Power transmission line dynamic inspection path planning method and multi-mode interaction system

Abstract

The invention relates to a power transmission line dynamic inspection path planning method and a multi-modal interaction system. The power transmission line dynamic inspection path planning method comprises the steps of multi-source data acquisition and processing, construction of a fusion algorithm model, fusion algorithm initialization, fusion algorithm iterative optimization, path dynamic adjustment and multi-modal interaction closed loop. The multi-modal interaction system comprises a fusion dynamic path optimization module, a multi-modal interaction closed loop module and a multi-source data support module which are connected through data communication. According to the method, static basic information and dynamic information of inspection are combined, a systematic inspection network is constructed, global path optimization is performed, the inspection efficiency is improved, and the standardization and accuracy of the overall inspection operation are improved.

Description

Technical Field

[0001] This invention relates to a method for dynamic inspection path planning of transmission lines based on an ant colony-particle swarm optimization algorithm and a multimodal interactive system, belonging to the field of transmission line inspection technology. Background Technology

[0002] Transmission line inspection is a core support link in ensuring the safe and stable operation of the power system, and its operational efficiency and coordination level are directly related to the continuity and reliability of power supply. Currently, transmission line inspection route planning mostly relies on static basic information such as the location of transmission towers and the preset inspection range, and is mainly completed by manual experience. The planning process is highly subjective, inefficient, and difficult to adapt to the dynamic needs of complex inspection environments.

[0003] Existing power transmission inspection route planning technologies lack comprehensive consideration of multi-dimensional constraints such as real-time personnel location and road network data. They fail to construct a systematic inspection network and cannot perform global route optimization. The application of route planning algorithms is relatively simple, making it difficult to effectively integrate historical inspection data with real-time environmental information to achieve dynamic adaptation and adjustment. This results in insufficient adaptability to complex environmental changes, hindering the improvement of inspection efficiency. At the same time, related service functions such as route guidance, deviation reminders, and automatic shooting are relatively scattered and independent, failing to form a closed-loop collaborative mechanism. The standardization and accuracy of the overall inspection operation need to be further improved.

[0004] Therefore, there is an urgent need for a dynamic inspection path planning method for transmission lines. This method should combine static basic information such as the location of transmission towers and the preset inspection range with dynamic information such as the real-time location of personnel and road network data. It should comprehensively consider multi-dimensional constraints, construct a systematic inspection network, and optimize the global path. It should effectively integrate historical inspection data with real-time environmental information to achieve dynamic adaptation and adjustment, thereby improving inspection efficiency. Furthermore, it should integrate related service functions such as path guidance, deviation reminders, and automatic shooting to form a closed-loop collaborative mechanism, thereby improving the standardization and accuracy of the overall inspection operation. Summary of the Invention

[0005] The purpose of this invention is to overcome the above-mentioned shortcomings and provide a dynamic inspection path planning method and multimodal interaction system for transmission lines. Based on the ant colony-particle swarm optimization algorithm, it combines static basic information and dynamic information of the inspection to construct a systematic inspection network and optimize the global path. It effectively integrates historical inspection data and real-time environmental information to achieve dynamic adaptation and adjustment, thereby improving inspection efficiency. It integrates related service functions such as path guidance to form a closed-loop collaborative mechanism, thereby improving the standardization and accuracy of the overall inspection operation.

[0006] The objective of this invention is achieved as follows: A method for dynamic inspection path planning of transmission lines includes the following steps: Step S1: Multi-source data acquisition and processing S1.1 Obtain the coordinates of the transmission tower The data includes: total number of poles (n), road network topology, real-time location of inspection personnel, real-time traffic data, historical inspection route records, and historical data on pole defects. It is a positive integer not greater than n; S1.2 normalizes the real-time traffic data to generate the real-time traffic impact factor Road(t); based on historical data of tower defects, it calculates the tower inspection risk factor. ; Step S2: Construct a model based on the ant colony-particle swarm optimization algorithm, establish a multi-objective optimization function that integrates actual path length, inspection time, and risk coverage, and calculate the dynamic weight minF. The calculation formula is as follows: ,in: Actual path length , in: Let i be the straight-line distance between towers i and j. Road condition weight (the worse the road condition, the greater the weight); Inspection time T (unit: h): ,in: To ensure standard inspection speed, This is the attenuation coefficient of road conditions on inspection speed; Risk coverage ,in: For the first Whether the base tower is included in the planning path (1 indicates inclusion, 0 indicates non-inclusion); Weight values ​​based on real-time traffic conditions The update is performed using the following formula: , , ; Step S3: Initialization of the fusion algorithm Ant colony algorithm parameters: Set the number of ants (n is the number of towers), initial pheromone concentration Pheromones importance The initial heuristic function is calculated using the following formula: (Incorporating tower risk factors); Particle swarm optimization parameters: Particle dimension = 2, number of particles Inertial weight Learning factor , ; Inspection network construction: Based on road network connectivity and real-time traffic conditions, eliminate impassable road sections. This forms an effective inspection network adjacency matrix.

[0007] Step S4: Iterative optimization of the fusion algorithm Will and As the particle position vector The particle velocity and position are updated to optimize key particle parameters. The calculation formula is as follows: , ,in, It is a random number. This represents the optimal position for an individual particle. The optimal position globally. This is a boundary constraint function to prevent parameters from going out of bounds. Ants are based on the optimized... and The next tower is selected based on the transition probability.

[0008] The pheromone update rule is modified by introducing road conditions and risk factors to enhance the memorization of high-quality routes. The calculation formula is as follows: ,in, ( For pheromone intensity, For ants (objective function value) The pheromone increment for the globally optimal path. The fusion coefficient is the global optimal solution for 10 consecutive generations. If the change is ≤0.08%, or the number of iterations reaches 150, output the current optimal inspection path; Step S5: Dynamic Path Adjustment The path will be dynamically adjusted when any one of the following three conditions is met: Condition 1: Real-time changes in traffic conditions ≥0.25; Condition 2: Personnel deviate from the planned path by ≥5m; Condition 3: Add temporary inspection tasks; After triggering dynamic path adjustment, steps S1 to S4 are re-executed to quickly generate a new optimal path; Step S6: Multimodal interaction closed loop S6.1 calculates the current location of inspection personnel in real time. Shortest deviation from the planned path A positioning deviation quantification formula is constructed, and the calculation formula is as follows: , in, The coordinates of two adjacent towers in the planned path are given, the denominator is the planar distance, the numerator is the planar deviation distance, and the square root term is the elevation correction factor. S6.2 Automatic shooting based on positioning accuracy threshold When the inspection personnel arrive at the designated inspection location on the pole, i.e., the preset pole coordinates, and the spatial distance between the personnel's current position and the target point being photographed... When the threshold is met, the camera function will be activated. The calculation formula is: .

[0009] Furthermore, the real-time traffic data in step S1 includes the congestion coefficient K and road capacity. The corresponding formula for calculating the real-time traffic impact factor Road(t) is: ,in (0 indicates completely unobstructed traffic, 1 indicates completely congested traffic). (1 indicates the best road condition, 0 indicates impassable).

[0010] Furthermore, the tower inspection risk factor in step S1 The calculation formula is: ,in, The higher the value, the higher the priority of tower inspection.

[0011] Furthermore, in step S2, the initial weight value is set to: .

[0012] Furthermore, the formula for calculating the change in real-time traffic factors in step S5 is as follows: .

[0013] Furthermore, in step S6.2, the automatic photo-taking position accuracy is set to 2m, that is... Automatic photo taking function will be activated when the distance is ≤2m.

[0014] A multimodal interactive system for dynamic inspection of transmission lines, based on any of the aforementioned dynamic inspection path planning methods for transmission lines, includes a fusion dynamic path optimization module, a multimodal interactive closed-loop module, and a multi-source data support module connected via data communication; step S1 of the dynamic inspection path planning method for transmission lines is executed by the multi-source data support module; steps S2 to S5 are executed by the fusion dynamic path optimization module; and step S6 is executed by the multimodal interactive closed-loop module.

[0015] Compared with the prior art, the beneficial effects of the present invention are: The transmission line dynamic inspection path planning method and multimodal interaction system of this invention incorporate real-time road conditions and historical risk factors into the optimal path calculation, effectively avoiding congested road sections and high-risk omissions. The multimodal interaction closed loop achieves accurate and efficient yaw correction through the positioning deviation quantification formula, and relies on the positioning accuracy threshold to trigger automatic shooting, ensuring the accuracy of shooting and full coverage of key parts. Overall, it significantly improves the standardization of inspection operations and the efficiency of transmission line inspection, significantly reduces the human error rate, can flexibly adapt to complex road condition changes, and effectively improves inspection quality and safety assurance capabilities. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating the workflow of a dynamic inspection path planning method for power transmission lines according to the present invention. Detailed Implementation Example 1

[0017] See Figure 1 The present invention relates to a method for dynamic inspection path planning of transmission lines, comprising the following steps: Step S1: Multi-source data acquisition and processing S1.1 Obtain the coordinates of the transmission tower The data includes: total number of poles (n), road network topology, real-time location of inspection personnel, real-time traffic data, historical inspection route records, and historical data on pole defects. The real-time traffic data is a positive integer not greater than n; it includes the congestion coefficient K and road capacity. ; S1.2 normalizes the real-time traffic data to generate the real-time traffic impact factor Road(t); based on historical data of tower defects, it calculates the tower inspection risk factor. ; The formula for calculating the real-time traffic impact factor Road(t) is as follows: ,in (0 indicates completely unobstructed traffic, 1 indicates completely congested traffic). (1 indicates the best road condition, 0 indicates impassable). The risk factors of pole and tower inspection The calculation formula is: , in, The larger the value, the higher the priority of tower inspection; Step S2: Construct a model based on the ant colony-particle swarm optimization algorithm, establish a multi-objective optimization function that integrates actual path length, inspection time, and risk coverage, and calculate the dynamic weight minF. The calculation formula is as follows: , Where: actual path length , in: Let i be the straight-line distance between towers i and j. Road condition weight (the worse the road condition, the greater the weight); Inspection time T (unit: h): ,in: To ensure standard inspection speed, This is the attenuation coefficient of road conditions on inspection speed; Risk coverage : ,in: For the first Whether the base tower is included in the planning path (1 indicates inclusion, 0 indicates non-inclusion); Set the initial weight value to: Weight values ​​based on real-time traffic conditions The update is performed using the following formula: ; Step S3: Initialization of the fusion algorithm Ant colony algorithm parameters: Set the number of ants (n is the number of towers), initial pheromone concentration Pheromones importance The initial heuristic function is calculated using the following formula: (Incorporating tower risk factors); Particle swarm optimization parameters: Particle dimension = 2, number of particles Inertial weight Learning factor , ; Inspection network construction: Based on road network connectivity and real-time traffic conditions, eliminate impassable road sections. This forms an effective inspection network adjacency matrix.

[0018] Step S4: Iterative optimization of the fusion algorithm Will and As the particle position vector The particle velocity and position are updated to optimize key particle parameters. The calculation formula is as follows: , , in, It is a random number. This represents the optimal position for an individual particle. The optimal position globally. This is a boundary constraint function to prevent parameters from going out of bounds. Ants are based on the optimized... and The next tower is selected based on the transition probability.

[0019] The pheromone update rule is modified by introducing road conditions and risk factors to enhance the memorization of high-quality routes. The calculation formula is as follows: , in, ( For pheromone intensity, For ants (objective function value) The pheromone increment for the globally optimal path. The fusion coefficient is the global optimal solution for 10 consecutive generations. If the change is ≤0.08%, or the number of iterations reaches 150, output the current optimal inspection path; Step S5: Dynamic Path Adjustment The path will be dynamically adjusted when any one of the following three conditions is met: Condition 1: Real-time changes in traffic conditions ≥0.25; the formula for calculating the change in the real-time traffic factor is: ; Condition 2: Personnel deviate from the planned path by ≥5m; Condition 3: Add temporary inspection tasks; After triggering dynamic path adjustment, steps S1 to S4 are re-executed to quickly generate a new optimal path; Step S6: Multimodal interaction closed loop S6.1 calculates the current location of inspection personnel in real time. Shortest deviation from the planned path A positioning deviation quantification formula is constructed, and the calculation formula is as follows: , in, The coordinates of two adjacent towers in the planned path are given, the denominator is the planar distance, the numerator is the planar deviation distance, and the square root term is the elevation correction factor. S6.2 Automatic shooting based on positioning accuracy threshold The automatic photo-taking position accuracy is set to 2m. When the inspection personnel arrive at the designated inspection position on the tower, i.e., the preset tower coordinates, the spatial distance between the personnel's current position and the target point will be determined. When the threshold is met, the camera function will be activated. The calculation formula is: .

[0020] Example 2 The present invention relates to a multimodal interactive system for dynamic inspection of transmission lines, based on the dynamic inspection path planning method for transmission lines in Embodiment 1, comprising a fusion dynamic path optimization module, a multimodal interactive closed-loop module, and a multi-source data support module connected via data communication; step S1 of the dynamic inspection path planning method for transmission lines is executed by the multi-source data support module; steps S2 to S5 are executed by the fusion dynamic path optimization module; and step S6 is executed by the multimodal interactive closed-loop module.

[0021] The transmission line dynamic inspection path planning method and multimodal interaction system of this invention, based on the ant colony-particle swarm fusion algorithm, incorporates real-time road conditions and historical risk factors into the optimal path calculation, effectively avoiding congested road sections and high-risk omissions. The multimodal interaction closed loop achieves accurate and efficient yaw correction through the positioning deviation quantification formula, and relies on the positioning accuracy threshold to trigger automatic shooting, ensuring the accuracy of shooting and full coverage of key parts. Overall, it significantly improves the standardization of inspection operations and the efficiency of transmission line inspection, significantly reduces the human error rate, can flexibly adapt to complex road condition changes, and effectively improves inspection quality and safety assurance capabilities.

[0022] Additionally, it should be noted that the above-described specific implementation is merely an optimized solution of this patent, and any modifications or improvements made by those skilled in the art based on the above concept are within the scope of protection of this patent.

Claims

1. A method for dynamic inspection path planning of transmission lines, characterized in that: Includes the following steps: Step S1: Multi-source data acquisition and processing S1.1 Obtain the coordinates of the transmission tower The data includes: total number of poles (n), road network topology, real-time location of inspection personnel, real-time traffic data, historical inspection route records, and historical data on pole defects. It is a positive integer not greater than n; S1.2 normalizes the real-time traffic data to generate the real-time traffic impact factor Road(t); Calculate the tower inspection risk factor based on historical tower defect data. ; Step S2: Construct a model based on the ant colony-particle swarm optimization algorithm, establish a multi-objective optimization function that integrates actual path length, inspection time, and risk coverage, and calculate the dynamic weight minF. The calculation formula is as follows: ,in: Actual path length L: , in: Let i be the straight-line distance between towers i and j. Road condition weight (the worse the road condition, the greater the weight); Inspection time T (unit: h): ,in: To ensure standard inspection speed, This is the attenuation coefficient of road conditions on inspection speed; Risk coverage : ,in: For the first Whether the base tower is included in the planning path (1 indicates inclusion, 0 indicates non-inclusion); Weight values ​​based on real-time traffic conditions The update is performed using the following formula: , , ； Step S3: Initialization of the fusion algorithm Ant colony algorithm parameters: Set the number of ants ( (Number of towers), initial pheromone concentration Pheromones importance The initial heuristic function is calculated using the following formula: (Incorporating tower risk factors); Particle swarm optimization parameters: Particle dimension = 2, number of particles Inertial weight Learning factor , , ; Inspection network construction: Based on road network connectivity and real-time traffic conditions, eliminate impassable road sections. This forms an effective inspection network adjacency matrix; Step S4: Iterative optimization of the fusion algorithm Will and As the particle position vector The particle velocity and position are updated to optimize key particle parameters. The calculation formula is as follows: ， ， in, It is a random number. This represents the optimal position for an individual particle. The optimal position globally. This is a boundary constraint function to prevent parameters from going out of bounds. Ants are based on the optimized... and Select the next tower based on the transition probability; The pheromone update rule is modified by introducing road conditions and risk factors to enhance the memorization of high-quality routes. The calculation formula is as follows: ， in, ( For pheromone intensity, For ants (objective function value) The pheromone increment for the globally optimal path. The fusion coefficient is the global optimal solution for 10 consecutive generations. If the change is ≤0.08%, or the number of iterations reaches 150, output the current optimal inspection path; Step S5: Dynamic Path Adjustment The path will be dynamically adjusted when any one of the following three conditions is met: Condition 1: Real-time changes in traffic conditions ; Condition 2: Personnel deviate from the planned path by ≥5m; Condition 3: Add temporary inspection tasks; After triggering dynamic path adjustment, steps S1 to S4 are re-executed to quickly generate a new optimal path; Step S6: Multimodal interaction closed loop S6.1 calculates the current location of inspection personnel in real time. Shortest deviation from the planned path A positioning deviation quantification formula is constructed, and the calculation formula is as follows: ， in, The coordinates of two adjacent towers in the planned path are given, the denominator is the planar distance, the numerator is the planar deviation distance, and the square root term is the elevation correction factor. S6.2 Automatic shooting based on positioning accuracy threshold When the inspection personnel arrive at the designated inspection location on the pole, i.e., the preset pole coordinates, and the spatial distance between the personnel's current position and the target point being photographed... When the threshold is met, the camera function will be activated. The calculation formula is: 。 2. The method for dynamic inspection path planning of transmission lines according to claim 1, characterized in that: The real-time traffic data in step S1 includes the congestion coefficient K and road capacity. The corresponding formula for calculating the real-time traffic impact factor Road(t) is: ,in (0 indicates completely unobstructed traffic, 1 indicates completely congested traffic). (1 indicates the best road condition, 0 indicates impassable).

3. The method for dynamic inspection path planning of transmission lines according to claim 1, characterized in that: The tower inspection risk factors in step S1 The calculation formula is: ,in, The higher the value, the higher the priority of tower inspection.

4. The method for dynamic inspection path planning of transmission lines according to claim 1, characterized in that: In step S2, the initial weight value is set to: .

5. The method for dynamic inspection path planning of transmission lines according to claim 1, characterized in that: The formula for calculating the change in real-time traffic factors in step S5 is as follows: .

6. The method for dynamic inspection path planning of transmission lines according to claim 1, characterized in that: In step S6.2, the automatic photo-taking position accuracy is set to 2m, that is... The automatic photo-taking function will be activated at that time.

7. A multimodal interactive system for dynamic inspection of transmission lines, characterized in that: The method for dynamic inspection path planning of transmission lines according to any one of claims 1 to 6 includes a fusion dynamic path optimization module, a multimodal interactive closed-loop module, and a multi-source data support module connected by data communication; step S1 of the dynamic inspection path planning method of transmission lines is executed by the multi-source data support module; steps S2 to S5 are executed by the fusion dynamic path optimization module; and step S6 is executed by the multimodal interactive closed-loop module.

Images