Method and System for UAV Photovoltaic Inspection Path Planning Considering Multi-Constraint Coupling

Abstract

The present invention discloses a method and system for unmanned aerial vehicle (UAV) photovoltaic inspection path planning considering multi-constraint coupling. The method includes: establishing a wind speed model with time window segmentation, and defining an objective function for the UAV dynamic trajectory optimization problem; setting the initial parameters of the accelerated opposition algorithm based on chaotic single candidates; generating random solutions and opposition solutions of the objective function according to the accelerated opposition learning mechanism, and selecting the better solution as the initial solution of the objective function; entering the main loop to update the initial solution; checking whether the solution is within the boundary range, and correcting the out-of-bounds solution based on a preset correction rule until the maximum number of iterations is reached, and outputting the solution with the lowest objective function as the inspection path. It can achieve multi-objective collaborative optimization of endurance time, inspection timeliness and wind resistance, and obtain an inspection path with higher inspection quality.

Description

Technical Field

[0001] The present invention belongs to the technical field of UAV inspection, and particularly relates to a UAV photovoltaic inspection path planning method and system considering multi-constraint coupling. Background Art

[0002] Rural photovoltaic power stations are usually widely distributed and have complex environments, and photovoltaic modules need to be regularly inspected to detect faults. Traditional manual inspection has low efficiency and high costs, and UAV autonomous inspection has become the mainstream trend. However, existing path planning often takes the "shortest path" as the core, but UAVs cannot complete full-area coverage inspection in complex weather, resulting in low inspection quality. Summary of the Invention

[0003] The present invention provides a UAV photovoltaic inspection path planning method and system considering multi-constraint coupling, which is used to solve the technical problem that UAVs cannot complete full-area coverage inspection in complex weather, resulting in low inspection quality.

[0004] In a first aspect, the present invention provides a UAV photovoltaic inspection path planning method considering multi-constraint coupling, including:

[0005] Establish a wind speed model with time window segmentation, and define the objective function of the UAV dynamic trajectory optimization problem for the UAV photovoltaic inspection path planning considering the UAV energy consumption constraint, time penalty constraint, and wind field situation;

[0006] Set the initial parameters of the accelerated opposition algorithm based on chaotic single candidates;

[0007] Generate a random solution and an opposite solution of the objective function according to the accelerated opposition learning mechanism, and select the better solution as the initial solution of the objective function;

[0008] Enter the main loop to update the initial solution;

[0009] Check whether the solution is within the boundary range, and correct the out-of-bounds solution based on a preset correction rule until the maximum number of iterations is reached, and output the solution with the lowest objective function value as the inspection path.

[0010] In a second aspect, the present invention provides a UAV photovoltaic inspection path planning system considering multi-constraint coupling, including:

[0011] A definition module configured to establish a wind speed model with time window segmentation, and define the objective function of the UAV dynamic trajectory optimization problem for the UAV photovoltaic inspection path planning considering the UAV energy consumption constraint, time penalty constraint, and wind field situation;

[0012] A setting module configured to set the initial parameters of the accelerated opposition algorithm based on chaotic single candidates;

[0013] A selection module, configured to generate a random solution and an opposite solution of the objective function according to an accelerated opposition-based learning mechanism, and select a better solution as the initial solution of the objective function;

[0014] A loop module, configured to enter a main loop to update the initial solution;

[0015] An output module, configured to check whether the solution is within the boundary range, and correct the out-of-bounds solution based on a preset correction rule until the maximum number of iterations is reached, and output the solution with the lowest objective function as the inspection path.

[0016] In a third aspect, an electronic device is provided, which includes: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the steps of the method for planning a drone photovoltaic inspection path considering multi-constraint coupling according to any embodiment of the present invention.

[0017] In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the program instructions are executed by a processor, the processor is enabled to execute the steps of the method for planning a drone photovoltaic inspection path considering multi-constraint coupling according to any embodiment of the present invention.

[0018] The method and system for planning a drone photovoltaic inspection path considering multi-constraint coupling of the present application have the following beneficial effects:

[0019] Couple and model the drone energy consumption constraint, the time window penalty function and the influence of the dynamic wind field. By constructing an objective function that integrates fixed cost, dynamic energy cost, and penalty cost, realize the multi-objective collaborative optimization of endurance time, inspection timeliness, and wind resistance;

[0020] Design an accelerated opposition algorithm based on chaotic single candidates, and improve the solution convergence efficiency through a three-stage optimization strategy, so as to realize a faster production of the drone photovoltaic inspection path. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0022] Figure 1 It is a flowchart of a method for planning a drone photovoltaic inspection path considering multi-constraint coupling provided by an embodiment of the present invention;

[0023] Figure 2 The structural block diagram of a UAV photovoltaic inspection path planning system considering multi-constraint coupling provided by an embodiment of the present invention;

[0024] Figure 3 It is the schematic structural diagram of an electronic device provided by an embodiment of the present invention. Specific embodiments

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0026] Please refer to Figure 1 , which shows the flowchart of a method for planning a UAV photovoltaic inspection path considering multi-constraint coupling of the present application.

[0027] As Figure 1 shown, the method for planning a UAV photovoltaic inspection path considering multi-constraint coupling specifically includes the following steps:

[0028] Step S101, establish a wind speed model with time window segmentation, consider the UAV energy consumption constraint, time penalty constraint, and define the objective function of the UAV photovoltaic inspection path planning problem of the UAV dynamic trajectory optimization under the wind field condition.

[0029] In this step, the wind speed model is modeled as follows:

[0030] The wind direction is divided into 15 direction intervals, equally spaced, and each interval is 24°;

[0031] Construct the probability distribution of the wind direction:

[0032] ,

[0033] where is the wind direction, is the average wind speed, is a concentration parameter used to describe the concentration of the wind direction, generally taking values between 0.5 and 5, is the first kind of zero-order Bessel function;

[0034] Construct the probability distribution of the wind speed:

[0035] ,

[0036] ,

[0037] ,

[0038] wherein, is the wind speed, is the shape parameter used to describe the shape of the wind speed, generally taking values between 1 and 3, is the scale parameter of the

[0039] The joint probability density function of wind speed and wind direction can be written as:

[0040] .

[0041] Obtain the wind field data for the next 6 hours from the meteorological data center, and divide the time window at 10-minute intervals. Preprocess the data and extract the global wind speed and wind direction means for each window. During actual inspection, update the meteorological parameters of the next window every 10 minutes through satellite communication.

[0042] Define the objective function for the UAV dynamic trajectory optimization problem, and the expression is:

[0043] ,

[0044] wherein, is the fixed cost of the UAV, is the dynamic energy cost, is the penalty cost, is the surface state function of the photovoltaic panel, is the weight coefficient ranging from [0,1];

[0045] ,

[0046] ,

[0047] ,

[0048] ,

[0049] ,

[0050] wherein, , , are respectively the fixed cost of the first UAV, the fixed cost of the second UAV, the th fixed cost of the UAV, is the number of UAVs, is the empty weight of the UAV, is the air fluid density, is the blade area of the drone, is the inspection time of point The drone flies from point to point the distance of, is the actual wind speed of the drone at time t, is the movement speed of the drone relative to the air, is the globally predicted wind speed value, is the angle between the wind direction and the due north direction, is the angle between the drone flight path and the due north direction, is a binary variable indicating whether the drone has completed the task, and are the upper and lower bounds of the time window respectively, and are the penalty coefficients for exceeding the time window, is the actual time to reach point, is the current period light intensity, is the reference light intensity, is the current photovoltaic panel fouling rate, the cleaning state reference value, is the environmental sensitivity coefficient, is the number of time windows, is the acceleration due to gravity.

[0051] Step S102, set the initialization parameters of the accelerated opposition algorithm based on the chaotic single candidate.

[0052] In this step, the initialization parameters include: the adaptive maximum number of iterations based on the convergence rate of the objective function , the initial maximum number of iterations , the total dimension of the problem , the control factor , the change window time , the threshold of the number of successful attempts , the threshold of the number of iterations in the exploration phase , the dimension of the problem , the maximum jump probability , the minimum jump probability and the adjustment factor .

[0053] Step S103, generate a random solution and an opposite solution of the objective function according to the accelerated opposition learning mechanism, and select the better solution as the initial solution of the objective function.

[0054] In this step, the adaptive maximum number of iterations based on the convergence rate of the objective function is determined. , and the expression is:

[0055] ,

[0056] In the formula, is the initial maximum number of iterations, is the control factor, is the best objective function value at the -th iteration, is the best objective function value at the -th iteration, is the change window time;

[0057] A random solution is generated using a mixed probability distribution, and the expression is:

[0058] ,

[0059] In the formula, is the updated solution for dimension , is the lower bound of dimension , is the lower bound of dimension , is a uniformly distributed random number, is a standard normal distribution number, is the random probability, is the random probability, satisfying ;

[0060] For each random solution , an opposite solution of the current solution is generated with a jump probability , and the expression is:

[0061] ,

[0062] This expression is the main idea of the opposition learning mechanism in the algorithm. By generating a corresponding term opposite to the current random solution with a probability of , the one with the smaller objective function value of the two is selected as the initial solution, and this initialization step improves the applicability to the subsequent optimization process.

[0063] ,

[0064] ,

[0065] In the formula, is the maximum value of the jump probability, is the minimum value of the jump probability, is the adjustment factor, is the acceleration coefficient at the th iteration, is the dimension of the problem, is the total dimension of the problem;

[0066] Compare the objective function value of the random solution and the objective function value of the opposite solution , and keep the one with the minimum objective function value as the initial solution.

[0067] Step S104, enter the main loop and update the initial solution.

[0068] In this step, when the number of iterations is less than the set value, enter the exploration phase. Among them, the rule for updating the solution in the exploration phase is:

[0069] Calculate the weight and the adaptive weight , and the expression is:

[0070] ,

[0071] ,

[0072] In the formula, is the exponential function, represents the th iteration, is the adaptive maximum number of iterations based on the convergence rate of the objective function;

[0073] Use the original SCO algorithm to update the solution with the adaptive weight , and the expression is:

[0074] ,

[0075] In the formula, is the updated solution, is a random number;

[0076] With a probability of 1 - use the new strategy. The new strategy introduces sine / cosine perturbations to prevent the updated solution from converging quickly, and the expression is:

[0077]

[0078] In the formula, is the imaginary symbol, is a random number, is the step function;

[0079] When the number of iterations is greater than the set value, enter the exploitation phase. The rule for updating the solution in the exploitation phase is:

[0080] If consecutive updates fail, update the solution using a preset mutation strategy, and the mutation strategy is as follows:

[0081] Cauchy mutation is triggered by with the expression:

[0082] ,

[0083] ,

[0084] ,

[0085] wherein is a random number from 0 to 1, is the average mean fitness change of the previous iteration, is the average optimal fitness change of the previous iteration, is the mutation trigger probability factor, is the probability of triggering Cauchy mutation, is the dimension of the updated solution.

[0086] Gaussian mutation is triggered by with the expression:

[0087] ,

[0088] ,

[0089] wherein is the probability of triggering Gaussian mutation, represents sampling from a Gaussian distribution;

[0090] Levy mutation is triggered with a probability of with the expression:

[0091] ,

[0092] ,

[0093] wherein is the probability of triggering Levy mutation, is , is the gamma function, is ;

[0094] If mutation is not triggered, update the candidate solution normally, and the expression is:

[0095] ,

[0096] wherein is a random number.

[0097] In step S105, check whether the solution is within the boundary range, and correct the out-of-bounds solution based on a preset correction rule until the maximum number of iterations is reached, and output the solution with the lowest objective function as the inspection path.

[0098] In this step, the expression of the correction rule is:

[0099] ,

[0100] ,

[0101] ,

[0102] wherein, is the updated solution of dimension , is the lower bound of dimension , is the dynamic fractal contraction coefficient, is the upper bound of dimension , is a very small number, generally taken as 2.22e-16, is the fractal noise function, is the Riemann function, is infinity, is the initial value of the dynamic fractal contraction coefficient, is the attenuation factor, represents the th iteration, is the adaptive maximum number of iterations based on the convergence rate of the objective function.

[0103] It should be noted that the lowest solution refers to the objective function value recorded after each iteration. After reaching the maximum number of iterations, compare the objective function values after each iteration, and the order of the UAV inspection path when the objective function value is the smallest is the optimal solution.

[0104] The lowest solution refers to the UAV inspection path plan with the smallest objective function value during the algorithm iteration process. The objective function is a quantitative index for the multi-constraint optimization problem:

[0105] ,

[0106] In summary, the lowest solution is the path plan corresponding to the minimum value of the objective function globally searched by the algorithm within the feasible solution space.

[0107] In summary, the method of the present application comprehensively considers the energy consumption constraint of the UAV, the time penalty constraint, and the UAV photovoltaic inspection path planning under the wind field conditions. It introduces a wind speed model with time window segmentation, and uses an accelerated opposition algorithm based on chaotic single candidates to solve the optimal inspection path of the UAV. It solves the problem that the existing path planning often takes the "shortest path" as the core, ignoring the energy consumption constraint of the UAV, the time window penalty function, and the influence of wind speed and wind direction on the endurance and inspection quality of the UAV, and solves the problem that traditional algorithms need to frequently adjust parameters during solution, resulting in slow convergence speed and easy to fall into local optimum. It can realize the multi-objective collaborative optimization of endurance time, inspection timeliness and wind resistance, and obtain an inspection path with higher inspection quality.

[0108] In a specific embodiment, to further verify the effectiveness of the proposed method, the present invention uses the traveling salesman problem eil51 test set to compare the average path length, average solution time, and average cost of three different algorithms running independently 30 times, and uses MATLAB software to verify the proposed mathematical model.

[0109] Table 1 Comparison of results of three algorithms

[0110] ,

[0111] The algorithm of the present invention performs best in terms of average path length, average solution time, and average cost, which are 447.97, 16.75 seconds, and 4231.3 respectively, superior to the Improved Sparrow Search Algorithm (ISSA) (467.31, 18.14 seconds, 4481.5) and the Grey Wolf Optimization (GWO) (458.56, 16.96 seconds, 4314.9). This shows that the algorithm of the present invention has higher efficiency and effect in path optimization problems, can find shorter and lower-cost paths in a shorter time, and is suitable for application scenarios with high requirements for path length, solution time, and cost.

[0112] At the same time, aiming at the multi-constraint coupling problem in the photovoltaic inspection task, the present invention constructs a dynamic path optimization model by integrating multi-dimensional constraints such as wind speed, time window, and energy consumption. The experimental results show that the method of the present invention performs significantly better than traditional methods in complex constraint scenarios, and the specific data are as follows:

[0113] (1) Wind speed constraint satisfaction rate

[0114] In the simulation scenario (average wind speed 8m / s, gust up to 12m / s), in the path planned by the algorithm of the present invention:

[0115] Only 3.2% of the flight segments exceed the maximum wind resistance level of the UAV (the designed wind resistance capacity is 10 m / s), while the exceeding ratios of the traditional genetic algorithm (GA) and particle swarm optimization (PSO) are 15.7% and 18.4% respectively.

[0116] The wind energy utilization rate is increased by 21%: By optimizing the flight attitude through the real-time wind speed segmented model, the cruising speed of the UAV in the downwind segment is increased by 15%, and the energy consumption in the upwind segment is reduced by 18%.

[0117] (2) Proportion of time window penalty cost

[0118] In time-sensitive inspection tasks (time window width ±10 minutes):

[0119] The number of nodes violating the time window is reduced by 45%: Through the constraint of the penalty function (the expression of the penalty cost), only 2.3% of the nodes exceed the upper and lower limits of the time window, while the violation rates of the SSA and GWO algorithms are 7.8% and 9.1% respectively.

[0120] (3) Energy consumption balance of multiple UAVs

[0121] The standard deviation of the energy consumption of a single UAV is reduced to 8.7%: Compared with 15.2% of the traditional method, the present invention optimizes the path allocation through the dynamic energy cost model (the expression of the dynamic energy cost), avoiding some UAVs from running out of power prematurely.

[0122] To verify the response ability of the method of the present invention under dynamic meteorological conditions, the following two types of extreme scenario tests are designed:

[0123] (1) Wind speed constraint satisfaction rate

[0124] Simulate that the wind speed suddenly increases from 8 m / s to 15 m / s (lasting for 3 minutes), and then returns to the initial value.

[0125] The algorithm in this paper only needs 2 iterations (about 0.8 seconds) to complete the path adjustment, and the increase amplitude of the path length is controlled within 4.2% of the original path. And in terms of energy consumption stability, because the dynamic wind speed model is used, the energy consumption fluctuation of the UAV in the gust is reduced by 51%, avoiding the energy waste caused by frequent speed changes.

[0126] (2) Scenario of dynamic changes in light and fouling rate

[0127] The fouling rate of the photovoltaic panel rapidly increases from the initial 20% to 50% (simulating a sandstorm), and at the same time the local light intensity drops suddenly by 30%.

[0128] Based on the surface state function of the photovoltaic panel, the algorithm automatically offsets the path towards the area with a high fouling rate and sufficient light, and the integrity rate of fault detection is increased to 98.7%. After the sudden change of the fouling rate, the path update delay is less than 1.2 seconds, ensuring that the inspection task is not affected by environmental mutations.

[0129] In order to compare the solution of the method of this application with other algorithms under multiple constraints, 100 simulation iterations were carried out in MATLAB based on a 1 km² photovoltaic power station. The comparison table of the satisfaction of multiple constraints is as follows, where the "improvement range" is the optimization ratio of the method of the present invention relative to other algorithms.

[0130] Table 2 Comparison table of the satisfaction of multiple constraints

[0131] 。

[0132] Please refer to Figure 2 , which shows the structural block diagram of an unmanned aerial vehicle (UAV) photovoltaic inspection path planning system considering multi-constraint coupling of this application.

[0133] As Figure 2 shown, the UAV photovoltaic inspection path planning system 200 includes a definition module 210, a setting module 220, a selection module 230, a loop module 240, and an output module 250.

[0134] Among them, the definition module 210 is configured to establish a wind speed model with time window segmentation, and define the objective function of the UAV dynamic trajectory optimization problem for the UAV photovoltaic inspection path planning considering the UAV energy consumption constraint, time penalty constraint, and wind field situation; the setting module 220 is configured to set the initial parameters of the accelerated opposition algorithm based on the chaotic single candidate; the selection module 230 is configured to generate a random solution and an opposite solution of the objective function according to the accelerated opposition learning mechanism, and select the better solution as the initial solution of the objective function; the loop module 240 is configured to enter the main loop to update the initial solution; the output module 250 is configured to check whether the solution is within the boundary range, and correct the out-of-bounds solution based on a preset correction rule until the maximum number of iterations is reached, and output the solution with the lowest objective function as the inspection path.

[0135] It should be understood that Figure 2 the modules recorded in Figure 1 correspond to the respective steps in the method described with reference to Figure 2 . Therefore, the operations and features described above for the method and the corresponding technical effects also apply to the

[0136] In some other embodiments, the embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored. When the program instructions are executed by a processor, the processor is caused to execute the method for planning the photovoltaic inspection path of a drone considering multi-constraint coupling in any of the above method embodiments;

[0137] As an implementation manner, the computer-readable storage medium of the present invention stores computer-executable instructions, and the computer-executable instructions are set as follows:

[0138] Establish a wind speed model with time window segmentation, consider the energy consumption constraint of the drone, the time penalty constraint, and define the objective function of the dynamic trajectory optimization problem of the photovoltaic inspection path of the drone under the wind field condition;

[0139] Set the initial parameters of the accelerated opposition algorithm based on a chaotic single candidate;

[0140] Generate a random solution and an opposite solution of the objective function according to the accelerated opposition learning mechanism, and select the better solution as the initial solution of the objective function;

[0141] Enter the main loop to update the initial solution;

[0142] Check whether the solution is within the boundary range, and correct the out-of-bounds solution based on a preset correction rule until the maximum number of iterations is reached, and output the solution with the lowest objective function as the inspection path.

[0143] The computer-readable storage medium may include a storage program area and a storage data area. Among them, the storage program area may store an operating system and application programs required for at least one function; the storage data area may store data created according to the use of the system for planning the photovoltaic inspection path of a drone considering multi-constraint coupling. In addition, the computer-readable storage medium may include a high-speed random access memory, and may also include a memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the computer-readable storage medium may optionally include a memory remotely provided with respect to the processor, and these remote memories may be connected to the system for planning the photovoltaic inspection path of a drone considering multi-constraint coupling through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0144] Figure 3 is a schematic structural diagram of an electronic device provided by the embodiments of the present invention, as Figure 3 shown, the device includes: a processor 310 and a memory 320. The electronic device may further include: an input device 330 and an output device 340. The processor 310, the memory 320, the input device 330, and the output device 340 may be connected through a bus or other means,Figure 3 Take the connection via the bus as an example. The memory 320 is the computer-readable storage medium described above. The processor 310 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions, and modules stored in the memory 320, that is, implements the method for planning the UAV photovoltaic inspection path considering multi-constraint coupling in the above method embodiments. The input device 330 can receive input digital or character information, and generate key signal inputs related to user settings and function controls of the UAV photovoltaic inspection path planning system considering multi-constraint coupling. The output device 340 can include display devices such as a display screen.

[0145] The above electronic device can execute the method provided by the embodiments of the present invention, and has corresponding functional modules and beneficial effects for executing the method. For technical details not described in detail in this embodiment, reference can be made to the method provided by the embodiments of the present invention.

[0146] As an implementation manner, the above electronic device is applied to a UAV photovoltaic inspection path planning system considering multi-constraint coupling, and is used for a client, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0147] Establish a wind speed model with time window segmentation, and define the objective function of the UAV dynamic trajectory optimization problem for the UAV photovoltaic inspection path planning considering the UAV energy consumption constraint, time penalty constraint, and wind field situation;

[0148] Set the initial parameters of the accelerated opposition algorithm based on the chaotic single candidate;

[0149] Generate a random solution and an opposition solution of the objective function according to the accelerated opposition learning mechanism, and select the better solution as the initial solution of the objective function;

[0150] Enter the main loop to update the initial solution;

[0151] Check whether the solution is within the boundary range, and correct the out-of-bounds solution based on a preset correction rule until the maximum number of iterations is reached, and output the solution with the lowest objective function as the inspection path.

[0152] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiments.

[0153] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for path planning of UAV photovoltaic inspection considering multi-constraint coupling, characterized in that Including: Establish a wind speed model with time window segmentation, consider the energy consumption constraint of the UAV, the time penalty constraint, and the UAV's photovoltaic inspection path planning under the wind field condition, and define the objective function of the UAV dynamic trajectory optimization problem; Set the initial parameters of the accelerated opposition algorithm based on chaotic single candidate; Generate the random solution and the opposition solution of the objective function according to the accelerated opposition learning mechanism, and select the better solution as the initial solution of the objective function. Among them, generating the random solution and the opposition solution of the objective function according to the accelerated opposition learning mechanism and selecting the better solution as the initial solution of the objective function includes: Determine the adaptive maximum number of iterations t based on the convergence rate of the objective function max , and the expression is: where \(t_0\) is the initial maximum number of iterations, \(\gamma\) is the control factor, \(f\) best \((t')\) is the best objective function value at the \(t'\)-th iteration, \(f\) best \((t - \tau)\) is the best objective function value at the \((t - \tau)\)-th iteration, and \(\tau\) is the change window time; Generate a random solution using a mixed probability distribution, and the expression is: In the formula, K(j) is the updated solution of dimension j, lb(j) is the lower bound of dimension j, ub(j) is the lower bound of dimension j, ι1 is a uniformly distributed random number, ι2 is a standard normal distribution number, p1 is a random probability, p2 is a random probability, and p1 + p2 = 1; For each random solution K, with a jump probability J r Generate the opposite solution of the current solution The expression is: Where J rmax is the maximum jump probability, J rmin is the minimum jump probability, α is the adjustment factor, ac(t′) is the acceleration coefficient at the t′-th iteration, j is the dimension of the problem, and D is the total dimension of the problem; Compare the objective function values of the random solution K and the opposite solution and retain the one with the smallest objective function value as the initial solution; Enter the main loop to update the initial solution; Check whether the solution is within the boundary range, and correct the out-of-bounds solution based on the preset correction rule until the maximum number of iterations is reached, and output the solution with the lowest objective function as the inspection path.

2. A method for planning the photovoltaic inspection path of an unmanned aerial vehicle considering multi-constraint coupling according to claim 1, characterized in that The establishing of the wind speed model with time window segmentation, considering the energy consumption constraint of the UAV, the time penalty constraint, and the UAV's photovoltaic inspection path planning under the wind field condition, and defining the objective function of the UAV dynamic trajectory optimization problem includes: Obtain the wind field data in a preset future time period, divide the time window at a preset time interval, and extract the global wind speed and the mean wind direction of each window; Define the objective function of the UAV dynamic trajectory optimization problem, and the expression is: f = w1·(f1 + f2) + (1 - w1)·f3 + f pv , where f1 is the fixed cost of the UAV, f2 is the dynamic energy cost, f3 is the penalty cost, and f pv is the surface state function of the photovoltaic panel, and w1 is a weight coefficient ranging from [0,1]; f1 = C1 + C2 + … + C A , Wherein, C1, C2, C A are respectively the fixed cost of the first UAV, the fixed cost of the second UAV, and the fixed cost of the A-th UAV. A is the number of UAVs, W is the unloaded weight of the UAV, ρ is the air fluid density, ζ is the blade area of the UAV, is the inspection time at point b, d ab is the distance from point a to point b of the UAV, is the actual wind speed of the UAV at time t, V air is the moving speed of the UAV relative to the air, W t is the globally predicted wind speed value, D t is the angle between the wind direction and the due north direction, θ ab is the angle between the UAV flight path and the due north direction, is a binary variable indicating whether the UAV z has completed the task, l b and u b are respectively the upper and lower bounds of the time window. θ1 and θ2 are the penalty coefficients for exceeding the time window, r b is the actual time of arrival at point b, I(t) is the light intensity at the current time period, I ref is the reference light intensity, S(t) is the current soiling rate of the photovoltaic panel, S ref is the reference value of the cleaning state, ξ is the environmental sensitivity coefficient, k is the number of time windows, and g is the acceleration due to gravity.

3. A method for planning an unmanned aerial vehicle photovoltaic inspection path considering multi-constraint coupling according to claim 1, characterized in that, The initialization parameters include: an adaptive maximum number of iterations t based on the convergence rate of the objective function max , an initial maximum number of iterations t0, the total dimension D of the problem, a control factor γ, a change window time τ, a threshold m for the number of successful attempts, a threshold k' for the number of iterations in the exploration phase, the dimension j of the problem, a maximum jump probability J rmax , a minimum jump probability J rmin and an adjustment factor α.

4. A method for planning an unmanned aerial vehicle photovoltaic inspection path considering multi-constraint coupling according to claim 1, characterized in that, The entering the main loop and updating the initial solution includes: When the number of iterations is less than the set value, enter the exploration stage. Among them, the solution update rule in the exploration stage is: Calculate the weight σ(t′) and the adaptive weight p, and the expression is: where exp is the exponential function, t′ represents the t′-th iteration, and t max is the adaptive maximum number of iterations based on the convergence rate of the objective function; Update the solution using the original SCO algorithm with the adaptive weight p, and the expression is: In the formula, Y(j) is the updated solution, and a1 is a random number; Use the new strategy with a probability of 1 - p. The new strategy introduces sine / cosine perturbation to avoid the rapid convergence of the updated solution, and the expression is: In the formula, i is the imaginary symbol, a2 is a random number, and H(·) is the step function; When the number of iterations is greater than the set value, enter the exploitation stage. The solution update rule in the exploitation stage is: If the update fails continuously for m times, update the solution using the preset mutation strategy. The mutation strategy is: Cauchy mutation is triggered with probability p 柯西 and the expression is: Wherein, is a random number from 0 to 1, is the average mean fitness change of the previous iteration, Δf best is the average mean of the optimal fitness change of the previous iteration, η is the mutation trigger probability factor, p 柯西 is the probability of triggering Cauchy mutation, and K(j) is the updated solution of dimension j. Gaussian mutation is triggered with probability p 高斯 and the expression is as follows: Y(j) = K(j)(1 + randn(1)), where p 高斯 is the probability of triggering Gaussian mutation, and randn(1) represents sampling from a Gaussian distribution; The Levy mutation triggers the mutation with probability p 利维 The expression is as follows: Wherein, P 利维 is the probability of triggering Levy mutation, and X is the gamma function, is If the mutation is not triggered, update the candidate solution normally, and the expression is: In the formula, a3 is a random number.

5. A method for planning an unmanned aerial vehicle photovoltaic inspection path considering multi-constraint coupling according to claim 1, characterized in that The expression of the correction rule is: where Y(j) is the updated solution of dimension j, lb(j) is the lower bound of dimension j, l is the dynamic fractal contraction coefficient, ub(j) is the upper bound of dimension j, ∈ is an extremely small number, generally taken as 2.22e-16, is the fractal noise function, ζ(k) is the Riemann function, ∞ is infinity, l0 is the initial value of the dynamic fractal contraction coefficient, v is the attenuation factor, t′ represents the t′-th iteration, t max is the adaptive maximum number of iterations based on the convergence rate of the objective function.

6. A UAV photovoltaic inspection path planning system considering multi-constraint coupling, characterized in that Including: A definition module configured to establish a wind speed model with time window segmentation, consider the energy consumption constraint of the UAV, the time penalty constraint, and the UAV's photovoltaic inspection path planning under the wind field condition, and define the objective function of the UAV dynamic trajectory optimization problem; A setting module configured to set the initial parameters of the accelerated opposition algorithm based on chaotic single candidate; A selection module, configured to generate a random solution and an opposite solution of the objective function according to an accelerated opposition-based learning mechanism, and select a better solution as the initial solution of the objective function, wherein generating the random solution and the opposite solution of the objective function according to the accelerated opposition-based learning mechanism, and selecting a better solution as the initial solution of the objective function includes: Determine the adaptive maximum number of iterations t based on the convergence rate of the objective function max , and the expression is: wherein, t0 is the initial maximum number of iterations, γ is the control factor, and f best (t′) is the best objective function value at the t′-th iteration, and f best (t - τ) is the best objective function value at the (t - τ)-th iteration, and τ is the change window time; Generating a random solution by adopting a mixed probability distribution, and the expression is: In the formula, K(j) is the updated solution of dimension j, lb(j) is the lower bound of dimension j, ub(j) is the upper bound of dimension j, ι1 is a uniformly distributed random number, ι2 is a standard normally distributed number, p1 is a random probability, p2 is a random probability, and p1 + p2 = 1; For each random solution K, with a jump probability J r Generate the opposite solution of the current solution The expression is: where J rmax is the maximum jump probability, J rmin is the minimum jump probability, α is the adjustment factor, ac(t′) is the acceleration coefficient at the t′-th iteration, j is the dimension of the problem, and D is the total dimension of the problem; Compare the objective function values of the random solution K and the opposite solution and retain the one with the smallest objective function value as the initial solution; A loop module, configured to enter a main loop to update the initial solution; An output module, configured to check whether the solution is within the boundary range, and correct the out-of-bounds solution based on a preset correction rule until the maximum number of iterations is reached, and output the solution with the lowest objective function as the inspection path.

7. An electronic device, characterized in that, including: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images