Substation unmanned aerial vehicle three-dimensional path planning method based on improved ant colony algorithm

Abstract

The invention relates to a transformer substation unmanned aerial vehicle three-dimensional path planning method based on an improved ant colony algorithm. The method comprises the following steps that an electric power unmanned aerial vehicle inspection three-dimensional environment model is generated, and self-adaptive grid division is carried out; performing path search on the initialized ant colony in the electric unmanned aerial vehicle inspection three-dimensional environment model after grid division; each ant individual in the ant colony selects a next node according to a dynamic transition probability calculation model, the ant individual determines the next node which actually moves through a variable step size search behavior, and path information of each ant individual from a starting point to an ending point is recorded; when all the ant individuals arrive at the end point, screening the optimal ant individual of the iteration, executing the artificial ant foraging behavior, and updating the pheromone concentration of each path in the space; iteration is repeated until the preset number of iterations is reached, iteration is ended, and the path with the highest pheromone concentration is selected as the final path of the unmanned aerial vehicle.

Description

Technical Field

[0001] The invention relates to a three-dimensional path planning method for a substation unmanned aerial vehicle based on an improved ant colony algorithm, and belongs to the technical field of unmanned aerial vehicle path planning. Background Art

[0002] At present, most substations in China still rely on inspection robots to inspect equipment. However, due to the wide variety of equipment in substations and the different installation locations and heights, inspection robots can only "shoot from above" on the ground, limiting their ability to fully and accurately obtain the operating status of equipment. Especially in complex equipment environments, the viewing angle and range of movement of inspection robots are restricted, making it difficult to cover the key parts of all equipment. Therefore, it is particularly necessary to replace inspection robots with more maneuverable drones. Drones can flexibly conduct multi-directional inspections at different heights and angles to ensure comprehensive monitoring of equipment status. However, how to plan the inspection routes of substation drones to improve inspection efficiency is still a major challenge currently faced.

[0003] To design an efficient path planning solution in a substation, it is first necessary to accurately grid the three-dimensional map. The commonly used grid method divides the grid along the coordinate axis according to a fixed size. When a grid vertex touches an obstacle, the grid will be marked as a prohibited grid. The grid size determines the size and number of grids, which affects the path planning accuracy and calculation speed of the ant colony algorithm. Summary of the invention

[0004] In order to solve the above problems existing in the prior art, the present invention proposes a three-dimensional path planning method for substation UAV based on an improved ant colony algorithm.

[0005] The technical solution of the present invention is as follows:

[0006] On the one hand, the present invention provides a three-dimensional path planning method for a substation drone based on an improved ant colony algorithm, comprising the following steps:

[0007] Generate a three-dimensional environmental model for power drone inspection and perform adaptive grid division on the three-dimensional environmental model for power drone inspection;

[0008] Initialize the ant colony to search for paths in the grid-divided three-dimensional environment model of the power drone inspection, and set the starting point and end point of the drone as the starting point and end point of the ant colony;

[0009] Each ant in the ant colony selects the next node according to the dynamic transfer probability calculation model. The ant individual determines the next node to move to through variable step length search behavior, and records the path information of each ant individual from the starting point to the end point.

[0010] When all ant individuals reach the end point, the best ant individual of this iteration is selected and the worker ant foraging behavior is performed to update the pheromone concentration of each path in the space;

[0011] The iteration is repeated until the preset number of iterations is reached and the path with the highest pheromone concentration is selected as the final path of the UAV.

[0012] As a preferred embodiment of the present invention, the steps of adaptively gridding the three-dimensional environment model of the power drone inspection are as follows:

[0013] Set the latitude, and divide the three-dimensional environment model space of the power drone inspection into multiple slices equally according to the slice latitude, and each slice is a grid;

[0014] When a grid vertex touches an obstacle, the grid adaptively adjusts the size of the direction of the vertex, as shown in the following formula:

[0015]

[0016] Where: dk Indicates the size length of the grid when the mth adjustment is made; ε d0 represents the initial length of the grid; δ represents the adjustment step size.

[0017] As a preferred embodiment of the present invention, the dynamic transition probability calculation model is specifically shown in the following formula:

[0018]

[0019] in: represents the probability of ant individual k moving from node i to node j; represents the pheromone concentration of edge (i, j) at time t; represents the heuristic function of edge (i, j) at time t; N represents the total number of next nodes that ant individual k can choose at node i; s represents the next node selected by ant individual k at node i; represents the pheromone concentration of edge (i,s) at time t; represents the heuristic function of edge (i, s) at time t; rand 1 represents the iteration factor threshold; ξ represents the iteration factor; T represents the current number of iterations; T max Indicates the maximum number of iterations.

[0020] As a preferred embodiment of the present invention, the variable step length search behavior is specifically to perform a variable step length random search in the grid formed by the node and the current node before the ant individual moves to the next node, as shown in the following formula:

[0021] P j=P i +(P′ j -P i )·rand·γ

[0022]

[0023] Where: P j represents the coordinates of the next node calculated by random search with variable step length; P′ j represents the candidate next node coordinates calculated by the dynamic transition probability calculation model; P i Represents the current node coordinates; rand represents a random number; γ represents the step factor; n represents the variable step factor.

[0024] As a preferred embodiment of the present invention, the ant individuals with the best path in each generation of ant colonies are regarded as worker ants that have found food, and other ant individuals are summoned to approach. The formula for summoning ant colony behavior is as follows:

[0025]

[0026] Among them: the new position of ant individual k after being summoned; represents the current position of ant individual k; Indicates the location of the ant individual on the optimal path.

[0027] As a preferred embodiment of the present invention, the optimal ant individual search behavior formula is as follows:

[0028]

[0029] in: represents the individual position of the ant on the next optimal path obtained by searching; ε represents the adjustment coefficient.

[0030] On the other hand, the present invention also provides a three-dimensional path planning system for substation drones based on an improved ant colony algorithm, including a grid division module and an ant colony path planning module;

[0031] The grid division module is used to generate a three-dimensional environment model for power drone inspection and to perform adaptive grid division on the three-dimensional environment model for power drone inspection;

[0032] The ant colony path planning module is used to initialize the ant colony to search for paths in the three-dimensional environment model of the power drone inspection after grid division, and set the starting point and end point of the drone as the starting point and end point of the ant colony; each ant individual in the ant colony selects the next node according to the dynamic transfer probability calculation model, and the ant individual determines the next node to be actually moved through the variable step length search behavior, and records the path information of each ant individual from the starting point to the end point; when all ant individuals reach the end point, the optimal ant individual of this iteration is selected and the worker ant foraging behavior is performed, and the pheromone concentration of each path in the space is updated; the iteration is repeated until the preset number of iterations is reached and the iteration is terminated, and the path with the highest pheromone concentration is selected as the final path of the drone.

[0033] On the other hand, the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present invention when executing the program.

[0034] In yet another aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any embodiment of the present invention.

[0035] The present invention has the following beneficial effects:

[0036] 1. The present invention significantly improves the algorithm's optimization ability and path planning accuracy by introducing improved strategies such as dynamic probability transfer selection, variable step-size search behavior and worker ant foraging behavior; it can effectively reduce the distance of the planned path, thereby improving inspection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 is a flow chart of the method of the present invention;

[0038] Figure 2 This is a schematic diagram of traditional grid segmentation;

[0039] Figure 3 Schematic diagram of adaptive grid segmentation of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0042] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0043] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0044] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0045] Embodiment 1:

[0046] See also Figure 1 , a three-dimensional path planning method for substation UAV based on improved ant colony algorithm, including the following steps:

[0047] Generate a three-dimensional environmental model for power drone inspection and perform adaptive grid division on the three-dimensional environmental model for power drone inspection;

[0048] Initialize the ant colony to search for paths in the grid-divided three-dimensional environment model of the power drone inspection, and set the starting point and end point of the drone as the starting point and end point of the ant colony;

[0049] Each ant in the ant colony selects the next node according to the dynamic transfer probability calculation model. The ant individual determines the next node to move to through variable step length search behavior, and records the path information of each ant individual from the starting point to the end point.

[0050] When all ant individuals reach the end point, the best ant individual of this iteration is selected and the worker ant foraging behavior is performed to update the pheromone concentration of each path in the space;

[0051] Repeat the iteration until the preset number of iterations is reached, and then the path with the highest pheromone concentration is selected as the final path of the drone;

[0052] The ant colony algorithm imitates the foraging behavior of ants in nature and uses "pheromones" for communication and decision-making. Specifically, ants will choose a path with a certain probability based on the pheromones they left before, and leave new pheromones on the path they pass. Subsequent ants will be affected by the accumulation, diffusion and volatilization of pheromones, which will determine the path selection. The higher the pheromone concentration, the greater the probability that subsequent ants will choose the path, and eventually the optimal path found by the ant colony is formed. The key components of the ant colony algorithm include state transition probability judgment and pheromone update.

[0053] Before using the ant colony algorithm (ACO) for inspection path planning, the optimization space needs to be divided into grids. The commonly used grid method divides the grid uniformly along the coordinate axis according to a fixed size. When the vertex of a grid touches an obstacle, the grid will be marked as a prohibited grid, and the ant colony will not select this grid when selecting a path. This grid method is applicable to two-dimensional and three-dimensional space, and both divide the optimization space equally. The grid size directly determines the size and number of grids, which affects the path planning accuracy and calculation speed of the ant colony algorithm; therefore, reasonable consideration needs to be made between balancing the grid size and algorithm efficiency.

[0054] As a preferred implementation of this embodiment, the steps of adaptively gridding the three-dimensional environment model of the power drone inspection are as follows:

[0055] Set the latitude, and divide the three-dimensional environment model space of the power drone inspection into multiple slices equally according to the slice latitude, and each slice is a grid;

[0056] When a grid vertex touches an obstacle, the grid adaptively adjusts the size of the direction of the vertex, as shown in the following formula:

[0057]

[0058] Where: dk Indicates the size length of the grid when the mth adjustment is made; ε d0 represents the initial length of the grid; δ represents the adjustment step size.

[0059] Comparison of traditional grid method and adaptive grid method in three-dimensional space partition model Figure 2 and Figure 3 The adaptive grid method can increase the grid density in the area near the obstacle without changing the global grid size, thereby improving the accuracy of grid division and helping to optimize the path optimization accuracy.

[0060] In the later stages of iteration, the traditional ant colony algorithm is prone to excessive concentration of pheromones, which causes the algorithm to fall into a local optimal solution and is difficult to escape from. In order to enhance the algorithm's optimization ability in the later stages of iteration, as a preferred implementation of this embodiment, the dynamic transition probability calculation model is specifically shown in the following formula:

[0061]

[0062] in: represents the probability of ant individual k moving from node i to node j; represents the pheromone concentration of edge (i, j) at time t; represents the heuristic function of edge (i, j) at time t; N represents the total number of next nodes that ant individual k can choose at node i; s represents the next node selected by ant individual k at node i; represents the pheromone concentration of edge (i,s) at time t; represents the heuristic function of edge (i, s) at time t; rand 1 represents the iteration factor threshold; ξ represents the iteration factor; T represents the current number of iterations; T max Represents the maximum number of iterations; by introducing the iteration factor ξ, the way ants choose paths is dynamically adjusted as the number of iterations changes. In the early stage of iteration, the ξ value is small, and the algorithm is more inclined to the traditional probability transfer function, which can quickly find a significantly superior path while retaining the good convergence of the ant colony algorithm; as the number of iterations increases, the ξ value increases, and the path selection of the ant colony gradually tilts towards the random mode, reducing the impact of excessive pheromone accumulation and enhancing the algorithm's ability to jump out of the local optimal solution.

[0063] The traditional ant colony algorithm uses a grid division method to divide the map, and each grid vertex is used as the path endpoint that the ants can choose, which leads to low accuracy in path optimization. As a preferred implementation of this embodiment, the variable step search behavior is specifically to perform a variable step random search in the grid formed by the node and the current node before the ant individual moves to the next node, as shown in the following formula:

[0064] P j =P i +(P′ j -P i )·rand·γ

[0065]

[0066] Where: P j represents the coordinates of the next node calculated by random search with variable step length; P′ j represents the candidate next node coordinates calculated by the dynamic transition probability calculation model; P iRepresents the current node coordinates; rand represents a random number; γ represents the step factor; n represents the variable step factor.

[0067] In nature, when worker ants find food, they will pass the location of the food to other ants to gather the ant colony to carry the food together. By introducing this behavior into the ant colony algorithm, the ants with the best path in each generation of ant colonies can be regarded as worker ants that have found food, and they will gather other ants to approach while continuing to search for food. In this way, the algorithm's search ability and convergence speed can be effectively improved.

[0068] As a preferred implementation of this embodiment, the ant individuals with the best path in each generation of ant colonies are regarded as worker ants that have found food, and other ant individuals are summoned to approach. The formula for summoning ant colony behavior is as follows:

[0069]

[0070] Among them: the new position of ant individual k after being summoned; represents the current position of ant individual k; Indicates the location of the ant individual on the optimal path.

[0071] As a preferred implementation of this embodiment, the optimal ant individual search behavior formula is as follows:

[0072]

[0073] in: It represents the individual position of the ant in the next optimal path searched; ε represents the adjustment coefficient, which is used to adjust the search range.

[0074] Embodiment 2:

[0075] A three-dimensional path planning system for substation UAV based on improved ant colony algorithm, including a grid division module and an ant colony path planning module;

[0076] The grid division module is used to generate a three-dimensional environment model for power drone inspection and to perform adaptive grid division on the three-dimensional environment model for power drone inspection;

[0077] The ant colony path planning module is used to initialize the ant colony to search for paths in the three-dimensional environment model of the power drone inspection after grid division, and set the starting point and end point of the drone as the starting point and end point of the ant colony; each ant individual in the ant colony selects the next node according to the dynamic transfer probability calculation model, and the ant individual determines the next node to be actually moved through the variable step length search behavior, and records the path information of each ant individual from the starting point to the end point; when all ant individuals reach the end point, the optimal ant individual of this iteration is selected and the worker ant foraging behavior is performed, and the pheromone concentration of each path in the space is updated; the iteration is repeated until the preset number of iterations is reached and the iteration is terminated, and the path with the highest pheromone concentration is selected as the final path of the drone.

[0078] The system is used to implement the method in Example 1, which will not be described in detail here.

[0079] Embodiment three:

[0080] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any embodiment of the present invention when executing the program.

[0081] Embodiment 4:

[0082] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method described in any embodiment of the present invention is implemented.

[0083] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0084] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0085] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0086] In several embodiments provided in the present application, if any function 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 application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0087] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A three-dimensional path planning method for substation drones based on improved ant colony algorithm, characterized in that: The following steps are involved: Generate a three-dimensional environmental model for power drone inspection and perform adaptive grid division on the three-dimensional environmental model for power drone inspection; Initialize the ant colony to search for paths in the grid-divided three-dimensional environment model of the power drone inspection, and set the starting point and end point of the drone as the starting point and end point of the ant colony; Each ant in the ant colony selects the next node according to the dynamic transfer probability calculation model. The ant individual determines the next node to move to through variable step length search behavior, and records the path information of each ant individual from the starting point to the end point. When all ant individuals reach the end point, the best ant individual of this iteration is selected and the worker ant foraging behavior is performed to update the pheromone concentration of each path in the space; The iteration is repeated until the preset number of iterations is reached and the path with the highest pheromone concentration is selected as the final path of the UAV.

2. According to the method of three-dimensional path planning of substation UAV based on improved ant colony algorithm in claim 1, it is characterized in that: The steps for adaptive grid division of the three-dimensional environment model of power UAV inspection are as follows: Set the latitude, and divide the three-dimensional environment model space of the power drone inspection into multiple slices equally according to the slice latitude, and each slice is a grid; When a grid vertex touches an obstacle, the grid adaptively adjusts the size of the direction of the vertex, as shown in the following formula: Where: dk Indicates the size length of the grid when the mth adjustment is made; ε d0 represents the initial length of the grid; δ represents the adjustment step size.

3. The three-dimensional path planning method for substation drone based on improved ant colony algorithm according to claim 1 is characterized in that: The dynamic transition probability calculation model is specifically shown in the following formula: in: represents the probability that ant individual k moves from node i to node ; represents the pheromone concentration of edge (i, j) at time t; represents the heuristic function of edge (i, j) at time t; N represents the total number of next nodes that ant individual k can choose at node i; s represents the next node selected by ant individual k at node i; represents the pheromone concentration of edge (i, s) at time t; represents the heuristic function of edge (i, s) at time t; rand1 represents the iteration factor threshold; ξ represents the iteration factor; T represents the current number of iterations; T max represents the maximum number of iterations; α represents the pheromone importance factor; β represents the expected heuristic factor.

4. The three-dimensional path planning method for substation drone based on improved ant colony algorithm according to claim 3 is characterized in that: The variable step length search behavior is specifically to perform a variable step length random search in the grid formed by the node and the current node before the ant individual moves to the next node, as shown in the following formula: P j =P i +(P′ j -P i )·rand·γ Where: P j represents the coordinates of the next node calculated by random search with variable step length; P′ j represents the candidate next node coordinates calculated by the dynamic transition probability calculation model; P i Represents the current node coordinates; rand represents a random number; γ represents the step factor; n represents the variable step factor.

5. The three-dimensional path planning method for substation drone based on improved ant colony algorithm according to claim 4 is characterized in that: The ant individuals with the best path in each generation of ant colonies are regarded as worker ants that have found food, and they call other ants to approach. The formula for calling the ant colony behavior is as follows: Among them: the new position of ant individual k after being summoned; represents the current position of ant individual k; Indicates the location of the ant individual on the optimal path.

6. The three-dimensional path planning method for substation drone based on improved ant colony algorithm according to claim 5 is characterized in that: The optimal ant individual search behavior formula is as follows: in: represents the individual position of the ant on the next optimal path obtained by searching; ε represents the adjustment coefficient.

7. A three-dimensional path planning system for substation drones based on improved ant colony algorithm, characterized in that: Including grid division module and ant colony path planning module; The grid division module is used to generate a three-dimensional environment model for power drone inspection and to perform adaptive grid division on the three-dimensional environment model for power drone inspection; The ant colony path planning module is used to initialize the ant colony to search for paths in the three-dimensional environment model of the power drone inspection after grid division, and set the starting point and end point of the drone as the starting point and end point of the ant colony; each ant individual in the ant colony selects the next node according to the dynamic transfer probability calculation model, and the ant individual determines the next node to be actually moved through the variable step length search behavior, and records the path information of each ant individual from the starting point to the end point; when all ant individuals reach the end point, the optimal ant individual of this iteration is selected and the worker ant foraging behavior is performed, and the pheromone concentration of each path in the space is updated; the iteration is repeated until the preset number of iterations is reached and the iteration is terminated, and the path with the highest pheromone concentration is selected as the final path of the drone.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images