Transmission line inspection path optimization method and system

Abstract

This scheme relates to a method and system for optimizing the inspection path of a transmission line. The method includes: constructing a transmission line inspection model and constraints; obtaining the minimum number of inspection groups according to the transmission line inspection model; optimizing the inspection path of each inspection group based on the minimum number of inspection groups and the transmission line inspection model through an improved K-Means algorithm and a hybrid genetic simulated annealing algorithm to obtain an optimized inspection path; calculating the total inspection time of each inspection group and adjusting the inspection nodes in the inspection group; optimizing the inspection path of the adjusted inspection group again according to the hybrid genetic simulated annealing algorithm until the optimal path is obtained. By combining the hybrid genetic simulated annealing algorithm and the improved K-Means algorithm, the inspection paths of multiple inspection groups can be planned, and the workload of each inspection group can be balanced, thereby improving the inspection efficiency of the transmission line.

Description

Technical Field

[0001] The present invention relates to the technical field of power transmission line inspection, and in particular to a method and system for optimizing a power transmission line inspection path. Background Art

[0002] The transmission line is realized by using a transformer to step up the voltage of the electric energy generated by the generator, and then connecting it to the transmission line through control equipment such as circuit breakers. According to the structural form, the existing transmission lines can be divided into overhead transmission lines and cable lines. Daily inspection of transmission lines is a basic and important task to ensure reliable power supply. In recent years, unmanned aerial vehicles (UAVs) have been used instead of manual inspections. Since UAV inspections are limited by the control range and endurance of remote control, they cannot perform ultra-long-distance flights and long-term inspections. In addition, the inspection tasks of transmission lines are large in volume, and generally multiple inspection teams need to be assigned to complete the inspection tasks. Therefore, it is necessary to plan the inspection routes of multiple inspection teams to reduce working time and ensure that UAVs can efficiently complete inspection tasks within the energy consumption range.

[0003] However, in traditional transmission line inspection route planning, especially in multi-inspection group route planning, the workload of each inspection group may be unbalanced, which may lead to low inspection efficiency or even inability to complete the inspection task. Therefore, traditional transmission line inspection has the problem of low inspection efficiency. Summary of the invention

[0004] Based on this, in order to solve the above technical problems, a method and system for optimizing the inspection path of a transmission line are provided, which can improve the inspection efficiency of the transmission line.

[0005] A method for optimizing a transmission line inspection path, the method comprising:

[0006] Acquire an inspection starting node and an inspection target node, and construct a transmission line inspection model according to the inspection starting node and the inspection target node, and construct constraint conditions for the transmission line inspection model;

[0007] Obtaining the minimum number of inspection groups according to the transmission line inspection model;

[0008] Based on the minimum number of inspection groups and the transmission line inspection model, the inspection path of each inspection group is optimized by using an improved K-Means algorithm and a hybrid genetic simulated annealing algorithm to obtain an optimized inspection path;

[0009] Calculating the total inspection time of each inspection group according to the optimized inspection path, and adjusting the inspection nodes in the inspection group according to each total inspection time to obtain an adjusted inspection group;

[0010] The adjusted inspection group is again subjected to inspection path optimization according to the hybrid genetic simulated annealing algorithm until an optimal path is obtained.

[0011] In one of the embodiments, the transmission line inspection model description formula is: G = (N, S, T), where G represents the constructed transmission line inspection model; N represents the node set consisting of the inspection departure node and the inspection target node, N = {n0, n1, n2,, ..., n n}, n0 represents the inspection departure node; S represents the edge set, S ij ={(n i , n j )|n1,n2∈N,i≠j},S ij Represents node n i and n j The edges between them; T represents the travel time matrix, T = R (n+1)×(n+1) , the element T in T ij Represents slave node n i to n j Journey time.

[0012] In one embodiment, the constraint is defined as: in,

[0013] Ensure that the number of inspection groups is k:

[0014] Ensure that there is only one visited node before any inspection target node is visited, and there is only one node to be visited afterwards:

[0015] Eliminate sub-loops using MTZ constraints: Among them, u i represents the level of sequential access to the inspection target node i, and q represents the maximum number of inspections that can be performed by any inspection group;

[0016] t p <t max , where t p represents the inspection distance and total time required by the pth inspection group, where p∈{1, 2, ..., k}, k is the number of inspection groups, and the total time required by each inspection group cannot exceed the maximum working time t max ;

[0017] t md <β, where t md It represents the maximum difference in the total time required by each inspection group, and β represents the threshold of the maximum difference in working time between inspection groups.

[0018] In one embodiment, the minimum number of inspection groups k is defined as:

[0019] in, (t tr +nt c ) / t max =1,t tr represents the optimal path time of a single inspection group, t av represents the average round-trip time from the inspection starting node to each inspection target node; t c It represents the time required for UAV to inspect the transmission line. The time required for a single inspection team to complete the task is t tr +nt c ;t max Indicates the maximum working time of the UAV.

[0020] In one embodiment, the inspection path of each inspection group is optimized according to the hybrid genetic simulated annealing algorithm to obtain the optimized inspection path, including:

[0021] Initialize parameters, including population size k, crossover probability pc, mutation probability pn, and initial temperature T0;

[0022] The population is initialized by random generation, and the fitness of the individuals in the population is calculated according to the constraint conditions; wherein the initialized population is P0;

[0023] Perform a selection operation on the current population, select the individuals with the top 10% fitness as P1, and directly copy them into the next generation as the best individuals, and the remaining individuals enter the crossover mutation operation;

[0024] After performing crossover and mutation operations on the current population, population P2 is obtained; after performing simulated annealing operations on the current population, P3 is obtained;

[0025] The optimal individual population P1 and the solution P3 generated by hybrid genetic simulated annealing are merged into a new population P4;

[0026] The termination condition of population P4 is judged according to the constraints. If the condition is met, the optimized inspection path is output. If not, the current population is crossover, mutation, and simulated annealing are performed again, and a new population P4 is synthesized again until the optimized inspection path is output.

[0027] In one embodiment, when performing a crossover operation on the current population, a two-point crossover is used, including:

[0028] Two points are randomly selected on the parent chromosome according to the crossover probability, namely point 1 and point 2, and the middle part of the crossover point 1 and point 2 is exchanged. After the crossover, the genes in the middle part of point 1 and point 2 are kept unchanged, and the gene conflict detection and correction are performed on the two parts before point 1 and after point 2 of the offspring chromosome, including:

[0029] The mapping relationship between gene points is obtained based on the middle part of intersection point 1 and point 2, and the offspring chromosome is corrected in the order from the first node to intersection point 1, and from intersection point 2 to the end. It is determined whether each node conflicts with the gene after the crossover, and the correction is made according to the mapping relationship.

[0030] In one embodiment, when performing a mutation operation on the current population, a two-point transformation mutation is adopted, including:

[0031] The chromosomes are traversed, and each gene is determined once whether it mutates based on the mutation probability;

[0032] If the gene position mutates, a gene at another position on the chromosome is randomly selected and the two are exchanged.

[0033] In one embodiment, the inspection path of each inspection group is optimized by using an improved K-Means algorithm and a hybrid genetic simulated annealing algorithm to obtain an optimized inspection path, including:

[0034] Initialize parameters, including total time The initial value is infinite, and the maximum number of iterations is N. max , and parameters in the hybrid genetic simulated annealing algorithm;

[0035] Perform initial classification, randomly select k inspection target nodes to add to k sets, and fill other nodes into the sets according to the shortest path length to the selected k nodes;

[0036] According to the hybrid genetic simulated annealing algorithm, the inspection path of each inspection group is optimized to obtain an optimized inspection path.

[0037] In one embodiment, the total inspection time of each inspection group is calculated according to the optimized inspection path, and the inspection nodes in the inspection group are adjusted according to each total inspection time to obtain an adjusted inspection group, and the inspection path of the adjusted inspection group is optimized again according to the hybrid genetic simulated annealing algorithm until the optimal path is obtained, including:

[0038] Step 1: Calculate the total inspection time t of each inspection group total ;

[0039] Step 2: If each inspection team takes time tp The maximum difference in time spent between inspection groups does not exceed the set threshold, and t diff Does not exceed the set threshold, and the total time t total If it is less than the value calculated in the previous iteration, the current value is taken as the optimization result and step 5 is performed;

[0040] Step 3: If the maximum difference value t diff The inspection team spends time t p If only one of the constraints is satisfied, the optimization result obtained in the previous iteration is retained and step five is performed;

[0041] Step 4: If the maximum difference value t diff The inspection team spends time t p The constraints of t are not met, but the current total time is less than the result of the previous iteration, and t p If the standard deviation of is less than the standard deviation of the previous iteration result, the current value is taken as the optimization result and step 5 is performed;

[0042] Step 5: Randomly select a target node from the inspection group with the longest time, move it to the group with the shortest time, and repeat steps 1 to 4; when the number of iterations reaches the maximum value N max , the current result is taken as the final optimization result.

[0043] A transmission line inspection path optimization system, applied to a drone, comprising:

[0044] A construction module, used to obtain an inspection starting node and an inspection target node, and to construct a transmission line inspection model according to the inspection starting node and the inspection target node, and to construct constraint conditions for the transmission line inspection model;

[0045] An inspection group quantity calculation module, used to obtain the minimum number of inspection groups according to the transmission line inspection model;

[0046] An inspection path optimization module is used to optimize the inspection path of each inspection group based on the minimum number of inspection groups and the transmission line inspection model through an improved K-Means algorithm and a hybrid genetic simulated annealing algorithm to obtain an optimized inspection path;

[0047] An inspection group adjustment module is used to calculate the total inspection time of each inspection group according to the optimized inspection path, and adjust the inspection nodes in the inspection group according to each total inspection time to obtain an adjusted inspection group;

[0048] The optimal path acquisition module is used to optimize the inspection path of the adjusted inspection group again according to the hybrid genetic simulated annealing algorithm until the optimal path is obtained.

[0049] The above-mentioned transmission line inspection path optimization method and system obtains the inspection starting node and the inspection target node, and constructs a transmission line inspection model according to the inspection starting node and the inspection target node, and constructs constraints for the transmission line inspection model; obtains the minimum number of inspection groups according to the transmission line inspection model; based on the minimum number of inspection groups and the transmission line inspection model, optimizes the inspection path of each inspection group through an improved K-Means algorithm and a hybrid genetic simulated annealing algorithm to obtain an optimized inspection path; calculates the total inspection time of each inspection group according to the optimized inspection path, and adjusts the inspection nodes in the inspection group according to each total inspection time to obtain an adjusted inspection group; and optimizes the inspection path of the adjusted inspection group again according to the hybrid genetic simulated annealing algorithm until the optimal path is obtained. By constructing a transmission line inspection model and constraints, and then solving the theoretical minimum number of inspection groups, combined with a hybrid genetic simulated annealing algorithm and an improved K-Means algorithm, the inspection paths of multiple inspection groups can be planned, and the workload of each inspection group can be balanced. The minimum number of inspection groups can be used to efficiently complete the inspection task of the transmission line, thereby improving the inspection efficiency of the transmission line. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A diagram showing an application environment of a method for optimizing a power transmission line inspection path in an embodiment;

[0051] Figure 2 A schematic diagram of a flow chart of a method for optimizing a power transmission line inspection path in one embodiment;

[0052] Figure 3 A schematic diagram of a hybrid genetic simulated annealing algorithm process in one embodiment;

[0053] Figure 4 An example diagram of two points crossing in one embodiment;

[0054] Figure 5 An example diagram of gene conflict detection and correction in one embodiment;

[0055] Figure 6 The structure block diagram of a transmission line inspection path optimization system in one embodiment. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0057] The power transmission line inspection path optimization method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Figure 1 As shown, the application environment includes a drone 110. The drone 110 can obtain the inspection starting node and the inspection target node, and construct a transmission line inspection model according to the inspection starting node and the inspection target node, and construct constraints for the transmission line inspection model; the drone 110 can obtain the minimum number of inspection groups according to the transmission line inspection model; the drone 110 can optimize the inspection path of each inspection group based on the minimum number of inspection groups and the transmission line inspection model through the improved K-Means algorithm and the hybrid genetic simulated annealing algorithm to obtain an optimized inspection path; the drone 110 can calculate the total inspection time of each inspection group according to the optimized inspection path, and adjust the inspection nodes in the inspection group according to the total inspection time to obtain an adjusted inspection group; the drone 110 can optimize the inspection path of the adjusted inspection group again according to the hybrid genetic simulated annealing algorithm until the optimal path is obtained.

[0058] In one embodiment, Figure 2 As shown, a method for optimizing a transmission line inspection path is provided, comprising the following steps:

[0059] Step 202: Obtain an inspection starting node and an inspection target node, build a transmission line inspection model based on the inspection starting node and the inspection target node, and build constraint conditions for the transmission line inspection model.

[0060] The drone can obtain the inspection starting node and the inspection target node through the computer program stored inside, where one inspection starting node can correspond to multiple inspection target nodes. When the drone inspects the transmission line, it starts from the inspection starting node, arrives at the inspection target nodes in sequence along the inspection path, and then returns to the inspection starting node. After obtaining the inspection starting node and the inspection target node, the transmission line inspection model and constraint conditions can be constructed.

[0061] Step 204, obtaining the minimum number of inspection groups according to the transmission line inspection model.

[0062] Among them, a drone can be used as an inspection group to inspect the transmission line at each inspection target node. The transmission line inspection model can include a node set consisting of each inspection target node, the travel time of the drone from the inspection starting node to the inspection target node, and other inspection data for calculating the minimum number of inspection groups.

[0063] Step 206, based on the minimum number of inspection groups and the transmission line inspection model, the inspection path of each inspection group is optimized by using an improved K-Means algorithm and a hybrid genetic simulated annealing algorithm to obtain an optimized inspection path.

[0064] Step 208 , calculating the total inspection time of each inspection group according to the optimized inspection path, and adjusting the inspection nodes in the inspection group according to each total inspection time to obtain an adjusted inspection group.

[0065] Step 210, the adjusted inspection group is again optimized for the inspection path according to the hybrid genetic simulated annealing algorithm until the optimal path is obtained.

[0066] In this embodiment, by constructing a transmission line inspection model and constraints, and then solving for the theoretical minimum number of inspection groups, combined with a hybrid genetic simulated annealing algorithm and an improved K-Means algorithm, the inspection paths of multiple inspection groups can be planned, and the workload of each inspection group can be balanced. The minimum number of inspection groups can be used to efficiently complete the inspection task of the transmission line, thereby improving the inspection efficiency of the transmission line.

[0067] In one embodiment, the transmission line inspection model description formula is: G = (N, S, T), where G represents the constructed transmission line inspection model; N represents a node set consisting of an inspection departure node and an inspection target node, and N = {n0, n1, n2, ..., n n}, n0 represents the inspection departure node; S represents the edge set, S ij ={(n i , n j )|n1,n2∈N,i≠j},S ij Represents node n i and n j The edges between them; T represents the travel time matrix, T = R (n+1)×(n+1) , the element T in T ij Represents slave node n i to n j Journey time.

[0068] In one embodiment, the constraints are defined as: in, Ensure that the number of inspection groups is k: Ensure that there is only one visited node before any inspection target node is visited, and there is only one node to be visited afterwards: Eliminate sub-loops using MTZ constraints: Among them, u irepresents the level of sequential access to the inspection target node i, q represents the maximum number of inspections that can be performed by any inspection group; t p <t max , where t p represents the inspection distance and total time required by the pth inspection group, where p∈{1, 2, ..., k}, k is the number of inspection groups, and the total time required by each inspection group cannot exceed the maximum working time t max ;t md <β, where t md It represents the maximum difference in the total time required by each inspection group, and β represents the threshold of the maximum difference in working time between inspection groups.

[0069] In one embodiment, the minimum number of inspection groups k is defined as: in, (t tr +nt c ) / t max =1,t tr represents the optimal path time of a single inspection group, t av represents the average round-trip time from the inspection starting node to each inspection target node; t c It represents the time required for UAV to inspect the transmission line. The time required for a single inspection team to complete the task is t tr +nt c ;t max Indicates the maximum working time of the UAV, which is usually 8 hours.

[0070] In one embodiment, Figure 3 As shown, a transmission line inspection path optimization method provided may also include a process of performing path planning according to a hybrid genetic simulated annealing algorithm, and the specific process includes: initializing parameters, the parameters include population size k, crossover probability pc, mutation probability pn, and initial temperature T0; initializing the population by random generation, and calculating the fitness of the individuals in the population according to the constraint conditions; wherein the initialized population is P0; performing a selection operation on the current population, selecting individuals with fitness in the top 10% as P1, and directly copying them into the next generation as the optimal individuals, and the remaining individuals enter the crossover and mutation operation; performing crossover and mutation operations on the current population to obtain population P2; performing simulated annealing operations on the current population to obtain P3; merging the optimal individual population P1 and the solution P3 generated by hybrid genetic simulated annealing into a new population P4; judging the termination conditions of population P4 according to the constraints, if the conditions are met, outputting the optimized inspection path, if not, performing crossover, mutation, and simulated annealing operations on the current population again, and synthesizing a new population P4 again until the optimized inspection path is output.

[0071] In one embodiment, when performing a crossover operation on the current population, a two-point crossover is used, specifically including: Figure 4 As shown, two points are randomly selected on the parent chromosome according to the crossover probability, namely point 1 and point 2, and the middle part of the crossover point 1 and point 2 is exchanged. After the crossover, the genes in the middle part of point 1 and point 2 are kept unchanged, and the gene conflict detection and correction are performed on the two parts before point 1 and after point 2 of the offspring chromosome, as shown in Figure 5 As shown, it specifically includes: obtaining the mapping relationship between gene points according to the middle part of intersection point 1 and point 2, correcting the offspring chromosomes, and the order is from the first node to intersection point 1, and from intersection point 2 to the end, judging whether each node conflicts with the gene after the crossover, and correcting it according to the mapping relationship.

[0072] In one embodiment, when performing a mutation operation on the current population, a two-point transformation mutation is used, specifically including: traversing the chromosomes, determining whether each gene has mutated once based on the mutation probability; if the gene position mutates, randomly selecting a gene at another position of the chromosome and exchanging the two.

[0073] In one embodiment, the provided transmission line inspection path optimization method may also include a process of optimizing the inspection path of each inspection group by using an improved K-Means algorithm and a hybrid genetic simulated annealing algorithm. The specific process includes: initializing parameters, including the total time The initial value is infinite, and the maximum number of iterations is N. max , and the parameters in the hybrid genetic simulated annealing algorithm; perform initial classification, randomly select k inspection target nodes to add to k sets, and fill other nodes into the sets according to the shortest path length with the selected k nodes; according to the hybrid genetic simulated annealing algorithm, optimize the inspection path of each inspection group to obtain the optimized inspection path.

[0074] In one embodiment, a transmission line inspection path optimization method provided may further include a process of obtaining an optimal path, and the specific process includes:

[0075] Step 1: Calculate the total inspection time t of each inspection group total ;

[0076] Step 2: If each inspection team takes time t p The maximum difference in time spent between inspection groups does not exceed the set threshold, and t diff Does not exceed the set threshold, and the total time t total If it is less than the value calculated in the previous iteration, the current value is taken as the optimization result and step 5 is performed;

[0077] Step 3: If the maximum difference value t diffThe inspection team spends time t p If only one of the constraints is satisfied, the optimization result obtained in the previous iteration is retained and step five is performed;

[0078] Step 4: If the maximum difference value t diff The inspection team spends time t p The constraints of t are not met, but the current total time is less than the result of the previous iteration, and t p If the standard deviation of is less than the standard deviation of the previous iteration result, the current value is taken as the optimization result and step 5 is performed;

[0079] Step 5: Randomly select a target node from the inspection group with the longest time, move it to the group with the shortest time, and repeat steps 1 to 4; when the number of iterations reaches the maximum value N max , the current result is taken as the final optimization result.

[0080] It should be understood that, although the various steps in the above-mentioned flow chart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the above-mentioned flow chart may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0081] In one embodiment, Figure 6 As shown, a transmission line inspection path optimization system is provided, which is applied to UAVs, including: a construction module 610, an inspection group number calculation module 620, an inspection path optimization module 630, an inspection group adjustment module 640 and an optimal path acquisition module 650, wherein:

[0082] A construction module 610 is used to obtain an inspection starting node and an inspection target node, and to construct a transmission line inspection model according to the inspection starting node and the inspection target node, and to construct constraint conditions for the transmission line inspection model;

[0083] The inspection group number calculation module 620 is used to obtain the minimum number of inspection groups according to the transmission line inspection model;

[0084] The inspection path optimization module 630 is used to optimize the inspection path of each inspection group based on the minimum number of inspection groups and the transmission line inspection model through an improved K-Means algorithm and a hybrid genetic simulated annealing algorithm to obtain an optimized inspection path;

[0085] The inspection group adjustment module 640 is used to calculate the total inspection time of each inspection group according to the optimized inspection path, and adjust the inspection nodes in the inspection group according to each total inspection time to obtain an adjusted inspection group;

[0086] The optimal path acquisition module 650 is used to optimize the inspection path of the adjusted inspection group again according to the hybrid genetic simulated annealing algorithm until the optimal path is obtained.

[0087] In one embodiment, the construction module 610 is also used to construct a transmission line inspection model. The transmission line inspection model description formula is: G = (N, S, T), where G represents the constructed transmission line inspection model; N represents a node set consisting of the inspection departure node and the inspection target node, N = {n0, n1, n2,, ..., n n}, n0 represents the inspection departure node; S represents the edge set, S ij ={(n i , n j )|n1,n2∈N,i≠j},S ij Represents node n i and n j The edges between them; T represents the travel time matrix, T = R (n+1)×(n+1) , the element T in T ij Represents slave node n i to n j Journey time.

[0088] In one embodiment, the construction module 610 is further used to construct a constraint condition, where the constraint condition is defined as: in, Ensure that the number of inspection groups is k: Ensure that there is only one visited node before any inspection target node is visited, and there is only one node to be visited afterwards: Eliminate sub-loops using MTZ constraints: Among them, u i represents the level of sequential access to the inspection target node i, q represents the maximum number of inspections that can be performed by any inspection group; t p <t max , where t p represents the inspection distance and total time required by the pth inspection group, where p∈{1, 2, ..., k}, k is the number of inspection groups, and the total time required by each inspection group cannot exceed the maximum working time t max ;t md <β, where t mdIt represents the maximum difference in the total time required by each inspection group, and β represents the threshold of the maximum difference in working time between inspection groups.

[0089] In one embodiment, the inspection group number calculation module 620 is further used to define a minimum number of inspection groups, and the minimum number of inspection groups k is defined as: in, (t tr +nt c ) / t max =1,t tr represents the optimal path time of a single inspection group, t av represents the average round-trip time from the inspection starting node to each inspection target node; t c It represents the time required for UAV to inspect the transmission line. The time required for a single inspection team to complete the task is t tr +nt c ;t max Indicates the maximum working time of the UAV.

[0090] In one embodiment, the inspection path optimization module 630 is also used to initialize parameters, including population size k, crossover probability pc, mutation probability pn, and initial temperature T0; the population is initialized by random generation, and the fitness of the individuals in the population is calculated according to the constraint conditions; wherein the initialized population is P0; a selection operation is performed on the current population, and the individuals with the top 10% fitness are selected as P1, which are directly copied into the next generation as the optimal individuals, and the remaining individuals enter the crossover and mutation operations; after performing crossover and mutation operations on the current population, population P2 is obtained; simulated annealing operations are performed on the current population to obtain P3; the optimal individual population P1 and the solution P3 generated by hybrid genetic simulated annealing are merged into a new population P4; the termination condition of population P4 is judged according to the constraints, and if the conditions are met, the optimized inspection path is output, if not, the current population is again subjected to crossover, mutation, and simulated annealing operations, and a new population P4 is synthesized again until the optimized inspection path is output.

[0091] In one embodiment, the inspection path optimization module 630 is also used to use two-point crossover when performing a crossover operation on the current population, including: randomly selecting two points on the parent chromosome according to the crossover probability, namely point 1 and point 2, exchanging the middle part of crossover point 1 and point 2, keeping the genes in the middle part of point 1 and point 2 unchanged after crossover, and performing gene conflict detection and correction on the two parts before point 1 and after point 2 of the offspring chromosome, including: obtaining the mapping relationship between gene points according to the middle part of crossover point 1 and point 2, and correcting the offspring chromosome in the order from the first node to crossover point 1, from crossover point 2 to the end, judging whether each node conflicts with the gene after the crossover, and correcting it according to the mapping relationship.

[0092] In one embodiment, the inspection path optimization module 630 is also used to use two-point transformation mutation when performing mutation operations on the current population, including: traversing the chromosome, determining whether each gene has mutated once based on the mutation probability; if the gene position mutates, randomly selecting a gene at another position of the chromosome and exchanging the two.

[0093] In one embodiment, the optimal path acquisition module 650 is also used to initialize parameters, including the total time The initial value is infinite, and the maximum number of iterations is N. max , and the parameters in the hybrid genetic simulated annealing algorithm; perform initial classification, randomly select k inspection target nodes to add to k sets, and fill other nodes into the sets according to the shortest path length with the selected k nodes; according to the hybrid genetic simulated annealing algorithm, optimize the inspection path of each inspection group to obtain the optimized inspection path.

[0094] In one embodiment, the optimal path acquisition module 650 is further configured to perform the following steps: Step 1: Calculate the total inspection time t of each inspection group. total ; Step 2, if each inspection group takes time t p The maximum difference in time spent between inspection groups does not exceed the set threshold, and t diff Does not exceed the set threshold, and the total time t total If the maximum difference value t is less than the value calculated in the previous iteration, the current value is taken as the optimization result and step 5 is performed; in step 3, if the maximum difference value t diff The inspection team spends time t p If only one of the constraints is satisfied, the optimization result obtained in the previous iteration is retained and step 5 is performed; in step 4, if the maximum difference value t diff The inspection team spends time t p The constraints of t are not met, but the current total time is less than the result of the previous iteration, and t p If the standard deviation of is less than the standard deviation of the previous iteration result, the current value is taken as the optimization result and step five is performed; in step five, a target node is randomly selected from the inspection group set with the longest time, and it is moved to the set with the shortest time, and steps one to four are repeated; when the number of iterations reaches the maximum value N max , the current result is taken as the final optimization result.

[0095] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program inside the drone, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0096] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0097] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for optimizing a transmission line inspection path, characterized in that: The method comprises: Obtain an inspection starting node and an inspection target node, and construct a transmission line inspection model according to the inspection starting node and the inspection target node, and construct constraint conditions for the transmission line inspection model; wherein the transmission line inspection model description formula is: G = (N, S, T), wherein G represents the constructed transmission line inspection model; N represents a node set consisting of the inspection starting node and the inspection target node, N = {n0, n1, n2,, ..., n n }, n0 represents the inspection departure node; S represents the edge set, S ij ={(n i ,n j )|n1,n2∈N,i≠j},S ij Represents node n i and n j The edges between them; T represents the travel time matrix, T = R (n+1)×(n+1) , the elements contained in T are represented by T ij Represents that, and the element T ij Represents slave node n i to n j The travel time is: in, Ensure that the number of inspection groups is k: Ensure that there is only one visited node before any inspection target node is visited, and there is only one node to be visited afterwards: Eliminate sub-loops using MTZ constraints: Among them, u i represents the level of sequential access to the inspection target node i, q represents the maximum number of inspections that can be performed by any inspection group; t p <t max , where t p represents the inspection distance and total time required by the pth inspection group, where p∈{1,2,...,k}, k is the number of inspection groups, and the total time required by each inspection group cannot exceed the maximum working time t max ;t md <β, where t md It represents the maximum difference in the total time required by each inspection group, and β represents the threshold value of the maximum difference in working time between inspection groups; The minimum number of inspection groups is obtained according to the transmission line inspection model; the minimum number of inspection groups k is defined as: in, (t tr +nt c ) / t max =1,t tr represents the optimal path time of a single inspection group, t av represents the average round-trip time from the inspection starting node to each inspection target node; t c It represents the time required for UAV to inspect the transmission line. The time required for a single inspection team to complete the task is t tr +nt c ;t max Indicates the maximum working time of the UAV; Based on the minimum number of inspection groups and the transmission line inspection model, the inspection path of each inspection group is optimized by an improved K-Means algorithm and a hybrid genetic simulated annealing algorithm to obtain an optimized inspection path, including: initializing parameters, including the total time The initial value is infinite, and the maximum number of iterations is N. max , and the parameters in the hybrid genetic simulated annealing algorithm; perform initial classification, randomly select k inspection target nodes to add to k sets, and fill other nodes into the sets according to the shortest path length with the selected k nodes; optimize the inspection path of each inspection group according to the hybrid genetic simulated annealing algorithm to obtain the optimized inspection path; Calculating the total inspection time of each inspection group according to the optimized inspection path, and adjusting the inspection nodes in the inspection group according to each total inspection time to obtain an adjusted inspection group; The adjusted inspection group is again subjected to inspection path optimization according to the hybrid genetic simulated annealing algorithm until an optimal path is obtained.

2. The method for optimizing the inspection path of a power transmission line according to claim 1, characterized in that: The method of optimizing the inspection path of each inspection group according to the hybrid genetic simulated annealing algorithm to obtain the optimized inspection path includes: Initialize parameters, including population size k, crossover probability pc, mutation probability pn, and initial temperature T0; The population is initialized by random generation, and the fitness of the individuals in the population is calculated according to the constraint conditions; wherein the initialized population is P0; Perform a selection operation on the current population, select the individuals with the top 10% fitness as P1, and directly copy them into the next generation as the best individuals, and the remaining individuals enter the crossover mutation operation; After performing crossover and mutation operations on the current population, population P2 is obtained; after performing simulated annealing operations on the current population, P3 is obtained; The optimal individual population P1 and the solution P3 generated by hybrid genetic simulated annealing are merged into a new population P4; The termination condition of population P4 is judged according to the constraints. If the condition is met, the optimized inspection path is output. If not, the current population is crossover, mutation, and simulated annealing are performed again, and a new population P4 is synthesized again until the optimized inspection path is output.

3. The method for optimizing the inspection path of a power transmission line according to claim 2, characterized in that: When performing a crossover operation on the current population, a two-point crossover is used, including: Two points are randomly selected on the parent chromosome according to the crossover probability, namely point 1 and point 2, and the middle part of the crossover point 1 and point 2 is exchanged. After the crossover, the genes in the middle part of point 1 and point 2 are kept unchanged, and the gene conflict detection and correction are performed on the two parts before point 1 and after point 2 of the offspring chromosome, including: The mapping relationship between gene points is obtained based on the middle part of intersection point 1 and point 2, and the offspring chromosome is corrected in the order from the first node to intersection point 1, and from intersection point 2 to the end. It is determined whether each node conflicts with the gene after the crossover, and the correction is made according to the mapping relationship.

4. The method for optimizing the inspection path of a power transmission line according to claim 2, characterized in that: When performing mutation operation on the current population, two-point transformation mutation is adopted, including: The chromosomes are traversed, and each gene is determined once whether it mutates based on the mutation probability; If the gene position mutates, a gene at another position on the chromosome is randomly selected and the two are exchanged.

5. The method for optimizing the inspection path of a power transmission line according to claim 1, characterized in that: The total inspection time of each inspection group is calculated according to the optimized inspection path, and the inspection nodes in the inspection group are adjusted according to each total inspection time to obtain an adjusted inspection group, and the inspection path of the adjusted inspection group is optimized again according to the hybrid genetic simulated annealing algorithm until the optimal path is obtained, including: Step 1: Calculate the total inspection time t of each inspection group total ; Step 2: If each inspection team takes time t p The maximum difference in time spent between inspection groups does not exceed the set threshold, and t diff Does not exceed the set threshold, and the total time t total If it is less than the value calculated in the previous iteration, the current value is taken as the optimization result and step 5 is performed; Step 3: If the maximum difference value t diff The inspection team spends time t p If only one of the constraints is satisfied, the optimization result obtained in the previous iteration is retained and step five is performed; Step 4: If the maximum difference value t diff The inspection team spends time t p The constraints of t are not met, but the current total time is less than the result of the previous iteration, and t p If the standard deviation of is less than the standard deviation of the previous iteration result, the current value is taken as the optimization result and step 5 is performed; Step 5: Randomly select a target node from the inspection group with the longest time, move it to the group with the shortest time, and repeat steps 1 to 4; when the number of iterations reaches the maximum value N max , the current result is taken as the final optimization result.

6. A transmission line inspection path optimization system, applied to drones, characterized in that: The system comprises: A construction module is used to obtain an inspection starting node and an inspection target node, and to construct a transmission line inspection model according to the inspection starting node and the inspection target node, and to construct constraint conditions for the transmission line inspection model; wherein the transmission line inspection model description formula is: G = (N, S, T), wherein G represents the constructed transmission line inspection model; N represents a node set consisting of the inspection starting node and the inspection target node, N = {n0, n1, n2,, ..., n n }, n0 represents the inspection departure node; S represents the edge set, S ij ={(n i ,n j )|n1,n2∈N,i≠j},S ij Represents node n i and n j The edges between them; T represents the travel time matrix, T = R (n+1)×(n+1) , the element T in T ij Represents slave node n i to n j The travel time is: in, Ensure that the number of inspection groups is k: Ensure that there is only one visited node before any inspection target node is visited, and there is only one node to be visited afterwards: Eliminate sub-loops using MTZ constraints: Among them, u i represents the level of sequential access to the inspection target node i, q represents the maximum number of inspections that can be performed by any inspection group; t p <t max , where t p represents the inspection distance and total time required by the pth inspection group, where p∈{1,2,...,k}, k is the number of inspection groups, and the total time required by each inspection group cannot exceed the maximum working time t max ;t md <β, where t md It represents the maximum difference in the total time required by each inspection group, and β represents the threshold value of the maximum difference in working time between inspection groups; The inspection group number calculation module is used to obtain the minimum number of inspection groups according to the transmission line inspection model; the minimum number of inspection groups k is defined as: in, (t tr +nt c ) / t max =1,t tr represents the optimal path time of a single inspection group, t av represents the average round-trip time from the inspection starting node to each inspection target node; t c It represents the time required for UAV to inspect the transmission line. The time required for a single inspection team to complete the task is t tr +nt c ;t max Indicates the maximum working time of the UAV; The inspection path optimization module is used to optimize the inspection path of each inspection group based on the minimum number of inspection groups and the transmission line inspection model through the improved K-Means algorithm and the hybrid genetic simulated annealing algorithm to obtain the optimized inspection path, including: initializing parameters, including the total time The initial value is infinite, and the maximum number of iterations is N. max , and the parameters in the hybrid genetic simulated annealing algorithm; perform initial classification, randomly select k inspection target nodes to add to k sets, and fill other nodes into the sets according to the shortest path length with the selected k nodes; optimize the inspection path of each inspection group according to the hybrid genetic simulated annealing algorithm to obtain the optimized inspection path; An inspection group adjustment module is used to calculate the total inspection time of each inspection group according to the optimized inspection path, and adjust the inspection nodes in the inspection group according to each total inspection time to obtain an adjusted inspection group; The optimal path acquisition module is used to optimize the inspection path of the adjusted inspection group again according to the hybrid genetic simulated annealing algorithm until the optimal path is obtained.

Images