Coordinated inspection path optimization method and device, computer device, medium and product

Abstract

The application relates to a cooperative inspection path optimization method and device, computer equipment, a medium and a product. The method comprises the following steps: obtaining a directed graph model corresponding to a target inspection area which is constructed in advance; wherein the directed graph model comprises a node set and an arc segment set, the arc segment set comprises an arc segment between any two nodes, and each arc segment has a corresponding distance parameter; based on the attribute parameters of the inspection equipment and the distance parameters of the arc segments, a cooperative path optimization model is constructed and solved to minimize the overall inspection time, and a cooperative inspection scheme is obtained; wherein the inspection equipment comprises a set of unmanned aerial vehicles; the cooperative path optimization model comprises a constraint condition and an objective function; the cooperative inspection scheme comprises target arc segments that need to be inspected by each unmanned aerial vehicle in the set of unmanned aerial vehicles and target nodes to be inspected that need to be charged at target charging nodes by the unmanned aerial vehicles, and the target charging node refers to the charging node closest to the target node to be inspected. The method can improve the inspection efficiency.

Description

Technical Field

[0001] This application relates to the field of collaborative inspection technology using unmanned aerial vehicles (UAVs), and in particular to a collaborative inspection path optimization method, apparatus, computer equipment, medium, and product. Background Technology

[0002] With the continuous expansion of highway construction, the number of power facilities along the routes, such as transmission lines, power poles, and substations, has increased significantly. These highway power facilities are the core foundation for ensuring the normal operation of lighting, monitoring, and communication systems along the highways. Highway power facilities are exposed to the complex outdoor environment for extended periods, making them susceptible to damage from lightning strikes, strong winds, icing, and vehicle impacts. This can lead to defects such as line damage, pole tilting, and insulator aging. If these defects are not detected and addressed promptly, they can cause power outages, equipment failures, and even traffic accidents, seriously threatening the safe and stable operation of the highway. Therefore, conducting regular inspections of highway power facilities is crucial.

[0003] In related technologies, drone inspection is one of the important methods for inspecting power facilities along highways. In this mode, operators control drones equipped with sensors to conduct aerial inspections. However, this mode suffers from low inspection efficiency. Summary of the Invention

[0004] Therefore, it is necessary to provide a collaborative inspection path optimization method, device, computer equipment, medium, and product that can improve inspection efficiency in order to address the above-mentioned technical problems.

[0005] Firstly, this application provides a collaborative inspection path optimization method, including:

[0006] Obtain a pre-constructed directed graph model corresponding to the target inspection area; wherein, the directed graph model includes a set of nodes and a set of arcs, the set of nodes includes the start and end nodes of the inspection task, the node to be inspected, and the charging node, and the set of arcs includes the arcs between any two nodes, and each arc has a corresponding distance parameter;

[0007] Based on the attribute parameters of the inspection equipment and the distance parameters of the arc segment, a collaborative path optimization model with the goal of minimizing the overall inspection time is constructed and solved to obtain a collaborative inspection scheme.

[0008] The inspection equipment includes a set of drones; the collaborative path optimization model includes constraints and an objective function; the collaborative inspection scheme includes: the target arc segment that each drone in the drone set needs to inspect and the target charging node that the drone needs to go to for charging, wherein the target charging node is the charging node closest to the target charging node.

[0009] In one embodiment, the attribute parameters of the inspection device include the flight speed and single charging time of the UAV; the step of constructing and solving a collaborative path optimization model with the objective of minimizing the overall inspection time based on the attribute parameters of the inspection device and the distance parameters of the arc segment to obtain a collaborative inspection scheme includes: determining the flight time corresponding to the arc segment according to the flight speed and the distance parameters of each arc segment; and constructing and solving a collaborative path optimization model with the objective of minimizing the overall inspection time based on the flight time and the single charging time to obtain the collaborative inspection scheme.

[0010] In one embodiment, the inspection equipment further includes a vehicle set, and at least some arc segments in the arc set are first arc segments, which are used to characterize the driving road segments corresponding to the inspection tasks performed by the vehicles in the vehicle set; the collaborative inspection scheme further includes the target first arc segments that each vehicle in the vehicle set needs to inspect.

[0011] In one embodiment, the attribute parameters of the inspection equipment include the vehicle's driving speed, the drone's flight speed, and the single charging time. The step of constructing and solving a collaborative path optimization model based on the inspection equipment's attribute parameters and the distance parameters of the arc segments to minimize the overall inspection time, thereby obtaining a collaborative inspection scheme, includes: determining the driving time corresponding to the first arc segment based on the driving speed and the distance parameters of each first arc segment; determining the flight time corresponding to the arc segment based on the flight speed and the distance parameters of each arc segment; and constructing and solving a collaborative path optimization model based on the driving time, the flight time, and the single charging time to minimize the overall inspection time, thereby obtaining the collaborative inspection scheme.

[0012] In one embodiment, the objective function is used to minimize the total time for all inspection devices to complete all inspection tasks, the total time being the maximum value between the completion times of all UAV inspections and all vehicle inspections; the inputs to the objective function include: the flight time corresponding to each arc segment, the travel time corresponding to each first arc segment, and the single charging time; the decision variables of the objective function include: UAV inspection variables for each arc segment, vehicle inspection variables for each first arc segment, and UAV charging variables for each node to be inspected; the UAV inspection variables are used to characterize whether the UAV inspects the arc segment, the vehicle inspection variables are used to characterize whether the vehicle inspects the first arc segment, and the UAV charging variables are used to characterize whether the UAV goes to the nearest charging node to charge at the node to be inspected.

[0013] In one embodiment, the constraint includes at least one of the following:

[0014] The initial power constraint is used to characterize the remaining power of the UAV when it arrives at the first node in the first step, which is less than or equal to the difference between the initial power of the UAV and the power consumed by the UAV in flying from the start and end nodes to the first node.

[0015] The first power consumption constraint is used to characterize the current remaining power of the drone when it has not been charged in the previous node. It is equal to the difference between the remaining power in the previous node and the power consumption in this flight segment.

[0016] The second power consumption constraint is used to characterize the current remaining power of the drone when it returns to the previous node after charging at the nearest charging node. It is equal to the difference between the remaining power of the drone when it returns to the previous node and the power consumed during this flight segment. The remaining power of the drone when it returns to the previous node is determined based on the initial power of the drone and the power required for the drone to fly from the previous node to the nearest charging node.

[0017] The safe power constraint is used to characterize that the remaining power of the drone is greater than or equal to the safe buffer power of the drone; the safe buffer power refers to the power required for the drone to fly from any node in the node set to the nearest charging node.

[0018] Secondly, this application also provides a collaborative inspection path optimization device, comprising:

[0019] The acquisition module is used to acquire a pre-constructed directed graph model corresponding to the target inspection area; wherein, the directed graph model includes a set of nodes and a set of arcs, the set of nodes includes the start and end nodes of the inspection task, the node to be inspected, and the charging node, and the set of arcs includes the arcs between any two nodes, and each arc has a corresponding distance parameter;

[0020] The solution module is used to construct and solve a collaborative path optimization model with the goal of minimizing the overall inspection time, based on the attribute parameters of the inspection equipment and the distance parameters of the arc segment, so as to obtain a collaborative inspection scheme.

[0021] The inspection equipment includes a set of drones; the collaborative path optimization model includes constraints and an objective function; the collaborative inspection scheme includes: the target arc segment that each drone in the drone set needs to inspect and the target charging node that the drone needs to go to for charging, wherein the target charging node is the charging node closest to the target charging node.

[0022] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the collaborative inspection path optimization method provided in the first aspect of this application.

[0023] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the collaborative inspection path optimization method provided in the first aspect of this application.

[0024] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the collaborative inspection path optimization method provided in the first aspect of this application.

[0025] The aforementioned collaborative inspection path optimization method, device, computer equipment, computer-readable storage medium, and computer program product acquire a pre-constructed directed graph model corresponding to the target inspection area. The directed graph model includes a set of nodes and a set of arcs. The node set includes the start and end nodes of the inspection task, nodes to be inspected, and charging nodes. The arc set includes arcs between any two nodes, and each arc has a corresponding distance parameter. Based on the attribute parameters of the inspection equipment and the distance parameters of the arcs, a collaborative path optimization model is constructed and solved to minimize the overall inspection time, resulting in a collaborative inspection scheme. The inspection equipment includes a set of drones. The collaborative path optimization model includes constraints and an objective function. The collaborative inspection scheme includes: the target arcs that each drone in the drone set needs to inspect, and the target nodes to be inspected that the drones need to reach for charging. The target charging node is the charging node closest to the target node to be inspected. This application's embodiments construct a collaborative path optimization model to minimize the overall inspection time. It supports drones traveling to the nearest charging node to the inspection point during their inspection journey. Based on this, the drone's inspection path is planned, yielding the target arc segment and target nodes to be inspected. With this scheme, when a drone needs charging during inspection, it does not need to return to a fixed charging point but instead proceeds to the nearest charging node to continue its inspection mission. This reduces the unnecessary flight mileage and time spent traveling to and from fixed charging points, thereby shortening the overall completion time of the inspection mission and improving inspection efficiency. Furthermore, collaborative inspection by multiple drones offers high mobility, is not limited by terrain or traffic conditions, and can quickly cover a large area, thus improving inspection coverage. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is a diagram illustrating the application environment of a collaborative inspection path optimization method in one embodiment.

[0028] Figure 2 This is a flowchart illustrating a collaborative inspection path optimization method in one embodiment;

[0029] Figure 3 This is a flowchart illustrating step 202 in one embodiment;

[0030] Figure 4 This is a flowchart illustrating step 202 in another embodiment;

[0031] Figure 5 This is a flowchart illustrating a collaborative inspection path optimization method in a specific example.

[0032] Figure 6 This is a structural block diagram of a collaborative inspection path optimization device in one embodiment;

[0033] Figure 7 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0034] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0035] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0036] Currently, there are two main modes of inspection for power facilities along highways. The first is the ground inspection mode, where inspectors drive vehicles equipped with high-definition cameras and infrared detectors to conduct close-range inspections of power facilities along the highway. The advantage of this mode is high inspection accuracy, capable of clearly identifying even minor defects. However, this mode is limited by highway traffic flow, resulting in lower inspection efficiency. For power facilities crossing complex sections such as mountains, bridges, and tunnels, ground inspection vehicles have difficulty reaching them, creating blind spots. The second mode is the drone inspection mode, where operators control drones equipped with sensors to conduct aerial inspections of areas inaccessible to ground vehicles. The advantage of this mode is high mobility, unrestricted by terrain and traffic conditions, and the ability to quickly cover large areas. However, drones are limited by battery life, resulting in shorter single inspection times and a limited effective inspection range. When inspecting long-distance power facilities along highways, drones need to frequently return to recharge, significantly reducing inspection efficiency.

[0037] In recent years, the ground-air collaborative inspection model has gradually become a research hotspot. This model combines the high-precision inspection advantages of ground inspection vehicles with the high mobility and coverage advantages of drones, and is expected to achieve comprehensive and efficient inspection of power facilities along highways.

[0038] In existing ground-air collaborative inspection path planning methods, most treat the inspection start and end points as the only charging nodes for drones. When the drone's battery is low, it must return to the fixed node to recharge. In long-distance inspection missions, drones need to frequently travel back and forth between the start and end points, generating a large amount of invalid flight mileage and time, leading to an increase in the overall time consumption of the inspection mission and a decrease in inspection efficiency. Therefore, this charging mode generates a large amount of invalid flight time, resulting in an increase in the overall time consumption of the inspection mission, and this efficiency loss increases significantly with the extension of highway inspection mileage.

[0039] To address the aforementioned issues, this application proposes a collaborative inspection path optimization method that supports drone charging during transit, thereby improving the efficiency and coverage of power facility inspections along highways.

[0040] The collaborative inspection path optimization method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104, or it can be located in the cloud or on other network servers. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, drones, low-altitude aircraft, IoT devices, and portable wearable devices. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0041] In one exemplary embodiment, such as Figure 2 As shown, a collaborative inspection path optimization method is provided, which is then applied to... Figure 1 Taking the server in the example, the explanation includes the following steps 201 and 202. Wherein:

[0042] Step 201: Obtain the directed graph model corresponding to the pre-constructed target inspection area.

[0043] The directed graph model includes a set of nodes and a set of arcs. The set of nodes includes the start and end nodes of the inspection task, the node to be inspected, and the charging node. The set of arcs includes the arcs between any two nodes, and each arc has a corresponding distance parameter.

[0044] For example, the actual road network structure of the target inspection area (such as a section of a highway) is determined, obtaining the inspection start and end points, the locations of the equipment to be inspected, and the locations of charging stations, where there are multiple charging stations. Then, based on the inspection start and end points, the locations of the equipment to be inspected, and the locations of the charging stations, the start and end point nodes, the nodes to be inspected, and the charging nodes are determined respectively. Any two nodes are connected by an arc segment, abstracting the complex road network of the target inspection area into a directed graph model G: ,in Let represent a set of nodes, denoted as . It includes the start and end nodes of the inspection task, the node to be inspected, and the charging node. The start and end nodes are the departure and return points of the inspection equipment. For ease of subsequent calculation, they are represented by 0 and 0 respectively. Represents a virtual start and virtual end point. Set of arc segments. Due to the maneuverability advantage of low-altitude flight, drones are not limited by network topology and can traverse... Arbitrary arcs in the middle, by introducing virtual arc segments and The virtual start and end points of the inspection task are represented by the arcs between the virtual start point and the virtual end point, and the arcs between the virtual end point and the virtual start point, respectively. Each arc in the directed graph model has a corresponding (flight) distance parameter.

[0045] Each arc segment has a direction, therefore there are two arc segments with opposite directions between any two nodes, such as arc segments. This represents the arc segment pointing from node i to node j. This represents the arc segment pointing from node j to node i.

[0046] Step 202: Based on the attribute parameters of the inspection equipment and the distance parameters of the arc segment, construct and solve the collaborative path optimization model with the goal of minimizing the overall inspection time, and obtain the collaborative inspection scheme.

[0047] The inspection equipment includes a collection of drones. Let d represent the drone; the cooperative path optimization model includes constraints and objective function; the cooperative inspection scheme includes: the target arc segment that each drone in the drone set needs to inspect and the target charging node that the drone (during the inspection) needs to go to for charging. The target charging node is the charging node that is closest to the target charging node.

[0048] In related technologies, when a drone departs from a warehouse, its battery capacity is at its initial charge. As the inspection operation continues, the drone's battery capacity gradually decreases. When faced with road sections far from the warehouse or long road segments, the drone, limited by its battery capacity, will have to return to the warehouse. To solve this problem, this application embodiment sets up some drone charging stations (corresponding charging nodes) within the road network area to improve drone operation efficiency. Specifically, when the drone's battery level is lower than the charge required for its next road segment inspection, it can choose to charge at the nearest charging station instead of returning to the warehouse. This helps to shorten the overall damage inspection completion time of the road network area.

[0049] For example, firstly, the drone's attribute parameters, such as flight speed, battery level, and charging parameters, are obtained, along with the distance parameters for each arc segment. Based on these attribute and distance parameters, a collaborative path optimization model is constructed to minimize the overall inspection time. This model includes constraints and an objective function. Then, the collaborative path optimization model is solved according to the constraints and objective function. When the overall inspection time is minimized, a collaborative inspection scheme is obtained, which includes the target arc segments that each drone needs to inspect in the arc segment set, and the target nodes to be inspected that each drone needs to charge (going to the nearest target charging node to charge and then returning to that target node). Here, the overall inspection time is the maximum value among the inspection completion times of all drones in the drone set, and the inspection completion time for each drone refers to the time taken to inspect, charge, and return from the start and end nodes.

[0050] After receiving the collaborative inspection plan, each drone conducts inspections sequentially according to its corresponding target arc segment. During the inspection, it travels to the nearest target charging node to recharge at its corresponding target inspection node. After charging, it returns to the target inspection node and proceeds to the next node. In this way, the drones achieve collaborative inspection of the target inspection area, and instead of returning to a fixed point to charge, they travel to charging nodes during the inspection process.

[0051] In the aforementioned collaborative inspection path optimization method, a pre-constructed directed graph model corresponding to the target inspection area is obtained. This directed graph model includes a set of nodes and a set of arcs. The node set includes the start and end nodes of the inspection task, nodes to be inspected, and charging nodes. The arc set includes arcs between any two nodes, each arc having a corresponding distance parameter. Based on the attribute parameters of the inspection equipment and the distance parameters of the arcs, a collaborative path optimization model is constructed and solved to minimize the overall inspection time, resulting in a collaborative inspection scheme. The inspection equipment includes a set of drones. The collaborative path optimization model includes constraints and an objective function. The collaborative inspection scheme includes: the target arcs that each drone in the drone set needs to inspect, and the target nodes to be inspected that the drones need to reach for charging. The target charging node is the charging node closest to the target node to be inspected. This application's embodiments construct a collaborative path optimization model to minimize the overall inspection time. It supports drones traveling to the nearest charging node to the inspection point during their inspection journey. Based on this, the drone's inspection path is planned, yielding the target arc segment and target nodes to be inspected. With this scheme, when a drone needs charging during inspection, it does not need to return to a fixed charging point but instead proceeds to the nearest charging node to continue its inspection mission. This reduces the unnecessary flight mileage and time spent traveling to and from fixed charging points, thereby shortening the overall completion time of the inspection mission and improving inspection efficiency. Furthermore, collaborative inspection by multiple drones offers high mobility, is not limited by terrain or traffic conditions, and can quickly cover a large area, thus improving inspection coverage.

[0052] In one exemplary embodiment, the inspection device's attribute parameters include the drone's flight speed and single-charge duration. For example... Figure 3 As shown, step 202 includes steps 301 and 302. Wherein:

[0053] Step 301: Determine the flight time corresponding to each arc segment based on the flight speed and the distance parameters of each arc segment.

[0054] For example, each drone maintains a constant flight speed. For each arc segment, the distance parameter of the arc segment is divided by the flight speed of the drone to obtain the flight time of the drone for that arc segment. The flight time refers to the time required for the drone to pass through the arc segment.

[0055] Step 302: Based on flight time and single charging time, construct and solve a collaborative path optimization model with the goal of minimizing the overall inspection time to obtain a collaborative inspection scheme.

[0056] Alternatively, assuming that the charging time for each drone is the same and fixed, the charging time for each drone can be determined in advance based on actual needs, historical experience, expert knowledge, etc.

[0057] For example, a cooperative path optimization model is constructed based on flight duration and single-charge duration. This model includes an objective function and constraints. The input to the objective function includes the flight duration corresponding to each arc segment. And the single charging time of drones The decision variables of the objective function include the drone inspection variables for each arc segment. And the drone charging variables at each node to be inspected The drone inspection variable characterizes whether the drone inspects an arc segment, while the drone charging variable characterizes whether the drone goes to the nearest charging node to charge at the node to be inspected. The output of the objective function is the overall inspection time, which is the maximum value among the inspection completion times of each drone. Constraints include drone battery constraints and path continuity constraints to ensure the drone's battery safety and path feasibility throughout the inspection process.

[0058] R: The set of steps for the drone, with the maximum number of steps per drone controlled within a certain limit. Within a step, This represents a specific step of the drone; where step 0 in R corresponds to the start of the inspection task.

[0059] The variables for drone inspection and drone charging are represented as follows:

[0060] : 0-1 variable, if arc segment If the drone d is inspected in step r, the value is 1; otherwise, it is 0. : A 0-1 variable. If the drone d goes to the nearest charging node to node i to charge, it is 1; otherwise, it is 0.

[0061] The constructed collaborative path optimization model is solved. When the overall inspection time is minimized, the corresponding UAV inspection variables and UAV charging variables are obtained. The overall inspection time is the maximum value among the inspection completion times of all UAVs. The inspection completion time of each UAV is the sum of its total flight time and total charging time. The total flight time is determined based on the UAV inspection variables, the distance parameters of each arc segment, and the UAV inspection variables themselves. The total charging time is determined based on the UAV charging variables and the single charging time. When a UAV inspection variable is 0, the arc segment corresponding to that variable is determined not to be the UAV's target arc segment. When a UAV inspection variable is 1, the arc segment corresponding to that variable is determined to be the UAV's target arc segment. When a UAV charging variable is 0, the UAV will not proceed to the nearest charging node at the corresponding inspection node. When a UAV charging variable is 1, the UAV will proceed to the nearest charging node at the corresponding inspection node. This yields the collaborative inspection scheme.

[0062] After obtaining the collaborative inspection plan, each drone is controlled to inspect according to the target arc segment. When it reaches the target node to be inspected, the drone is controlled to go to the target charging node closest to that node to charge. After charging is completed, it returns to the target node to be inspected and continues to perform the inspection task.

[0063] Therefore, in this embodiment, the collaborative path optimization model is solved based on the drone's flight speed and single charging time, enabling the drone to go to the nearest charging node for charging during the inspection, thereby reducing the invalid flight mileage and time caused by going back and forth to fixed charging points, effectively shortening the overall inspection time and improving inspection efficiency.

[0064] The above scheme can improve the efficiency and coverage of multi-UAV collaborative inspection. Based on this, in order to improve the inspection accuracy of the target inspection area, collaborative inspection is achieved by combining it with ground inspection vehicles. The following is an example.

[0065] In one exemplary embodiment, the inspection equipment further includes a vehicle set, denoted as... Let k represent a vehicle. At least some arcs in the arc set are the first arcs, which are used to characterize the driving segments corresponding to the inspection tasks performed by the vehicles in the vehicle set; the collaborative inspection scheme also includes the target first arcs that each vehicle in the vehicle set needs to inspect.

[0066] That is, a subset of the arc segment set A The first arc segment corresponds to the actual road arc, which includes the road segments that are actually passable by ground vehicles. Each first arc segment has a corresponding distance parameter.

[0067] For example, when the inspection equipment includes a set of drones and a set of vehicles, during model construction, the set of drones corresponds to all arc segments, while the set of vehicles corresponds to the first arc segment among all arc segments. The attribute parameters of the inspection equipment include the attribute parameters of the drones and the attribute parameters of the vehicles. Therefore, when executing step 202, based on the attribute parameters of the drones, the attribute parameters of the vehicles, and the distance parameters of the arc segments (including the distance parameters of the first arc segment), a collaborative path optimization model with the objective of minimizing the overall inspection time is constructed and solved, obtaining the target arc segment and target inspection node corresponding to each drone, and the target first arc segment corresponding to each vehicle. Here, the overall inspection time is the maximum value among the inspection completion times of all drones and all vehicles. The inspection completion time of each drone refers to the time taken to inspect and charge from the start and end nodes and return to the start and end nodes, and the inspection completion time of each vehicle refers to the time taken to inspect from the start and end nodes and return to the start and end nodes.

[0068] In this embodiment, multiple drones and multiple vehicles are used to conduct ground-air collaborative inspections of power facilities along the highway. By combining the high-precision inspection advantages of ground inspection vehicles with the high mobility, coverage, and efficiency advantages of drones, comprehensive and efficient inspections of power facilities along the highway can be achieved.

[0069] The path optimization scheme for the ground-air cooperative mode is explained in detail below.

[0070] In one exemplary embodiment, the attribute parameters of the inspection equipment include the vehicle's travel speed, and the drone's flight speed and single charging time. For example... Figure 4 As shown, step 202 includes steps 401 to 403, wherein:

[0071] Step 401: Determine the travel time corresponding to the first arc segment based on the travel speed and the distance parameters of each first arc segment.

[0072] For example, each vehicle maintains a constant driving speed. For each first arc segment, the distance parameter of the first arc segment (i.e., the arc segment) is divided by the vehicle's driving speed to obtain the (vehicle's) travel time for the first arc segment. The travel time refers to the time required for the vehicle to pass through the first arc segment.

[0073] Step 402: Determine the flight time corresponding to each arc segment based on the flight speed and the distance parameters of each arc segment.

[0074] For example, each drone maintains a constant flight speed. For each arc segment, the distance parameter of the arc segment is divided by the flight speed of the drone to obtain the flight time of the drone for that arc segment. The flight time refers to the time required for the drone to pass through the arc segment.

[0075] Step 403: Based on driving time, flight time and single charging time, construct and solve a collaborative path optimization model with the goal of minimizing the overall inspection time to obtain a collaborative inspection scheme.

[0076] Alternatively, assuming that the charging time for each drone is the same and fixed, the charging time for each drone can be determined in advance based on actual needs, historical experience, expert knowledge, etc.

[0077] For example, a cooperative path optimization model is constructed based on driving time, flight time, and single charging time. This model includes an objective function and constraints.

[0078] The objective function minimizes the total time required for all inspection devices to complete all inspection tasks. The total time is the maximum of the completion times for all drone inspections and all vehicle inspections. The input to the objective function includes the flight time corresponding to each arc segment. The driving time corresponding to each first arc segment And the single charging time of drones The decision variables for the objective function include: the drone inspection variables for each arc segment. Drone charging variables at each inspection node and vehicle inspection variables in each first arc segment The objective function defines the following variables: drone inspection variable (whether the drone inspects an arc segment), vehicle inspection variable (whether the vehicle inspects the first arc segment), and drone charging variable (whether the drone goes to the nearest charging node to charge at the node to be inspected). The output of the objective function is the overall inspection time, which is the maximum of the inspection completion times of each drone and each vehicle. The inspection completion time for each drone refers to the time taken to inspect, charge, and return from the start and end nodes. The inspection completion time for each vehicle refers to the time taken to inspect and return from the start and end nodes. Constraints include drone battery constraints, path continuity constraints, and node balance constraints to ensure battery safety and path feasibility for both drones and vehicles throughout the inspection process.

[0079] The set of steps for ground vehicles, with the number of ground patrols per vehicle controlled within a certain range. Within a step, This represents a specific step, where step 0 in S corresponds to the start of the inspection task.

[0080] R: The set of steps for the drone, with the maximum number of steps per drone controlled within a certain limit. Within a step, This represents a specific step of the drone; where step 0 in R corresponds to the start of the inspection task.

[0081] : 0-1 variable, if arc segment If the ground vehicle k is inspected in step s, the result is 1; otherwise, the result is 0.

[0082] : 0-1 variable, if arc segment If the drone d is inspected in step r, the value is 1; otherwise, it is 0.

[0083] : A 0-1 variable. If the drone d goes to the nearest charging node to node i to charge, it is 1; otherwise, it is 0.

[0084] The constructed collaborative path optimization model is solved. When the overall inspection time is minimized, the corresponding UAV inspection variables and UAV charging variables are obtained. The overall inspection time is the maximum value among the total times required for all inspection devices to complete all inspection tasks (i.e., inspection completion time). The inspection completion time for each UAV is the sum of its total flight time and total charging time. The total flight time is determined based on the UAV inspection variables, the distance parameters of each arc segment, and the UAV inspection variables themselves. The total charging time is determined based on the UAV charging variables and the single charging time. The inspection completion time for each vehicle is its total travel time. When the UAV inspection variable is 0, it is determined that the arc segment corresponding to that UAV inspection variable does not belong to the UAV's target arc segment; when the UAV inspection variable is 1, it is determined that the arc segment corresponding to that UAV inspection variable belongs to the UAV's target arc segment. When the UAV charging variable is 0, it is determined that the UAV will not go to the nearest charging node to charge at the corresponding inspection node; when the UAV charging variable is 1, it is determined that the UAV will go to the nearest charging node to charge at the corresponding inspection node. When the vehicle inspection variable is 0, it is determined that the first arc segment corresponding to the vehicle inspection variable does not belong to the target first arc segment of the vehicle; when the vehicle inspection variable is 1, it is determined that the first arc segment corresponding to the vehicle inspection variable belongs to the target first arc segment of the drone. This yields a collaborative inspection scheme for drones and vehicles.

[0085] After obtaining the collaborative inspection plan, each drone is controlled to start from the start and end nodes and inspect according to the target arc. When it reaches the target node to be inspected, the drone is controlled to go to the target charging node closest to that node to charge. After charging, it returns to the target node to be inspected and continues to perform the inspection task. After the inspection is completed, it returns to the start and end nodes. At the same time, each vehicle is controlled to start from the start and end nodes and inspect according to the first target arc. After the inspection is completed, it returns to the start and end nodes.

[0086] Optionally, the objective of the cooperative path optimization model in this embodiment is to minimize the total time for all inspection devices to complete all inspection tasks. This total time is the maximum of the completion times for all UAV inspections and all vehicle inspections. The model allocates each arc segment to ground vehicles and UAVs in an optimal manner and arranges the charging scheme for the UAVs. The objective function of the model is:

[0087]

[0088] in, Represents arc segment The corresponding flight time (that is, the time it takes for the drone to pass through the arc segment). Indicates the first arc segment The corresponding travel time (that is, the time it takes for the vehicle to pass through the arc segment). This indicates the duration of a single charge for the drone.

[0089] In the specific solution, , and Substituting the values ​​into the objective function and considering the constraints, we solve for the objective function by minimizing its output, obtaining the values ​​of each decision variable: value, The value and The value of .

[0090] Therefore, in this embodiment, a collaborative path optimization model is solved based on the drone's flight speed, single charging time, and vehicle speed, enabling the drone to charge at the nearest charging node during the inspection, thereby reducing the invalid flight mileage and time caused by traveling to and from fixed charging points, effectively shortening the overall inspection time and improving inspection efficiency; at the same time, the collaborative solution with ground vehicles can ensure inspection accuracy.

[0091] In one exemplary embodiment, the variables of the cooperative path optimization model further include:

[0092] : Continuous variable, the remaining battery power of drone d when it reaches node i in step r.

[0093] : Continuous variable, the cumulative travel time of ground vehicle k to reach node i in step s.

[0094] : Continuous variable, the cumulative travel time of drone d to reach node i in step r.

[0095] The constraints include at least one of the following: initial power constraint, first power consumption constraint, second power consumption constraint, and safe power constraint.

[0096] The initial battery constraint characterizes the remaining battery power of the drone when it reaches the first node in the first step. It is less than or equal to the difference between the drone's initial battery power and the battery power consumed by the drone flying from the start-stop node to the first node. The formula for the initial battery constraint is:

[0097]

[0098] in, This represents the remaining battery power of drone d when it reaches the first node i in step 1. This indicates the drone's initial battery level (i.e., initial battery capacity). Indicates the power of the drone. Represents arc segment The corresponding flight time (that is, the time it takes for the drone to pass through the arc segment). Represents arc segment The corresponding drone inspection variables, if arc segment If the drone d is inspected in step 1, the result is 1; otherwise, the result is 0. This indicates the amount of electricity consumed by the drone as it flies from the start point to the first node.

[0099] The first power consumption constraint characterizes the drone's current remaining power when it was not charged at the previous node. It is equal to the difference between the remaining power at the previous node and the power consumed during this flight segment. The formula for the first power consumption constraint is:

[0100]

[0101] in, This represents the remaining battery power of drone d when it reaches the current node j in step r. This represents the remaining battery power of drone d when it reaches node i in step r-1. Indicates the power of the drone. This indicates the flight time corresponding to the arc segment (that is, the time it takes for the drone to pass through the arc segment). Represents arc segment The corresponding drone inspection variables, if arc segment If the drone d is inspected in step r, the value is 1; otherwise, it is 0. This represents the drone charging variable corresponding to node i to be inspected. If drone d arrives at node i in step r-1... If the device is ready to charge at the nearest charging node, the value is 1; otherwise, it is 0. This paragraph Power consumption during flight. M is a very large positive number; the "big M method" is used here.

[0102] The second power consumption constraint characterizes the drone's current remaining power when it returns to the previous node after charging at the nearest charging node. It is equal to the difference between the drone's remaining power upon returning to the previous node and the power consumed during this flight segment. The remaining power upon returning to the previous node is determined based on the drone's initial power and the power required to fly from the previous node to the nearest charging node. The formula for the second power consumption constraint is:

[0103]

[0104] in, This represents the remaining battery power of drone d when it reaches the current node j in step r. This indicates the drone's initial battery level (i.e., initial battery capacity). Indicates that the drone started from the previous node. The amount of electricity required to fly to the nearest charging station. This indicates the remaining battery power of the drone when it returns to the previous node. Indicates the power of the drone. Represents arc segment The corresponding flight time (that is, the time it takes for the drone to pass through the arc segment). Represents arc segment The corresponding drone inspection variables, if arc segment If the drone d is inspected in step r, the value is 1; otherwise, it is 0. This represents the drone charging variable corresponding to node i to be inspected. If drone d arrives at node i in step r-1... If the device is ready to charge at the nearest charging node, the value is 1; otherwise, it is 0.

[0105] In other words, this constraint is a constraint on the drone's ground charging behavior, where the drone starts charging from the node. Energy consumption required to fly to the nearest charging station This indicates that it is at the node After selecting charging, it returns to the node. The remaining battery power at that time is Accordingly, it reaches the next node. The remaining battery power at that time is .

[0106] The safe power constraint characterizes a drone's remaining power level as greater than or equal to its safe power buffer. The safe power buffer refers to the amount of power required for the drone to fly from any node in the node set to the nearest charging node. The formula for the safe power constraint is:

[0107]

[0108] in, This represents the remaining battery power of drone d when it reaches node i in step r. This represents the safe power buffer, used to ensure that the drone can reach the nearest charging station for charging at any point. The safe power buffer for the drone can be determined in advance based on actual needs, historical experience, etc. For a specific area, it needs to be calculated in advance. Once the calculation is completed, the input model is known. For example, a 10% power buffer ensures that the drone's power is safe at all times.

[0109] If the drone is at the node Once the drone chooses to fly to the nearest charging station, it will fly back to the node after charging is complete. Continue the inspection operation. During the inspection process, the drone must maintain a safe battery level at all times.

[0110] Optionally, the constraints may also include:

[0111] The start and end point constraints characterize each inspection device's departure from and return to the start and end points once, forcing vehicles and drones to depart from and return to virtual nodes. The formula for the vehicle's start and end point constraints is as follows:

[0112]

[0113]

[0114] in, Represents arc segment The vehicle inspection variable, with a value of 1 indicating an arc segment. The ground vehicle k conducts the first step (step 1) inspection. Represents arc segment The vehicle inspection variable, with a value of 1 indicating an arc segment. Ground vehicle k performs inspections in step s.

[0115] The formula for the start and end point constraints of the drone is:

[0116]

[0117]

[0118] in, Represents arc segment The drone inspection variable, with a value of 1 indicating an arc segment. The drone is used for the first step (step 1) inspection. Represents arc segment The drone inspection variable, with a value of 1 indicating an arc segment. The drone d is used for inspection in step r.

[0119] The flow balance constraint characterizes the number of times each inspection device enters a node to be inspected as the number of times it leaves that node, ensuring a balance between the inflow and outflow of vehicles and drones at each node. The constraint formula is:

[0120]

[0121]

[0122] in, , These represent the arc segments corresponding to vehicle k in step s. Vehicle inspection variables, arcs Vehicle inspection variables, , These represent the arc segments corresponding to UAV d in step r. Drone inspection variables, arc segments The variables of drone inspection.

[0123] The path continuity constraint is used to characterize that after each inspection device reaches the node to be inspected in the current step, it leaves the node in the next step, ensuring that after the inspection device reaches the node in the s-th step, it leaves the node in the s-th step. The steps involve leaving the node. The constraint formula is:

[0124]

[0125]

[0126] in, This represents the arc segment corresponding to vehicle k in step s+1. Vehicle inspection variables, This represents the arc segment corresponding to drone d in step r+1. The variables of drone inspection.

[0127] The time accumulation constraint is used to represent the cumulative travel time of vehicles and drones. The cumulative travel time at a given node is the sum of the cumulative travel time at the previous node and the travel time for that arc segment. The constraint formula is:

[0128]

[0129] in, This represents the cumulative travel time of vehicle k in step s to reach node j. This represents the cumulative travel time of vehicle k to reach node i in step s-1. Represents arc segment The corresponding travel time. This represents the cumulative flight time of drone d when it reaches node j in step t. This represents the cumulative flight time of drone d in step r-1 when it reaches node i. Represents arc segment The corresponding flight duration.

[0130] Arc traversal constraint is used to characterize that each node to be inspected is inspected at least once by an inspection device, ensuring that the power facilities of each arc are inspected at least by ground vehicles or drones.

[0131]

[0132] in, =1, =1; =1, =0; or, =0, =1.

[0133] Path selection constraints are used to ensure that vehicles and drones can only select one arc segment at each step:

[0134]

[0135]

[0136] Variable range constraints restrict the range of values ​​for each variable. Specifically:

[0137]

[0138]

[0139]

[0140]

[0141]

[0142] Therefore, by constructing the aforementioned multi-dimensional constraints, this embodiment ensures efficient collaborative inspection of multiple drones and vehicles, thereby improving both inspection efficiency and accuracy.

[0143] The collaborative inspection path optimization method of this application embodiment is described below through a specific example.

[0144] like Figure 5 As shown, the collaborative inspection path optimization method includes the following steps:

[0145] Step 501: Obtain the directed graph model corresponding to the pre-constructed target inspection area.

[0146] The directed graph model includes a set of nodes and a set of arcs. The set of nodes includes the start and end nodes of the inspection task, the node to be inspected, and the charging node. The set of arcs includes the arcs between any two nodes. At least some of the arcs in the set of arcs are first arcs. The first arcs are used to characterize the driving segments corresponding to the vehicles in the vehicle set performing the inspection task. Each arc has a corresponding distance parameter.

[0147] Step 502: Obtain a pre-built collaborative path optimization model with the goal of minimizing the overall inspection time, including the objective function and constraints.

[0148] The objective function is to minimize the total time for all inspection equipment to complete all inspection tasks. The total time is the maximum value between the completion time of all drone inspections and the completion time of all vehicle inspections.

[0149] The inputs to the objective function include: the flight time corresponding to each arc segment, the travel time corresponding to each first arc segment, and the charging time per charge.

[0150] The decision variables of the objective function include: drone inspection variables for each arc segment, vehicle inspection variables for each first arc segment, and drone charging variables for each node to be inspected. The drone inspection variable is used to characterize whether the drone inspects the arc segment, the vehicle inspection variable is used to characterize whether the vehicle inspects the first arc segment, and the drone charging variable is used to characterize whether the drone goes to the nearest charging node to charge at the node to be inspected.

[0151] Step 503: Determine the travel time corresponding to the first arc segment based on the travel speed and the distance parameters of each first arc segment;

[0152] Step 504: Determine the flight time corresponding to each arc segment based on the flight speed and the distance parameters of each arc segment;

[0153] Step 505: Substitute the driving time, flight time, and single charging time into the objective function, and solve the collaborative path optimization model based on the constraints to obtain the collaborative inspection scheme.

[0154] The collaborative inspection scheme includes: the target arc segment that each drone in the drone ensemble needs to inspect, the target node to be inspected that the drone needs to go to for charging, and the target first arc segment that each vehicle in the vehicle ensemble needs to inspect. The target charging node refers to the charging node that is closest to the target node to be inspected.

[0155] In summary, this application's embodiments deploy multiple drone charging stations along highways. By constructing an objective function and multi-dimensional constraints, inspection path planning for ground vehicles and drones is performed. The resulting optimized solution supports drone charging during inspections, breaking the limitations of traditional fixed-node charging modes. This effectively reduces the drone's ineffective flight mileage and time, significantly shortens the total time required for long-distance power facility inspection tasks, and improves inspection efficiency.

[0156] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0157] Based on the same inventive concept, this application also provides a collaborative inspection path optimization device for implementing the collaborative inspection path optimization method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the collaborative inspection path optimization device provided below can be found in the limitations of the collaborative inspection path optimization method described above, and will not be repeated here.

[0158] In one exemplary embodiment, such as Figure 6 As shown, a collaborative inspection path optimization device is provided, including: an acquisition module 601 and a solution module 602, wherein:

[0159] The acquisition module 601 is used to acquire the directed graph model corresponding to the pre-constructed target inspection area; wherein, the directed graph model includes a set of nodes and a set of arcs. The set of nodes includes the start and end nodes of the inspection task, the node to be inspected, and the charging node. The set of arcs includes the arcs between any two nodes, and each arc has a corresponding distance parameter.

[0160] The solver module 602 is used to construct and solve a collaborative path optimization model with the goal of minimizing the overall inspection time based on the attribute parameters of the inspection equipment and the distance parameters of the arc segment, so as to obtain a collaborative inspection scheme.

[0161] The inspection equipment includes a collection of drones; the collaborative path optimization model includes constraints and an objective function; the collaborative inspection scheme includes: the target arc segment that each drone in the drone collection needs to inspect and the target charging node that the drone needs to go to for charging. The target charging node is the charging node that is closest to the target charging node.

[0162] In one embodiment, the attribute parameters of the inspection equipment include the flight speed of the UAV and the single charging time; the solution module 602 is specifically used to: determine the flight time corresponding to each arc segment based on the flight speed and the distance parameter of each arc segment; and construct and solve a collaborative path optimization model with the goal of minimizing the overall inspection time based on the flight time and the single charging time, thereby obtaining a collaborative inspection scheme.

[0163] In one embodiment, the inspection equipment further includes a vehicle set, and at least some arc segments in the arc set are first arc segments, which are used to characterize the driving road segments corresponding to the inspection tasks performed by the vehicles in the vehicle set; the collaborative inspection scheme further includes the target first arc segment that each vehicle in the vehicle set needs to inspect.

[0164] Furthermore, the attribute parameters of the inspection equipment include the vehicle's driving speed, the drone's flight speed, and the duration of a single charge. The solution module 602 is specifically used to: determine the driving time corresponding to the first arc segment based on the driving speed and the distance parameters of each first arc segment; determine the flight time corresponding to the arc segment based on the flight speed and the distance parameters of each arc segment; and construct and solve a collaborative path optimization model with the goal of minimizing the overall inspection time based on the driving time, flight time, and duration of a single charge, thereby obtaining a collaborative inspection scheme.

[0165] In one embodiment, the objective function minimizes the total time for all inspection devices to complete all inspection tasks. The total time is the maximum of the completion times of all drone inspections and all vehicle inspections. The inputs to the objective function include: the flight time corresponding to each arc segment, the travel time corresponding to each first arc segment, and the single charging time. The decision variables of the objective function include: drone inspection variables for each arc segment, vehicle inspection variables for each first arc segment, and drone charging variables for each node to be inspected. The drone inspection variables characterize whether the drone inspects an arc segment, the vehicle inspection variables characterize whether the vehicle inspects a first arc segment, and the drone charging variables characterize whether the drone goes to the nearest charging node to charge at the node to be inspected.

[0166] In one embodiment, the constraint includes at least one of the following:

[0167] The initial power constraint is used to characterize the remaining power of the drone when it reaches the first node in the first step. It is less than or equal to the difference between the initial power of the drone and the power consumed by the drone flying from the start and end nodes to the first node.

[0168] The first power consumption constraint is used to characterize the drone's current remaining power when the drone has not been charged in the previous node. It is equal to the difference between the remaining power in the previous node and the power consumption in this flight segment.

[0169] The second power consumption constraint is used to characterize the current remaining power of the drone after it returns to the previous node after charging at the nearest charging node. It is equal to the difference between the remaining power of the drone when it returns to the previous node and the power consumed during this flight segment. The remaining power of the drone when it returns to the previous node is determined based on the drone's initial power and the power required for the drone to fly from the previous node to the nearest charging node.

[0170] The safe power constraint is used to characterize that the remaining power of the drone is greater than or equal to the safe power buffer of the drone; the safe power buffer refers to the amount of power required for the drone to fly from any node in the node set to the nearest charging node.

[0171] Each module in the aforementioned collaborative inspection path optimization device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0172] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7 As shown, this computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores collaborative inspection path optimization data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a collaborative inspection path optimization method.

[0173] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a collaborative inspection path optimization method.

[0174] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements a collaborative inspection path optimization method.

[0175] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements a collaborative inspection path optimization method.

[0176] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0177] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0178] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A collaborative inspection path optimization method, characterized in that, The method includes: Obtain a pre-constructed directed graph model corresponding to the target inspection area; wherein, the directed graph model includes a set of nodes and a set of arcs, the set of nodes includes the start and end nodes of the inspection task, the node to be inspected, and the charging node, and the set of arcs includes the arcs between any two nodes, and each arc has a corresponding distance parameter; Based on the attribute parameters of the inspection equipment and the distance parameters of the arc segment, a collaborative path optimization model with the goal of minimizing the overall inspection time is constructed and solved to obtain a collaborative inspection scheme. The inspection equipment includes a set of drones; the collaborative path optimization model includes constraints and an objective function; the collaborative inspection scheme includes: the target arc segment that each drone in the drone set needs to inspect and the target charging node that the drone needs to go to for charging, wherein the target charging node is the charging node closest to the target charging node.

2. The method according to claim 1, characterized in that, The attribute parameters of the inspection equipment include the flight speed and single charging time of the drone; Based on the attribute parameters of the inspection equipment and the distance parameters of the arc segment, a collaborative path optimization model is constructed and solved to minimize the overall inspection time, resulting in a collaborative inspection scheme, including: Based on the flight speed and the distance parameters of each arc segment, the flight duration corresponding to the arc segment is determined; Based on the flight duration and the single charging duration, a collaborative path optimization model with the objective of minimizing the overall inspection duration is constructed and solved to obtain the collaborative inspection scheme.

3. The method according to claim 1, characterized in that, The inspection equipment also includes a vehicle set, and at least some of the arc segments in the arc segment set are first arc segments, which are used to characterize the driving road segments corresponding to the vehicles in the vehicle set performing the inspection task. The collaborative inspection scheme also includes the first arc segment of the target that each vehicle in the vehicle set needs to inspect.

4. The method according to claim 3, characterized in that, The attribute parameters of the inspection equipment include the vehicle's driving speed, the drone's flight speed, and the duration of a single charge. Based on the attribute parameters of the inspection equipment and the distance parameters of the arc segment, a collaborative path optimization model is constructed and solved to minimize the overall inspection time, resulting in a collaborative inspection scheme, including: Based on the driving speed and the distance parameters of each of the first arc segments, the driving time corresponding to the first arc segment is determined; Based on the flight speed and the distance parameters of each arc segment, the flight duration corresponding to the arc segment is determined; Based on the driving time, the flight time, and the single charging time, a collaborative path optimization model with the objective of minimizing the overall inspection time is constructed and solved to obtain the collaborative inspection scheme.

5. The method according to claim 4, characterized in that, The objective function is used to minimize the total time for all inspection equipment to complete all inspection tasks. The total time is the maximum value between the completion time of all UAV inspections and the completion time of all vehicle inspections. The inputs to the objective function include: the flight duration corresponding to each arc segment, the travel duration corresponding to each first arc segment, and the single charging duration; The decision variables of the objective function include: drone inspection variables for each arc segment, vehicle inspection variables for each first arc segment, and drone charging variables for each node to be inspected; the drone inspection variables are used to characterize whether the drone inspects the arc segment, the vehicle inspection variables are used to characterize whether the vehicle inspects the first arc segment, and the drone charging variables are used to characterize whether the drone goes to the nearest charging node to charge at the node to be inspected.

6. The method according to any one of claims 1 to 5, characterized in that, The constraints include at least one of the following: The initial power constraint is used to characterize the remaining power of the UAV when it arrives at the first node in the first step, which is less than or equal to the difference between the initial power of the UAV and the power consumed by the UAV in flying from the start and end nodes to the first node. The first power consumption constraint is used to characterize the current remaining power of the drone when it has not been charged in the previous node. It is equal to the difference between the remaining power in the previous node and the power consumption in this flight segment. The second power consumption constraint is used to characterize the current remaining power of the drone when it returns to the previous node after charging at the nearest charging node. It is equal to the difference between the remaining power of the drone when it returns to the previous node and the power consumed during this flight segment. The remaining power of the drone when it returns to the previous node is determined based on the initial power of the drone and the power required for the drone to fly from the previous node to the nearest charging node. The safe power constraint is used to characterize that the remaining power of the drone is greater than or equal to the safe buffer power of the drone; the safe buffer power refers to the power required for the drone to fly from any node in the node set to the nearest charging node.

7. A collaborative inspection path optimization device, characterized in that, The device includes: The acquisition module is used to acquire a pre-constructed directed graph model corresponding to the target inspection area; wherein, the directed graph model includes a set of nodes and a set of arcs, the set of nodes includes the start and end nodes of the inspection task, the node to be inspected, and the charging node, and the set of arcs includes the arcs between any two nodes, and each arc has a corresponding distance parameter; The solution module is used to construct and solve a collaborative path optimization model with the goal of minimizing the overall inspection time, based on the attribute parameters of the inspection equipment and the distance parameters of the arc segment, so as to obtain a collaborative inspection scheme. The inspection equipment includes a set of drones; the collaborative path optimization model includes constraints and an objective function; the collaborative inspection scheme includes: the target arc segment that each drone in the drone set needs to inspect and the target charging node that the drone needs to go to for charging, wherein the target charging node is the charging node closest to the target charging node.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

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

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images