: ;in, is the edge weight between node i and node j, that is, the Euclidean distance between the two points; when And when node i and node j are connected by an edge: ;when When nodes i and j are not connected by edges: ; For the Laplacian matrix Perform eigendecomposition and obtain eigenvalues and the eigenvector , select the smallest non-zero eigenvalue The corresponding eigenvector ,set up , the local diameter estimate within the region for: ;in, is the difference of the eigenvector elements, is the average distance; according to the estimated value of the diameter of each local area Perform global diameter fusion, the global diameter D is: ;in, is the weight of the region.

[0009] Preferably, in step 3, analyzing the distance change between adjacent points in the point cloud data and calculating the roughness of the surface of the transmission line specifically includes: assuming that the point cloud data is , represents the coordinate set of points on the surface of the transmission line and its surroundings, where n is the total number of points, and the radius neighborhood method is used to calculate each point With adjacent points The distance between them is: ;in, For point With adjacent points The distance between the transmission lines and the roughness of the transmission line surface The calculation formula is: ; Where n is the total number of points, k is the number of adjacent points of each point, Yes With adjacent points The distance change between .

[0010] Preferably, in step 3, the intensity information of the laser radar is used to obtain the salt spray concentration at sea at that time, which specifically includes: using the laser radar to scan the sea area, the received echo intensity is I, the measurement distance is d, and the measurement angle is , forming the original data set , where n represents different measurement points, and obtains information on offshore wind speed v, humidity h, and temperature t; establishes a relationship model between salt spray concentration and lidar intensity, which is: ; Where I is the echo intensity, is the laser radar echo intensity without salt fog, is the attenuation coefficient of salt spray to laser, is the salt spray concentration, d is the measuring distance, f is the correction factor, and the point Substituting into the relationship model between salt spray concentration and lidar intensity, we get: ;in, is the salt spray concentration, They are the wind speed, humidity and temperature values ​​corresponding to the measurement point respectively.

[0011] Preferably, the corrosion identification model established in step 4 is based on a neural network algorithm; the geometric feature data Z and roughness data of the transmission line are and salt spray concentration data As input, let the geometric feature data be , the roughness data is , the salt spray concentration data is ; Normalize the geometric feature data, roughness data and salt spray concentration data, and use the linear normalization formula for the geometric feature data: ;in, is the minimum value in the geometric feature data, is the maximum value in the geometric feature data, is the normalized geometric eigenvalue; the same normalization method is used for the roughness data and the salt spray concentration data, and the normalized roughness data is obtained as , the normalized salt spray concentration data is , the normalized geometric features, roughness and salt spray concentration data are combined into a feature vector ; The convolutional neural network is used to calculate the risk value H of the corrosion degree, which is expressed as: Among them, W is the weight coefficient, F is the output function, is the convolutional neural network model of the feature vector X.

[0012] Preferably, set a risk value threshold and ,when When When The transmission line is judged to be severely corroded.

[0013] Preferably, different degrees of maintenance are performed according to the risk value; when the transmission line is determined to be slightly corroded, the monitoring period is shortened and corrosion changes are closely monitored; when the transmission line is determined to be moderately corroded, the transmission line is subjected to comprehensive anti-corrosion treatment, using hot-dip galvanizing and spraying anti-corrosion paint to form an anti-corrosion protective film; when the transmission line is determined to be severely corroded, the transmission line is replaced.

[0014] Compared with the known prior art, the technical solution provided by the present invention has the following beneficial effects: the present invention combines geometric features, roughness and salt spray concentration to analyze the degree of corrosion of offshore transmission lines, and can more accurately and comprehensively understand the conditions of transmission lines; the present invention uses an adaptive local geometric analysis algorithm to adaptively perform region division and feature extraction according to the characteristics of point cloud data, and more accurately extract the diameter characteristics of transmission lines, which is particularly suitable for situations where point cloud data is unevenly distributed or transmission lines have complex structures. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below; obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention; it is obvious that the described embodiments are part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0018] The present invention will be further described below in conjunction with the embodiments.

[0019] Example: Refer to Figure 1, a transmission line status monitoring and evaluation method assisted by airborne laser radar, comprising the following steps: step 1, using airborne laser radar equipment to perform three-dimensional scanning of offshore transmission lines and their surrounding environment to obtain point cloud data and aircraft position; step 2, transmitting the collected point cloud data to a ground data processing center for preprocessing; step 3, extracting the geometric features of the transmission line based on the preprocessed point cloud data; and analyzing the distance change between adjacent points in the point cloud data to calculate the roughness of the transmission line surface; finally, using the intensity information of the laser radar to obtain the salt spray concentration at sea at that time; step 4, using the extracted geometric features, roughness and salt spray concentration of the transmission line as input, establishing a corrosion recognition model, and judging the degree of corrosion of the transmission line; step 5, applying the trained corrosion recognition model to offshore transmission line monitoring, collecting point cloud data of the transmission line in real time through the laser radar, extracting features and inputting them into the corrosion recognition model, realizing real-time recognition and monitoring of the degree of corrosion of the transmission line, and completing the closed loop.

[0020] Preferably, step 2 specifically includes: step 2.1, performing noise reduction processing on the point cloud data, for each point in the point cloud data , calculate its local density , define a radius r, and count the number of points within the radius r to represent the local density , the formula is: ; where X is the indicator function, For point To adjacent point The distance between When X=1, otherwise X=0; find all local densities greater than point , forming a set , ; Calculation point To Collection The distance of a point , then point To a local density greater than The average distance of the points The calculation formula is: ; where m is the set The number of midpoints; defines the denoising metric: ;in, It is the maximum value of the local density of all points in the point cloud; set the denoising threshold ,when When Mark as noise points and remove them; Step 2.2: Perform straight-through filtering on the denoised point cloud data. , extract its coordinate value on the Z axis , set the threshold range in the Z-axis direction ,judge Whether the threshold conditions are met, that is: ; If the conditions are met, the points in the point cloud data are retained , add it to the new filtered point cloud data set; if the condition is not met, the point in the point cloud data is discarded , continue to process the next point; after traversing all the points, the new point cloud data set contains the points retained after the straight-through filtering, that is, the transmission line point cloud within the threshold range.

[0021] Preferably, in step 3, the geometric features of the transmission line are extracted based on the preprocessed point cloud data, specifically including: adaptively dividing the point cloud data of the transmission line into multiple local areas using a density clustering algorithm according to the density distribution of the point cloud data, and the divided area set is , for each region , calculate its point cloud density and the average spacing , calculate the cloud density The formula is: ;in is the number of points in the region, is the volume of the region; the average spacing It is obtained by calculating the average distance between points in the region. and Two points in the area, point and The Euclidean distance between for: ; then the average spacing for: ;in, Indicates from The number of combinations of selecting 2 elements; extracting local areas The characteristics of each local area In the local area, a local geometric graph is constructed, and the points in the area are taken as nodes of the graph. The edge weight between two points is the Euclidean distance between the nodes. The Laplace matrix of the graph is calculated. , whose elements The definition of is: hour: ;in, is the edge weight between node i and node j, that is, the Euclidean distance between the two points; when And when node i and node j are connected by an edge: ;when When nodes i and j are not connected by edges: ; For the Laplacian matrix Perform eigendecomposition and obtain eigenvalues and the eigenvector , select the smallest non-zero eigenvalue The corresponding eigenvector ,set up , the local diameter estimate within the region for: ;in, is the difference of the eigenvector elements, is the average distance; according to the estimated value of the diameter of each local area Perform global diameter fusion, the global diameter D is: ;in, is the weight of the region.

[0022] Preferably, in step 3, analyzing the distance change between adjacent points in the point cloud data and calculating the roughness of the surface of the transmission line specifically includes: assuming that the point cloud data is , represents the coordinate set of points on the surface of the transmission line and its surroundings, where n is the total number of points, and the radius neighborhood method is used to calculate each point With adjacent points The distance between them is: ;in, For point With adjacent points The distance between the transmission lines and the roughness of the transmission line surface The calculation formula is: ; Where n is the total number of points, k is the number of adjacent points of each point, Yes With adjacent points The distance change between .

[0023] Preferably, in step 3, the intensity information of the laser radar is used to obtain the salt spray concentration at sea at that time, which specifically includes: using the laser radar to scan the sea area, the received echo intensity is I, the measurement distance is d, and the measurement angle is , forming the original data set , where n represents different measurement points, and obtains information on offshore wind speed v, humidity h, and temperature t; establishes a relationship model between salt spray concentration and lidar intensity, which is: ; Where I is the echo intensity, is the laser radar echo intensity without salt fog, is the attenuation coefficient of salt spray to laser, is the salt spray concentration, d is the measuring distance, f is the correction factor, and the point Substituting into the relationship model between salt spray concentration and lidar intensity, we get: ;in, is the salt spray concentration, They are the wind speed, humidity and temperature values ​​corresponding to the measurement point respectively.

[0024] Preferably, the corrosion identification model established in step 4 is based on a neural network algorithm; the geometric feature data Z and roughness data of the transmission line are and salt spray concentration data As input, let the geometric feature data be , the roughness data is , the salt spray concentration data is ; Normalize the geometric feature data, roughness data and salt spray concentration data, and use the linear normalization formula for the geometric feature data: ;in, is the minimum value in the geometric feature data, is the maximum value in the geometric feature data, is the normalized geometric eigenvalue; the same normalization method is used for the roughness data and the salt spray concentration data, and the normalized roughness data is obtained as , the normalized salt spray concentration data is , the normalized geometric features, roughness and salt spray concentration data are combined into a feature vector ; The convolutional neural network is used to calculate the risk value H of the corrosion degree, which is expressed as: Among them, W is the weight coefficient, F is the output function, is the convolutional neural network model of the feature vector X.

[0025] Preferably, set a risk value threshold and ,when When When The transmission line is judged to be severely corroded.

[0026] Preferably, different degrees of maintenance are performed according to the risk value; when the transmission line is determined to be slightly corroded, the monitoring period is shortened and corrosion changes are closely monitored; when the transmission line is determined to be moderately corroded, the transmission line is subjected to comprehensive anti-corrosion treatment, using hot-dip galvanizing and spraying anti-corrosion paint to form an anti-corrosion protective film; when the transmission line is determined to be severely corroded, the transmission line is replaced.

[0027] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the protection scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring and evaluating the state of a power transmission line assisted by an airborne laser radar, characterized in that: The following steps are involved: Step 1: Use airborne laser radar equipment to perform three-dimensional scanning of the offshore power transmission line and its surrounding environment to obtain point cloud data and aircraft position; Step 2: Transmit the collected point cloud data to the ground data processing center for preprocessing; Step 3: Extract the geometric features of the power transmission line based on the preprocessed point cloud data; And analyze the distance change between adjacent points in the point cloud data, and calculate the roughness of the transmission line surface; finally, use the intensity information of the lidar to obtain the salt spray concentration at sea at that time; step 4, use the extracted geometric features, roughness and salt spray concentration of the transmission line as input, establish a corrosion recognition model, and judge the corrosion degree of the transmission line; step 5, apply the trained corrosion recognition model to the monitoring of offshore transmission lines, collect the point cloud data of the transmission line in real time through the lidar, extract features and input them into the corrosion recognition model, realize real-time recognition and monitoring of the corrosion degree of the transmission line, and complete the closed loop.

2. The airborne laser radar-assisted transmission line status monitoring and assessment method according to claim 1 is characterized in that: The step 2 specifically includes: step 2.1, performing noise reduction processing on the point cloud data, for each point in the point cloud data , calculate its local density , define a radius r, and count the number of points within the radius r to represent the local density , the formula is: ; where X is the indicator function, For point To adjacent point The distance between When X=1, otherwise X=0; find all local densities greater than point , forming a set , ; Calculation point To Collection The distance of a point , then point To the local density greater than The average distance of the points The calculation formula is: ; where m is the set The number of midpoints; defines the denoising metric: ;in, It is the maximum value of the local density of all points in the point cloud; set the denoising threshold ,when When Mark as noise points and remove them; Step 2.2: Perform straight-through filtering on the denoised point cloud data. , extract its coordinate value on the Z axis , set the threshold range in the Z-axis direction ,judge Whether the threshold conditions are met, that is: ; If the conditions are met, the points in the point cloud data are retained , add it to the new filtered point cloud data set; if the condition is not met, the point in the point cloud data is discarded , continue to process the next point; after traversing all the points, the new point cloud data set contains the points retained after the straight-through filtering, that is, the transmission line point cloud within the threshold range.

3. The airborne laser radar-assisted transmission line status monitoring and assessment method according to claim 1 is characterized in that: In step 3, the geometric features of the power transmission line are extracted based on the preprocessed point cloud data, which specifically includes: adaptively dividing the point cloud data of the power transmission line into multiple local areas using a density clustering algorithm according to the density distribution of the point cloud data. The divided area set is , for each region , calculate its point cloud density and the average spacing , calculate the cloud density The formula is: ;in is the number of points in the region, is the volume of the region; the average spacing It is obtained by calculating the average distance between points in the region. and Two points in the area, point and The Euclidean distance between for: ; then the average spacing for: ;in, Indicates from The number of combinations of selecting 2 elements; extracting local areas The characteristics of each local area In the local area, a local geometric graph is constructed, and the points in the area are taken as nodes of the graph. The edge weight between two points is the Euclidean distance between the nodes. The Laplace matrix of the graph is calculated. , whose elements The definition of is: hour: ;in, is the edge weight between node i and node j, that is, the Euclidean distance between the two points; when And when node i and node j are connected by an edge: ;when When nodes i and j are not connected by edges: ; For the Laplacian matrix Perform eigendecomposition and obtain eigenvalues and the eigenvector , select the smallest non-zero eigenvalue The corresponding eigenvector ,set up ; local diameter estimate within the region for: ;in, is the difference of the eigenvector elements, is the average distance; according to the estimated value of the diameter of each local area Perform global diameter fusion, the global diameter D is: ;in, is the weight of the region.

4. The airborne laser radar-assisted transmission line status monitoring and assessment method according to claim 1, characterized in that: In step 3, the distance change between adjacent points in the point cloud data is analyzed to calculate the roughness of the surface of the transmission line, which specifically includes: assuming that the point cloud data is ; represents the coordinate set of points on the surface of the transmission line and its surroundings, where n is the total number of points, and the radius neighborhood method is used to calculate each point With adjacent points The distance between them is: ;in, For point With adjacent points The distance between the transmission lines and the roughness of the transmission line surface The calculation formula is: ; Where n is the total number of points, k is the number of adjacent points of each point, Yes With adjacent points The distance change between them.

5. The airborne laser radar-assisted transmission line status monitoring and assessment method according to claim 1 is characterized in that: In step 3, the intensity information of the laser radar is used to obtain the salt spray concentration at sea at that time, which specifically includes: using the laser radar to scan the sea area, the received echo intensity is I, the measurement distance is d, and the measurement angle is , forming the original data set , where n represents different measurement points, and obtains information on offshore wind speed v, humidity h, and temperature t; establishes a relationship model between salt spray concentration and lidar intensity, which is: ; Where I is the echo intensity, is the laser radar echo intensity without salt fog, is the attenuation coefficient of salt spray to laser, is the salt spray concentration, d is the measuring distance, f is the correction factor, and the point Substituting into the relationship model between salt spray concentration and lidar intensity, we get: ;in, is the salt spray concentration, They are the wind speed, humidity and temperature values ​​corresponding to the measurement point respectively.

6. The airborne laser radar-assisted transmission line status monitoring and assessment method according to claim 1, characterized in that: In the step 4, the corrosion identification model is established based on the neural network algorithm; the geometric feature data Z and roughness data of the transmission line are and salt spray concentration data As input, let the geometric feature data be , the roughness data is , the salt spray concentration data is ; Normalize the geometric feature data, roughness data and salt spray concentration data, and use the linear normalization formula for the geometric feature data: ;in, is the minimum value in the geometric feature data, is the maximum value in the geometric feature data, is the normalized geometric eigenvalue; the same normalization method is used for the roughness data and the salt spray concentration data, and the normalized roughness data is obtained as , the normalized salt spray concentration data is , the normalized geometric features, roughness and salt spray concentration data are combined into a feature vector ; The convolutional neural network is used to calculate the risk value H of the corrosion degree, which is expressed as: ; Where W is the weight coefficient, F is the output function, is the convolutional neural network model of the feature vector X.

7. The airborne laser radar-assisted transmission line status monitoring and assessment method according to claim 6 is characterized in that: Setting risk value thresholds and ,when When When The transmission line is judged to be severely corroded.

8. The airborne laser radar-assisted transmission line status monitoring and assessment method according to claim 7, characterized in that: Carry out maintenance to varying degrees based on the risk value; when the transmission line is judged to be slightly corroded, shorten the monitoring period and pay close attention to corrosion changes; when the transmission line is judged to be moderately corroded, carry out comprehensive anti-corrosion treatment on the transmission line, use hot-dip galvanizing and spray anti-corrosion paint to form an anti-corrosion protective film; when the transmission line is judged to be severely corroded, replace the transmission line.

Images