UAV cluster distribution network line inspection path planning method, equipment and medium

Abstract

The present invention discloses a method, device and medium for planning inspection paths of distribution network lines of drone clusters, and the inspection path planning method comprises the following steps: S1: establishing an inspection path planning model of distribution network lines of drone clusters; S2: based on the established inspection path planning model of distribution network lines of drone clusters, using a harmony search algorithm to map the optimization process of the inspection path to finding the most beautiful harmony; S3: introducing a parameter adaptive adjustment strategy in the harmony search algorithm, and optimizing the inspection path planning model of distribution network lines of drone clusters using the improved harmony search algorithm, thereby obtaining the optimal inspection path of drone clusters. The present invention performs collaborative inspections through drone clusters, so that the drone clusters can dispatch the least number of drones to complete the inspection tasks of distribution network lines in the shortest time under the requirements of the determined inspection tasks, thereby effectively improving the inspection efficiency and reducing the inspection costs.

Description

Technical Field

[0001] The present invention belongs to the technical field of electric power inspection, and specifically relates to the technical field of unmanned aerial vehicle inspection. Background Art

[0002] With the development of society and the improvement of industrial production capacity, the demand for power resources in today's society is increasing, and the reliability requirements for power supply are also getting higher and higher. As the basic content of power system operation and maintenance management, the maintenance and inspection of distribution lines is the focus. Heavy and complex, poor safety, and low efficiency are the shortcomings that traditional manual inspections cannot avoid. In recent years, with the rapid development of drone technology, drones have been widely used in military, entertainment, agriculture, rescue, aerospace, power inspection and other fields. The distribution line inspection supported by drone technology overcomes the problems of large inspection area span, complex terrain, harsh natural environment, and material aging caused by long-term exposure of distribution line equipment. The inspection efficiency, accuracy and cost advantages are more obvious.

[0003] UAV inspection flight path planning is currently a major research direction for UAV inspection. Currently, most of the UAV path planning algorithms are focused on single UAV research, and there is relatively little research on multi-UAV path planning. Compared with the single UAV path planning problem, the UAV cluster collaborative path planning problem has more constraints, higher coordination requirements, more complex calculations, and more difficult implementation. Existing research is generally based on single-UAV single-time path planning, which leads to low inspection efficiency due to the limited endurance of UAVs. Among the existing path planning algorithms, traditional algorithms are not suitable for UAV cluster flight path planning, and swarm intelligent bionic optimization algorithms such as genetic algorithms are prone to fall into local optimality. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method for patrol path planning of distribution network lines by drone clusters based on a harmony search algorithm, so as to improve patrol efficiency through drone cluster flight path planning.

[0005] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0006] The method for inspection path planning of UAV cluster distribution network line based on harmony search algorithm includes the following steps:

[0007] S1: Establish a UAV cluster distribution network line inspection path planning model, including determining the UAV cluster distribution network line path planning objective function and the UAV cluster distribution network line inspection path planning constraints corresponding to the objective function. The objective function is the flight path with the minimum inspection cost of the UAV cluster between any warehouse sites.

[0008]

[0009] Among them, α represents a certain planning scheme, N represents the number of drones used, T represents the total flight time, and R is a number that is always greater than the total flight time;

[0010] The inspection path planning constraints of the UAV cluster distribution network line include UAV performance constraints, objective environmental threat constraints, and distribution network line inspection requirement constraints;

[0011] S2: Based on the established UAV cluster distribution network line inspection path planning model, the harmony search algorithm is used to map the inspection path optimization process into the search for the most beautiful harmony;

[0012] S3: Introduce a parameter adaptive adjustment strategy into the harmony search algorithm, and use the improved harmony search algorithm to optimize the UAV cluster distribution network line inspection path planning model to obtain the optimal path for UAV cluster inspection.

[0013] Preferably, the UAV performance constraints include the maximum flight time and the flight altitude; the objective environmental threat constraints include collision constraints and geographic fence constraints; the distribution network line inspection requirement constraints include inspection tasks, path integrity, and recyclability of path planning solutions; wherein:

[0014] Maximum flight time: This is determined by the drone’s own performance and the maximum flight time limit for the drone to perform line inspections;

[0015] Flight altitude: h i represents the flight altitude of the i-th route, h min Indicates the minimum flight altitude, h max represents the maximum flight altitude. The constraint is expressed as:

[0016] h min ≤h≤h max i=1,2,3,…,n (2)

[0017] Collision constraints: The coordinated flight of drone clusters to perform tasks needs to consider the collaborative relationship of the clusters in the spatial and temporal domains;

[0018] Geographic fence constraints: When the drone swarm is performing a mission, the drone swarms on each control station platform must always fly within the set route range, and are prohibited from flying outside the route range, and consider preventing them from flying into prohibited geographical areas;

[0019] Inspection tasks: n power towers and m transmission lines within the distribution network inspection area;

[0020] Path integrity: The planned route should be a complete path that takes off from any warehouse site and lands at any warehouse site;

[0021] Recyclability of the path planning solution: After the mission is completed, the number of drones at each warehouse site remains unchanged.

[0022] Preferably, the specific steps of step S2 are as follows:

[0023] S21: Set the basic parameters of the harmony search algorithm, including harmony library size, harmony memory library, harmony library learning probability, pitch adjustment rate, pitch adjustment bandwidth, and maximum number of iterations K max ;

[0024] S22: Randomly generate feasible harmony variables equal to the number of HMSs and store them in the harmony memory library as the initial harmony memory library.

[0025] Preferably, the specific steps of step S3 are as follows:

[0026] S31: Calculate the adaptive harmony library learning probability, pitch adjustment rate and pitch adjustment bandwidth;

[0027]

[0028]

[0029]

[0030] Among them, HCMR i is the probability of learning the harmony memory library during the i-th search, PCR i is the pitch adjustment rate during the i-th search, K i is the current iteration number, HCMR min Learning probability for the minimum harmonic memory, HCMR max is the maximum harmonic memory learning probability, PAR min is the minimum pitch adjustment rate, PAR max is the maximum pitch adjustment rate;

[0031] S32: Generate a new harmony according to the adaptive HMCR, generate a random number rand1 between (0,1), if rand1 is less than HMCR, randomly generate a harmony variable in the harmony library, otherwise, randomly generate a harmony variable outside the harmony library;

[0032] S33: After a set of harmony variables is generated through step 32, if the harmony variables are obtained from the harmony library, a random number rand2 is generated between (0, 1). If rand2 is less than PAR, the pitch bandwidth is adjusted according to formula (5) to obtain new harmony variables.

[0033] S34: performing disturbance adjustment on the generated new harmony variable, and updating the generated new harmony variable;

[0034] S35: merging the updated new harmony variables and the initial harmony memory library, performing non-dominated sorting, and obtaining the Pareto optimal frontier of each layer;

[0035] S36: selecting harmony variables with equal number of HMSs according to the non-dominated order of the optimal solution, and updating the harmony memory bank;

[0036] S37: Determine the iteration termination condition. If it is satisfied, stop the iteration and output the Pareto optimal solution set; otherwise, return to S31.

[0037] Preferably, the disturbance adjustment includes randomly specifying two positions in part of the new harmonic variables, exchanging the variables at the two positions, and obtaining a new solution after disturbance; randomly deleting a new harmonic variable, and taking the average of the best harmony and the worst harmony in the new harmonic variable library as a replacement.

[0038] On the other hand, the present invention provides a computer device, comprising at least one processor and a memory; the memory stores computer execution instructions; the at least one processor executes the computer execution instructions stored in the memory, so that the at least one processor executes the drone cluster distribution network line inspection path planning method based on the harmony search algorithm.

[0039] In addition, the present invention provides a computer-readable storage medium, in which computer execution instructions are stored. When the processor executes the computer execution instructions, the drone cluster distribution network line inspection path planning method based on the harmony search algorithm is implemented.

[0040] Compared with the prior art, the drone cluster distribution network line inspection path planning method based on the harmony search algorithm of the present invention can perform collaborative inspections through drone clusters and improve inspection efficiency.

[0041] Based on the harmony search algorithm, the inspection path planning of drone cluster distribution network lines does not require strict mathematical processing of the objective function and constraint function. It can solve various complex problems in parallel and distribute them, introduce a parameter adaptive adjustment strategy, and generate appropriate parameter values ​​according to the number of iterations, thereby enhancing the global search capability of the algorithm, increasing the diversity of solutions, and not easily falling into the local optimum.

[0042] Compared with the prior art that uses the harmony search algorithm to plan the inspection path of a single UAV, the present invention improves the objective function and path planning constraint design of UAV cluster flight inspection based on the characteristics of collaborative inspection of multiple UAVs. When the inspection task requirements are determined, in addition to the constraints on a single UAV, collision constraints, path integrity and the recyclability constraints of the path planning scheme are designed, so that the UAV cluster can dispatch the least number of UAVs in the shortest time to complete the distribution network line inspection task under the determined inspection task requirements, and the scheme can operate cyclically to effectively improve the inspection efficiency and reduce the inspection cost.

[0043] The specific technical solutions adopted by the present invention and the beneficial effects brought about by them will be disclosed in detail in the following specific embodiments in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments:

[0045] Figure 1 It is the overall flow chart of the present invention.

[0046] Figure 2 Schematic diagram of the inspection of the network distribution lines for drone clusters.

[0047] Figure 3 Flowchart for improving harmony search algorithm. DETAILED DESCRIPTION

[0048] The technical solutions of the embodiments of the present invention are explained and described below in conjunction with the drawings of the embodiments of the present invention, but the following embodiments are only preferred embodiments of the present invention, not all. Based on the embodiments in the implementation mode, other embodiments obtained by those skilled in the art without creative work are all within the protection scope of the present invention.

[0049] The present invention is further described below in conjunction with the accompanying drawings and implementation modes.

[0050] like Figure 1 The figure shows the overall flow chart of the present invention, which is a method for planning the inspection path of a UAV cluster distribution network line based on a harmony search algorithm, and specifically includes the following steps:

[0051] S1: Establish a UAV cluster distribution network line inspection path planning model, including determining the UAV cluster distribution network line inspection path planning objective function and the UAV cluster distribution network line inspection path planning constraints corresponding to the objective function.

[0052] The objective function of the drone cluster inspection distribution network route planning is to find the flight path with the lowest inspection cost between any warehouse sites, including the number of drones used N and the total flight time T.

[0053]

[0054] Among them, α represents a certain planning scheme, and R is a number that is always greater than the total flight time, that is, the value of the second item is always between 0 and 1, so as to ensure the priority of the optimization objectives.

[0055] The inspection path planning constraints of the UAV cluster distribution network line include: UAV performance constraints, objective environmental threat constraints, and distribution network line inspection requirement constraints; determine the objective function of the UAV cluster distribution network line path planning, and establish the UAV cluster distribution network line inspection path planning model;

[0056] The UAV performance constraints include the maximum flight time and flight altitude; the objective environmental threat constraints include collision constraints and geographic fence constraints; the distribution network line inspection requirement constraints include inspection tasks, path integrity, and the recyclability of path planning solutions; the details are as follows:

[0057] Maximum flight time: This is determined by the drone’s own performance and the maximum flight time limit for the drone to perform line inspections;

[0058] Flight altitude: To ensure the flight safety of drones, it is necessary to restrict the flight altitude of drones. i represents the flight altitude of the i-th route, h min Indicates the minimum flight altitude, h max represents the maximum flight altitude. The constraint is expressed as:

[0059] h min ≤h≤h max i=1,2,3,…,n (2)

[0060] Collision constraints: The coordinated flight of drone swarms to perform tasks needs to consider the coordinated relationship of the swarms in the spatial and temporal domains. The judgment of collision conflicts needs to be comprehensively judged from the perspectives of navigation space and time coupling;

[0061] Geographic fence constraints: When the drone swarm is performing a mission, the drone swarms on each control station platform must always fly within the set route range and are prohibited from flying outside the route range. At the same time, consideration should also be given to preventing the drones from flying into prohibited geographical areas;

[0062] Inspection tasks: n power towers and m transmission lines within the distribution network inspection area;

[0063] Path integrity: The planned route should be a complete path that takes off from any warehouse site and lands at any warehouse site;

[0064] Recyclability of path planning solutions: After the mission is completed, the number of original drones at each warehouse site remains unchanged, ensuring that the path planning solution can be recycled.

[0065] like Figure 2 The figure shows a schematic diagram of the inspection of the distribution network line by a drone cluster. The transmission lines and power towers in the transmission line are inspected, each power tower is regarded as an independent task point, and the transmission cable between the two towers is regarded as an independent task line segment. A fixed drone warehouse site is set up in the distribution network line inspection area for parking, charging and storage of drones, and each drone is allowed to take off and land at any site. The drones shown in the figure include UAV1, UAV2, UAV3, and UAV4.

[0066] In order to realize the optimization process of the inspection path of the UAV cluster distribution network line, a parameter adaptive adjustment strategy is introduced based on the harmony search algorithm. The flow chart of the improved harmony search algorithm is as follows: Figure 3 shown.

[0067] S2: Based on the established UAV cluster distribution network line inspection path planning model, the harmony search algorithm is used to map the optimization process of the inspection path to the search for the most beautiful harmony, simulating the process of musicians repeatedly adjusting the tones of various instruments to form harmony, and constantly updating and adjusting to achieve the most beautiful harmony. The specific steps are as follows:

[0068] S21: Set the basic parameters of the harmony search algorithm: harmony library size (HMS), harmony memory library (HM), harmony library learning probability (HMCR), pitch adjustment rate (PAR), pitch adjustment bandwidth (BW), maximum number of iterations K max ;

[0069] S22: randomly generate feasible harmony variables equal to the number of HMS and store them in the harmony memory bank as the initial harmony memory bank;

[0070] S3: Introduce a parameter adaptive adjustment strategy into the harmony search algorithm, and use the improved harmony search algorithm to optimize the UAV cluster distribution network line inspection path planning model, so as to obtain the optimal path for UAV cluster inspection. The specific steps are as follows:

[0071] S31: Calculate the adaptive harmony library learning probability (HMCR), pitch adjustment rate (PAR) and pitch adjustment bandwidth (BW);

[0072]

[0073]

[0074]

[0075] Among them, HCMRi is the probability of learning the harmony memory library during the i-th search, PCR i is the pitch adjustment rate during the i-th search, K i is the current iteration number, HCMR min Learning probability for the minimum harmonic memory, HCMR max is the maximum harmonic memory learning probability, PAR min is the minimum pitch adjustment rate, PAR max is the maximum pitch adjustment rate;

[0076] S32: Generate a new harmony according to the adaptive HMCR, generate a random number rand1 between (0,1), if rand1 is less than HMCR, randomly generate a harmony variable in the harmony library, otherwise, randomly generate a harmony variable outside the harmony library;

[0077] S33: After a set of harmony variables is generated through step 32, if the harmony variables are obtained from the harmony library, a random number rand2 is generated between (0, 1). If rand2 is less than PAR, the pitch bandwidth is adjusted according to formula (5) to obtain new harmony variables.

[0078] S34: performing disturbance adjustment on the generated new harmony variables and updating the generated new harmony variables, wherein the specific operations include: exchanging variables at two randomly designated positions in part of the new harmony variables to obtain a new solution after disturbance; randomly deleting a new harmony variable and taking the average of the best harmony and the worst harmony in the new harmony variable library as a replacement;

[0079] S35: merging the updated new harmony variables and the initial harmony memory library, performing non-dominated sorting, and obtaining the Pareto optimal frontier of each layer;

[0080] S36: selecting harmony variables with equal number of HMSs according to the non-dominated order of the optimal solution, and updating the harmony memory bank;

[0081] S37: Determine the iteration termination condition. If it is satisfied, stop the iteration and output the Pareto optimal solution set; otherwise, return to S31.

[0082] The present invention adopts computer equipment to plan and calculate the inspection path of the UAV cluster distribution network line based on the harmony search algorithm, and refers to the structure of commonly used computer equipment, including at least one processor and a memory; the memory stores computer execution instructions; the at least one processor executes the computer execution instructions stored in the memory, so that the at least one processor executes the UAV cluster distribution network line inspection path planning method based on the harmony search algorithm.

[0083] When the computer device is running, a computer-readable storage medium is required, in which computer execution instructions are stored. When the processor executes the computer execution instructions, the drone cluster distribution network line inspection path planning and calculation based on the harmony search algorithm is implemented.

[0084] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Those skilled in the art should understand that the present invention includes but is not limited to the contents described in the drawings and the above specific embodiments. Any modification that does not deviate from the functional and structural principles of the present invention will be included in the scope of the claims.

Claims

1. A method for inspection path planning of UAV cluster distribution network lines based on harmony search algorithm, characterized in that: The steps include: S1: Establish a UAV cluster distribution network line inspection path planning model, including determining the UAV cluster distribution network line path planning objective function and the UAV cluster distribution network line inspection path planning constraints corresponding to the objective function. The objective function is the flight path with the minimum inspection cost of the UAV cluster between any warehouse sites. Among them, α represents a certain planning scheme, N represents the number of drones used, T represents the total flight time, and R is a number that is always greater than the total flight time; The inspection path planning constraints of the UAV cluster distribution network line include UAV performance constraints, objective environmental threat constraints, and distribution network line inspection requirement constraints; S2: Based on the established UAV cluster distribution network line inspection path planning model, the harmony search algorithm is used to map the inspection path optimization process into the search for the most beautiful harmony; S3: Introduce a parameter adaptive adjustment strategy into the harmony search algorithm, and use the improved harmony search algorithm to optimize the UAV cluster distribution network line inspection path planning model, so as to obtain the optimal path for UAV cluster inspection. The specific steps of step S3 are as follows: S31: Calculate the adaptive harmony library learning probability, pitch adjustment rate and pitch adjustment bandwidth; Among them, HCMR i is the probability of learning the harmony memory library during the i-th search, PAR i is the pitch adjustment rate during the i-th search, K i is the current iteration number, HCMR min Learning probability for the minimum harmonic memory, HCMR max is the maximum harmonic memory learning probability, PAR min is the minimum pitch adjustment rate, PAR max is the maximum pitch adjustment rate; S32: Generate a new harmony according to the adaptive HMCR, generate a random number rand1 between (0,1), if rand1 is less than HMCR, randomly generate a harmony variable in the harmony library, otherwise, randomly generate a harmony variable outside the harmony library; S33: After a set of harmony variables is generated through step 32, if the harmony variables are obtained from the harmony library, a random number rand2 is generated between (0, 1). If rand2 is less than PAR, the pitch bandwidth is adjusted according to formula (5) to obtain new harmony variables. S34: performing disturbance adjustment on the generated new harmony variable, and updating the generated new harmony variable; S35: merging the updated new harmony variables and the initial harmony memory library, performing non-dominated sorting, and obtaining the Pareto optimal frontier of each layer; S36: selecting harmony variables with equal number of HMSs according to the non-dominated order of the optimal solution, and updating the harmony memory bank; S37: Determine the iteration termination condition. If it is satisfied, stop the iteration and output the Pareto optimal solution set; otherwise, return to S31.

2. The method for inspection path planning of UAV cluster distribution network line based on harmony search algorithm according to claim 1 is characterized in that: The UAV performance constraints include the maximum flight time and the flight altitude; the objective environmental threat constraints include collision constraints and geographic fence constraints; the distribution network line inspection requirement constraints include inspection tasks, path integrity, and the recyclability of path planning solutions; among which: Maximum flight time: This is determined by the drone’s own performance and the maximum flight time limit for the drone to perform line inspections; Flight altitude: h j represents the flight altitude of the jth route, h min Indicates the minimum flight altitude, h max represents the maximum flight altitude. The constraint is expressed as: h min ≤h j ≤h max j=1,2,3,…,n (2) Collision constraints: The coordinated flight of drone clusters to perform tasks needs to consider the collaborative relationship of the clusters in the spatial and temporal domains; Geographic fence constraints: When the drone swarm is performing a mission, the drone swarms on each control station platform must always fly within the set route range, and are prohibited from flying outside the route range, and consider preventing them from flying into prohibited geographical areas; Inspection tasks: x power towers and m transmission lines within the distribution network inspection area; Path integrity: The planned route should be a complete path that takes off from any warehouse site and lands at any warehouse site; Recyclability of the path planning solution: After the mission is completed, the number of drones at each warehouse site remains unchanged.

3. The method for inspection path planning of UAV cluster distribution network line based on harmony search algorithm according to claim 1 is characterized in that: The specific steps of step S2 are as follows: S21: Set the basic parameters of the harmony search algorithm, including harmony library size, harmony memory library, harmony library learning probability, pitch adjustment rate, pitch adjustment bandwidth, and maximum number of iterations K max ; S22: Randomly generate feasible harmony variables equal to the number of HMSs and store them in the harmony memory library as the initial harmony memory library.

4. The method for inspection path planning of UAV cluster distribution network line based on harmony search algorithm according to claim 1 is characterized in that: The disturbance adjustment includes randomly specifying two positions in part of the new harmony variables, exchanging the variables at the two positions, and obtaining a new solution after disturbance; randomly deleting a new harmony variable, and taking the average of the best harmony and the worst harmony in the new harmony variable library as a replacement.

5. A computer device, characterized in that: It includes at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the drone cluster distribution network line inspection path planning method based on the harmony search algorithm as described in any one of claims 1 to 4.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions. When the processor executes the computer-executable instructions, the method for inspection path planning of drone cluster distribution network lines based on the harmony search algorithm as described in any one of claims 1 to 4 is implemented.

Images