A path planning method for inspection robots based on substation environment

Abstract

The present invention provides a path planning method for an inspection robot based on a substation environment, belonging to the technical field of substation inspection. It includes constructing a weighted map of the substation, obtaining multiple optimal planning paths by using an iterative method, and selecting the optimal planning path with the highest pheromone concentration as the optimal inspection path of the inspection robot. It includes calculating the heuristic estimated cost of each node to obtain an initial planning path, introducing an inspection importance weight factor to calculate the heuristic information between nodes and evaluate the path fitness, so as to obtain the optimal initial planning path in the current iteration process; calculating the pheromone increment between nodes to update the pheromone concentration between nodes; calculating the selection probability based on the ant colony algorithm, and selecting the next node according to the selection probability until a planning path is constructed, which is used as the optimal planning path for this iteration. The present invention solves the problem of insufficient path planning of the existing automatic inspection system in a complex environment.

Description

Technical Field

[0001] The present invention relates to a path planning method for inspection robots based on substation environment, and belongs to the technical field of substation inspection. Background Art

[0002] In modern power systems, substations, as key facilities, undertake the important tasks of power conversion and distribution. Their normal operation directly affects the safety and stability of the entire power network. With the continuous growth of power load, the number and scale of substations are also continuously expanding, facing increasingly complex equipment maintenance and safety monitoring challenges. The previous manual inspection method, which relies on human labor for equipment inspection, not only has low efficiency, but also has significant safety risks in substations with complex environments and high hazards. Therefore, there is an urgent need for a new type of intelligent inspection system to improve inspection efficiency, reduce labor costs, and ensure the safety of power facilities.

[0003] Traditional inspection methods involve manual inspection, specifically including regular inspections, equipment status assessment, etc. These means can perform certain monitoring work when the technical means are relatively backward. However, with the increase in the types of equipment and the progress of technology, the limitations of manual inspection gradually become apparent: First, the work intensity of manual inspection is large, which may cause fatigue of the staff, resulting in misinspection or missed inspection; Second, the interior of substations is often full of obstacles and complex corridor layouts, and it is difficult to avoid potential safety hazards during manual inspection. In addition, the flexibility of manual inspection is insufficient and it cannot respond quickly to the actual state of the equipment.

[0004] To solve these problems, the rise of automated inspection robots provides a new solution for substation inspection work. Inspection robots can not only navigate autonomously in complex environments and avoid obstacles, but also realize real-time monitoring of equipment status by integrating advanced sensors and monitoring devices. However, there is a problem of insufficient path planning in the existing automatic inspection system in complex environments. Summary of the Invention

[0005] The purpose of the present invention is to provide a path planning method for inspection robots based on substation environment, which can effectively avoid obstacles in complex environments, and at the same time consider the priority of inspection tasks and the shortest distance of the path, ensuring that the robot can complete tasks efficiently and safely during the inspection process, and solving the problem of insufficient path planning in the existing automatic inspection system in complex environments.

[0006] To solve the above technical problems, the present invention is implemented by adopting the following technical solutions.

[0007] The present invention provides a path planning method for inspection robots based on substation environment, including:

[0008] Take the equipment inside the substation as nodes, take the accessible paths between the equipment as edges, initialize the pheromone concentration between the nodes, and construct a weighted map of the substation;

[0009] According to the weighted map of the substation, use an iterative method to obtain multiple optimal planning paths, and select the optimal planning path with the highest pheromone concentration as the optimal inspection path of the inspection robot;

[0010] Among them, the iterative method includes:

[0011] Calculate the heuristic estimated cost of each node to obtain an initial planning path;

[0012] Based on the initial planning path, introduce an inspection importance weight factor to calculate the heuristic information between nodes, and evaluate the path fitness according to the heuristic information to obtain the optimal initial planning path in the current iteration process;

[0013] According to the path fitness and the pheromone concentration between nodes, calculate the pheromone increment between nodes and update the pheromone concentration between nodes;

[0014] Based on the ant colony algorithm, calculate the selection probability according to the pheromone concentration and heuristic information between nodes, and select the next node according to the selection probability until a planning path is constructed as the optimal planning path for this iteration.

[0015] Furthermore, it also includes that the inspection robot conducts automatic inspection according to the optimal inspection path of the inspection robot, obtains the inspection result according to the path data of the inspection robot's automatic inspection, adjusts the internal environment information of the substation according to the inspection result, and updates the weighted map of the substation, where the inspection result includes equipment failure and encountering obstacles.

[0016] Furthermore, calculating the heuristic estimated cost of each node to obtain an initial planning path includes:

[0017] Introduce a safety penalty weight factor to improve the heuristic function, and use the improved heuristic function to calculate the heuristic estimated cost of each intermediate node from the current node to the target node;

[0018] According to the heuristic estimated cost, select intermediate nodes from the current node to the target node as the initial planning path.

[0019] Furthermore, the improved heuristic function is expressed as:

[0020] ;

[0021] In the formula, represents the The heuristic estimated cost of the intermediate node represents the heuristic estimated cost of the th intermediate node calculated by the original heuristic function of the A* algorithm. represents the safety penalty weight factor, represents the th distance between the intermediate node and the safety area.

[0022] Furthermore, based on the initial planned path, a patrol importance weight factor is introduced to calculate the heuristic information between nodes, and the path fitness is evaluated according to the heuristic information to obtain the optimal initial planned path in the current iteration process; among them, the heuristic information between the nodes is expressed as:

[0023] ;

[0024] In the formula, represents the heuristic information between the th node and the th node in the initial planned path, represents the patrol importance weight factor of the th node, represents the th coordinate of the node and the th coordinate of the node the Euclidean distance between them.

[0025] Furthermore, according to the path fitness and the pheromone concentration between nodes, calculate the pheromone increment between nodes and update the pheromone concentration between nodes, including:

[0026] Calculate the pheromone evaporation rate according to the fitness of the current initial planned path and the fitness of the optimal initial planned path in the current iteration process;

[0027] Obtain the pheromone increment according to the fitness of the optimal initial planned path in the current iteration process and the pheromone concentration between nodes;

[0028] Update the pheromone concentration between nodes according to the pheromone evaporation rate and the pheromone increment.

[0029] Furthermore, the pheromone evaporation rate is expressed as:

[0030] ;

[0031] In the formula, represents the pheromone evaporation rate of the th iteration process, represents the exponential function, Represents an adjustment parameter, represents the fitness of the optimal initial planning path in the current iteration process, Represents the fitness of the initial planning path in the

[0032] Further, according to the pheromone evaporation rate and the pheromone increment, update the pheromone concentration between nodes, where the update formula of the pheromone concentration is expressed as:

[0033] ;

[0034] In the formula, represents the pheromone concentration between the th node and the th node after update, represents the pheromone evaporation rate in the th iteration process, represents the pheromone concentration between the th node and the th node before update, represents the pheromone increment from the th node moving to the th node.

[0035] Further, the calculation expression of the selection probability is:

[0036] ;

[0037] In the formula, represents the probability of selecting to move from the th node to the th node, represents the pheromone concentration between the th node and the th node, represents the pheromone concentration between the th node and its neighbor node , where, represents the pheromone importance factor, which is used to adjust the influence of pheromone in path selection, represents the th node and the th node heuristic information, represents the th node and its neighbor node heuristic information, where, represents the heuristic information importance factor, which is used to adjust the influence of heuristic information in path selection, represents the The set of all neighbor nodes of a node.

[0038] Furthermore, after obtaining the optimal inspection path, it also includes removing redundant points in the optimal inspection path through the RDP algorithm to perform smoothing and optimization processing on the optimal inspection path:

[0039] (1) Connect the initial node and the termination node of the optimal inspection path to form a straight line segment as the reference section, and at the same time add the initial node and the termination node to the optimal inspection node set;

[0040] (2) Calculate the vertical distance from each node in the optimal inspection path to the reference section, determine the maximum value of the vertical distance and the node corresponding to the maximum vertical distance;

[0041] (3) Compare the maximum value of the vertical distance with a preset threshold:

[0042] If the maximum value of the vertical distance is less than or equal to the preset threshold, connect all the nodes in the optimal inspection node set as the final optimal inspection path;

[0043] If the maximum value of the vertical distance is greater than the preset threshold, then add the node with the maximum vertical distance as the splitting node to the optimal inspection node set. For all sub-paths split by the splitting node, repeat steps (2)-(3) until the maximum value of the vertical distance of all nodes in all sub-paths is less than or equal to the preset threshold, and connect all the nodes in the optimal inspection node set as the final optimal inspection path.

[0044] Compared with the prior art, the beneficial effects achieved by the present invention:

[0045] 1. By combining the A* algorithm and the ant colony algorithm, the present invention realizes the intelligent planning of the substation inspection path. First, the A* algorithm is used to quickly calculate the initial planned path, providing a good starting point for the subsequent ant colony algorithm. Then, by introducing the inspection importance weight factor and dynamically updating the pheromone concentration according to the path fitness and pheromone increment, the planned path can fully consider the importance of each device in the substation and the priority of the inspection. Finally, the optimal planned path with the highest pheromone concentration is selected as the optimal inspection path of the inspection robot, ensuring that the inspection robot can perform inspections along the most efficient and accurate route, thus greatly improving the efficiency and accuracy of the inspection;

[0046] 2. The present invention obtains the internal environment information of the substation, constructs the network topology of the internal environment of the substation, and initializes the pheromone concentration between nodes, obtaining a weighted map that can reflect the actual layout and passage conditions of the substation. On this basis, through an iterative optimization process, the path selection is continuously adjusted according to the heuristic estimated cost, heuristic information, and pheromone concentration, so that the planned optimal inspection path can well adapt to the complex environment of the substation. In addition, since this method adopts the strategy of dynamically updating the pheromone concentration, it can flexibly respond to changes in the equipment layout or passage conditions in the substation, ensuring the real-time and effectiveness of the inspection path. This environmental adaptability and flexibility make this method have a wider applicability and higher reliability in practical applications;

[0047] 3. The present invention not only realizes the intelligent path planning of the inspection robot based on the substation environment, but also can dynamically adjust the internal environment information of the substation according to the inspection results including equipment failures and obstacles encountered after the inspection robot completes the automatic inspection. This dynamic adjustment mechanism enables the weighted map of the substation to reflect the actual situation of the substation in real time, including key information such as equipment status and path passability. By continuously updating the weighted map of the substation, the inspection robot can utilize more accurate environmental information during the next inspection, thereby further optimizing the inspection path and improving the inspection efficiency and accuracy. The combination of this dynamic optimization and intelligent inspection makes the operation and maintenance management of the substation more intelligent and efficient;

[0048] 4. The present invention also introduces a safety penalty weight factor during the path planning process, calculates the heuristic estimated cost between nodes by improving the heuristic function, so as to obtain a safer initial planned path, enabling the inspection robot to fully consider safety factors when planning the path and avoid selecting potentially dangerous areas. In addition, during the path selection process, the present invention further ensures the reliability and optimality of the inspection path by dynamically updating the pheromone concentration between nodes and calculating the selection probability, improving the safety and reliability of the inspection process, and reducing the risk of equipment damage or casualties caused by improper path planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 The figure shows a schematic flowchart of a method for path planning of an inspection robot based on the substation environment provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0050] The technical solution of the present invention will be described in detail below with reference to the drawings and specific embodiments. It should be understood that the specific features in the embodiments of the present invention and the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. Without conflict, the technical features in the embodiments of the present invention and the embodiments can be combined with each other.

[0051] The term "and / or" is merely a description of the relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. Additionally, the character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0052] Embodiment 1

[0053] As Figure 1 shown, this embodiment introduces a path planning method for an inspection robot based on the substation environment, including:

[0054] Step 1: Take the equipment inside the substation as nodes, take the accessible paths between the equipment as edges, initialize the pheromone concentration between the nodes, and construct a weighted map of the substation.

[0055] The present invention collects the environmental information inside the substation through sensors, cameras or other data collection means. The environmental information inside the substation includes the specific positions, types of equipment, and accessible paths between the equipment, etc., providing basic data for constructing the network topology structure and path planning.

[0056] Based on the obtained environmental information, the present invention abstracts the internal environment of the substation into a network topology structure, where the equipment serves as the nodes of the network topology structure, and the accessible paths between the equipment serve as the edges of the network topology structure. At the same time, the pheromone concentration between the nodes is initialized. The pheromone concentration is a key parameter in the ant colony algorithm, used to simulate the accumulation of pheromones in the biological foraging process. Through the above process, the present invention obtains a weighted map that can reflect the internal environmental structure and traffic conditions of the substation, providing a model basis for path planning.

[0057] Step 2: According to the weighted map of the substation, use an iterative method to obtain multiple optimal planned paths, and select the optimal planned path with the highest pheromone concentration as the optimal inspection path of the inspection robot:

[0058] Among them, the iterative method includes:

[0059] According to the weighted map of the substation, calculate the heuristic estimated cost of each node based on the A* algorithm to obtain an initial planned path.

[0060] The A* algorithm is a heuristic search algorithm that uses a heuristic function to estimate the cost from the current node to the target node. The present invention improves the heuristic function by introducing a safety penalty weight factor, making the planned path safer. This step can quickly generate an initial planned path from the starting point to the ending point.

[0061] Based on the initial planned path, a heuristic information between nodes is calculated by introducing an inspection importance weight factor, and the path fitness is evaluated according to the heuristic information to obtain the optimal initial planned path in the current iteration process.

[0062] In the ant colony algorithm, heuristic information is used to guide ants to select the next node. By introducing an inspection importance weight factor in the present invention, the heuristic information can reflect the inspection priority and importance of equipment, making the path planning more in line with the actual inspection requirements of the substation and improving the inspection efficiency and accuracy.

[0063] According to the path fitness and the pheromone concentration between nodes, the pheromone increment between nodes is calculated to update the pheromone concentration between nodes.

[0064] In the present invention, the pheromone concentration is dynamically updated according to the fitness of the path, i.e., the quality of the path, and the pheromone increment between nodes, enabling the path planning process to gradually converge to the optimal solution and improving the stability and accuracy of path planning.

[0065] Based on the ant colony algorithm, the selection probability is calculated according to the pheromone concentration and heuristic information between nodes, and the next node is selected according to the selection probability until a planned path is constructed as the optimal planned path for this iteration.

[0066] The ant colony algorithm finds the optimal path by simulating the pheromone accumulation and selection behavior in the biological foraging process. The present invention is based on the ant colony algorithm, calculates the selection probability according to the pheromone concentration and heuristic information between nodes, and selects the next node accordingly, gradually constructing a complete path from the starting point to the ending point by simulating the biological foraging behavior.

[0067] In the ant colony algorithm, the path with a higher pheromone concentration indicates its better quality. Therefore, after the iteration ends, the optimal planned path with the highest pheromone concentration is selected as the optimal inspection path of the inspection robot, obtaining an optimal path that meets the inspection requirements of the substation, providing guidance for the automatic inspection of the inspection robot, realizing the intelligent inspection of substation equipment, improving the inspection efficiency and accuracy of substation equipment, and reducing the cost and risk of manual inspection.

[0068] Embodiment 2

[0069] Based on the same inventive concept as Embodiment 1, this embodiment introduces a path planning method for an inspection robot based on the substation environment, including the following steps:

[0070] Step 1: Take the equipment inside the substation as nodes, take the accessible paths between the equipment as edges, initialize the pheromone concentration between nodes, and construct a weighted substation map.

[0071] Step 2: According to the substation weighted map, use the iterative method to obtain multiple optimal planning paths, and select the optimal planning path with the highest pheromone concentration as the optimal inspection path of the inspection robot.

[0072] Among them, the iterative method includes:

[0073] Step 2.1: Calculate the heuristic estimated cost of each node to obtain the initial planning path.

[0074] In this embodiment, according to the substation weighted map, based on the A* algorithm, calculate the heuristic estimated cost of each node to obtain the initial planning path, including:

[0075] Introduce a safety penalty weight factor to improve the heuristic function, and use the improved heuristic function to calculate the heuristic estimated cost of each intermediate node between the current node and the target node;

[0076] According to the heuristic estimated cost, select an intermediate node between the current node and the target node as the initial planning path.

[0077] In this embodiment, the improved heuristic function is expressed as:

[0078] ;

[0079] In the formula, represents the heuristic estimated cost of the th intermediate node calculated by the improved heuristic function, represents the heuristic estimated cost of the th intermediate node calculated by the original heuristic function of the A* algorithm, represents the safety penalty weight factor, represents the th intermediate node's distance from the safe area.

[0080] Step 2.2: Based on the initial planning path, introduce an inspection importance weight factor to calculate the heuristic information between nodes, and evaluate the path fitness according to the heuristic information to obtain the optimal initial planning path in the current iteration process.

[0081] In this embodiment, the heuristic information between nodes is expressed as:

[0082] ;

[0083] In the formula, represents the heuristic information between the th node and the th node in the initial planning path, represents the The inspection importance weight factor of the nodes, Indicates the coordinates of the th node and the coordinates of the th node.

[0084] Step 3.3: Dynamically update the pheromone concentration between nodes according to the path fitness and the pheromone increment between nodes.

[0085] In this embodiment, calculating the pheromone increment between nodes according to the path fitness and the pheromone concentration between nodes, and updating the pheromone concentration between nodes includes:

[0086] Calculating the pheromone evaporation rate according to the fitness of the current initial planned path and the fitness of the optimal initial planned path in the current iteration process, and the pheromone evaporation rate is expressed as:

[0087] ;

[0088] In the formula, Indicates the pheromone evaporation rate of the th iteration process, Indicates the exponential function, Indicates the adjustment parameter, Indicates the fitness of the optimal initial planned path in the current iteration process, Indicates the fitness of the initial planned path of the

[0089] Obtaining the pheromone increment according to the fitness of the optimal initial planned path in the current iteration process and the pheromone concentration between nodes;

[0090] Updating the pheromone concentration between nodes according to the pheromone evaporation rate and the pheromone increment, where the update formula of the pheromone concentration is expressed as:

[0091] ;

[0092] In the formula, Indicates the updated pheromone concentration between the th node and the th node, Indicates the pheromone evaporation rate of the th iteration process, Indicates the pheromone concentration between the th node and the th node before update, Indicates moving from the th node to the The pheromone increment of a node.

[0093] Step 3.4: Based on the ant colony algorithm, calculate the selection probability according to the pheromone concentration and heuristic information between nodes, and select the next node according to the selection probability until a planned path is constructed as the optimal planned path for this iteration.

[0094] In this embodiment, the calculation expression of the selection probability is:

[0095] ;

[0096] In the formula, represents the probability of moving from the -th node to the -th node, represents the pheromone concentration between the -th node and the -th node, represents the pheromone concentration between the -th node and the neighbor node , where represents the pheromone importance factor, which is used to adjust the influence of pheromone in path selection, represents the heuristic information between the -th node and the -th node, represents the heuristic information between the -th node and the neighbor node , where represents the heuristic information importance factor, which is used to adjust the influence of heuristic information in path selection, represents the set of all neighbor nodes of the -th node.

[0097] Step 4: After obtaining the optimal inspection path, it further includes removing redundant points in the optimal inspection path through the RDP algorithm to perform smoothing and optimization processing on the optimal inspection path.

[0098] In this embodiment, removing redundant points in the optimal inspection path through the RDP algorithm to perform smoothing and optimization processing on the optimal inspection path includes:

[0099] (1) Connect the initial node and the termination node of the optimal inspection path to form a straight line segment as the reference section, and at the same time add the initial node and the termination node to the optimal inspection node set.

[0100] In this embodiment, the optimal inspection node set is used to store all nodes on the final inspection path.

[0101] (2) Calculate the vertical distance from each node in the optimal inspection path to the reference section, determine the maximum value of the vertical distance and the node corresponding to the maximum vertical distance.

[0102] In this embodiment, by traversing each node in the optimal inspection path and calculating the vertical distance from each node to the reference section, the maximum value of the vertical distance and the node corresponding to the maximum vertical distance are determined to quantify the deviation degree between each node and the reference section, and the node with the largest deviation degree is found.

[0103] (3) Compare the maximum value of the vertical distance with a preset threshold:

[0104] The purpose is to decide whether to split the path according to the deviation degree of the node. If the maximum value of the vertical distance is less than or equal to the preset threshold, it means that all nodes are close enough to the reference section, and the reference section can be directly used as part of the inspection path, and all the nodes that have been added to the optimal inspection node set are connected to form the final path. If the maximum value of the vertical distance is greater than the preset threshold, it means that at least one node is far from the reference section, and the node needs to be split.

[0105] In this embodiment, if the maximum value of the vertical distance is less than or equal to the preset threshold, all the nodes in the optimal inspection node set are connected as the final optimal inspection path;

[0106] In this embodiment, if the maximum value of the vertical distance is greater than the preset threshold, the node with the maximum vertical distance is added as a split node to the optimal inspection node set. For all the sub-paths split by the split node, repeat steps (2)-(3) until the maximum value of the vertical distance of all nodes in all sub-paths is less than or equal to the preset threshold, and all the nodes in the optimal inspection node set are connected as the final optimal inspection path.

[0107] In this embodiment, taking the node with the maximum vertical distance as the split node, the original path can be split into two or more sub-paths.

[0108] Step 5: The inspection robot performs automatic inspection according to the optimal inspection path of the inspection robot, obtains the inspection result according to the path data of the automatic inspection of the inspection robot, adjusts the internal environment information of the substation according to the inspection result, and updates the weighted map of the substation.

[0109] In this embodiment, the inspection results include equipment failures and obstacles encountered.

[0110] After the inspection robot conducts automatic inspection according to the optimal inspection path, an inspection result is obtained based on the path data of the automatic inspection of the inspection robot. The internal environment information of the substation is adjusted according to the inspection result, and the weighted map of the substation is updated, where the inspection result includes equipment failures and encountering obstacles. The equipment represents the nodes of the weighted map of the substation, and the passable paths between the equipment represent the edges of the weighted map of the substation.

[0111] In this embodiment, the inspection robot can reflect changes or abnormal situations found during the inspection, such as equipment status, environmental parameters, new passable paths, or obstacle changes, onto the internal environment information and weighted map of the substation, facilitating the continuous update and maintenance of the weighted map of the substation, ensuring that the inspection path of the substation always remains in an optimal state, and improving the inspection efficiency and safety.

[0112] Embodiment 3

[0113] Based on the same inventive concept as other embodiments, this embodiment provides a computer-readable storage medium with computer instructions stored thereon, characterized in that when the computer instructions are executed by a processor, the steps of the method in Embodiment 1 or 2 above are implemented.

[0114] Embodiment 4

[0115] Based on the same inventive concept as other embodiments, this embodiment also provides a computer program product, including computer instructions, characterized in that when the computer instructions are executed by a processor, the steps of the method in Embodiment 1 or 2 above are implemented.

[0116] In summary of the above embodiments, the present invention realizes the intelligent planning of the inspection path of the substation by combining the A* algorithm and the ant colony algorithm. First, the A* algorithm is used to quickly calculate the initial planned path, providing a good starting point for the subsequent ant colony algorithm. Then, by introducing the inspection importance weight factor and dynamically updating the pheromone concentration according to the path fitness and pheromone increment, the planned path can fully consider the importance of each device in the substation and the priority of the inspection. Finally, the optimal planned path with the highest pheromone concentration is selected as the optimal inspection path of the inspection robot, ensuring that the inspection robot can perform inspections along the most efficient and accurate route, thus greatly improving the inspection efficiency and accuracy.

[0117] By acquiring the internal environmental information of a substation, constructing the network topology of the substation's internal environment, and initializing the pheromone concentration between nodes, a weighted map that can reflect the actual layout and traffic conditions of the substation is obtained. On this basis, through an iterative optimization process, the path selection is continuously adjusted according to the heuristic estimated cost, heuristic information, and pheromone concentration, so that the planned optimal inspection path can well adapt to the complex environment of the substation. In addition, since this method adopts the strategy of dynamically updating the pheromone concentration, it can flexibly cope with changes in the equipment layout or traffic conditions in the substation, ensuring the real-time and effectiveness of the inspection path. This environmental adaptability and flexibility make this method have wider applicability and higher reliability in practical applications;

[0118] The present invention not only realizes the intelligent path planning of the inspection robot based on the substation environment, but also can dynamically adjust the internal environmental information of the substation according to the inspection results including equipment failures and encountered obstacles after the inspection robot completes the automatic inspection. This dynamic adjustment mechanism enables the weighted map of the substation to reflect the actual situation of the substation in real time, including key information such as equipment status and path passability. By continuously updating the weighted map of the substation, the inspection robot can utilize more accurate environmental information during the next inspection, thereby further optimizing the inspection path and improving the inspection efficiency and accuracy. The combination of this dynamic optimization and intelligent inspection makes the operation and maintenance management of the substation more intelligent and efficient;

[0119] The present invention also introduces a safety penalty weight factor during the path planning process, and calculates the heuristic estimated cost between nodes by improving the heuristic function, so as to obtain a safer initial planned path, enabling the inspection robot to fully consider safety factors when planning the path and avoid selecting potentially dangerous areas. In addition, during the path selection process, the present invention further ensures the reliability and optimality of the inspection path by dynamically updating the pheromone concentration between nodes and calculating the selection probability, enhancing the safety and reliability of the inspection process, and reducing the risk of equipment damage or casualties caused by improper path planning. Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0120] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices produce a means for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0121] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction means that implements the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0122] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0123] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the spirit and scope protected by the claims of the present invention. These all fall within the protection scope of the present invention.

Claims

1. A patrol robot path planning method based on a substation environment, characterized in that: include: The devices inside the substation are regarded as nodes, the accessible paths between the devices are regarded as edges, the pheromone concentration between the nodes is initialized, and a weighted map of the substation is constructed; According to the weighted map of the substation, an iterative method is used to obtain multiple optimal planning paths, and the optimal planning path with the highest pheromone concentration is selected as the optimal inspection path for the inspection robot; Among them, the iterative method includes: Calculate the heuristic estimated cost of each node and obtain the initial planning path; Based on the initial planned path, the inspection importance weight factor is introduced to calculate the heuristic information between the nodes, and the path fitness is evaluated according to the heuristic information to obtain the optimal initial planned path in the current iteration process; According to the path fitness and the pheromone concentration between nodes, the pheromone increment between nodes is calculated and the pheromone concentration between nodes is updated; Based on the ant colony algorithm, the selection probability is calculated according to the pheromone concentration and heuristic information between the nodes, and the next node is selected according to the selection probability until a planning path is constructed as the optimal planning path for this iteration.

2. The inspection robot path planning method based on the substation environment according to claim 1 is characterized in that: It also includes a patrol robot performing automatic patrol according to the optimal patrol path, obtaining patrol results based on the path data of the automatic patrol of the patrol robot, adjusting the internal environment information of the substation according to the patrol results, and updating the weighted map of the substation, wherein the patrol results include equipment failures and obstacles encountered.

3. The inspection robot path planning method based on the substation environment according to claim 1 is characterized in that: Calculate the heuristic estimated cost of each node and get the initial planning path, including: The safety penalty weight factor is introduced to improve the heuristic function, and the improved heuristic function is used to calculate the heuristic estimated cost of each intermediate node between the current node and the target node; According to the heuristic estimated cost, an intermediate node is selected from the current node to the target node as the initial planning path.

4. The inspection robot path planning method based on the substation environment according to claim 3 is characterized in that: The improved heuristic function is expressed as: ； In the formula, represents the first The heuristic estimated cost of the intermediate nodes, It represents the first value calculated by the original heuristic function of the A* algorithm. The heuristic estimated cost of the intermediate nodes, represents the safety penalty weight factor, Indicates The distance between the intermediate node and the safe area.

5. The inspection robot path planning method based on the substation environment according to claim 1 is characterized in that: The heuristic information between the nodes is expressed as: ； In the formula, Indicates the first Nodes and The heuristic information between nodes, Indicates The inspection importance weight factor of each node, Indicates The coordinates of the nodes and The coordinates of the nodes The Euclidean distance between .

6. The inspection robot path planning method based on the substation environment according to claim 1 is characterized in that: According to the path fitness and the pheromone concentration between nodes, the pheromone increment between nodes is calculated and the pheromone concentration between nodes is updated, including: Calculate the pheromone volatilization rate according to the fitness of the current initial planning path and the fitness of the optimal initial planning path in the current iteration process; According to the fitness of the optimal initial planning path in the current iteration and the pheromone concentration between nodes, the pheromone increment is obtained; The pheromone concentration between nodes is updated according to the pheromone volatilization rate and the pheromone increment.

7. The inspection robot path planning method based on the substation environment according to claim 6 is characterized in that: The pheromone volatilization rate is expressed as: ； In the formula, Indicates The pheromone volatilization rate of the iteration process is represents the exponential function, represents the adjustment parameters, Represents the fitness of the optimal initial planning path in the current iteration process, Indicates The fitness of the initial planning path of the iterative process.

8. The inspection robot path planning method based on the substation environment according to claim 7 is characterized in that: According to the pheromone volatilization rate and the pheromone increment, the pheromone concentration between nodes is updated, wherein the updating formula of the pheromone concentration is expressed as: ； In the formula, Indicates the updated Nodes and The pheromone concentration between nodes, Indicates The pheromone volatilization rate of the iteration process is Indicates the number before the update Nodes and The pheromone concentration between nodes, Indicates that from The node moves to The pheromone increment of each node.

9. The inspection robot path planning method based on the substation environment according to claim 1 is characterized in that: The calculation expression of the selection probability is: ； In the formula, Indicates that from The node chooses to move to The probability of a node, Indicates Nodes and The pheromone concentration between nodes, Indicates nodes and neighbor nodes The pheromone concentration between Represents the pheromone importance factor, which is used to adjust the influence of pheromone in path selection. Indicates Nodes and The heuristic information between nodes, Indicates nodes and neighbor nodes The heuristic information between Represents the heuristic information importance factor, which is used to adjust the influence of heuristic information in path selection. Indicates The set of all neighbor nodes of a node.

10. The inspection robot path planning method based on the substation environment according to claim 1 is characterized in that: After obtaining the optimal inspection path, the method further includes removing redundant points in the optimal inspection path by using an RDP algorithm to smooth and optimize the optimal inspection path: (1) Connecting the initial node and the terminal node of the optimal inspection path to form a straight line segment as a reference segment, and adding the initial node and the terminal node to the optimal inspection node set; (2) Calculate the vertical distance from each node in the optimal inspection path to the reference section, determine the maximum vertical distance and the corresponding node with the maximum vertical distance; (3) Compare the maximum vertical distance with the preset threshold: If the maximum vertical distance is less than or equal to the preset threshold, all nodes in the optimal inspection node set are connected as the final optimal inspection path; If the maximum vertical distance is greater than a preset threshold, the node with the maximum vertical distance is added as a split node to the optimal inspection node set. For all sub-paths split by the split node, steps (2) to (3) are repeated until the maximum vertical distances of all nodes in all sub-paths are less than or equal to the preset threshold. All nodes in the optimal inspection node set are connected as the final optimal inspection path.

Images