Multi-specialty and multi-nest scheduling method based on power joint inspection and related device

Abstract

The invention discloses a multi-specialty and multi-nest scheduling method and related device based on electric power joint inspection, and the method comprises the steps: formulating the inspection strategy of each specialty of transmission, transformation and distribution to design an inspection plan, and integrating the inspection plan into an unmanned aerial vehicle joint inspection plan library to obtain an inspection task set; clustering a plurality of types of routing inspection tasks with similar features in the routing inspection task set by adopting a clustering algorithm to obtain a routing inspection flight task consisting of a plurality of devices; based on the established waypoint of the inspection flight task and the endurance time of the unmanned aerial vehicle, generating an inspection route of the unmanned aerial vehicle through a TSP algorithm; and based on the inspection route of the unmanned aerial vehicle, performing one-to-one matching on each inspection flight task and each unmanned aerial vehicle nest by adopting a greedy algorithm, and finally forming automatic scheduling of the unmanned aerial vehicle nest. The problems that in the prior art, routing inspection tasks are distributed unreasonably, cross-professional multi-nest routing inspection is not fully considered, and systematic and comprehensive research on the whole process of routing inspection operation is lacked are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power inspection, and particularly to a scheduling method and related devices for multiple specialties and multiple airframes based on power joint inspection. Background Art

[0002] With the rapid development of social economy, the power demand continues to climb, and the scale of the power system is also growing day by day. The traditional manual inspection method is difficult to meet the inspection requirements of such large scale and high efficiency. In recent years, unmanned aerial vehicles (UAVs) have been widely used in the field of power inspection due to their advantages such as flexibility, no terrain restrictions, and the ability to carry a variety of detection devices.

[0003] However, with the continuous expansion of the power system inspection scope, single UAV inspection also faces many challenges. Specifically, 1) The endurance of a single UAV is limited and it is difficult to cover a large inspection area; and when facing multiple different types of power facilities, a single UAV is difficult to quickly switch and coordinate between different tasks, and cannot give full play to the cluster advantages of UAVs. 2) In the field of UAV intelligent scheduling, although there have been some related researches and applications, the intelligent scheduling scheme for the joint inspection multi-airframe system of power transmission, transformation and distribution still needs to be improved. Most of the existing intelligent scheduling algorithms focus on single-objective optimization, such as only considering the shortest inspection time or the lowest cost, etc., without comprehensively considering various requirements of power inspection, such as inspection quality, importance level of power facilities, equipment failure risk and other factors. 3) In the current power inspection work, due to the large differences in inspection technical standards and methods among different specialties of power transmission, transformation and distribution, the lack of multi-specialty composite talents, the dispersion of resources and the lack of sharing mechanism, etc., the multi-specialty joint inspection of power transmission, transformation and distribution has not been effectively realized. Summary of the Invention

[0004] The present invention provides a scheduling method and related devices for multiple specialties and multiple airframes based on power joint inspection, which are used to solve the problems existing in the prior art that the inspection task allocation is unreasonable, the cross-specialty multi-airframe inspection tasks are not fully considered, and there is a lack of systematic and comprehensive research on the whole process of inspection operations.

[0005] In view of this, in the first aspect of the present invention, a scheduling method for multiple specialties and multiple airframes based on power joint inspection is provided, and the method includes:

[0006] S1. Formulate inspection strategies for each specialty of power transmission, transformation and distribution, design inspection plans for each specialty of power transmission, transformation and distribution according to the inspection strategies, and integrate the inspection plans for each specialty of power transmission, transformation and distribution into the UAV joint inspection plan library to obtain an inspection task set;

[0007] S2. Use a clustering algorithm to cluster several inspection tasks with similar characteristics in the inspection task set to obtain inspection flight tasks composed of several devices;

[0008] S3. Generate an inspection route for the UAV through the TSP algorithm based on the established waypoints of the inspection flight mission and the endurance time of the UAV.

[0009] S4. Based on the inspection route of the UAV, use the greedy algorithm to match each of the inspection flight missions with each UAV nest one by one.

[0010] Optionally, step S2 includes:

[0011] Determine several similar features in the inspection task set, where the features include: distance from the nest, distribution area of inspection equipment, and proposed inspection date;

[0012] Perform standardization processing on each of the features;

[0013] Use the elbow method to confirm the value of k, where k is the number of clusters;

[0014] Generate k clusters according to the value of k and each of the features, and update the cluster centers of each cluster;

[0015] Output inspection flight missions consisting of several devices with similar distances from the nest, similar distribution areas of the inspection equipment, and similar proposed inspection dates through the K-Means clustering algorithm.

[0016] Optionally, step S3 includes:

[0017] Construct a route planning solution model according to the established waypoints of the inspection flight mission;

[0018] Among them, the expression of the route planning solution model is:

[0019]

[0020] In the formula, is the minimum value of the path from waypoint c1 to waypoint c n ; is the distance from the end point c n to the starting point c1 when the UAV returns for inspection;

[0021] Solve the minimum path value in the route planning solution model through the TSP algorithm, and obtain the route corresponding to the minimum path value to get the route with the shortest path as the initial inspection route of the UAV;

[0022] Conduct an inspection simulation on the UAV based on the initial inspection route to obtain the inspection completion time. If the inspection completion time is within the endurance time range of the UAV, it is used as the inspection route of the UAV. Otherwise, return to recluster the inspection tasks until each inspection flight mission can meet the flight duration requirement of a single UAV.

[0023] Optionally, step S4 includes:

[0024] Calculate the scouting ranges of the UAVs respectively according to the endurance times of the UAVs, and calculate the scouting ranges required for each of the inspection flight tasks;

[0025] Sort the scouting ranges of the UAVs and the scouting ranges required for each of the inspection flight tasks respectively;

[0026] Starting from the inspection flight task corresponding to the smallest required scouting range, select the UAV that meets the inspection flight task and wastes the least remaining scouting range, match it with the inspection flight task, and sequentially complete the matching of the remaining inspection flight tasks with the UAVs, so as to achieve a one-to-one matching of each of the inspection flight tasks with each UAV nest.

[0027] The second aspect of the present invention provides a scheduling system for multiple specialties and multiple nests based on power joint inspection, and the system includes:

[0028] A generating unit, configured to formulate inspection strategies for each specialty of power transmission, transformation and distribution, design inspection plans for each specialty of power transmission, transformation and distribution according to the inspection strategies, integrate the inspection plans for each specialty of power transmission, transformation and distribution into a UAV joint inspection plan library, and obtain an inspection task set;

[0029] A clustering unit, configured to cluster several inspection tasks with similar characteristics in the inspection task set by using a clustering algorithm to obtain inspection flight tasks composed of several devices;

[0030] A solving unit, configured to generate inspection routes of the UAVs through a TSP algorithm based on the established waypoints of the inspection flight tasks and the endurance time of the UAVs;

[0031] A matching unit, configured to perform a one-to-one matching of each of the inspection flight tasks with each UAV nest by using a greedy algorithm based on the inspection routes of the UAVs.

[0032] Optionally, the clustering unit is specifically configured to:

[0033] Determine several similar characteristics in the inspection task set, and the characteristics include: distance from the nest, distribution area of inspection equipment, and planned inspection date;

[0034] Perform standardization processing on each of the characteristics;

[0035] Use the elbow method to confirm the value of k, where k is the number of clusters;

[0036] Generate k clusters according to the value of k and each of the characteristics, and update the cluster centers of each cluster;

[0037] Output an inspection flight mission consisting of several devices with distances close to the nest, distribution areas close to the inspection equipment, and inspection dates close to the planned inspection dates through the K-Means clustering algorithm.

[0038] Optionally, the solving unit is specifically configured to:

[0039] Construct a route planning solution model according to the established waypoints of the inspection flight mission;

[0040] Among them, the expression of the route planning solution model is:

[0041]

[0042] In the formula, is the minimum path value from waypoint c1 to waypoint c n , is the distance from the end point c n to the starting point c1 when the UAV returns for inspection;

[0043] Solve the minimum path value in the route planning solution model through the TSP algorithm, and obtain the route corresponding to the minimum path value, and obtain the shortest route as the initial inspection route of the UAV;

[0044] Based on the initial inspection route, perform inspection simulation on the UAV to obtain the inspection completion time. If the inspection completion time is within the endurance time range of the UAV, it is used as the inspection route of the UAV. Otherwise, return to re-cluster the inspection task until each inspection flight task can meet the flight duration requirements of a single UAV.

[0045] Optionally, the matching unit is specifically configured to:

[0046] Calculate the visible range of each UAV according to the endurance time of each UAV, and calculate the required inspection range of each inspection flight task;

[0047] Sort the visible ranges of each UAV and the required inspection ranges of each inspection flight task respectively;

[0048] Starting from the inspection flight task corresponding to the smallest required inspection range, select the UAV that meets the inspection flight task and wastes the least remaining inspection range, match it with the inspection flight task, and sequentially complete the matching of the remaining inspection flight tasks and each UAV, so as to achieve a one-to-one matching of each inspection flight task and each UAV nest. The third aspect of the present invention provides a scheduling device for multiple specialties and multiple nests based on power joint inspection. The device includes a processor and a memory:

[0049] The memory is used to store program code and transfer the program code to the processor;

[0050] The processor is used to execute the steps of the scheduling method for multi - specialty and multi - drone - nest based on power joint inspection as described in the first aspect above according to the instructions in the program code.

[0051] The fourth aspect of the present invention provides a computer - readable storage medium, which is used to store program code, and the program code is used to execute the scheduling method for multi - specialty and multi - drone - nest based on power joint inspection as described in the first aspect above.

[0052] It can be seen from the above technical solutions that the present invention has the following advantages:

[0053] The present invention provides a scheduling method for multi - specialty and multi - drone - nest based on power joint inspection, including inspection strategy and plan compilation, inspection plan warehousing, inspection task aggregation, route planning, and drone - nest matching scheduling. And the inspection task aggregation, route planning, and intelligent scheduling of drone - nests are realized by using the clustering algorithm model, path - planning algorithm model, and drone - nest automatic matching algorithm model.

[0054] Among them, in the inspection task aggregation stage, by constructing a clustering algorithm model, multi - dimensional factors such as the planned inspection time of the task, the distribution range of equipment, and the distance from the drone - nest are comprehensively considered to achieve more scientific and reasonable task allocation. In the route planning stage, a set of dynamic and adaptive intelligent route planning methods is designed. By constructing an optimal path - planning algorithm model, the shortest flight path is calculated based on the distribution of equipment waypoints in the flight task; this method no longer relies on pre - set fixed routes but can intelligently and flexibly generate routes according to the real - time requirements of actual inspection tasks. In the drone - nest matching scheduling stage, a set of intelligent scheduling strategies for drone - nests that can satisfy the one - to - one matching of inspection tasks and drones within the coverage range and endurance time of the drones is designed, realizing the operation of drones based on inspection tasks and making effective and reasonable use of resources. The scheduling method of the present invention aims to achieve the optimal design of each link in the entire inspection process, with the overall process being automated. Through the aggregation and allocation of inspection tasks, the optimal route planning, and finally the matching and scheduling of drone - nests, the unified and efficient management of multiple drone - nests and various professional inspection tasks is realized. Thus, it solves the problems in the prior art that the inspection task allocation is unreasonable, the cross - specialty and multi - drone - nest inspection tasks are not fully considered, and there is a lack of systematic and comprehensive research on the entire inspection operation process. Description of the Drawings

[0055] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0056] Figure 1 Schematic flow chart of a scheduling method for a multi - professional and multi - airframe based on power joint inspection provided by an embodiment of the present invention;

[0057] Figure 2 Schematic diagram of the control level of the inspection object equipment provided by an embodiment of the present invention;

[0058] Figure 3 Schematic structural diagram of a scheduling system for a multi - professional and multi - airframe based on power joint inspection provided by an embodiment of the present invention. Detailed implementation manners

[0059] To make the objectives, features, and advantages of the present invention more obvious and understandable, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the embodiments described below are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0060] Please refer to Figure 1 , a scheduling method for a multi - professional and multi - airframe based on power joint inspection provided in the embodiments of the present invention, includes:

[0061] Step 101: Formulate inspection strategies for each specialty of power transmission, transformation, and distribution, design inspection plans for each specialty of power transmission, transformation, and distribution according to the inspection strategies, and integrate the inspection plans for each specialty of power transmission, transformation, and distribution into the UAV joint inspection plan library to obtain an inspection task set.

[0062] It should be noted that in the power transmission, transformation, and distribution joint inspection operation, the operation activities are carried out in an orderly manner based on the inspection plan. Among them, the inspection plan is compiled based on the inspection strategy, and the inspection strategy standardizes and restricts the implementation of the inspection plan and provides comprehensive and accurate guidance for the inspection plan.

[0063] The following is an example description of formulating the inspection strategy, compiling the inspection plan according to the inspection strategy, and storing the inspection plan in the library to obtain the inspection task set in this embodiment:

[0064] (1) Formulating the inspection strategy:

[0065] Organization for formulating inspection strategies: Led by the company's production technology department, relevant departments and units such as the Electric Power Research Institute, Machine Inspection Center, and Power Supply Bureau are organized to formulate inspection strategies for various professional equipment of power transmission, transformation, and distribution in the company according to the requirements of equipment inspection management work and risk control, and organize regular revisions.

[0066] Principles for formulating inspection strategies: When formulating inspection strategies for various specialties of power transmission, transformation, and distribution, the following four types of principles should be met:

[0067] ① "Four - part" control principle: Determine the equipment control level according to two dimensions of equipment health and importance, and achieve hierarchical, classified, and professional control of equipment;

[0068] ② Dynamic control principle: When the importance or health of equipment changes, the equipment control level should be dynamically adjusted, and the equipment inspection strategy should be adjusted in a timely manner;

[0069] ③ Differential inspection strategy principle: Based on different equipment control levels, differential inspection strategies should be formulated and implemented;

[0070] ④ Preventive inspection principle: For equipment sites with conditions for intelligent inspection, a trial operation of no less than 1 month should be carried out.

[0071] After the trial operation is qualified, it can be officially put into operation after being approved by relevant departments. After being officially put into operation, a certain dual - track operation cycle of intelligent inspection and manual inspection (such as 3 months) should be set, and intelligent inspection single - track operation can be applied for after meeting the inspection quality requirements.

[0072] Contents of formulating inspection strategies: Each specialty of power transmission, transformation, and distribution formulates its inspection strategy, and its content should distinguish the inspection items, cycles, and work requirements for different equipment under three situations: daily inspection, professional inspection, and dynamic inspection.

[0073] Details of the inspection strategy content are as follows:

[0074] Daily inspection: Daily inspection of equipment is a routine and repetitive inspection of equipment according to a fixed cycle (such as weekly, monthly, etc.). Its purpose is to timely discover potential problems and early fault signs of equipment and ensure the normal basic operation status of equipment. Daily inspection is divided into "Level I, Level II, Level III, and Level IV" from high to low according to the control level of the inspected equipment (as Figure 2 shown) to determine its inspection items, inspection cycles, and inspection requirements.

[0075] (2) Compilation of inspection plans:

[0076] Each specialty of power transmission, transformation, and distribution formulates annual, monthly, weekly (daily) inspection work plans for its own specialty according to the operation and inspection strategies of its own specialty, and carries out relevant machine inspection work according to the plans, and dynamically adjusts the work plans according to the actual situation to ensure the high - quality completion of the annual machine inspection strategy.

[0077] (3) Inspection plan warehousing:

[0078] Receive the inspection plans of each specialty of power transmission, transformation and distribution and integrate them into the UAV joint inspection plan library. The UAV joint inspection plan library should include inspection items (such as infrared temperature measurement, human-machine collaborative inspection, equipment monitoring and warning, etc.), equipment information of inspection objects (such as equipment type, equipment name, equipment regional location, etc.), completion time of inspection plan, responsible specialty, key points of work, etc.

[0079] Step 102: Use a clustering algorithm to cluster several inspection tasks with similar features in the inspection task set to obtain inspection flight tasks composed of several devices.

[0080] It should be noted that in the inspection task aggregation stage, the present invention uses a clustering algorithm to cluster several inspection tasks with similar features in the inspection task set. Among them, the features can be: the distance from the nest, the distribution area of inspection equipment, and the planned inspection date (i.e., the planned inspection completion time). Those skilled in the art can select different types of features according to the actual situation, which will not be elaborated here. Currently existing clustering algorithms include K-Means clustering algorithm, DBSCAN clustering algorithm, Gaussian mixture model clustering algorithm, hierarchical clustering algorithm, etc. The present invention selects the K-Means clustering algorithm to aggregate the inspection tasks within the inspection range of the nest to obtain inspection flight tasks composed of several devices.

[0081] Step 103: Generate the inspection route of the UAV through the TSP algorithm based on the established waypoints of the inspection flight task and the endurance time of the UAV.

[0082] It should be noted that the main content of inspection route planning is to form the shortest path of UAV inspection under the condition of meeting the maximum endurance time of the UAV by using an intelligent algorithm based on the established waypoints of the devices included in the aggregated inspection flight tasks. Relevant algorithms for the shortest inspection path in the case of determined waypoints include Dijkstra algorithm, bidirectional search algorithm, particle swarm optimization algorithm, ant colony algorithm, TSP algorithm, etc. The present invention selects the TSP algorithm as the basic algorithm for route planning.

[0083] Step 104: Based on the inspection route of the UAV, use the greedy algorithm to match each inspection flight task with each UAV nest one by one.

[0084] It should be noted that on the basis of achieving the inspection task aggregation in the above step 102 and determining the optimal flight route in step 103, the present invention uses a greedy algorithm to implement intelligent matching and scheduling of the nest. The greedy algorithm is an algorithm that makes the optimal decision in the current state at each step of selection. When matching the unmanned aerial vehicle (UAV) with the task, first calculate the minimum inspection range required for each task, then sort the UAVs in descending order of the inspection range, and sort the tasks in ascending order of the required inspection range. Starting from the task with the smallest required inspection range, select the UAV that can meet this task and wastes the least remaining inspection range to match it.

[0085] In one embodiment, step 102 includes the following steps:

[0086] Step 1021: Determine several similar features in the inspection task set. The features include: the distance from the nest, the distribution area of the inspection equipment, and the proposed inspection date.

[0087] It should be noted that three types of information are determined for the inspection task, namely the location area of the inspection equipment included in the inspection task, the distance from the nest, and the proposed inspection date (i.e., the proposed inspection completion time).

[0088] Step 1022: Perform standardization processing on each feature.

[0089] It should be noted that for feature standardization processing: perform standardization processing on the three types of feature information of the equipment location area, the distance from the nest, and the proposed inspection date, so that each feature information has the same scale. The method of standardization processing is as follows:

[0090]

[0091] Among them, z represents the standardized equipment feature information, x represents the original equipment feature information, represents the mean of the equipment feature information, represents the standard deviation of the equipment feature information. The standardized data follows a standard normal distribution, that is, the mean is 0 and the standard deviation is 1.

[0092] Step 1023: Use the elbow method to confirm the value of k, where k is the number of clusters.

[0093] It should be noted that to confirm the value of k (the number of clusters): The value of k is the number of clusters, that is, it represents how many clusters the data set is to be divided into. The value of k can be randomly generated or determined manually. In addition to subjectively judging the number of clusters based on experience, the method for the present invention to judge the value of k uses the elbow method. The mathematical expression of the key index SSE of the elbow method is as follows:

[0094]

[0095] Among them, x iis the i-th device, c j is the j-th cluster center (the initial cluster centers are randomly generated by the system based on the device coordinate data. In the subsequent process, the average value of the coordinates of all devices in the same cluster is calculated, and it is continuously iterated and optimized to finally determine the optimal cluster centers of each cluster). n is the total number of devices, and k is the total number of clusters. The core of the elbow method is that as the degree of aggregation of each cluster continuously increases, the sum of squared errors (SSE) will continuously decrease. Generally, when the change degree of the sum of squared errors becomes significantly smaller, that is, this turning point is selected as the value of k.

[0096] Step 1024: Generate k clusters according to the value of k and each feature, and update the cluster centers of each cluster.

[0097] It should be noted that Step 1024 is to update the cluster centers according to the newly divided clusters, which specifically includes the following steps:

[0098] ① After the value of k is given, the system will randomly generate k cluster centers according to the number of clusters and the average values of the planned inspection completion time of the devices, the distance from the device to the nest, and the three-dimensional coordinate positions of the areas where the devices are located. After calculating the distance from each device to each cluster center, each device is assigned to the nearest cluster center to form k clusters;

[0099] ② For each cluster, recalculate the cluster center. Generally, the mean value of the positions of all devices in the cluster is taken as the new cluster center;

[0100] Repeat Step ① and Step ②, and continuously optimize the coordinate selection of the cluster centers until one of the following stopping conditions is met:

[0101] The change of the cluster center is less than a preset threshold, that is, the change of the cluster center position is very small, and it can be considered that it has converged.

[0102] The preset maximum number of iterations is reached to avoid infinite loops.

[0103] The total sum of distances within the cluster no longer significantly decreases, that is, the clustering result has stabilized.

[0104] ③ Generally, the Euclidean distance is used for distance calculation, and the specific mathematical expression is as follows:

[0105]

[0106] Among them, represents the distance between device x and the cluster center of the cluster to which it belongs, x i represents the i-th device, represents the cluster center of the cluster to which the device belongs. When the position of the cluster center no longer changes, it can be regarded as the completion of K-means clustering.

[0107] Step 1025: Output an inspection flight mission consisting of several devices with similar distances from the nest, similar distribution areas of the inspection equipment, and similar planned inspection dates through the K-Means clustering algorithm.

[0108] It should be noted that multiple inspection flight missions with similar distributions of inspection equipment, similar distances from the nest, and similar planned inspection times can be obtained through the K-Means clustering algorithm. Further, after completing the clustering of inspection tasks, it is necessary to determine the distances of all inspection equipment positions in each cluster of tasks from the nest from the maximum flight range of the UAV. If the conditions cannot be met, the inspection tasks need to be aggregated again.

[0109] In one embodiment, step 103 includes the following steps:

[0110] Step 1031: Construct a route planning solution model according to the established waypoints of the inspection flight mission;

[0111] Among them, the expression of the route planning solution model is:

[0112]

[0113] In the formula, is the minimum path value from waypoint c1 to waypoint c n , is the distance from the end point c n to the starting point c1 when the UAV returns from inspection.

[0114] It should be noted that it is defined that G=(V, E) is a complete graph of the aggregated task clusters with weights. The number of waypoints |V|=n (the vertices represent waypoint c), and each edge is assigned a weight d ij representing the distance from waypoint c i to waypoint c j . Let be any permutation of all waypoints (the permutation represents the order of visiting waypoints), be the total length of the permutation , then the construction of the route planning solution model is completed, such as the expression of the above route planning solution model.

[0115] Step 1032: Solve the minimum path value in the route planning solution model through the TSP algorithm, and obtain the route corresponding to the minimum path value to get the shortest route as the initial inspection route of the UAV.

[0116] It should be noted that in order to find the minimum path value, the TSP algorithm is used, and the recursive equation can be obtained:

[0117]

[0118] Among them, represents the shortest path from the first waypoint c1 to visit all waypoints and reach the last waypoint c i , C represents all possible paths from waypoint c1 to c i .

[0119] In the case where the shortest path cannot be determined, the waypoint c i-1 is arbitrary and is defined as c j (c j cannot be c1), it is necessary to determine that the shortest path from c1 to c i must satisfy that the path from c1 to c j is the shortest. d ji is the distance from c j to c i . Calculate all possible path values and compare them to find the minimum path value, and the corresponding flight route is the shortest path flight route, which is the initial inspection flight route of the UAV.

[0120] Step 1033: Perform inspection simulation on the UAV based on the initial inspection flight route to obtain the inspection completion time. If the inspection completion time is within the UAV's endurance time range, it is used as the UAV's inspection flight route; otherwise, return to re-cluster the inspection tasks until each inspection flight task can meet the flight duration requirement of a single UAV.

[0121] It should be noted that after obtaining the shortest path flight route, the algorithm needs to simulate the UAV to perform inspections according to the flight route, and estimate the inspection completion time t. If the time t is within the interval [0, T max , T max is the maximum endurance time of the UAV, then this path is the optimal path; if the time t is not within the interval [0, T max , then re-aggregate the inspection tasks until each task can meet the UAV's endurance time (flight duration of a single UAV) requirement. Finally, through the above TSP algorithm process, the shortest inspection path within the UAV's endurance time can be obtained.

[0122] In one embodiment, step 104 includes the following steps:

[0123] Step 1041: Calculate the visible range of each UAV according to the endurance time of each UAV, and calculate the visible range required for each inspection flight task.

[0124] It should be noted that calculate the flight radius of each UAV according to the endurance time of each UAV, so as to determine the visible range of the UAV. For each inspection flight task i, calculate the visible range r required for the inspection flight taski。 Assume the task area is circular and calculate according to the formula (where C is the circumference and S is the area).

[0125] Step 1042: Sort the patrol ranges of each drone and the required patrol ranges of each inspection flight task respectively.

[0126] It should be noted that for j drones, sort them in descending order according to the patrol range R j ; for tasks, sort them in ascending order according to r i .

[0127] Step 1043: Start from the inspection flight task corresponding to the smallest required patrol range, select the drone that meets this inspection flight task and wastes the least remaining patrol range, match it with this inspection flight task, and sequentially complete the matching of the remaining inspection flight tasks and each drone, so as to achieve a one-to-one matching of each inspection flight task and each drone nest.

[0128] It should be noted that for each task, traverse the sorted drone list to find the drone j that satisfies r i ≤R j and R j -r i is the smallest, assign task i to drone j, and mark this drone as assigned. It can be understood that through the above steps 1041 - 1042, each flight task can be automatically matched with the drone nest.

[0129] A scheduling method for multiple specialties and multiple drone nests based on power joint inspection provided by an embodiment of the present invention includes inspection strategy and plan compilation, inspection plan warehousing, inspection task aggregation, flight route planning, and drone nest matching and scheduling. And the inspection task aggregation, flight route planning, and intelligent scheduling of drone nests are realized by using a clustering algorithm model, a path planning algorithm model, and a drone nest automatic matching algorithm model. Among them, in the inspection task aggregation stage, by constructing a clustering algorithm model and comprehensively considering multi-dimensional factors such as the planned inspection time of the task, the distribution range of equipment, and the distance from the drone nest, more scientific and reasonable task allocation is realized. In the flight route planning stage, a set of dynamic and adaptive intelligent flight route planning methods is designed. By constructing an optimal path planning algorithm model, the shortest flight path is calculated based on the distribution of equipment waypoints in the flight task; this method no longer relies on pre-set fixed flight routes, but can intelligently and flexibly generate flight routes according to the real-time requirements of actual inspection tasks. In the drone nest matching and scheduling stage, a set of intelligent scheduling strategies for drone nests that meet the one-to-one matching of inspection tasks and drones within the coverage range and endurance time of the drones is designed, realizing that the drones carry out operations based on inspection tasks and making the resources effectively and reasonably utilized. The scheduling method of the present invention is committed to realizing the optimal design of each link in the entire inspection process, and the overall process is automated. Through inspection task aggregation and allocation, optimal flight route planning, and finally the matching and scheduling of drone nests, unified and efficient management of multiple drone nests and various professional inspection tasks is realized.

[0130] The above is a scheduling method for multiple specialties and multiple drone nests based on power joint inspection provided by an embodiment of the present invention. The following is a scheduling system for multiple specialties and multiple drone nests based on power joint inspection provided by an embodiment of the present invention.

[0131] Please refer to Figure 3 , a scheduling system for multiple specialties and multiple drone nests based on power joint inspection provided by an embodiment of the present invention, includes:

[0132] A generating unit 201, configured to formulate inspection strategies for each specialty of power transmission, transformation, and distribution, design inspection plans for each specialty of power transmission, transformation, and distribution according to the inspection strategies, and integrate the inspection plans for each specialty of power transmission, transformation, and distribution into a drone joint inspection plan library to obtain an inspection task set.

[0133] A clustering unit 202, configured to cluster several inspection tasks with similar characteristics in the inspection task set by using a clustering algorithm to obtain inspection flight tasks composed of several pieces of equipment.

[0134] A solving unit 203, configured to generate an inspection flight route of the drone by using a TSP algorithm based on the established waypoints of the inspection flight task and the endurance time of the drone.

[0135] A matching unit 204, configured to perform one-to-one matching of each inspection flight task and each drone nest by using a greedy algorithm based on the inspection flight route of the drone.

[0136] Furthermore, in the embodiments of the present invention, a scheduling device for multiple specialties and multiple machine nests based on combined power inspections is further provided. The device includes a processor and a memory:

[0137] The memory is used to store program codes and transmit the program codes to the processor;

[0138] The processor is used to execute the steps of the scheduling method for multiple specialties and multiple machine nests based on combined power inspections as described in the above method embodiments according to the instructions in the program codes.

[0139] Furthermore, in the embodiments of the present invention, a computer-readable storage medium is further provided. The computer-readable storage medium is used to store program codes, and the program codes are used to execute the method described in the above method embodiments.

[0140] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0141] In several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some interfaces, and the indirect coupling or communication connection of devices or units can be in electrical, mechanical, or other forms.

[0142] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0143] In addition, in each embodiment of the present invention, the functional units can be integrated into one processing unit, or each unit exists physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0144] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0145] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of various embodiments of the present invention.

Claims

1. A scheduling method for multi - specialty and multi - drone nests based on power joint inspection, characterized in that, Including: S1. Formulate inspection strategies for each specialty of power transmission, transformation and distribution, design inspection plans for each specialty of power transmission, transformation and distribution according to the inspection strategies, and integrate the inspection plans for each specialty of power transmission, transformation and distribution into the UAV joint inspection plan library to obtain an inspection task set; S2. Use a clustering algorithm to cluster several inspection tasks with similar characteristics in the inspection task set to obtain inspection flight tasks composed of several devices; S3. Generate an inspection route for the UAV through the TSP algorithm based on the established waypoints of the inspection flight task and the endurance time of the UAV; S4. Based on the inspection route of the UAV, use a greedy algorithm to match each inspection flight task with each UAV hangar one by one.

2. The scheduling method for multi-specialty and multi-machine nests based on power joint inspection according to claim 1, wherein Step S2 includes: Determine several similar characteristics in the inspection task set, and the characteristics include: distance from the hangar, distribution area of inspection equipment, and planned inspection date; Perform standardization processing on each of the characteristics; Use the elbow method to confirm the value of k, where k is the number of clusters; Generate k clusters according to the value of k and each of the characteristics, and update the cluster centers of each cluster; Output inspection flight tasks composed of several devices with distances from the hangar being close, distribution areas of the inspection equipment being close, and planned inspection dates being close through the K-Means clustering algorithm.

3. The scheduling method for multi-specialty and multi-aircraft nests based on combined power inspection according to claim 1, characterized in that, Step S3 includes: Construct a route planning solution model according to the established waypoints of the inspection flight task; Among them, the expression of the route planning solution model is: In the formula, is the minimum value of the path from waypoint c1 to waypoint c n . is the distance from the end point c n to the starting point c1 when the UAV returns for inspection; Solve the minimum path value in the route planning solution model through the TSP algorithm, and obtain the route corresponding to the minimum path value to get the route with the shortest path as the initial inspection route of the UAV; Based on the initial inspection route, conduct inspection simulation on the UAV to obtain the inspection completion time. If the inspection completion time is within the endurance time range of the UAV, it is used as the inspection route of the UAV. Otherwise, return to recluster the inspection tasks until each inspection flight task can meet the flight duration requirement of a single UAV.

4. The scheduling method for multi - specialty and multi - airframe based on power joint inspection according to claim 1, characterized in that Step S4 includes: Calculate the observable ranges of each UAV according to the endurance times of each UAV respectively, and calculate the required observable ranges of each inspection flight task; Sort the observable ranges of each UAV and the required observable ranges of each inspection flight task respectively; Starting from the inspection flight task corresponding to the smallest required observable range, select the UAV that meets the inspection flight task and wastes the least remaining observable range, match it with the inspection flight task, and sequentially complete the matching of the remaining inspection flight tasks with each UAV, so as to achieve the one-to-one matching of each inspection flight task with each UAV hangar.

5. A scheduling system for multi - specialty and multi - airframe based on power joint inspection, characterized in that, Including: A generation unit for formulating inspection strategies for each specialty of power transmission, transformation and distribution, designing inspection plans for each specialty of power transmission, transformation and distribution according to the inspection strategies, and integrating the inspection plans for each specialty of power transmission, transformation and distribution into the UAV joint inspection plan library to obtain an inspection task set; A clustering unit for using a clustering algorithm to cluster several inspection tasks with similar characteristics in the inspection task set to obtain inspection flight tasks composed of several devices; A solving unit, configured to generate an inspection route of the UAV through the TSP algorithm based on the established waypoints of the inspection flight mission and the endurance time of the UAV; A matching unit, configured to perform one-to-one matching of each of the inspection flight missions and each UAV nest based on the inspection route of the UAV by using a greedy algorithm.

6. The scheduling system of multi - specialty and multi - airframe based on power joint inspection according to claim 5, characterized in that, A clustering unit, specifically configured to: Determine several similar features in the inspection task set, where the features include: the distance from the nest, the distribution area of inspection equipment, and the planned inspection date; Perform standardization processing on each of the features; Use the elbow method to confirm the value of k, where k is the number of clusters; Generate k clusters according to the value of k and each of the features, and update the cluster centers of each cluster; Output, through the K-Means clustering algorithm, an inspection flight mission composed of several devices with similar distances from the nest, similar distribution areas of the inspection equipment, and similar planned inspection dates.

7. The scheduling system of multi-specialty and multi-aircraft nests based on power joint inspection according to claim 5, characterized in that, The solving unit, specifically configured to: Construct a route planning solution model according to the established waypoints of the inspection flight mission; Among them, the expression of the route planning solution model is: Wherein, is the minimum path from waypoint c1 to waypoint c n , is the distance from the end point c n to the starting point c1 when the UAV returns for inspection; Solve the minimum path value in the route planning solution model through the TSP algorithm, and obtain the route corresponding to the minimum path value, so as to obtain the route with the shortest path and use it as the initial inspection route of the UAV; Perform inspection simulation on the UAV based on the initial inspection route, obtain the inspection completion time, and if the inspection completion time is within the endurance time range of the UAV, use it as the inspection route of the UAV, otherwise, return to re-cluster the inspection tasks until each inspection flight mission can meet the flight duration requirement of a single UAV.

8. The scheduling system for multiple specialties and multiple machine nests based on power joint inspection according to claim 5, characterized in that, The matching unit, specifically configured to: Calculate the inspectable range of each UAV according to the endurance time of each UAV, and calculate the required inspection range of each inspection flight mission; Sort the inspection ranges of each UAV and the required inspection ranges of each inspection flight mission respectively; Starting from the inspection flight mission corresponding to the smallest required inspection range, select the UAV that meets the inspection flight mission and wastes the least remaining inspection range, match it with the inspection flight mission, and sequentially complete the matching of the remaining inspection flight missions and each UAV, so as to achieve one-to-one matching of each inspection flight mission and each UAV nest.

9. A scheduling device for multi - specialty and multi - drone nests based on power joint inspection, characterized in that, The device includes a processor and a memory: The memory is used to store program codes and transmit the program codes to the processor; The processor is used to execute the scheduling method for multiple specialties and multiple nests based on power joint inspection according to any one of claims 1-4 according to the instructions in the program codes.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store program codes, and the program codes are used to execute the scheduling method for multiple specialties and multiple nests based on power joint inspection according to any one of claims 1-4.

Images