Vehicle-machine collaborative unmanned aerial vehicle (UAV) power line inspection path and energy allocation optimization method

Abstract

The application belongs to the technical field of intelligent inspection and operation and maintenance of power systems, and provides a vehicle-machine cooperative unmanned aerial vehicle power inspection path and energy configuration optimization method, which comprises the following steps: by selecting parking points capable of covering all towers and planning an optimal driving path of an inspection vehicle, a model is established to optimize the configuration number of unmanned aerial vehicles and batteries to reduce redundancy, then the block coordinate descent and sequential convex approximation method are combined to optimize the unmanned aerial vehicle flight path and energy distribution under the given parking points, a vehicle-assisted battery replacement and charging scheduling mechanism is designed to ensure operation continuity, and finally a task scheduling scheme is generated. The application effectively improves the full coverage capability and operation continuity of power line inspection, significantly reduces the system device redundancy and energy consumption, and realizes efficient execution of the inspection task and minimization of the total operation cost through vehicle-machine cooperative optimization.

Description

Technical Field

[0001] This application belongs to the field of intelligent inspection and maintenance technology of power systems, and in particular relates to a vehicle-machine collaborative unmanned aerial vehicle (UAV) power inspection path and energy configuration optimization method. Background Technology

[0002] With the expansion of power grids and the increasing complexity of transmission lines, drones, with their flexibility and efficiency, are gradually replacing traditional manual inspections and becoming an important means of power line inspection. Currently, commonly used technical methods mainly focus on single-drone path planning algorithms, such as improvements to heuristic search methods like the A* algorithm and Dijkstra's algorithm, as well as preliminary vehicle-drone collaborative task allocation schemes that introduce ground vehicles as take-off and landing supply platforms.

[0003] However, the above methods suffer from problems such as incomplete inspection coverage, frequent task interruptions, high equipment redundancy, and high overall system operating costs due to the failure of parking point selection to be linked with the global path system, neglect of the hard constraints of drone endurance and vehicle power supply, fragmented optimization of path planning and resource allocation, and lack of energy scheduling mechanism to ensure continuous operation. Summary of the Invention

[0004] This application provides a vehicle-machine collaborative UAV power line inspection path and energy configuration optimization method, terminal equipment, and storage medium. It can solve the problems of incomplete inspection coverage, frequent task interruptions, high equipment redundancy, and high overall system operating costs caused by existing methods, such as failure to link parking point selection with the global path system, neglect of the hard constraints of UAV endurance and vehicle power supply, fragmented optimization of path planning and resource configuration, and lack of energy scheduling mechanism to ensure continuous operation.

[0005] In a first aspect, embodiments of this application provide a method for optimizing the path and energy configuration of vehicle-machine collaborative unmanned aerial vehicle (UAV) power grid inspection, including: Step 1, based on the distribution of power grid towers, under the constraint of UAVs covering all towers, determining a set of parking point selection schemes for the inspection vehicle, and calculating the total operation time of the optimal path of the inspection vehicle as the evaluation criterion for the parking point selection scheme; Step 2, establishing an optimization model for the configuration of the number of UAVs and the number of batteries, and determining the optimal number of UAVs and the optimal number of batteries under the premise of ensuring full inspection coverage, so as to reduce redundant equipment and energy consumption costs; Step 3, based on the set of parking points of the inspection vehicle... Step 1: Jointly optimize the UAV inspection path and energy allocation, using the block coordinate descent method combined with sequential convex approximation for iterative solution, and output the UAV inspection route that satisfies the constraints; Step 4: Design a vehicle-assisted UAV battery swapping and charging mechanism to plan the timing of UAV battery swapping during mission execution. The UAV battery swapping and charging mechanism is based on the vehicle battery capacity, the remaining power of the UAV battery, and the inspection progress; Step 5: Integrate the parking point location scheme set, the optimal number of UAVs and the optimal number of batteries, the UAV inspection route that satisfies the constraints, and the UAV battery swapping and charging mechanism to obtain a mission scheduling scheme.

[0006] In one possible implementation of the first aspect, step 1 above, based on the distribution of power grid towers, determines a set of parking point selection schemes for the inspection vehicle under the constraint of UAV coverage of all towers, and calculates the total operation time of the optimal route of the inspection vehicle as the evaluation criterion for the parking point selection scheme, specifically including:

[0007] A multi-layered nested optimization framework is constructed. The main program of the multi-layered nested optimization framework is the parking point selection scheme determination algorithm, and the subroutine is the inspection vehicle path planning algorithm. The main program is used to generate and iterate parking point selection schemes, and the subroutine is used to calculate the total operation time of the optimal path of the inspection vehicle under each parking point selection scheme and return the total operation time to the main program. The main program uses the total operation time as the evaluation criterion of the parking point selection scheme. The parking point selection scheme determination algorithm is the SCE-UA algorithm.

[0008] Optionally, in another possible implementation of the first aspect, the above-mentioned inspection vehicle path planning algorithm specifically includes:

[0009] Based on the parking spot selection scheme and the inspection time of each parking spot, a vehicle path optimization model is constructed with the goal of minimizing the total operation time of the inspection vehicle. The constraints of the vehicle path optimization model include: each selected parking spot is visited only once, the daily operation time of the inspection vehicle does not exceed the preset time, and the inspection vehicle must wait for all drones in the parking spot to complete their tasks before leaving.

[0010] An immune algorithm is used to solve the vehicle path optimization model. The vehicle driving path is iteratively optimized through initialization of antibody population, selection, crossover, mutation and memory mechanisms, and the total operation time of the inspection vehicle's optimal path is output.

[0011] Optionally, in another possible implementation of the first aspect, step 2 above, establishing an optimization model for the configuration of the number of drones and batteries, determines the optimal number of drones and batteries while ensuring full inspection coverage, specifically including:

[0012] Determine the drone and the i-th pole to be inspected, S. i Distance D between us :

[0013]

[0014] The 3D coordinates of the drone are defined as follows: The 3D coordinates of the i-th tower to be inspected are defined as follows: h is the fixed flight altitude of the UAV;

[0015] The energy transfer efficiency of the drone is set as follows:

[0016]

[0017] Where a, b, and c are constants related to the charging device;

[0018] Establish a UAV propulsion power model:

[0019]

[0020] Among them, P0 and P I These are two constant parameters: the blade profile power and the inductive power, respectively, during hovering. The tip velocity of the rotor blade. denoted as the average induced velocity of the rotor during hovering, d0 and s represent the fuselage drag ratio and rotor solidity, respectively, and ρ and A represent the air density and rotor disk area, respectively.

[0021] Mobile power P move Represented as:

[0022]

[0023] Where v move It refers to the drone's movement speed;

[0024] Hovering power P hover Represented as:

[0025]

[0026] The total energy consumption of the drone is:

[0027]

[0028] Among them, the total motion time and total hovering time of the drone are t m and t h P s This indicates the transmission power from the drone to the pole to be inspected;

[0029] Establish an objective function to minimize the number of drone hovering points:

[0030]

[0031] Among them, (X) i ,Y i () represents the two-dimensional coordinates of the drone, i = 1, 2, 3, ..., k, where k is the total number of hovering times;

[0032] Establish an objective function to minimize the number of poles to be inspected that are repeatedly covered:

[0033]

[0034] in, This is the number of nodes that are repeatedly covered, expressed as:

[0035]

[0036] Where n is the number of sensor nodes, u ij It is a binary variable, calculated by the following formula:

[0037]

[0038] in, d is the position coordinate of the j-th hovering point. max This is the maximum charging distance;

[0039] Establish the objective function to minimize the drone's flight distance:

[0040]

[0041] Where, d ab The position coordinates q of the a-th hovering point a and the position coordinates q of the b-th hovering point b The distances between them, a=1,2,3,…,k, b=1,2,3,…k, c ab For hovering point q a to q b The access order decision variable is designed as follows:

[0042]

[0043] An optimization model for the configuration of the number of drones and batteries can be constructed by combining the above objective functions:

[0044]

[0045] in, Let n be the set of positive integers. c This represents the total number of poles awaiting inspection and charging. It is the order in which the j-th hover point is visited;

[0046] The energy requirement for a single drone sortie is:

[0047]

[0048] in, For flight energy consumption, Energy consumption during hovering Energy consumption for inspection operations, , , , This refers to the flight time for a single sortie;

[0049] The battery's usable energy is:

[0050]

[0051] in, C represents the depth of discharge, i.e., the overall efficiency coefficient. bat Nominal capacity;

[0052] Set the energy requirement of the drone for a single sortie to not exceed the available battery energy;

[0053] The total number of mission deployments is:

[0054]

[0055] Where T represents the set of UAV mission time slots. Total number of sorties for the mission;

[0056] Let the total flight and operation time for a single sortie be:

[0057]

[0058] Assuming each drone is equipped with B rechargeable batteries that are charged in rotation, to ensure that the drone does not stop due to waiting for batteries, the battery turnover rate must not be slower than the flight rate. The conservatively feasible necessary and sufficient condition is as follows:

[0059]

[0060] in, For battery swapping time, The time required for a single battery to be fully charged by the vehicle's charging dock;

[0061] The maximum number of sorties a single drone can perform within the operation window H:

[0062]

[0063] The total electrical energy that the vehicle can provide during time window H is:

[0064]

[0065] in, For DC interface efficiency, C veh This refers to the available capacity of the vehicle's battery.

[0066] Total energy requirements of the vehicle for the mission:

[0067]

[0068] in, To achieve charging / recharging efficiency, the following conditions must be met:

[0069]

[0070] The lower bound of the number of drones is determined by the total number of mission sorties and the maximum number of sorties that a drone can perform:

[0071]

[0072] The lower bound of the battery quantity must ensure that each drone can operate continuously and cover the total number of mission sorties:

[0073]

[0074]

[0075] in, This is the lower bound for the number of batteries required for a single drone. This is the lower bound of the total number of batteries required by the system. Number of drones;

[0076] Considering the constraint of total task deployment on charging processing capacity, and denoted by M as the number of parallel charging channels, the total number of batteries that can be recharged within time window H will not exceed N. chg,max And it must meet the requirement of consuming one full charge per deployment:

[0077]

[0078]

[0079] Based on all constraints, an optimization model for the configuration of the number of drones and batteries is solved to obtain the optimal number of drones and batteries.

[0080] Optionally, in another possible implementation of the first aspect, step 3 above, based on the parking point set of the inspection vehicle, performs joint optimization of the UAV inspection path and energy allocation, using the block coordinate descent method combined with sequential convex approximation for iterative solution, and outputs the UAV inspection route that satisfies the constraints, specifically including:

[0081] Establish a joint optimization model: Suppose that the UAV performs an inspection task within the time slot set T={1,2,…,T}, and the trajectory variable is defined as... Energy allocation variables are ,in This represents the energy allocation in time slot t, and the objective function of the joint optimization model is expressed as minimizing the cumulative energy consumption across all time slots:

[0082]

[0083] Among them, E fly (t) represents flight energy consumption, E hover (t) represents hovering energy consumption, E comm (t) represents the energy required for energy distribution;

[0084] The constraints on the objective function include: energy constraints, i.e. E bat Battery capacity for a single drone; mission coverage constraints, i.e. , The towers to be inspected are grouped together to ensure that all towers are inspected at least once. The task coverage decision variable takes a value of 0 or 1; the track continuity constraint, i.e. Ensure that the drone speed does not exceed the maximum value;

[0085] At the current iteration point (q) (r) p (r) At point ), a first-order approximation is made for the non-convex functions of the objective function and constraints of the joint optimization model:

[0086] ;

[0087] in, Let x be the value of variable x in the r-th iteration;

[0088] The block coordinate descent method is used to alternately optimize the trajectory variables and energy allocation variables:

[0089] In each iteration, a fixed energy allocation is used. Solve for the trajectory variables The convex subproblem has the objective function as follows:

[0090]

[0091] in, This represents a convex function approximated by the sequential convex approximation method.

[0092] Fixed trajectory variables Update energy distribution Its subproblems are expressed as:

[0093]

[0094] Once the alternating iterations reach convergence, the UAV inspection route that satisfies the constraints is output.

[0095] Optionally, in another possible implementation of the first aspect, step 4 above, designing a vehicle-assisted UAV battery swapping and charging mechanism to plan the timing of UAV battery swapping during mission execution, the UAV battery swapping and charging mechanism is based on the vehicle battery capacity, the remaining power of the UAV battery, and the inspection progress, specifically including:

[0096] Introducing a power replenishment trigger condition: When any drone has a remaining battery power E t When the energy level falls below a preset threshold, a battery swap or charging operation is triggered; let E be the energy required for the drone to return to base. r Then the feasibility constraint for energy replenishment is:

[0097]

[0098] If this condition is not met, a battery swapping or charging operation will be triggered.

[0099] Let the maximum energy that the vehicle can provide within the time window H be... ;

[0100] The total energy requirement of the drone within time window H is ;in, Let k be the flight energy consumption for the kth sortie. Let k be the hovering energy consumption for the kth sortie. The energy consumption for the inspection operation during the k-th deployment;

[0101] Assume that the vehicle can support all drones to complete the inspection task, which requires the following conditions to be met. ;

[0102] Assuming each drone is equipped with B rechargeable batteries and the vehicle has M parallel charging channels, the feasibility conditions are as follows:

[0103]

[0104] in, This refers to the total duration of a single mission flight and operation; if the feasibility conditions are not met, the number of cycle batteries or the number of charging channels need to be increased.

[0105] Under feasible conditions, the upper bound of the maximum number of sorties per drone within time window H is:

[0106]

[0107] Meanwhile, the total number of batteries that the vehicle can recharge within time window H shall not exceed:

[0108]

[0109] And it is necessary to ensure that:

[0110]

[0111] Where, N task This represents the total number of mission sorties; if this condition is not met, it can be achieved by adding a parallel charging channel M or increasing the total battery capacity.

[0112] Optionally, in another possible implementation of the first aspect, after obtaining the task scheduling scheme by integrating the set of parking point selection schemes, the optimal number of drones and the optimal number of batteries, the drone inspection routes that satisfy the constraints, and the drone battery swapping and charging mechanisms, step 5 above further includes:

[0113] Establish a total cost decomposition model, and express the system operating cost as:

[0114]

[0115] Among them, C UAV C represents the purchase and maintenance costs of the drone. bat C represents the cost of purchasing and replacing batteries. veh This indicates the cost of vehicle operation and energy supply.

[0116] Secondly, embodiments of this application provide a terminal device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the aforementioned vehicle-machine collaborative UAV power line inspection path and energy configuration optimization method.

[0117] Thirdly, embodiments of this application provide a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the aforementioned vehicle-machine collaborative unmanned aerial vehicle power inspection path and energy configuration optimization method.

[0118] Beneficial Effects: First, based on the distribution of power grid towers, and under the constraint of ensuring UAV coverage of all towers, a set of parking point selection schemes for inspection vehicles is determined, and the total operation time of the optimal route for the inspection vehicle is calculated as the evaluation criterion for the parking point selection scheme. Next, an optimization model for the configuration of the number of UAVs and batteries is established. Under the premise of ensuring full inspection coverage, the optimal number of UAVs and batteries is determined to reduce redundant equipment and energy consumption costs. Then, based on the set of parking points for the inspection vehicles, joint optimization of UAV inspection paths and energy allocation is performed. A block coordinate descent method combined with sequential convex approximation is used for iterative solution, outputting UAV inspection routes that satisfy the constraints. Further, a vehicle-assisted UAV battery swapping and charging mechanism is designed to plan the timing of UAV battery swapping during mission execution. The UAV battery swapping and charging mechanism is based on the vehicle battery capacity, the remaining battery power of the UAV, and the inspection progress. Finally, based on the above optimization results, a task scheduling scheme is output. This application effectively improves the full coverage capability and operational continuity of power line inspection, significantly reduces system equipment redundancy and energy consumption, and achieves efficient execution of inspection tasks and minimizes total operating costs through vehicle-machine collaborative optimization. Attached Figure Description

[0119] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0120] Figure 1 This is a flowchart illustrating a vehicle-machine collaborative unmanned aerial vehicle (UAV) power line inspection path and energy configuration optimization method according to an embodiment of this application;

[0121] Figure 2 This is a flowchart illustrating the selection of a parking point scheme according to an embodiment of this application;

[0122] Figure 3 This is a schematic diagram of the structure of a system network model provided in an embodiment of this application;

[0123] Figure 4 This is a schematic diagram of the structure of the terminal device provided in the embodiments of this application. Detailed Implementation

[0124] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0125] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0126] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0127] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0128] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0129] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0130] The following description, with reference to the accompanying drawings, details a method for optimizing the path and energy configuration of vehicle-machine collaborative unmanned aerial vehicle (UAV) power line inspection, as well as the terminal equipment and storage medium provided in this application.

[0131] Figure 1 The illustration shows a flowchart of a vehicle-machine collaborative UAV power line inspection path and energy configuration optimization method provided in an embodiment of this application.

[0132] like Figure 1 As shown, the vehicle-machine collaborative UAV power line inspection path and energy configuration optimization method includes the following steps:

[0133] Step 1: Based on the distribution of power grid towers, under the constraint of ensuring that the UAV covers all towers, determine the set of parking point selection schemes for the inspection vehicle, and calculate the total operation time of the optimal route of the inspection vehicle as the evaluation criterion for the parking point selection scheme.

[0134] It should be noted that parking spot selection is a fundamental step in drone task allocation and inspection vehicle route planning. Drone task allocation at each parking spot is to calculate the inspection time at that spot, providing time parameters for vehicle route planning; the parking spot selection scheme directly affects the drone task sequence and the inspection vehicle's travel path. However, decision-makers find it difficult to directly determine the optimal number and combination of parking spots from a large set of candidate parking spots. Based on this, this application proposes a multi-layered nested optimization framework: a parking spot selection scheme determination algorithm as the main program, and an inspection vehicle route planning algorithm as a subroutine, thereby achieving a global search and evaluation of parking spot schemes, such as... Figure 2 As shown, within this framework, the main program generates a new parking spot selection scheme in each iteration. Subsequently, the UAV task allocation algorithm calculates the inspection time of each parking spot under this scheme and feeds the result into the inspection vehicle path planning algorithm. Based on this, the inspection vehicle path planning algorithm solves for the near-optimal inspection vehicle travel path and returns the total operation time of this path. The main program uses this total operation time as the evaluation criterion for the parking spot scheme, continuously guiding the selection scheme towards the globally optimal solution.

[0135] Furthermore, in this embodiment of the application, step 1 above includes:

[0136] A multi-layered nested optimization framework is constructed. The main program of the multi-layered nested optimization framework is the parking point selection scheme determination algorithm, and the subroutine is the inspection vehicle path planning algorithm. The main program is used to generate and iterate parking point selection schemes, and the subroutine is used to calculate the total operation time of the optimal path of the inspection vehicle under each parking point selection scheme and return the total operation time to the main program. The main program uses the total operation time as the evaluation criterion of the parking point selection scheme. The parking point selection scheme determination algorithm is the SCE-UA algorithm.

[0137] It should be noted that the SCE-UA algorithm has been successfully applied in the field of water resources, exhibiting strong robustness and better convergence. Compared with traditional evolutionary algorithms such as genetic algorithms, it can handle global optimization problems more efficiently. The solution process of this algorithm includes: initialization, sample point generation, sorting and labeling, and complex construction and evolution. In the initialization stage, the number of complexes and sample points are set. Then, sample points are randomly generated and their feasibility is judged. The encoding method is 0-1 encoding, where "1" indicates that the parking point is selected and "0" indicates that it is not selected. All feasible sample points will enter the sorting stage, be evaluated according to the total operation time of the inspection vehicle, and be assigned to different complexes. Then, through competitive evolution operations, the algorithm is continuously improved until the set of parking points that satisfies the full coverage constraint is output.

[0138] Furthermore, in this embodiment of the application, the patrol vehicle path planning algorithm in step 1 above specifically includes:

[0139] Based on the parking spot selection scheme and the inspection time of each parking spot, a vehicle path optimization model is constructed with the goal of minimizing the total operation time of the inspection vehicle. The constraints of the vehicle path optimization model include: each selected parking spot is visited only once, the daily operation time of the inspection vehicle does not exceed the preset time, and the inspection vehicle must wait for all drones in the parking spot to complete their tasks before leaving.

[0140] An immune algorithm is used to solve the vehicle path optimization model. The vehicle driving path is iteratively optimized through initialization of antibody population, selection, crossover, mutation and memory mechanisms, and the total operation time of the inspection vehicle's optimal path is output.

[0141] As one possible implementation, the immune algorithm uses the total operation time of the inspection vehicle as the antigen and randomly initializes the antibody population using real-number encoding, with each antibody corresponding to a vehicle path. Through iterative optimization using selection, crossover, mutation, and memory mechanisms, the algorithm minimizes the total operation time of the vehicle paths while satisfying the daily operation time constraint.

[0142] The objective function is to minimize the sum of job times for all workdays, denoted as:

[0143]

[0144] Where W represents the weekday collection. Vehicles depart from and return to the maintenance station daily, ensuring that each selected parking spot is visited only once, and each pole is served by a single parking spot.

[0145] Under the constraint of vehicle-drone collaboration, the inspection vehicle launches multiple drones at each parking point to perform inspection tasks. The vehicle can only continue moving after all drones have completed their tasks and returned. The inspection time at each parking point depends on the longest drone task duration at that point.

[0146]

[0147] Where k is the drone number, and U is the collection of drones participating in the inspection at the parking point. Let be the task time of the k-th drone at the i-th parking point. The task time of each drone consists of the round-trip flight time and the tower inspection time, ensuring that each tower is inspected by only one drone once. All scheduling variables satisfy the 0-1 and non-negativity constraints, and the final output is the optimal vehicle route and total operation time that meet the operation time constraints.

[0148] It should be noted that in step 1, the calculation of drone task allocation is only used to estimate the inspection time of each parking point for the purpose of optimizing the inspection vehicle route, and does not systematically model the drone's energy consumption and battery configuration; therefore, step 2, based on the established parking point location scheme and vehicle driving route, develops the model from the perspective of energy and resource allocation.

[0149] Step 2: Establish an optimization model for the configuration of the number of drones and batteries. Under the premise of ensuring full coverage of inspections, determine the optimal number of drones and batteries to reduce redundant equipment and energy costs.

[0150] As one possible implementation, this embodiment of the application consists of a drone and n poles to be inspected, denoted as S. i ,like Figure 3 As shown, where i∈{1,2,3,…,n}. The drone flies at a fixed altitude of h to charge the poles to be inspected, meaning the drone flies on plane β, and the poles to be inspected are randomly deployed, each of which can be powered by the drone. By visiting different hovering positions, the drone can simultaneously charge multiple poles within its effective charging range, ultimately ensuring that all poles receive power.

[0151] Furthermore, in this embodiment of the application, step 2 above includes:

[0152] Determine the drone and the i-th pole to be inspected, S. i Distance D between us :

[0153]

[0154] The 3D coordinates of the drone are defined as follows: The 3D coordinates of the i-th tower to be inspected are defined as follows: h is the fixed flight altitude of the UAV;

[0155] The energy transfer efficiency of the drone is set as follows:

[0156]

[0157] Where a, b, and c are constants related to the charging device;

[0158] Establish a UAV propulsion power model:

[0159]

[0160] Among them, P0 and P I These are two constant parameters: the blade profile power and the inductive power, respectively, during hovering. The tip velocity of the rotor blade. denoted as the average induced velocity of the rotor during hovering, d0 and s represent the fuselage drag ratio and rotor solidity, respectively, and ρ and A represent the air density and rotor disk area, respectively.

[0161] Mobile power P move Represented as:

[0162]

[0163] Where v move It refers to the drone's movement speed;

[0164] Hovering power P hover Represented as:

[0165]

[0166] The total energy consumption of the drone is:

[0167]

[0168] Among them, the total motion time and total hovering time of the drone are t m and t h P s This indicates the transmission power from the drone to the pole to be inspected;

[0169] To enable drones to charge all inspection towers with the fewest hovering points and shortest flight distances, and to ensure that the number of inspection towers requiring repeated charging is minimized, the improvement of overall charging performance can be directly affected by the following three optimization objectives.

[0170] Optimization Objective 1: Establish an objective function that minimizes the number of drone hovering points:

[0171]

[0172] Among them, (X) i ,Y i () represents the two-dimensional coordinates of the drone, i = 1, 2, 3, ..., k, where k is the total number of hovering times;

[0173] Optimization Objective 2: Establish an objective function to minimize the number of poles to be inspected that are repeatedly covered.

[0174]

[0175] in, This is the number of nodes that are repeatedly covered, expressed as:

[0176]

[0177] Where n is the number of sensor nodes, u ij It is a binary variable, calculated by the following formula:

[0178]

[0179] in, d is the position coordinate of the j-th hovering point. max This is the maximum charging distance;

[0180] Optimization Objective 3: Establish the objective function for minimizing the drone's flight distance:

[0181]

[0182] Where, d ab The position coordinates q of the a-th hovering point a and the position coordinates q of the b-th hovering point b The distances between them, a=1,2,3,…,k, b=1,2,3,…k, c ab For hovering point q a to q b The access order decision variable is designed as follows:

[0183]

[0184] Through the above energy modeling and optimization target setting, this application can balance different hovering point numbers, flight paths, and energy consumption, and further combine vehicle power supply capacity and battery charging and discharging efficiency to form an optimized configuration scheme for the number of drones and batteries. The final optimized model for the configuration of the number of drones and batteries is constructed as follows:

[0185]

[0186] in, Let n be the set of positive integers. c This represents the total number of poles awaiting inspection and charging. It is the order in which the j-th hover point is visited;

[0187] The energy requirement for a single drone sortie is:

[0188]

[0189] in, For flight energy consumption, Energy consumption during hovering Energy consumption for inspection operations, , , , This refers to the flight time for a single sortie;

[0190] The battery's usable energy is:

[0191]

[0192] in, C represents the depth of discharge, i.e., the overall efficiency coefficient. bat Nominal capacity;

[0193] Set the energy requirement of the drone for a single sortie to not exceed the available battery energy;

[0194] The total number of mission deployments is:

[0195]

[0196] Where T represents the set of UAV mission time slots. Total number of sorties for the mission;

[0197] Let the total flight and operation time for a single sortie be:

[0198]

[0199] Assuming each drone is equipped with B rechargeable batteries that are charged in rotation, to ensure that the drone does not stop due to waiting for batteries, the battery turnover rate must not be slower than the flight rate. The conservatively feasible necessary and sufficient condition is as follows:

[0200]

[0201] in, For battery swapping time, The time required for a single battery to be fully charged by the vehicle's charging dock;

[0202] The maximum number of sorties a single drone can perform within the operation window H:

[0203]

[0204] The total electrical energy that the vehicle can provide during time window H is:

[0205]

[0206] in, For DC interface efficiency, C veh This refers to the available capacity of the vehicle's battery.

[0207] Total energy requirements of the vehicle for the mission:

[0208]

[0209] in, To achieve charging / recharging efficiency, the following conditions must be met:

[0210]

[0211] The lower bound of the number of drones is determined by the total number of mission sorties and the maximum number of sorties that a drone can perform:

[0212]

[0213] The lower bound of the battery quantity must ensure that each drone can operate continuously and cover the total number of mission sorties:

[0214]

[0215]

[0216] in, This is the lower bound for the number of batteries required for a single drone. This is the lower bound of the total number of batteries required by the system. Number of drones;

[0217] Considering the constraint of total task deployment on charging processing capacity, and denoted by M as the number of parallel charging channels, the total number of batteries that can be recharged within time window H will not exceed N. chg,max And it must meet the requirement of consuming one full charge per deployment:

[0218]

[0219]

[0220] Based on all constraints, an optimization model for the configuration of the number of drones and batteries is solved to obtain the optimal number of drones and batteries.

[0221] Step 3: Based on the parking point set of the inspection vehicle, perform joint optimization of the UAV inspection path and energy allocation. Use the block coordinate descent method combined with the sequential convex approximation for iterative solution and output the UAV inspection route that satisfies the constraints.

[0222] Furthermore, in this embodiment of the application, step 3 above includes:

[0223] Establish a joint optimization model: Suppose that the UAV performs an inspection task within the time slot set T={1,2,…,T}, and the trajectory variable is defined as... Energy allocation variables are ,in This represents the energy allocation in time slot t, and the objective function of the joint optimization model is expressed as minimizing the cumulative energy consumption across all time slots:

[0224]

[0225] Among them, E fly (t) represents flight energy consumption, E hover (t) represents hovering energy consumption, E comm (t) represents the energy required for energy distribution;

[0226] The constraints on the objective function include: energy constraints, i.e. E bat Battery capacity for a single drone; mission coverage constraints, i.e. , The towers to be inspected are grouped together to ensure that all towers are inspected at least once. The task coverage decision variable takes a value of 0 or 1; the track continuity constraint, i.e. Ensure that the drone speed does not exceed the maximum value;

[0227] At the current iteration point (q) (r) p (r) At point ), a first-order approximation is made for the non-convex functions of the objective function and constraints of the joint optimization model:

[0228] ;

[0229] in, Let x be the value of variable x in the r-th iteration;

[0230] The block coordinate descent method is used to alternately optimize the trajectory variables and energy allocation variables:

[0231] In each iteration, a fixed energy allocation is used. Solve for the trajectory variables The convex subproblem has the objective function as follows:

[0232]

[0233] in, This represents a convex function approximated by the sequential convex approximation method.

[0234] Fixed trajectory variables Update energy distribution Its subproblems are expressed as:

[0235]

[0236] Once the alternating iterations reach convergence, the UAV inspection route that satisfies the constraints is output.

[0237] Step 4: Design a vehicle-assisted UAV battery swapping and charging mechanism to plan when the UAV will swap batteries during mission execution. The UAV battery swapping and charging mechanism is based on the vehicle battery capacity, the remaining power of the UAV battery, and the inspection progress.

[0238] Furthermore, in this embodiment of the application, step 4 above includes:

[0239] Introducing a power replenishment trigger condition: When any drone has a remaining battery power E t When the energy level falls below a preset threshold, a battery swap or charging operation is triggered; let E be the energy required for the drone to return to base. r Then the feasibility constraint for energy replenishment is:

[0240]

[0241] If this condition is not met, a battery swapping or charging operation will be triggered.

[0242] Let the maximum energy that the vehicle can provide within the time window H be... ;

[0243] The total energy requirement of the drone within time window H is ;in, Let k be the flight energy consumption for the kth sortie. Let k be the hovering energy consumption for the kth sortie. The energy consumption for the inspection operation during the k-th deployment;

[0244] Assume that the vehicle can support all drones to complete the inspection task, which requires the following conditions to be met. ;

[0245] Assuming each drone is equipped with B rechargeable batteries and the vehicle has M parallel charging channels, the feasibility conditions are as follows:

[0246]

[0247] in, This refers to the total duration of a single mission flight and operation; if the feasibility conditions are not met, the number of batteries or the number of charging channels need to be increased.

[0248] Under feasible conditions, the upper bound of the maximum number of sorties per drone within time window H is:

[0249]

[0250] Meanwhile, the total number of batteries that the vehicle can recharge within time window H shall not exceed:

[0251]

[0252] And it is necessary to ensure that:

[0253]

[0254] Where, N task This represents the total number of mission sorties; if this condition is not met, it can be achieved by adding a parallel charging channel M or increasing the total battery capacity.

[0255] Step 5: Integrate the set of parking point selection schemes, the optimal number of drones and the optimal number of batteries, the drone inspection routes that meet the constraints, and the drone battery swapping and charging mechanisms to obtain a task scheduling scheme.

[0256] After completing the design of parking site selection, UAV and battery configuration, flight path and energy distribution, and vehicle auxiliary power supply mechanism, this application generates the final task scheduling scheme. The scheme includes vehicle travel path, UAV inspection path, battery swapping plan, and task scheduling table. Through this scheduling table, the calculation results of the aforementioned optimization steps can be transformed into directly implementable operational plans, ensuring the feasibility of the inspection task in actual operation.

[0257] When outputting the scheduling plan, multiple constraints need to be considered comprehensively. Energy constraints require that the energy consumption of a single UAV mission must not exceed the battery capacity, and the total energy supply of vehicles must not exceed the onboard battery capacity; time constraints require that inspection tasks must be completed within the specified working time window H, and the battery swapping time τ must be met. sw With charging time τ ch The constraints include: coverage constraints requiring all target towers to be inspected by drones at least once; and path constraints requiring the trajectories of vehicles and drones to meet speed limits and continuity conditions. These constraints collectively ensure the feasibility and safety of the scheduling scheme.

[0258] Furthermore, in this embodiment of the application, after step 5 above, the following steps are also included:

[0259] Establish a total cost decomposition model, and express the system operating cost as:

[0260]

[0261] Among them, C UAV C represents the purchase and maintenance costs of the drone. bat C represents the cost of purchasing and replacing batteries. veh This indicates the cost of vehicle operation and energy supply.

[0262] This application provides a vehicle-machine collaborative UAV power grid inspection path and energy allocation optimization method. First, based on the distribution of power grid towers, and under the constraint of UAVs covering all towers, a set of parking point selection schemes for the inspection vehicle is determined, and the total operation time of the optimal inspection vehicle path is calculated as the evaluation criterion for the parking point selection scheme. Next, an optimization model for the configuration of the number of UAVs and batteries is established. Under the premise of ensuring full inspection coverage, the optimal number of UAVs and batteries is determined to reduce redundant equipment and energy costs. Then, based on the set of parking points for the inspection vehicle, joint optimization of the UAV inspection path and energy allocation is performed. A block coordinate descent method combined with sequential convex approximation is used for iterative solution, outputting UAV inspection routes that satisfy the constraints. Further, a vehicle-assisted UAV battery swapping and charging mechanism is designed to plan the timing of UAV battery swapping during mission execution. The UAV battery swapping and charging mechanism is based on the vehicle battery capacity, the remaining battery power of the UAV, and the inspection progress. Finally, based on the above optimization results, a task scheduling scheme is output. This application effectively improves the full coverage and operational continuity of power line inspection, significantly reduces system equipment redundancy and energy consumption, and achieves efficient execution of inspection tasks and minimizes total operating costs through vehicle-machine collaborative optimization.

[0263] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0264] To implement the above embodiments, this application also proposes a terminal device.

[0265] Figure 4 This is a schematic diagram of the structure of a terminal device according to an embodiment of this application.

[0266] like Figure 4 As shown, the terminal device 200 includes:

[0267] The system includes a memory 210 and at least one processor 220, and a bus 230 connecting different components (including the memory 210 and the processor 220). The memory 210 stores a computer program, which, when executed by the processor 220, implements the vehicle-machine cooperative UAV power inspection path and energy configuration optimization method described in this application embodiment.

[0268] Bus 230 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0269] Terminal device 200 typically includes various electronically readable media. These media can be any available media that can be accessed by terminal device 200, including volatile and non-volatile media, removable and non-removable media.

[0270] Memory 210 may also include computer system readable media in the form of volatile memory, such as RAM 240 and / or cache 250. Terminal device 200 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 260 may be used to read and write non-removable, non-volatile magnetic media (… Figure 4 Not shown; usually referred to as a "hard drive"). Although Figure 4 As not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 230 via one or more data media interfaces. Memory 210 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application.

[0271] A program / utility 280 having a set (at least one) of program modules 270 may be stored in, for example, memory 210. Such program modules 270 include—but are not limited to—an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 270 typically perform the functions and / or methods described in the embodiments of this application.

[0272] Terminal device 200 can also communicate with one or more external devices 290 (e.g., keyboard, pointing device, display 291, etc.), and with one or more devices that enable a user to interact with terminal device 200, and / or with any device that enables terminal device 200 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 292. Furthermore, terminal device 200 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 293. As shown, network adapter 293 communicates with other modules of terminal device 200 via bus 230. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with terminal device 200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0273] The processor 220 performs various functional applications and data processing by running programs stored in the memory 210.

[0274] It should be noted that the implementation process and technical principles of the terminal device in this embodiment are explained in the foregoing description of a vehicle-machine collaborative UAV power inspection path and energy configuration optimization method according to an embodiment of this application, and will not be repeated here.

[0275] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0276] This application provides a computer program product that, when run on a terminal device, enables the terminal device to implement the steps described in the various method embodiments above.

[0277] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, 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 computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a photographing device / terminal device, a recording medium, a computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0278] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0279] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0280] In the embodiments provided in this application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0281] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0282] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for vehicle-UE cooperative UAV power inspection path and energy configuration optimization, characterized in that, The method comprises the following steps: Step 1, based on the distribution of power grid towers, a set of parking point site selection schemes of the inspection vehicle is determined under the constraint condition that all towers are covered by the unmanned aerial vehicle, and the total operation time of the optimal path of the inspection vehicle is calculated as the evaluation standard of the parking point site selection scheme; Step 2, an optimization model of the number of unmanned aerial vehicles and the number of batteries is established, and the optimal number of unmanned aerial vehicles and the optimal number of batteries are determined to reduce the redundant equipment and energy consumption cost under the premise of ensuring full coverage of inspection; Step 3, based on the set of parking points of the inspection vehicle, the joint optimization of the unmanned aerial vehicle inspection path and energy distribution is carried out, the block coordinate descent method is used in combination with sequential convex approximation for iterative solution, and the unmanned aerial vehicle inspection route meeting the constraint is output; Step 4, a vehicle-assisted unmanned aerial vehicle battery replacement and charging mechanism is designed to plan the timing of battery replacement of the unmanned aerial vehicle during task execution, and the unmanned aerial vehicle battery replacement and charging mechanism is based on the vehicle battery capacity, the remaining battery capacity of the unmanned aerial vehicle and the inspection progress; Step 5, the set of parking point site selection schemes, the optimal number of unmanned aerial vehicles and the optimal number of batteries, the unmanned aerial vehicle inspection route meeting the constraint and the unmanned aerial vehicle battery replacement and charging mechanism are integrated to obtain a task scheduling scheme. 2.The vehicle-robot collaborative unmanned aerial vehicle power inspection path and energy configuration optimization method of claim 1, wherein, The step 1, based on the distribution of power grid towers, a set of parking point site selection schemes of the inspection vehicle is determined under the constraint condition that all towers are covered by the unmanned aerial vehicle, and the total operation time of the optimal path of the inspection vehicle is calculated as the evaluation standard of the parking point site selection scheme, specifically comprising: A multi-layer nested optimization framework is constructed, wherein the main program of the multi-layer nested optimization framework is a parking point site selection scheme determination algorithm, and the subprogram is an inspection vehicle path planning algorithm; the main program is used to generate and iterate the parking point site selection scheme, the subprogram is used to calculate the total operation time of the optimal path of the inspection vehicle under each parking point site selection scheme, and the total operation time is returned to the main program, and the main program uses the total operation time as the evaluation standard of the parking point site selection scheme; the parking point site selection scheme determination algorithm is a recombination complex SCE-UA algorithm. 3.The vehicle-robot collaborative UAV power inspection path and energy configuration optimization method of claim 2, wherein, The inspection vehicle path planning algorithm specifically comprises: Based on the parking point site selection scheme and the inspection time of each parking point, a vehicle path optimization model with the minimum total operation time of the inspection vehicle as the target is constructed; the constraints of the vehicle path optimization model include that each selected parking point is visited only once, the daily operation time of the inspection vehicle does not exceed the preset time length, and the inspection vehicle must wait for all unmanned aerial vehicles in the parking point to complete the task before leaving the parking point; An immune algorithm is used to solve the vehicle path optimization model, and the vehicle driving path is iteratively optimized through the initialization of the antibody group, selection, crossover, mutation and memory mechanism, and the total operation time of the optimal path of the inspection vehicle is output. 4.The vehicle-robot collaborative unmanned aerial vehicle power inspection path and energy configuration optimization method of claim 3, wherein, The step 2, an optimization model of the number of unmanned aerial vehicles and the number of batteries is established, and the optimal number of unmanned aerial vehicles and the optimal number of batteries are determined to reduce the redundant equipment and energy consumption cost under the premise of ensuring full coverage of inspection, specifically comprising: determining the distance D between the UAV and the i-th tower S to be inspected i to be inspected us : ； Wherein, the 3D coordinates of the unmanned aerial vehicle are defined as , the 3D coordinates of the i-th tower to be inspected are defined as , and h is the fixed flight height of the unmanned aerial vehicle. The energy transmission efficiency of the unmanned aerial vehicle is set as: ； Wherein, a, b and c are constants related to the charging device; An unmanned aerial vehicle propulsion power model is established: ； where P0 and P I are two constant parameters of the blade profile power and induced power in hover, respectively, is the tip speed of the rotor blade, is the average induced velocity of the rotor in hover, d0 and s represent the fuselage drag ratio and the rotor solidity, respectively, and p and A represent the air density and the rotor disc area, respectively. Mobile power P move is represented as: ； where v move is the speed of movement of the drone; Hover power P hover is represented as: ； The total energy consumption of the unmanned aerial vehicle is: ； Wherein the total movement time and the total hovering time of the unmanned aerial vehicle are t m and t h respectively s P represents the transmission power from the unmanned aerial vehicle to the tower to be inspected An unmanned aerial vehicle hovering point number minimization objective function is established: ； wherein (X i ,Y i ) is the two-dimensional coordinate of the UAV, i=1, 2, 3, …, k, and k is the total hovering times; A target function of minimizing the number of towers to be inspected with repeated coverage is established: ； wherein is the number of nodes that are covered repeatedly, expressed as: ； where n is the number of sensor nodes, u ij is a binary variable calculated by the following equation: ； wherein, is the position coordinate of the jthhover point, d max is the maximum charging distance; A target function of minimizing the flight distance of the UAV is established: ； wherein d ab is the distance between the position coordinates q a and the position coordinates q b of the a-th hovering point and the b-th hovering point, a = 1, 2, 3, …, k, b = 1, 2, 3, … k, c ab is the visiting order decision variable of the hovering point q a to q b , and is designed as: ； An optimization model of the number of UAVs and the number of batteries is constructed based on the above target functions: ； wherein, is a set of positive integers, n c is the total number of towers to be inspected that are charged, is the order of visiting the jthhover point; The energy requirement of a single UAV operation is: ； wherein, is the flight energy consumption, is the hovering energy consumption, is the patrol operation energy consumption, , , , is the single sortie flight time; The available energy of the battery is: ； wherein, C is the discharge depth, i.e. the efficiency synthesis factor bat is the nominal capacity; The energy requirement of a single UAV operation is set to be less than the available energy of the battery; The total number of operations is: ； Wherein, T is a set of unmanned aerial vehicle task time slots, is the total number of tasks dispatched; The total flight and operation time of a single operation is: ； To ensure that the UAV does not stop due to battery replacement, the battery turnover rhythm must not be slower than the flight rhythm. The conservative sufficient condition is: ； wherein, is the battery swap time, is the vehicle seat charging to full time for a monobloc battery; The maximum number of operations that can be performed by a single UAV within the operation time window H is: ； The total energy that can be provided by the vehicle within the time window H is: ； wherein, is the DC interface efficiency, C veh is the available capacity of the vehicle battery; The total energy requirement of the task for the vehicle is: ； wherein For the charging backfill efficiency, the conditions to be met are: ； The lower bound of the number of UAVs is determined by the total number of operations and the maximum number of operations that can be performed by a single UAV: ； The lower bound of the number of batteries must ensure that each UAV can continuously operate and cover the total number of operations: ； ； wherein, a lower bound of the number of batteries required for a single drone, a lower bound of the total number of batteries required for the system, a number of drones; Considering the constraint of total task dispatched quantity on charging processing capacity, let the number of charging parallel channels be M, then the total number of batteries that can be charged in time window H is not more than N chg,max , and each time one full battery is consumed. ； ； Based on all the constraints, the optimization model of the number of UAVs and the number of batteries is solved to obtain the optimal number of UAVs and the optimal number of batteries. 5.The vehicle-robot collaborative UAV power inspection path and energy configuration optimization method of claim 4, wherein, Step 3: Based on the set of parking points of the inspection vehicle, the joint optimization of the UAV inspection path and energy allocation is performed using the block coordinate descent method combined with sequential convex approximation for iterative solution, and the UAV inspection route that meets the constraints is output. Specifically, it includes: establishing a joint optimization model: assuming that the unmanned aerial vehicle performs a patrol task in a time slot set T = {1, 2,..., T}, a flight path variable is defined as the , an energy allocation variable is , wherein represents energy allocation at time slot t, and the objective function of the joint optimization model is represented as cumulative minimization of energy consumption at all time slots: ； where E fly (t) represents the flight energy consumption, E hover (t) represents the hovering energy consumption, E comm (t) represents the energy distribution required consumption; The constraint conditions of the objective function include: energy constraint, i.e. , wherein E bat is the battery capacity of the single unmanned aerial vehicle; task coverage constraint, i.e. , is the set of towers to be inspected, and all towers are ensured to be at least inspected once, wherein is a task coverage decision variable, and takes a value of 0 or 1; track continuity constraint, i.e. , ensures that the speed of the unmanned aerial vehicle does not exceed the maximum value; At the current iteration point (q (r) , p (r) ), a first order approximation of the non-convex function of the objective function and the constraint conditions of the joint optimization model is performed: ； wherein, x r is the value of the variable x at the rth iteration; The block coordinate descent method is used to alternately optimize the flight path variables and energy allocation variables: At each iteration, the energy allocation is fixed , a convex subproblem of the trajectory variable whose objective function is ； wherein denotes a convex function approximated by a sequential convex approximation method; Fixed track variable , updating the energy allocation whose subproblem is stated as: ； When the alternating iteration reaches the convergence condition, the UAV inspection route that meets the constraints is output. 6.The vehicle-robot collaborative UAV power inspection path and energy configuration optimization method of claim 5, wherein, Step 4: Design a vehicle-assisted UAV battery replacement and charging mechanism to plan the timing of battery replacement for the UAV during task execution. The UAV battery replacement and charging mechanism is based on the vehicle battery capacity, the remaining battery capacity of the UAV, and the inspection progress. Specifically, it includes: Introducing the trigger condition of energy supplement: when the residual energy E t of any UAV is lower than the preset threshold, triggering the battery swap or charging operation; assuming that the energy required for the UAV to return is E r The energy supplement feasibility constraint is: ； If the condition is not met, trigger the battery replacement operation or the charging operation; Let the maximum energy that the vehicle can provide in the time window H be ; The total energy requirement of the UAV in the time window H is ; wherein, is the flight energy consumption of the kth deployment, is the hovering energy consumption of the kth deployment, is the patrol operation energy consumption of the kth deployment; To ensure that the vehicle is able to support all the drones to complete the inspection task needs to meet ; Assuming that each UAV is equipped with B blocks of circular batteries and M parallel charging channels are configured on the vehicle, the feasibility condition is: ； wherein, is the total duration of single task flight and operation; if the feasibility condition is not met, the number of circulating batteries or the number of charging channels needs to be increased; Under the feasibility condition, the upper bound of the maximum number of operations of each UAV within the time window H is: ； At the same time, the total number of batteries that can be recharged by the vehicle within the time window H is not more than: ； And it needs to ensure that: ； where N task is the total number of tasks; if this condition is not met, it is achieved by adding parallel charging channels M or increasing the total amount of batteries.

7. The vehicle-robot collaborative unmanned aerial vehicle power inspection path and energy configuration optimization method according to claim 6, characterized in that, Step 5: Based on the optimization results of steps 1-4, the vehicle driving path, UAV inspection path, battery replacement plan, and task scheduling table are output. In addition, it includes: A total cost decomposition model is established to represent the system operation cost as: ； wherein C UAV represents the purchase and maintenance cost of the UAV, C bat represents the purchase and replacement cost of the battery, C veh represents the vehicle operation and energy supply cost.

8. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the method of any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, The computer program is executed by the processor to implement the method of any one of claims 1 to 6.

Images