Power transmission line inspection path planning method and system based on multi-source data fusion

Abstract

The application provides a power transmission line inspection path planning method and system based on multi-source data fusion, and the application constructs a tower corresponding track feature data set by mining the correlation among tower latitude and longitude, vehicle track, walking track and road network data. On this basis, three optimization algorithms are used to plan the optimal inspection path when a single person works on a single line, the optimal inspection path when multiple people work is planned based on a k-means clustering algorithm, and a new group inspection mode of spatially related towers is proposed by dividing the inspection area into communities. The application establishes a line inspection path planning model from different levels and different dimensions, provides strong support for power transmission line inspection path planning, inspection work plan development and vehicle management, realizes the rationalization and intelligentization of power transmission line inspection multi-level work, and achieves the purpose of shortening the inspection time and improving the inspection efficiency.

Description

Technical Field

[0001] This application relates to the field of power grid inspection technology, and in particular to a method and system for planning inspection routes for transmission lines based on multi-source data fusion. Background Technology

[0002] In recent years, with the continuous expansion of the power grid, the number of 110kV and above transmission lines has also been increasing, while the number of line maintenance personnel has remained unchanged or even decreased. This has led to a year-on-year increase in the average maintenance workload per person, resulting in a decline in the on-site attendance rate of tower inspection personnel and making it difficult to guarantee the quality of maintenance. Therefore, it is necessary to use technological means to help inspection personnel improve their inspection efficiency.

[0003] Currently, traditional inspection methods rely heavily on maintenance personnel's memory of inspection routes, which is highly subjective and leads to suboptimal route planning. Although GPS navigation is sometimes used, all current positioning software only has point-to-point positioning capabilities and lacks segmented analysis, overall judgment, and global planning for route inspection work. This results in inefficient personnel and vehicle deployment and inadequate inspection plans.

[0004] To this end, this application provides a method and system for planning inspection routes for transmission lines based on multi-source data fusion. Based on data such as tower latitude and longitude, vehicle trajectory, and inspection personnel walking trajectory, combined with navigation maps, the method fully explores the correlation and coupling between various data, constructs an optimal inspection route planning model, realizes scientific route planning, reduces manpower input, and improves inspection efficiency. Summary of the Invention

[0005] The purpose of this application is to provide a method and system for planning transmission line inspection routes based on multi-source data fusion, so as to solve the problems of slow inspection efficiency and incomplete and unreasonable inspection plans. The specific technical solution is as follows: Firstly, a method for planning transmission line inspection routes based on multi-source data fusion is provided, the method comprising:

[0006] Step S1: Using any one pole as the target pole, obtain the latitude and longitude data of the target pole, the vehicle trajectory data from the vehicle's starting point to the vehicle's boarding and alighting point at the target pole, and the walking trajectory data of the patrol personnel from the boarding and alighting point to the target pole.

[0007] Step S2: Based on the data from Step S1 and the first path planning model, calculate the trajectory set and time set for a single person inspecting a single tower.

[0008] Step S3: Repeat steps S1 and S2 to calculate the trajectory set and time set for a single person inspecting multiple towers;

[0009] Step S4: Calculate the optimal path and total time for a single-person patrol line based on the path trajectory set, time set obtained in S3 and the second path planning model;

[0010] Step S5: Calculate the optimal trajectory set and time set for multiple towers within the same target area by using the k-means clustering algorithm and the second path planning model.

[0011] Optionally, the trajectory set and time set for a single-person inspection of a single tower calculated based on the data from step S1 and the first path planning model include:

[0012] S201: Perform deduplication and sorting preprocessing on the vehicle trajectory point data and the pedestrian trajectory point data respectively; wherein, the vehicle trajectory point data includes vehicle speed and vehicle trajectory point latitude and longitude, and the pedestrian trajectory point data includes pedestrian trajectory point latitude and longitude.

[0013] S202: Determine the location of the vehicle's entry and exit points on the target tower based on the vehicle speed;

[0014] S203: Determine the travel time and trajectory from the vehicle's starting point to the target tower's pick-up / drop-off point based on the vehicle's starting point's latitude and longitude, the vehicle's arrival point's latitude and longitude, and the online navigation software.

[0015] S204: Determine the walking time of the personnel based on the latitude and longitude of the personnel trajectory points, the target tower, and the boarding / alighting points; the walking time of the personnel includes the walking time from the boarding / alighting point to the target tower and the walking time from the target tower back to the boarding / alighting point.

[0016] S205: Export the walking trajectory of a person during the walking time based on online navigation software;

[0017] S206: Obtain the trajectory set for a single person inspecting a single tower based on the vehicle trajectory and walking trajectory;

[0018] S207: Obtain the time set for a single person to inspect a single tower based on the vehicle travel time and walking time.

[0019] Optionally, determining the walking time of personnel based on the latitude and longitude of the personnel trajectory points, the target tower, and the boarding and alighting points includes:

[0020] Compare the latitude and longitude of the personnel trajectory points with the latitude and longitude of the boarding and alighting points;

[0021] When |latitude and longitude of the person's trajectory point - latitude and longitude of the boarding / alighting point| ≤ 1 second, and the distance between the two points shows an increasing trend, the moment when walking begins is obtained;

[0022] Compare the latitude and longitude of the personnel trajectory points with the latitude and longitude of the target tower;

[0023] If |latitude and longitude of the personnel trajectory point - latitude and longitude of the target tower| ≤ 1 second, and the distance between the two points shows a decreasing trend, then the time of arrival at the target tower is obtained;

[0024] Subtract the start time of walking from the time of arrival at the target tower to obtain the walking time from the pick-up / drop-off point to the target tower. Similarly, obtain the walking time from the target tower back to the pick-up / drop-off point.

[0025] Optionally, the step of calculating the optimal path and total time for a single-person patrol line based on the path trajectory set, time set, and the second path planning model obtained in S3 includes:

[0026] S401: The total time and patrol path for a single person to patrol a single route are recalculated from the path trajectory set and time set obtained in S3 by using the greedy algorithm, ant colony algorithm and simulated annealing algorithm respectively.

[0027] S402: Compare the total time obtained from the three algorithms;

[0028] S403: Determine the inspection path calculated by the algorithm with the shortest total time as the optimal path.

[0029] Optionally, the optimal trajectory set and time set for multiple towers inspected within the same target area by multiple people, calculated based on the k-means clustering algorithm and the second path planning model, include:

[0030] S501: Randomly select K base towers within the target area, the same number as the number of patrol personnel, as initial cluster points;

[0031] S502: For each other base tower in the target area, calculate its inspection time to each initial cluster point, and assign it to the set of initial cluster points with the shortest inspection time to obtain K cluster sets;

[0032] S503: Calculate the optimal path and total time for each cluster using the second path planning model;

[0033] S504: The working time of each inspector is calculated by adding the total time spent in each cluster set and the inspection time of the inspector corresponding to each cluster set;

[0034] S505: Compare the working hours of each patrol personnel with the preset working hours;

[0035] S506: If the time is less than the preset working time, and the variance of the highest working time and the lowest working time is less than the preset variance time, then the optimal trajectory set and time set for multiple people inspecting multiple towers in the same target area are obtained.

[0036] S507: If the condition of S506 is not met, randomly select a tower from the cluster set with the highest working time and place it in the cluster set with the lowest working time. Repeat steps S503-S506 for the preset number of times. If the repetition ends and the condition of S506 is still not met, then the result with the smallest mean square error of the total time consumption of each cluster set in the repeated iterations is determined as the optimal trajectory set and time set for multiple towers in the same target area inspected by multiple people.

[0037] Optionally, when the patrol mission involves multiple target areas, the method further includes:

[0038] A community partitioning algorithm is used to optimally partition multiple target regions into multiple new target regions;

[0039] The optimal trajectory set and time set are obtained by using the method in step S5 to perform path planning on the new target area.

[0040] Optionally, the step of using a community partitioning algorithm to optimally partition multiple target regions into multiple new target regions includes:

[0041] Calculate the difference in longitude or latitude between all pairs of towers within multiple target areas;

[0042] If the absolute value of the difference in longitude or latitude between any two poles is greater than 3 minutes, then the distance between the two poles will be set to 0.

[0043] If the absolute value of the difference in longitude or latitude between any two pairs is less than 3 minutes, then calculate the straight-line distance between the two pairs.

[0044] If the straight-line distance between any two towers is greater than 5 km, then the distance between the two towers will be set to 0.

[0045] If the straight-line distance between any two poles is less than 5 km, then the distances of all poles that meet the condition form a spatial matrix.

[0046] The Leuven algorithm is used to perform optimal community partitioning on the spatial matrix to obtain multiple new target regions.

[0047] Secondly, this application provides a transmission line inspection route planning system based on multi-source data fusion, the system comprising:

[0048] The acquisition unit is used to acquire the latitude and longitude data of any target tower, the vehicle trajectory data from the vehicle's starting point to the vehicle's boarding and alighting point at the target tower, and the walking trajectory data of the patrol personnel from the boarding and alighting point to the target tower, taking any target tower as the target tower.

[0049] The first calculation unit is used to calculate the trajectory set and time set of a single person inspecting a single tower based on the data in step S1 and the first path planning model.

[0050] The second calculation unit is used to repeat steps S1 and S2 to calculate the trajectory set and time set of a single person inspecting multiple towers;

[0051] The third calculation unit is used to calculate the optimal path and total time for a single person to patrol a single line based on the path trajectory set, time set, and second path planning model obtained from S3.

[0052] The fourth calculation unit is used to calculate the optimal trajectory set and time set for multiple towers inspected by multiple people in the same target area based on the k-means clustering algorithm and the second path planning model.

[0053] Thirdly, this application provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0054] Memory, used to store computer programs;

[0055] When a processor executes a program stored in memory, it implements any of the steps described in the first aspect.

[0056] Fourthly, this application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of any of the methods described in the first aspect.

[0057] Fifthly, a computer program product containing instructions is provided, which, when run on a computer, causes the computer to execute any of the above-described transmission line inspection path planning methods based on multi-source data fusion.

[0058] Beneficial effects of the embodiments in this application:

[0059] This application provides a method and system for transmission line inspection path planning based on multi-source data fusion. This application conducts in-depth research using multi-source trajectory data as a starting point, specifically by mining the correlations between tower latitude and longitude, vehicle trajectories, pedestrian trajectories, and road network data to construct a trajectory feature dataset corresponding to each tower. Based on this, three optimization algorithms are used to plan the optimal inspection path for single-person, single-line operations, and the optimal inspection path for multi-person operations is planned using the k-means clustering algorithm. Furthermore, the inspection area is divided into communities, proposing a new group inspection model for spatially associated towers. A line inspection path planning model is established from different levels and dimensions, providing strong support for transmission line inspection path planning, inspection work plan formulation, and vehicle management. This achieves the rationalization and intelligentization of multi-level work in transmission line inspection, shortening inspection time and improving inspection efficiency.

[0060] Of course, implementing any product or method of this application does not necessarily require achieving all of the advantages described above at the same time. Attached Figure Description

[0061] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0062] Figure 1 A flowchart illustrating a transmission line inspection route planning method based on multi-source data fusion, provided for embodiments of this application;

[0063] Figure 2 A schematic diagram illustrating the trajectory characteristics of a single-person inspection of a single-target tower.

[0064] Figure 3 Schematic diagrams were drawn to illustrate the vehicle and walking trajectories of a single person inspecting a single target tower.

[0065] Figure 4 A comparison chart of the patrol trajectories of the three optimization algorithms;

[0066] Figure 5 A comparison chart showing the cumulative time spent inspecting towers under three optimization algorithms;

[0067] Figure 6 The diagram illustrates the total time consumed for each patrol group when the number of patrol personnel is 3, 4, or 5.

[0068] Figure 7 When the number of patrol personnel is 4, the optimal patrol trajectory map is obtained in each set by the three algorithms;

[0069] Figure 8 When the number of patrol personnel is 5, the optimal patrol trajectory map is obtained in each set by the three algorithms;

[0070] Figure 9(a) shows the spatial layout of the poles and towers for the five existing work teams;

[0071] Figure 9(b) shows the spring layout for dividing the clubs;

[0072] Figure 9(c) shows the newly divided tower space layout;

[0073] Figure 10 A schematic diagram of the structure of a transmission line inspection route planning system based on multi-source data fusion provided in an embodiment of this application;

[0074] Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0075] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0076] This application provides a method for transmission line inspection route planning based on multi-source data fusion. The following detailed description, in conjunction with specific implementation methods, will illustrate this method for transmission line inspection route planning based on multi-source data fusion. Figure 1 As shown, the specific steps are as follows:

[0077] Step S1: Using any one pole as the target pole, obtain the latitude and longitude data of the target pole, the vehicle trajectory data from the vehicle's starting point to the vehicle's boarding and alighting points on the target pole, and the walking trajectory data of the patrol personnel from the boarding and alighting points to the target pole.

[0078] In this step, the vehicle's starting point can be either the starting point of the factory area or the pick-up / drop-off point on the previous tower.

[0079] In addition, the latitude and longitude data of the target towers can be collected using a latitude and longitude data acquisition device and then entered into the PMS (Power Production Management System) 2.0 system, providing 2D data. Vehicle trajectory data can be collected using vehicle-mounted dashcams, providing 2D data, with hundreds of thousands to tens of thousands of vehicle trajectory points collected daily. This data includes vehicle speed and the latitude and longitude of the trajectory points. Pedestrian trajectory data can be collected by mobile PDAs carried by patrol personnel, providing 2D data, with thousands to tens of thousands of pedestrian trajectory points collected daily, including the latitude and longitude of the pedestrians' trajectories.

[0080] Step S2: Based on the data from Step S1 and the first path planning model, calculate the trajectory set and time set for a single person inspecting a single tower.

[0081] The specific steps are as follows:

[0082] S201: Perform deduplication and sorting preprocessing on the vehicle trajectory point data and the walking trajectory point data respectively.

[0083] Specifically, data deduplication: at any given time, only one record of data with the same latitude and longitude is retained. Data sorting: traverse all data at the same time, starting from the data of the previous time, calculate the distance between the two points, and re-sort the data according to the shortest distance.

[0084] S202: As Figure 2 As shown, the location of the vehicle's entry and exit points on the target tower is determined based on the vehicle's speed. Figure 2 In the diagram, the boarding point and the alighting point are actually the same point, and the distance between them is negligible. They are only used to better distinguish the trajectory of the vehicle traveling to and from the target tower.

[0085] In this embodiment of the application, when the vehicle speed v = 0 m / s, it means that the vehicle has stopped, and the location of the vehicle at this time can be determined as the vehicle entry / exit point of the target tower.

[0086] S203: Determine the vehicle's travel time t2 and trajectory G2 from its starting point to the target tower's pick-up / drop-off point based on the vehicle's latitude and longitude, the vehicle's arrival point at the target tower's pick-up / drop-off point, and the online navigation software.

[0087] Specifically, the latitude and longitude of the vehicle's starting point and the latitude and longitude of the vehicle's arrival point at the target tower can be input into the online navigation software. In one example, this could be Gaode Maps. In this way, the travel time and the actual travel trajectory G2 of this segment can be obtained by exporting the data through the online navigation software.

[0088] S204: Determine the walking time of the personnel based on the latitude and longitude of the personnel trajectory points, the latitude and longitude of the target tower, and the latitude and longitude of the boarding and alighting points; the walking time of the personnel includes the walking time t3 from the boarding and alighting points to the target tower and the walking time t1 from the target tower back to the boarding and alighting points.

[0089] Optionally, determining the walking time of personnel based on the latitude and longitude of the personnel trajectory points, the target tower, and the boarding and alighting points includes:

[0090] Compare the latitude and longitude of the personnel trajectory points with the latitude and longitude of the boarding and alighting points.

[0091] When |latitude and longitude of the person's trajectory point - latitude and longitude of the boarding / alighting point| ≤ 1 second, and the distance between the two points shows an increasing trend, the time t at which walking begins is obtained. q .

[0092] The latitude and longitude of the personnel trajectory points are compared with the latitude and longitude of the target tower.

[0093] If |latitude and longitude of the personnel trajectory point - latitude and longitude of the target tower| ≤ 1 second, and the distance between the two points shows a decreasing trend, then the time t of reaching the target tower is obtained. d .

[0094] Subtracting the start time of walking from the time of arrival at the target tower from the time of starting the walk, we get the walking time t3 from the pick-up / drop-off point to the target tower. d -t q Similarly, the walking time t1 from the target tower back to the boarding / alighting point can be obtained.

[0095] S205: Export the walking trajectories G1 and G3 during the walking time based on the online navigation software.

[0096] S206: Based on the vehicle trajectory and walking trajectory, obtain the trajectory set (G1, G2, G3) for a single person to inspect a single tower.

[0097] S207: Based on the vehicle travel time and walking time, obtain the time set (t1, t2, t3) for a single person to inspect a single tower.

[0098] In addition, in this embodiment of the application, in order to facilitate the display and analysis of trajectory data, the coordinate system of each latitude and longitude data can be transformed. For example, the vehicle latitude and longitude under Gaode coordinates (GCJ02) can be converted to GPS coordinates (WGS84) first, and then converted to XY plane coordinates.

[0099] The method for single-person inspection of a single tower can be applied to feature value extraction and trajectory drawing of the inspection trajectory for any tower. Taking the travel of personnel on [Date] to handle floating debris on tower #7 of the 220kV Zhiyun 4Q03 line as an example, the vehicle and pedestrian trajectory data are as follows: Figure 3 As shown, the vehicle travel time t2 (3972s) from the work area to the pick-up / drop-off point, the walking time t3 (868s) from the pick-up / drop-off point to the tower, and the walking time t1 (806s) from the tower to the pick-up / drop-off point were obtained through calculation and analysis.

[0100] When an inspector needs to inspect multiple towers, the following steps can be performed.

[0101] Step S3: Repeat steps S1 and S2 to calculate the trajectory set and time set for a single person inspecting multiple towers. By repeating steps S1 and S2, the trajectory set and time set for each tower can be obtained. After integration, the time set and trajectory set for the entire line are obtained.

[0102] Step S4: Calculate the optimal path and total time for a single-person patrol line based on the path trajectory set, time set, and second path planning model obtained in S3.

[0103] Specifically, the steps include the following:

[0104] S401: The total time and patrol path for a single person to patrol a single route are obtained by recalculating the path trajectory set and time set obtained in S3 using the greedy algorithm, ant colony algorithm and simulated annealing algorithm respectively.

[0105] S402: Compare the total time taken by the three algorithms.

[0106] S403: Determine the inspection path calculated by the algorithm with the shortest total time as the optimal path.

[0107] To better reflect actual field conditions, the second path planning model fully considers walking and driving times. Through comparison of three optimization algorithms, a near-optimal inspection path is planned. Its specific applications include... Figure 4 and Figure 5 As shown.

[0108] 48 towers of the 500kV Hualong 5876 line were selected as inspection targets. Three optimization algorithms were used to calculate the shortest total inspection time, resulting in the order in which one person could inspect the 48 towers. Figure 4 As shown, the vertical axis represents the tower number, and the horizontal axis represents the inspection sequence; the corresponding cumulative inspection time for each tower is as follows. Figure 5 As shown in the figure, the simulated annealing algorithm has the shortest path planning time, so it can be selected as the optimal inspection path for the 48 towers of Hualong 5876 line.

[0109] Step S5: Calculate the optimal trajectory set and time set for multiple towers within the same target area by using the k-means clustering algorithm and the second path planning model.

[0110] Specifically, the steps include the following:

[0111] S501: Randomly select K base towers within the target area, the same number as the number of patrol personnel, as the initial cluster points; that is, set the number of patrol personnel to K.

[0112] S502: For each other base tower in the target area, calculate the inspection time to each initial cluster point, and assign it to the set of initial cluster points with the shortest inspection time to obtain K cluster sets.

[0113] S503: Calculate the optimal path and total time for each cluster using the second path planning model.

[0114] S504: The total time spent in each cluster set and the patrol time of the patrol personnel corresponding to each cluster set are added together to calculate the working time of each patrol personnel, which is the sum of patrol, vehicle travel and walking time.

[0115] S505: Compare the working hours of each patrol personnel with the preset working hours. For example, the preset working hours are 8 hours.

[0116] S506: If the time is less than the preset working time, and the variance between the highest and lowest working times is less than the preset variance time, then the optimal trajectory set and time set for multiple people inspecting multiple towers in the same target area are obtained. In one example, the preset variance time is, for example, 20 minutes.

[0117] S507: If the condition of S506 is not met, randomly select a tower from the cluster set with the highest working time and place it in the cluster set with the lowest working time. Repeat steps S503-S506 for the preset number of times. If the repetition ends and the condition of S506 is still not met, then the result with the smallest mean square error of the total time consumption of each cluster set in the repeated iterations is determined as the optimal trajectory set and time set for multiple towers in the same target area inspected by multiple people.

[0118] In this embodiment of the application, taking the inspection of 48 towers on the 500kV Hualong 5876 line as an example, the number of inspection personnel is set (3, 4, or 5 people), and the inspection time and path are calculated using this model. Figures 6 to 8 As shown. Figure 6 The total time (in seconds) for each patrol group when the number of patrol personnel is 3, 4, and 5 respectively; Figure 7 When the number of patrol personnel is 4, the optimal patrol trajectory in each set obtained by the three optimization algorithms; Figure 8 When the number of inspectors is 5, the optimal inspection trajectory in each set obtained by the three optimization algorithms is compared. By comparison, the path planned by the simulated annealing algorithm still requires the shortest time. Therefore, the corresponding clustering results and the planned path can be selected as the inspection path for the 48 towers of Hualong Line 5876.

[0119] Optionally, when the patrol mission involves multiple target areas, the method further includes:

[0120] A community partitioning algorithm is used to optimally partition multiple target regions into multiple new target regions;

[0121] The optimal trajectory set and time set are obtained by using the method in step S5 to perform path planning on the new target area.

[0122] By dividing the pole network into community-based structures, the interrelationships between poles are explored, enabling community-based management of all poles from a spatial perspective. This breaks away from the original power grid topology, which manages poles on a per-line basis. It effectively addresses issues such as uneven division of patrol areas by work teams, unreasonable allocation of newly commissioned lines, and the habit of only casually checking nearby lines during patrols. Given the scattered distribution of poles, the community-based division of poles allows for the calculation of total time spent in each community, leading to a more rational work assignment. Optimizing patrol routes and determining daily pole-climbing plans improves overall work efficiency.

[0123] Optionally, the step of using a community partitioning algorithm to optimally partition multiple target regions into multiple new target regions includes:

[0124] Calculate the difference in longitude or latitude between all pairs of towers within multiple target areas;

[0125] If the absolute value of the difference in longitude or latitude between any two poles is greater than 3 minutes, then the distance between the two poles will be set to 0.

[0126] If the absolute value of the difference in longitude or latitude between any two pairs is less than 3 minutes, then calculate the straight-line distance between the two pairs.

[0127] If the straight-line distance between any two towers is greater than 5 km, then the distance between the two towers will be set to 0.

[0128] If the straight-line distance between any two poles is less than 5 km, the distances of all poles that meet the conditions form a spatial matrix; by setting the above constraints, the amount of calculation is reduced.

[0129] The Leuven algorithm is used to perform optimal community partitioning on the spatial matrix to obtain multiple new target regions.

[0130] Taking 8765 towers of 220-500kV lines in Jinhua area as an example, as shown in Figure 9(a), after dividing them into communities, 17 communities with high modularity were obtained, as shown in Figure 9(b). For the divided community areas, the aforementioned model was used to calculate the inspection workload of each community. Based on this workload, the towers were evenly distributed to 5 work teams, as shown in Figure 9(c). The work division of the work teams was optimized. At the same time, from the perspective of the lines under the jurisdiction of a certain work team, the area inspection plan can be optimized by classifying and inspecting adjacent towers of different lines, reducing the time spent traveling back and forth to the same point, and optimizing the periodic inspection plan.

[0131] Secondly, this application provides a transmission line inspection route planning system based on multi-source data fusion, such as... Figure 10 As shown, the system includes:

[0132] The acquisition unit 110 is used to acquire the latitude and longitude data of any target tower, the vehicle trajectory data from the vehicle's starting point to the vehicle's boarding and alighting point at the target tower, and the walking trajectory data of the patrol personnel from the boarding and alighting point to the target tower, taking any tower as the target tower.

[0133] The first calculation unit 120 is used to calculate the trajectory set and time set of a single person inspecting a single tower based on the data in step S1 and the first path planning model.

[0134] The second calculation unit 130 is used to repeat steps S1 and S2 to calculate the trajectory set and time set of a single person inspecting multiple towers;

[0135] The third calculation unit 140 is used to calculate the optimal path and total time for a single person to patrol a single line based on the path trajectory set, time set and the second path planning model obtained by S3.

[0136] The fourth calculation unit 150 is used to calculate the optimal trajectory set and time set for multiple towers inspected by multiple people in the same target area based on the k-means clustering algorithm and the second path planning model.

[0137] Based on the same technical concept, embodiments of the present invention also provide an electronic device, such as... Figure 11 As shown, it includes a processor 1101, a communication interface 1102, a memory 1103, and a communication bus 1104. The processor 1101, communication interface 1102, and memory 1103 communicate with each other via the communication bus 1104.

[0138] Memory 1103 is used to store computer programs;

[0139] The processor 1101 is used to execute the program stored in the memory 1103 to implement the steps of the transmission line inspection route planning method.

[0140] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0141] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0142] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0143] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0144] In another embodiment of the present invention, a computer-readable storage medium is also provided, which stores a computer program that, when executed by a processor, implements the steps of any of the above-described transmission line inspection path planning methods.

[0145] In another embodiment of the present invention, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute any of the transmission line inspection path planning methods described in the above embodiments.

[0146] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (SSD)).

[0147] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0148] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily 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 this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for planning inspection routes of transmission lines based on multi-source data fusion, characterized in that, The method includes: Step S1: Using any one pole as the target pole, obtain the latitude and longitude data of the target pole, the vehicle trajectory data from the vehicle's starting point to the vehicle's boarding and alighting point at the target pole, and the walking trajectory data of the patrol personnel from the boarding and alighting point to the target pole. Step S2: Based on the data from Step S1 and the first path planning model, calculate the trajectory set and time set for a single person inspecting a single tower. Step S3: Repeat steps S1 and S2 to calculate the trajectory set and time set for a single person inspecting multiple towers; Step S4: Calculate the optimal path and total time for a single-person patrol line based on the path trajectory set, time set obtained in S3 and the second path planning model; Step S5: Based on the k-means clustering algorithm and the second path planning model, calculate the optimal trajectory set and time set for multiple towers within the same target area inspected by multiple people, including: S501: Randomly select K base towers within the target area, the same number as the number of patrol personnel, as initial cluster points; S502: For each other base tower in the target area, calculate its inspection time to each initial cluster point, and assign it to the set of initial cluster points with the shortest inspection time to obtain K cluster sets; S503: Calculate the optimal path and total time for each cluster using the second path planning model; S504: The working time of each inspector is calculated by adding the total time spent in each cluster set and the inspection time of the inspector corresponding to each cluster set; S505: Compare the working hours of each patrol personnel with the preset working hours; S506: If the time is less than the preset working time, and the variance of the highest working time and the lowest working time is less than the preset variance time, then the optimal trajectory set and time set for multiple people inspecting multiple towers in the same target area are obtained. S507: If the condition of S506 is not met, randomly select a tower from the cluster set with the highest working time and place it in the cluster set with the lowest working time. Repeat steps S503-S506 for the preset number of times. If the repetition ends and the condition of S506 is still not met, then the result with the smallest mean square error of the total time consumption of each cluster set in the repeated iterations is determined as the optimal trajectory set and time set for multiple towers in the same target area inspected by multiple people.

2. The method for planning transmission line inspection routes based on multi-source data fusion according to claim 1, characterized in that, The trajectory set and time set for a single-person inspection of a single tower, calculated based on the data from step S1 and the first path planning model, include: S201: Perform deduplication and sorting preprocessing on the vehicle trajectory point data and the pedestrian trajectory point data respectively; wherein, the vehicle trajectory point data includes vehicle speed and vehicle trajectory point latitude and longitude, and the pedestrian trajectory point data includes pedestrian trajectory point latitude and longitude. S202: Determine the location of the vehicle's entry and exit points on the target tower based on the vehicle speed; S203: Determine the travel time and trajectory from the vehicle's starting point to the target tower's pick-up / drop-off point based on the vehicle's starting point's latitude and longitude, the vehicle's arrival point's latitude and longitude, and the online navigation software. S204: Determine the walking time of the personnel based on the latitude and longitude of the personnel trajectory points, the target tower, and the boarding / alighting points; the walking time of the personnel includes the walking time from the boarding / alighting point to the target tower and the walking time from the target tower back to the boarding / alighting point. S205: Export the walking trajectory of a person during the walking time based on online navigation software; S206: Obtain the trajectory set for a single person inspecting a single tower based on the vehicle trajectory and walking trajectory; S207: Obtain the time set for a single person to inspect a single tower based on the vehicle travel time and walking time.

3. The method for transmission line inspection route planning based on multi-source data fusion according to claim 2, characterized in that, The determination of walking time based on the latitude and longitude of personnel trajectory points, target tower latitude and longitude, and pick-up / drop-off points includes: Compare the latitude and longitude of the personnel trajectory points with the latitude and longitude of the boarding and alighting points; When |latitude and longitude of the person's trajectory point - latitude and longitude of the boarding / alighting point| ≤ 1 second, and the distance between the two points shows an increasing trend, the moment when walking begins is obtained; Compare the latitude and longitude of the personnel trajectory points with the latitude and longitude of the target tower; If |latitude and longitude of the personnel trajectory point - latitude and longitude of the target tower| ≤ 1 second, and the distance between the two points shows a decreasing trend, then the time of arrival at the target tower is obtained; Subtract the start time of walking from the time of arrival at the target tower to obtain the walking time from the pick-up / drop-off point to the target tower. Similarly, obtain the walking time from the target tower back to the pick-up / drop-off point.

4. The method for transmission line inspection route planning based on multi-source data fusion according to claim 1, characterized in that, The optimal path and total time for a single-person patrol line calculated based on the path trajectory set, time set obtained from S3, and the second path planning model include: S401: The total time and patrol path for a single person to patrol a single route are recalculated from the path trajectory set and time set obtained in S3 by using the greedy algorithm, ant colony algorithm and simulated annealing algorithm respectively. S402: Compare the total time obtained from the three algorithms; S403: Determine the inspection path calculated by the algorithm with the shortest total time as the optimal path.

5. The method for transmission line inspection route planning based on multi-source data fusion according to claim 1, characterized in that, When the patrol mission involves multiple target areas, the method further includes: A community partitioning algorithm is used to optimally partition multiple target regions into multiple new target regions; The optimal trajectory set and time set are obtained by using the method in step S5 to perform path planning on the new target area.

6. The method for transmission line inspection route planning based on multi-source data fusion according to claim 5, characterized in that, The method of using a community partitioning algorithm to optimally partition multiple target regions into multiple new target regions includes: Calculate the difference in longitude or latitude between all pairs of towers within multiple target areas; If the absolute value of the difference in longitude or latitude between any two poles is greater than 3 minutes, then the distance between the two poles will be set to 0. If the absolute value of the difference in longitude or latitude between any two pairs is less than 3 minutes, then calculate the straight-line distance between the two pairs. If the straight-line distance between any two towers is greater than 5 km, then the distance between the two towers will be set to 0. If the straight-line distance between any two poles is less than 5 km, then the distances of all poles that meet the condition form a spatial matrix. The Leuven algorithm is used to perform optimal community partitioning on the spatial matrix to obtain multiple new target regions.

7. A transmission line inspection route planning system based on multi-source data fusion, characterized in that, The system includes: The acquisition unit is used to acquire the latitude and longitude data of any target tower, the vehicle trajectory data from the vehicle's starting point to the vehicle's boarding and alighting point at the target tower, and the walking trajectory data of the patrol personnel from the boarding and alighting point to the target tower, taking any target tower as the target tower. The first calculation unit is used to calculate the trajectory set and time set of a single person inspecting a single tower based on the data in step S1 and the first path planning model. The second calculation unit is used to repeat steps S1 and S2 to calculate the trajectory set and time set of a single person inspecting multiple towers; The third calculation unit is used to calculate the optimal path and total time for a single person to patrol a single line based on the path trajectory set, time set, and second path planning model obtained from S3. The fourth calculation unit is used to calculate the optimal trajectory set and time set for multiple personnel patrolling the same target area using the k-means clustering algorithm and the second path planning model. This includes: S501: Randomly selecting K poles within the target area, the same number as the number of patrol personnel, as initial cluster points; S502: For each other pole within the target area, calculating its patrol time to each initial cluster point, and assigning it to the set of initial cluster points with the shortest patrol time, resulting in K cluster sets; S503: Calculating the optimal path and total time for each cluster set using the second path planning model; S504: Adding the total time for each cluster set to the patrol time of the corresponding patrol personnel to calculate the optimal trajectory set for each patrol personnel. Working time; S505: Compare the working time of each patrolman with the preset working time; S506: If it is less than the preset working time, and the variance of the highest and lowest working time is less than the preset variance time, then the optimal trajectory set and time set for multiple patrols of multiple towers in the same target area are obtained; S507: If the condition of S506 is not met, then randomly select a tower from the cluster set with the highest working time and put it into the cluster set with the lowest working time, and repeat steps S503-S506 for the preset number of times. If the repetition ends and the condition of S506 is still not met, then the result with the smallest mean squared error of the total time consumption of each cluster set in the repeated iterations is determined as the optimal trajectory set and time set for multiple patrols of multiple towers in the same target area.

8. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the steps of the method described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method described in any one of claims 1-6.

Images