An unmanned aerial vehicle inspection route optimization method suitable for a photovoltaic module

Abstract

This application relates to the field of swarm intelligence optimization technology, specifically to a method for optimizing drone inspection routes for photovoltaic (PV) modules. The method includes: collecting spatial location data of each PV site in a PV power plant, the PV lines between any two connected PV sites, and the nodes along the PV lines; obtaining the terrain influence coefficient between any two connected PV sites; obtaining the terrain influence correction value between any two connected PV sites; obtaining the ascending and descending segments along the PV lines between any two connected PV sites in each direction; obtaining the unidirectional consumption degree and unilateral weights; constructing a weighted and directed graph of the PV power plant based on the unilateral weights; and optimizing the drone's patrol route for PV modules. This application improves the accuracy of drone-based PV module line inspection route planning.

Description

Technical Field

[0001] This application relates to the field of swarm intelligence optimization technology, specifically to a method for optimizing drone inspection routes for photovoltaic modules. Background Technology

[0002] With the continuous development of green and clean energy, the proportion of photovoltaic power generation in the power system is constantly increasing, thus raising the demand for the reliability and safety of photovoltaic power plants. To obtain sufficient power generation, a single photovoltaic power plant typically comprises multiple photovoltaic arrays, distributed across various hilltops with good sunlight. These arrays are connected by power lines, ultimately transmitting the converted solar energy to the grid-connected photovoltaic power station, achieving connection to the main power grid. For the stable operation of the entire photovoltaic power plant, regular inspections of the photovoltaic power lines are necessary.

[0003] Autonomous drone inspection boasts advantages such as low cost, wide coverage, and high efficiency. However, it requires autonomous path planning, specifically, autonomously planning a reasonable and optimal inspection route based on the known photovoltaic lines formed by photovoltaic modules within a photovoltaic power plant. When using heuristic algorithms based on swarm intelligence for autonomous drone path planning, it often relies on constructing a route graph structure. Traditionally, this is achieved by constructing an unweighted, undirected graph. However, in practice, photovoltaic arrays are deployed in well-lit areas on various hilltops, and the transmission lines between these arrays may need to traverse complex terrains such as mountains and valleys. Therefore, the unweighted, undirected 3D graph structure limits the global planning capabilities of swarm intelligence algorithms, resulting in insufficient optimization of drone paths. This causes the drones to consume more power during rapid ascents and descents, preventing them from inspecting larger areas. Summary of the Invention

[0004] To address the aforementioned technical problems, this application provides a method for optimizing drone inspection routes for photovoltaic modules, thereby resolving existing issues.

[0005] The method for optimizing drone inspection routes for photovoltaic modules proposed in this application adopts the following technical solution: One embodiment of this application provides a method for optimizing unmanned aerial vehicle (UAV) inspection routes for photovoltaic modules, the method comprising the following steps: The system collects spatial location data of each photovoltaic site in a photovoltaic power plant, the photovoltaic lines between any two connected photovoltaic sites, and the nodes of each line on the photovoltaic lines; the spatial location data includes longitude, latitude, and altitude. Based on the dispersion of the distance between any two connected photovoltaic sites and the spatial location data of photovoltaic lines, the terrain influence coefficient between any two connected photovoltaic sites is obtained. Based on the height difference of adjacent line nodes in the photovoltaic line between any two connected photovoltaic sites, the number of line nodes, and the terrain influence coefficient, the terrain influence correction value between any two connected photovoltaic sites is obtained. Based on the difference in altitude between the line nodes in the photovoltaic line between any two connected photovoltaic sites, obtain the ascending and descending segments along the photovoltaic line in each direction between any two connected photovoltaic sites. Based on the difference in altitude between any two connected photovoltaic sites and the number of ascending and descending segments, obtain the unidirectional consumption rate from any one photovoltaic site to the other. Based on the one-way consumption degree and terrain influence correction value, obtain the one-sided weight between any two connected photovoltaic sites and the other photovoltaic site. Construct a weighted and directed graph of a photovoltaic power plant based on unilateral weights; The drone navigation routes for photovoltaic modules are optimized based on weighted and directed graphs.

[0006] Furthermore, the method for obtaining the terrain influence coefficient is as follows: Based on the spatial location data of the photovoltaic lines between any two connected photovoltaic sites, the first height variance and photovoltaic goodness of fit of the photovoltaic lines between any two photovoltaic sites are obtained. For any two connected photovoltaic sites, calculate the ratio between the first height variance and the photovoltaic goodness of fit of the photovoltaic line, calculate the Euclidean distance between the spatial location data of any two connected photovoltaic sites, and use the product of the ratio and the Euclidean distance as the terrain influence coefficient between any two connected photovoltaic sites.

[0007] Furthermore, the method for obtaining the first height variance is as follows: For any two photovoltaic power stations, the variance of the altitude of all spatial location data on the photovoltaic power line is taken as the first altitude variance of the photovoltaic power line between any two photovoltaic power stations.

[0008] Furthermore, the method for obtaining the photovoltaic goodness of fit is as follows: For any two photovoltaic (PV) stations, a PV fitting curve is obtained by performing curve fitting on all spatial location data along the PV line. The goodness of fit of the PV fitting curve is then calculated as the PV goodness of fit of the PV line between any two PV stations.

[0009] Furthermore, the formula for calculating the terrain influence correction value is as follows: In the formula, B represents the terrain impact correction value between any two connected photovoltaic sites. This represents the terrain influence coefficient between any two connected photovoltaic sites. Represents the normalization function. This represents the mean of the absolute values ​​of the differences in altitude between all adjacent nodes on the photovoltaic line between any two connected photovoltaic sites. This represents a logarithmic function with base 2, where N represents the number of line nodes on the photovoltaic line between any two connected photovoltaic sites.

[0010] Furthermore, the method for obtaining the rising segment and the falling segment is as follows: In any two connected photovoltaic sites, for a photovoltaic line in the direction from one photovoltaic site to the other, the photovoltaic line is divided into node segments at each node of the photovoltaic line. The difference in altitude between the end node and the beginning node of each node segment in the direction is calculated. When the difference is greater than 0, the node segment is regarded as an ascending segment in the direction; when the difference is less than 0, the node segment is regarded as a descending segment in the direction.

[0011] Furthermore, the formula for calculating the unidirectional consumption degree is as follows: In the formula, C represents the unidirectional consumption rate from any one photovoltaic station to the other in any two connected photovoltaic stations. This represents the difference between the altitudes of any two connected photovoltaic (PV) sites and the altitude of the other PV site. and These represent the number of rising and falling segments between any two connected photovoltaic (PV) sites.

[0012] Furthermore, the method for obtaining the unilateral weight is as follows: Normalize the unidirectional consumption between any two connected photovoltaic sites along both directions of the photovoltaic line to obtain the normalized unidirectional consumption. The formula for calculating the unilateral weight is as follows: In the formula, W represents the one-sided weight between any two connected photovoltaic sites and the other photovoltaic site. B represents the normalized unidirectional consumption rate from any one photovoltaic site to the other among any two connected photovoltaic sites, and B represents the terrain impact correction value between any two connected photovoltaic sites.

[0013] Furthermore, the weighted and directed graph of the photovoltaic power plant constructed based on unilateral weights includes: Each photovoltaic node is treated as a node, and the one-sided weight between any two connected photovoltaic sites is used as the directed weight between any node corresponding to one photovoltaic site and the node corresponding to the other photovoltaic site, thus constructing a weighted and directed graph.

[0014] Furthermore, the optimization of the drone cruise route for photovoltaic modules based on a weighted and directed graph includes: Swarm intelligence algorithms are used to process weighted and directed graphs to obtain the optimal inspection path after drone flight path optimization.

[0015] This application has at least the following beneficial effects: This application takes various photovoltaic arrays and lines under a photovoltaic electric field as the research object. Based on the terrain and line relationships, a weighted directed graph is determined, and finally, a swarm intelligence optimization algorithm is used to optimize the inspection route of the UAV photovoltaic modules. Specifically, based on the complexity of the terrain and lines between two connected photovoltaic sites, a terrain influence correction value is obtained, reflecting the possibility of the line failing due to environmental influences and the tendency of the UAV to inspect the line during the inspection. At the same time, based on the changes in the height number and node segments of the unidirectional edges of the connected photovoltaic sites, the unidirectional consumption degree is obtained, reflecting the energy consumption of the unidirectional line during the UAV inspection. From this, the unidirectional weight value of the unidirectional edge is determined. By traversing the edges of all connected photovoltaic sites in the photovoltaic electric field, a weighted directed graph of the electric field is obtained. Finally, the optimal UAV inspection route is obtained using a swarm intelligence optimization algorithm. Compared to the traditional approach of simplifying the lines between photovoltaic power plants into an unweighted and undirected graph, this method uses specific quantification and evaluation methods to determine the bidirectional weight values ​​of each edge. This avoids the subjectivity of measuring the weight of a single edge based on empirical values, improves the accuracy of the weighted and directed graph, and enhances the accuracy of drones in planning inspection routes for photovoltaic module lines in complex geographical environments, thereby increasing inspection efficiency. Attached Figure Description

[0016] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, 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.

[0017] Figure 1 A flowchart of a method for optimizing drone inspection routes for photovoltaic modules provided in this application; Figure 2 This is a schematic diagram of a photovoltaic power station circuit provided in one embodiment of this application. Detailed Implementation

[0018] To further illustrate the technical means and effects adopted by this application to achieve the intended inventive objective, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a drone inspection route optimization method for photovoltaic modules proposed in this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0020] The following description, in conjunction with the accompanying drawings, details a specific scheme for optimizing the unmanned aerial vehicle (UAV) inspection route for photovoltaic modules provided in this application.

[0021] This application provides an embodiment of a method for optimizing drone inspection routes for photovoltaic modules. Specifically, it provides the following method for optimizing drone inspection routes for photovoltaic modules. Please refer to [link to relevant documentation]. Figure 1 The method includes the following steps: Step S1: Collect spatial location data of each photovoltaic site in the photovoltaic power plant, the photovoltaic lines between any two connected photovoltaic sites, and the nodes of each line on the photovoltaic lines.

[0022] This application focuses on photovoltaic power plants, which consist of multiple photovoltaic arrays that are distributed across open spaces on various hilltops based on the local terrain. The photovoltaic arrays are connected by photovoltaic lines composed of photovoltaic modules, and the power of the photovoltaic arrays is ultimately transmitted and aggregated to the grid-connected photovoltaic power station to achieve connection and power transmission with the main power grid.

[0023] A schematic diagram of a photovoltaic power station is shown below. Figure 2 As shown, 1 represents a grid-connected photovoltaic power station, 2 represents a photovoltaic array of photovoltaic modules, and 3 represents a transmission line for photovoltaic power. The grid-connected photovoltaic power station and the photovoltaic array are considered as photovoltaic sites. The photovoltaic array and the grid-connected photovoltaic power station in the photovoltaic field have a certain area. To simplify the analysis, the coordinates of the center point of the photovoltaic array and the grid-connected photovoltaic power station are used as the location of each photovoltaic site.

[0024] To enable the inspection of photovoltaic (PV) modules within a PV power plant, a 3D topographic map of the area covered by the PV power plant is obtained using the PV power plant's geospatial system. For any two PV sites, where the distance between them is relatively large, poles and high-voltage lines need to be erected between them. The line consisting of the poles, transformers, and high-voltage lines between the two PV sites is considered the PV line between them. This PV line between any two PV sites contains multiple line nodes and high-voltage lines, where line nodes include poles and transformers.

[0025] The three-dimensional topographic map of the photovoltaic power plant includes spatial location data of each photovoltaic site and the photovoltaic lines between any two photovoltaic sites. The spatial location data includes longitude, latitude, and altitude.

[0026] Step S2: Based on the distance between any two connected photovoltaic sites and the dispersion of the spatial location data of the photovoltaic lines, obtain the terrain influence coefficient between any two connected photovoltaic sites; based on the height difference of adjacent line nodes in the photovoltaic lines between any two connected photovoltaic sites, the number of line nodes, and the terrain influence coefficient, obtain the terrain influence correction value between any two connected photovoltaic sites.

[0027] In traditional swarm intelligence optimization processes, when using swarm intelligence algorithms to plan autonomous inspection paths for UAVs, the spatial relationships between photovoltaic (PV) arrays are often relied upon. This means that round trips between connected PV sites are considered equivalent, and the path planning bias depends solely on the distance between the connected PV sites. However, in practice, to improve the power generation efficiency of PV farms, the PV arrays are typically distributed dispersedly, with some individual sections located on hilltops where sunlight is more abundant. Therefore, connecting two PV sites often requires traversing complex terrain such as valleys and ridges, leading to unequal round trips between connected PV sites. Weighted directed graphs are therefore more suitable for autonomous UAV path planning in complex scenarios. However, the weights of connected routes are often determined based on empirical values, lacking practical basis and generalization ability. Therefore, this application focuses on determining the weights of routes between various PV sites within a PV farm.

[0028] For any two connected photovoltaic (PV) sites, the more complex the terrain of the PV lines between the sites, that is, the more drastic the changes in the spatial location data of the PV lines between the two sites, the more likely the PV lines between the two sites are to have faults due to tree branches blocking the light, birds nesting, or geological changes. Conversely, the simpler the terrain of the PV lines between the two connected sites, the easier it is to construct high-voltage transmission lines, and therefore the lower the probability of faults.

[0029] Based on the above analysis, for any two photovoltaic (PV) sites, the variance of the altitude of all spatial location data along the PV line is taken as the first altitude variance of the PV line between the two PV sites. A curve fitting is then performed on all spatial location data along the PV line to obtain a PV fitting curve. The goodness of fit of the PV fitting curve is calculated as the PV goodness of fit of the PV line between the two PV sites. The method for calculating the goodness of fit is a well-known technique and will not be elaborated upon in this embodiment.

[0030] Furthermore, to reflect the impact of terrain between any two connected photovoltaic (PV) sites on the high-voltage transmission line, a terrain influence coefficient between any two connected PV sites is obtained based on the first height variance, PV goodness of fit, and the distance between them. The calculation formula is as follows: In the formula, A represents the terrain influence coefficient between any two connected photovoltaic sites; This represents the Euclidean distance between the spatial locations of any two connected photovoltaic sites. This represents the first altitude variance between any two connected photovoltaic sites. This represents the photovoltaic goodness of fit of the photovoltaic line between any two photovoltaic sites.

[0031] The more complex the terrain and the greater the distance between two connected photovoltaic (PV) sites, the more prone the high-voltage transmission line between them is to failure. Therefore, this line is more likely to be prioritized for inspection during UAV patrols. Due to the complex terrain, the greater the fluctuation in altitude data in the spatial point cloud sequence between connected PV sites, the larger the first altitude variance, and the more difficult it is to perform curve fitting on the spatial point cloud sequence, resulting in a smaller PV fit goodness of fit. Consequently, the terrain influence between connected PV sites is greater; conversely, the terrain influence coefficient is smaller.

[0032] The importance of the route during drone inspections is measured by the complexity of the geographical terrain between two connected photovoltaic (PV) sites. While the construction of routes between PV sites depends on the terrain, optimization measures are sometimes implemented to control costs. For example, when connecting two PV sites that need to cross a deep valley, it might be preferable to build poles on the two mountain peaks to avoid the need to extend the route across the valley and then re-erect it on the mountain peak, thus increasing the route length and cost. Therefore, it is necessary to adjust for the terrain impact based on the actual route conditions between the two connected PV sites.

[0033] Specifically, when there are many high-voltage transmission line nodes between two connected photovoltaic sites, and the greater the fluctuation in the height difference between the nodes, it indicates that the line is built on complex terrain, and the possibility of line failure is greater. Conversely, if the terrain between connected photovoltaic sites is complex, but the height difference between the nodes is small, it indicates that the connected photovoltaic sites may have avoided the complex terrain through simple construction, and therefore the possibility of line failure is smaller.

[0034] Furthermore, to reflect the correction for the terrain influence coefficient between any two adjacent photovoltaic sites, the terrain influence correction value between any two connected photovoltaic sites is obtained based on the terrain influence coefficient and the number of line nodes on the photovoltaic line. The calculation formula is as follows: In the formula, B represents the terrain impact correction value between any two connected photovoltaic sites. This represents the terrain influence coefficient between any two connected photovoltaic sites. Represents the normalization function. This represents the mean of the absolute values ​​of the differences in altitude between all adjacent nodes on the photovoltaic line between any two connected photovoltaic sites. Let N represent the logarithmic function to the base 2, where N represents the number of nodes on the photovoltaic line between any two connected photovoltaic sites. It should be noted that taking the logarithm of the number of nodes in the line is to avoid the problem of uneven distribution of the number of nodes among connected photovoltaic sites in a photovoltaic power plant.

[0035] It should be noted that the more complex the terrain between two connected nodes, the larger the terrain influence coefficient. However, if the number of nodes on the transmission line between two connected photovoltaic sites is small, and the height variation of adjacent nodes is small, it indicates that optimization measures were adopted to reduce costs during the construction of the line. In this case, the line is less dependent on the terrain, resulting in a smaller normalized value and a smaller terrain influence coefficient, thus reducing the terrain influence coefficient of the connected line and obtaining a larger terrain influence correction value. Conversely, if there are many photovoltaic sites on the line and the height variation of adjacent nodes is large, it indicates that the transmission line traverses complex terrain, and the possibility of failure is higher, thus obtaining a larger terrain influence correction value.

[0036] Step S3: Based on the difference in altitude between the line nodes in the photovoltaic line between any two connected photovoltaic sites, obtain the ascending and descending segments along the photovoltaic line in each direction between any two connected photovoltaic sites; based on the difference in altitude between any two connected photovoltaic sites and the number of ascending and descending segments, obtain the unidirectional consumption degree from any one photovoltaic site to the other; based on the unidirectional consumption degree and the terrain influence correction value, obtain the unilateral weight between any one photovoltaic site and the other; construct a weighted and directed graph of the photovoltaic power plant based on the unilateral weight.

[0037] In step S2, the complexity of the terrain and transmission lines between two connected photovoltaic sites is used to assess the importance of the transmission line during UAV inspection, thereby constructing the weight value of a single edge of the photovoltaic power plant's transmission line map. However, the impact on the UAV during inspection varies. For a one-way route between the connected photovoltaic sites, if there are more ascending nodes among all nodes on the route, it indicates that the UAV is climbing, resulting in greater wear and tear on the UAV. Conversely, for the opposite route, if there are more descending nodes, the wear and tear on the UAV is less.

[0038] Furthermore, in any two connected photovoltaic sites, for a photovoltaic line in the direction from one photovoltaic site to the other, the photovoltaic line is divided into node segments at each node of the photovoltaic line. The difference in altitude between the end node and the beginning node of each node segment in the direction is calculated. When the difference is greater than 0, the node segment is regarded as an ascending segment in the direction; when the difference is less than 0, the node segment is regarded as a descending segment in the direction; when the difference is equal to 0, no classification processing is performed on the node segment.

[0039] Furthermore, to reflect the trend changes in the photovoltaic lines between any two connected photovoltaic sites, the unidirectional consumption rate from one photovoltaic site to the other is obtained based on the number of rising and falling segments in the photovoltaic lines. The calculation formula is as follows: In the formula, C represents the unidirectional consumption rate from any one photovoltaic station to the other in any two connected photovoltaic stations. This represents the difference between the altitudes of any two connected photovoltaic (PV) sites and the altitude of the other PV site. and These represent the number of rising and falling segments between any two connected photovoltaic (PV) sites. It should be noted that in the above description, all instances of "any photovoltaic site" refer to the same PV site.

[0040] It should be noted that the altitude difference between the initial and destination photovoltaic (PV) stations determines whether the overall trend of the one-way flight path is upward or downward. Furthermore, the distribution of upward and downward segments along the PV route reveals the trend of the route segments. If the overall trend is upward, the altitude difference between the destination and initial stations will be positive and relatively large. Additionally, a larger proportion of upward segments indicates more climbing time for the UAV in that direction, resulting in a higher one-way consumption rate. Conversely, a larger downward trend with more downward segments leads to a lower one-way consumption rate.

[0041] Furthermore, the unidirectional consumption between any two connected photovoltaic sites along both directions of the photovoltaic line is normalized to obtain the normalized unidirectional consumption. The normalization method is a well-known technique and will not be elaborated upon in this embodiment.

[0042] Furthermore, based on the normalized one-way consumption rate and the terrain impact correction value, the one-way weight between any two connected photovoltaic sites and the other photovoltaic site is obtained. The calculation formula is as follows: In the formula, W represents the one-sided weight between any two connected photovoltaic sites and the other photovoltaic site. Let B represent the normalized unidirectional energy dissipation from any two connected photovoltaic (PV) sites to the other, and let B represent the terrain impact correction value between any two connected PV sites. It should be noted that in the above description, all instances of "any one PV site" refer to the same PV site.

[0043] Specifically, the more complex the terrain and transmission lines between two connected photovoltaic (PV) sites, the larger the terrain impact correction value for that PV site. This indicates a higher probability of line failure, and the smaller the weight of the corresponding edge on the line graph for that PV site should be. This makes it more likely that the UAV will prioritize that line during path planning. Furthermore, for unidirectional altitude descent along that line, the smaller the unidirectional consumption value in that direction, the smaller the unidirectional edge weight, making it a better route for descent. Conversely, for altitude ascent, the larger the unidirectional consumption value, the lower the preference for that direction during selection.

[0044] Thus, the one-sided weight between any two connected photovoltaic sites in the photovoltaic field is obtained; further, each photovoltaic node is treated as a node, and the one-sided weight between any two connected photovoltaic sites is used as the directed weight between the node corresponding to one photovoltaic site and the node corresponding to the other photovoltaic site, thereby constructing a weighted and directed graph.

[0045] Step S4: Optimize the drone cruise route for photovoltaic modules based on the weighted and directed graph.

[0046] Based on step S3, a weighted and directed graph of photovoltaic modules under the photovoltaic field in this region is constructed. Based on this graph structure, a swarm intelligence optimization algorithm is used to optimize the path and flight route of the UAV, specifically as follows: Based on the above analysis, a weighted directed graph structure is constructed. The fitness function is the minimum flight cost and maximum inspection range of the UAV, with trajectory smoothing as a constraint. The swarm intelligence algorithm used is the Harris Eagle optimization algorithm. The initial population size is set to 50, the maximum number of iterations is 500, and the population is randomly initialized. The swarm intelligence algorithm then outputs the optimal inspection path for the UAV after route optimization. The swarm intelligence algorithm is a well-known technique and will not be described in detail in this embodiment.

[0047] The drones, following the planned optimal inspection path, can inspect the photovoltaic modules within the photovoltaic power plant. The drones can complete the inspection task without directly contacting the photovoltaic modules and lines. Through technologies such as computer vision, they can photograph and identify the photovoltaic modules and lines, promptly discovering defects in the system components, thereby improving the efficiency and accuracy of the inspection.

[0048] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this application. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0049] The various embodiments in this application are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0050] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them; modifications to the technical solutions described in the foregoing embodiments, or equivalent substitutions of some of the technical features, do not cause the essence of the corresponding technical solutions to deviate from the 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 optimizing unmanned aerial vehicle (UAV) inspection routes for photovoltaic modules, characterized in that, The method includes the following steps: The system collects spatial location data of each photovoltaic site in a photovoltaic power plant, the photovoltaic lines between any two connected photovoltaic sites, and the nodes of each line on the photovoltaic lines; the spatial location data includes longitude, latitude, and altitude. Based on the dispersion of the distance between any two connected photovoltaic sites and the spatial location data of photovoltaic lines, the terrain influence coefficient between any two connected photovoltaic sites is obtained. Based on the height difference of adjacent line nodes in the photovoltaic line between any two connected photovoltaic sites, the number of line nodes, and the terrain influence coefficient, the terrain influence correction value between any two connected photovoltaic sites is obtained. Based on the difference in altitude between the line nodes in the photovoltaic line between any two connected photovoltaic sites, obtain the ascending and descending segments along the photovoltaic line in each direction between any two connected photovoltaic sites. Based on the difference in altitude between any two connected photovoltaic sites and the number of ascending and descending segments, obtain the unidirectional consumption rate from any one photovoltaic site to the other. Based on the one-way consumption degree and terrain influence correction value, obtain the one-sided weight between any two connected photovoltaic sites and the other photovoltaic site. Construct a weighted and directed graph of a photovoltaic power plant based on unilateral weights; The drone navigation routes for photovoltaic modules are optimized based on weighted and directed graphs.

2. The method for optimizing UAV inspection routes for photovoltaic modules as described in claim 1, characterized in that, The method for obtaining the terrain influence coefficient is as follows: Based on the spatial location data of the photovoltaic lines between any two connected photovoltaic sites, the first height variance and photovoltaic goodness of fit of the photovoltaic lines between any two photovoltaic sites are obtained. For any two connected photovoltaic sites, calculate the ratio between the first height variance and the photovoltaic goodness of fit of the photovoltaic line, calculate the Euclidean distance between the spatial location data of any two connected photovoltaic sites, and use the product of the ratio and the Euclidean distance as the terrain influence coefficient between any two connected photovoltaic sites.

3. The method for optimizing UAV inspection routes for photovoltaic modules as described in claim 2, characterized in that, The method for obtaining the first height variance is as follows: For any two photovoltaic power stations, the variance of the altitude of all spatial location data on the photovoltaic power line is taken as the first altitude variance of the photovoltaic power line between any two photovoltaic power stations.

4. The method for optimizing UAV inspection routes for photovoltaic modules as described in claim 2, characterized in that, The method for obtaining the photovoltaic goodness of fit is as follows: For any two photovoltaic (PV) stations, a PV fitting curve is obtained by performing curve fitting on all spatial location data along the PV line. The goodness of fit of the PV fitting curve is then calculated as the PV goodness of fit of the PV line between any two PV stations.

5. The method for optimizing UAV inspection routes for photovoltaic modules as described in claim 1, characterized in that, The formula for calculating the terrain impact correction value is as follows: In the formula, B represents the terrain impact correction value between any two connected photovoltaic sites. This represents the terrain influence coefficient between any two connected photovoltaic sites. Represents the normalization function. This represents the mean of the absolute values ​​of the differences in altitude between all adjacent nodes on the photovoltaic line between any two connected photovoltaic sites. This represents a logarithmic function with base 2, where N represents the number of line nodes on the photovoltaic line between any two connected photovoltaic sites.

6. The method for optimizing UAV inspection routes for photovoltaic modules as described in claim 1, characterized in that, The method for obtaining the rising segment and the falling segment is as follows: In any two connected photovoltaic sites, for a photovoltaic line in the direction from one photovoltaic site to the other, the photovoltaic line is divided into node segments at each node of the photovoltaic line. The difference in altitude between the end node and the beginning node of each node segment in the direction is calculated. When the difference is greater than 0, the node segment is regarded as an ascending segment in the direction; when the difference is less than 0, the node segment is regarded as a descending segment in the direction.

7. The method for optimizing UAV inspection routes for photovoltaic modules as described in claim 1, characterized in that, The formula for calculating the unidirectional consumption rate is as follows: In the formula, C represents the unidirectional consumption rate from any one photovoltaic station to the other in any two connected photovoltaic stations. This represents the difference between the altitudes of any two connected photovoltaic (PV) sites and the altitude of the other PV site. and These represent the number of rising and falling segments between any two connected photovoltaic (PV) sites.

8. The method for optimizing UAV inspection routes for photovoltaic modules as described in claim 1, characterized in that, The method for obtaining the unilateral weight is as follows: Normalize the unidirectional consumption between any two connected photovoltaic sites along both directions of the photovoltaic line to obtain the normalized unidirectional consumption. The formula for calculating the unilateral weight is as follows: In the formula, W represents the one-sided weight between any two connected photovoltaic sites and the other photovoltaic site. B represents the normalized unidirectional consumption rate from any one photovoltaic site to the other among any two connected photovoltaic sites, and B represents the terrain impact correction value between any two connected photovoltaic sites.

9. The method for optimizing UAV inspection routes for photovoltaic modules as described in claim 1, characterized in that, The weighted and directed graph of the photovoltaic power plant constructed based on unilateral weights includes: Each photovoltaic node is treated as a node, and the one-sided weight between any two connected photovoltaic sites is used as the directed weight between any node corresponding to one photovoltaic site and the node corresponding to the other photovoltaic site, thus constructing a weighted and directed graph.

10. The method for optimizing UAV inspection routes for photovoltaic modules as described in claim 1, characterized in that, The optimization of UAV cruise routes for photovoltaic modules based on weighted and directed graphs includes: Swarm intelligence algorithms are used to process weighted and directed graphs to obtain the optimal inspection path after drone flight path optimization.

Images