Unmanned aerial vehicle-based photovoltaic power station inspection method, device, equipment and medium

Abstract

The application discloses a photovoltaic station inspection method and device based on a UAV, equipment and a medium. The method comprises the following steps: determining a plurality of alternative operation points according to photovoltaic array distribution information of a target photovoltaic station; determining a plurality of target operation points based on operation costs of the alternative operation points and a UAV working radius; determining a plurality of target operation areas according to the plurality of target operation points and the UAV working radius, and dividing each target operation area into a plurality of target sub-areas; determining target task types of each photovoltaic array in each target sub-area, determining a target inspection route of the target sub-area according to the target task types; assigning a UAV to each target sub-area, and scheduling the UAV to inspect the photovoltaic array in the target sub-area according to the target inspection route based on the assignment result. The scheme can schedule the UAV to perform photovoltaic inspection based on the optimal operation point and the inspection task type, improve the accuracy and efficiency of the inspection, and thus guarantee the safe and stable operation of the photovoltaic station.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicle control, and in particular to a photovoltaic station inspection method and device based on unmanned aerial vehicles, equipment and medium. BACKGROUND

[0002] With the development of photovoltaic technology and the increasing scale of photovoltaic power stations, the significance of photovoltaic inspection is increasingly prominent. Through regular inspection work, problems that occur in the operation of photovoltaic power stations can be found and solved in a timely manner, ensuring the safety and stability of the operation of photovoltaic power stations. The existing photovoltaic inspection technology mainly uses a flight path with a certain overlap rate, lacks purpose and planning of inspection, and can only give a rough positioning latitude and longitude, so the accuracy and efficiency of the inspection are low. SUMMARY

[0003] The present application provides a photovoltaic station inspection method and device based on unmanned aerial vehicles, which solves one of the above technical problems.

[0004] According to an aspect of the present application, a photovoltaic station inspection method based on unmanned aerial vehicles is provided, the method comprising:

[0005] acquiring photovoltaic array distribution information of a target photovoltaic station, and determining a plurality of alternative work points according to the photovoltaic array distribution information; wherein the target photovoltaic station comprises a plurality of photovoltaic arrays;

[0006] determining a plurality of target work points from the plurality of alternative work points based on work costs of the alternative work points and a working radius of an unmanned aerial vehicle;

[0007] determining a plurality of target work areas according to the plurality of target work points and the working radius of the unmanned aerial vehicle, and dividing each target work area into a plurality of target sub-areas;

[0008] determining a target task type of each photovoltaic array in each target sub-area, and determining a target inspection flight path of the target sub-area according to the target task type;

[0009] allocating an unmanned aerial vehicle to each target sub-area, and scheduling the unmanned aerial vehicle to inspect the photovoltaic arrays in the target sub-area according to the target inspection flight path based on the allocation result.

[0010] According to another aspect of the present application, a photovoltaic station inspection device based on unmanned aerial vehicles is provided, the device comprising:

[0011] an alternative work point determination module configured to acquire photovoltaic array distribution information of a target photovoltaic station, and determine a plurality of alternative work points according to the photovoltaic array distribution information; wherein the target photovoltaic station comprises a plurality of photovoltaic arrays;

[0012] a target operation point determination module configured to determine a plurality of target operation points from the plurality of candidate operation points based on operation cost and a working radius of the UAV;

[0013] a target sub-region determination module configured to determine a plurality of target operation regions according to the plurality of target operation points and the working radius of the UAV, and divide each of the target operation regions into a plurality of target sub-regions;

[0014] a target inspection route determination module configured to determine a target task type of each photovoltaic array in each of the target sub-regions, and determine a target inspection route of the target sub-region according to the target task type;

[0015] a photovoltaic array inspection module configured to assign a UAV to each of the target sub-regions, and schedule the UAV to inspect photovoltaic arrays in the target sub-region according to the target inspection route based on the assignment result.

[0016] According to another aspect of the present application, there is provided an electronic device, comprising:

[0017] at least one processor; and,

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the UAV-based photovoltaic power station inspection method according to any one of the embodiments of the present application.

[0020] According to another aspect of the present application, there is provided a computer readable storage medium storing computer instructions for enabling a processor to perform the UAV-based photovoltaic power station inspection method according to any one of the embodiments of the present application when executed by the processor.

[0021] The technical scheme of the embodiment of the present application acquires the photovoltaic array distribution information of a target photovoltaic station, determines a plurality of alternative operation points according to the photovoltaic array distribution information; wherein the target photovoltaic station comprises a plurality of photovoltaic arrays; determines a plurality of target operation points from the plurality of alternative operation points based on the operation cost of the alternative operation points and the working radius of the unmanned aerial vehicle; determines a plurality of target operation areas according to the plurality of target operation points and the working radius of the unmanned aerial vehicle, and divides each target operation area into a plurality of target sub-areas; determines the target task type of each photovoltaic array in each target sub-area, determines the target inspection route of the target sub-area according to the target task type; allocates an unmanned aerial vehicle to each target sub-area, and schedules the unmanned aerial vehicle to inspect the photovoltaic array in the target sub-area according to the target inspection route based on the allocation result. The technical scheme can schedule the unmanned aerial vehicle to perform photovoltaic inspection based on the optimal operation point and the inspection task type, improves the accuracy and efficiency of photovoltaic inspection, and thus guarantees the safe and stable operation of the photovoltaic station.

[0022] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creating laborious work.

[0024] Figure 1 is a flow chart of a photovoltaic station inspection method based on an unmanned aerial vehicle according to the first embodiment of the present application;

[0025] Figure 2 is a photovoltaic array distribution diagram of a target photovoltaic station according to the first embodiment of the present application;

[0026] Figure 3 is a convex hull schematic diagram of a photovoltaic array in a target photovoltaic station according to the first embodiment of the present application;

[0027] Figure 4 is a schematic diagram of a segmentation line division according to the first embodiment of the present application;

[0028] Figure 5 is a schematic diagram of an alternative operation point according to the first embodiment of the present application;

[0029] Figure 6 is a schematic diagram of a target operation area according to the first embodiment of the present application;

[0030] Figure 7 is a schematic diagram of a target sub-region according to an embodiment of the present application;

[0031] Figure 8 is a flow chart of a photovoltaic power station inspection method based on a UAV according to an embodiment of the present application;

[0032] Figure 9 is a schematic diagram of a target sub-region according to an embodiment of the present application;

[0033] Figure 10 is a structural schematic diagram of a photovoltaic power station inspection device based on a UAV according to an embodiment of the present application;

[0034] Figure 11 is a structural schematic diagram of an electronic device for implementing a photovoltaic power station inspection method based on a UAV according to an embodiment of the present application. DETAILED DESCRIPTION

[0035] In order to make the personnel in the art better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should fall within the scope of protection of the present application.

[0036] It should be noted that the terms "first", "second", "target" and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0037] Embodiment one

[0038] Figure 1A flowchart of a photovoltaic station inspection method based on a UAV is provided for the first embodiment of the present application. The present embodiment can be applicable to the case of scheduling a UAV to efficiently and accurately inspect a photovoltaic station. The method can be executed by a photovoltaic station inspection device based on a UAV. The photovoltaic station inspection device based on a UAV can be realized in the form of hardware and / or software and can be configured in an electronic device with data processing capability. It should be noted that the UAV scheduling and inspection logic provided by the present embodiment can also be applicable to other scenarios other than photovoltaic inspection scenarios. Only the specific implementation details of the present embodiment need to be adjusted according to the actual application scenario. Figure 1 As shown in FIG. 9, the method comprises the following steps.

[0039] In S110, photovoltaic array distribution information of a target photovoltaic station is obtained, and a plurality of alternative operation points are determined according to the photovoltaic array distribution information. The target photovoltaic station comprises a plurality of photovoltaic arrays.

[0040] The target photovoltaic station can refer to a photovoltaic station with photovoltaic array inspection requirements, and the target photovoltaic station comprises a plurality of photovoltaic arrays. Each photovoltaic array comprises a plurality of photovoltaic panels. The photovoltaic panels are inspected by a UAV to detect defects, dirt, etc. present in the photovoltaic panels. The photovoltaic array distribution information can be used to describe the position information of the photovoltaic arrays in the target photovoltaic station, the arrangement form of the photovoltaic panels, etc.

[0041] For example, the photovoltaic array distribution information can be obtained from a photovoltaic array image or a photovoltaic station design diagram. Figure 2 A photovoltaic array distribution diagram of a target photovoltaic station is provided for the first embodiment of the present application. As shown in FIG. 10, PV-i represents the i th photovoltaic array. As shown in FIG. 11, the target photovoltaic station comprises a total of 160 photovoltaic arrays. Figure 2 The alternative operation points can refer to candidate starting points (i.e., departure points or takeoff points) of the UAV when performing photovoltaic inspection tasks.

[0042] In the present embodiment, the photovoltaic array distribution information of the target photovoltaic station is first obtained, and a plurality of alternative operation points are determined according to the photovoltaic array distribution information. Two different ways can be set to determine the alternative operation points, one is the unrestricted way (i.e., unconditional restriction), and the other is the restricted way (i.e., conditional restriction). The actual inspection requirements can be flexibly selected. Alternatively, the plurality of alternative operation points are determined according to the photovoltaic array distribution information, which comprises: determining the surrounding contour information corresponding to the photovoltaic arrays in the target photovoltaic station according to the photovoltaic array distribution information; equally dividing the surrounding area corresponding to the surrounding contour information to obtain a plurality of division lines; and equally taking points on each division line to obtain a plurality of alternative operation points.

[0043] Specifically, the first step is to determine the enclosing contour information of the photovoltaic arrays in the target photovoltaic power plant based on the photovoltaic array distribution information. This enclosing contour information can describe the contour of the enclosing circle that covers all photovoltaic arrays in the target photovoltaic power plant. For example, the enclosing contour information can be the convex hull information or contour information formed by the outer photovoltaic arrays in the target photovoltaic power plant. Figure 3 This is a schematic diagram of the convex hull of a photovoltaic array in a target photovoltaic power station according to Embodiment 1 of the present invention, wherein the red part represents each photovoltaic array (and) Figure 2 (Correspondingly, the blue lines represent the convex hull.) Then, the bounding region corresponding to the bounding contour information is divided into multiple dividing lines at equal intervals. The bounding region can refer to a closed area composed of the bounding contour, encompassing all photovoltaic arrays in the target photovoltaic power station. Figure 4 This is a schematic diagram of a dividing line system provided in Embodiment 1 of the present invention, where green lines represent multiple dividing lines. Finally, points are taken at equal intervals along each dividing line to obtain multiple candidate operation points. Figure 5 This is a schematic diagram of an alternative work point provided in Embodiment 1 of the present invention, wherein the yellow dots on the green lines represent multiple alternative work points.

[0044] This scheme, through this setting, can quickly identify multiple evenly distributed candidate work points without any restrictions, so that the optimal work point can be determined from them later.

[0045] S120 determines multiple target work points from multiple candidate work points based on the operating costs of alternative work points and the working radius of the drone.

[0046] In this embodiment, after determining multiple candidate work points, it is necessary to determine the work cost for each candidate work point. For example, the work cost may include accessibility cost (related to the drone's flight distance), battery cost (related to the drone's battery level), and remote sensing signal cost (related to the strength of the remote sensing signal at the candidate work point). For example, multiple work cost parameters can be pre-set according to actual inspection needs, and each parameter can be assigned a corresponding weight value according to its importance. For each candidate work point, the parameter values ​​corresponding to each work cost parameter can be determined according to preset rules, and the weighted sum of the parameter values ​​corresponding to each work cost parameter can be used to obtain the work cost of each candidate work point.

[0047] The preset rules can be pre-set according to actual inspection needs. For example, for accessibility costs, a positive mapping relationship is set between drone flight distance and accessibility costs, that is, the farther the drone flies, the higher the accessibility cost; for battery costs, a positive mapping relationship is set between drone battery capacity and battery costs, that is, the more drone battery capacity, the higher the battery cost; for remote sensing signal costs, a positive mapping relationship is set between remote sensing signal strength and remote sensing signal costs, that is, the stronger the remote sensing signal at the candidate work point, the higher the remote sensing signal cost.

[0048] After determining the operational cost of each candidate work point, multiple target work points can be selected from these candidate work points based on their operational costs and the drone's working radius. A target work point can be understood as the optimal work point selected from the multiple candidate work points. Optionally, selecting multiple target work points from the multiple candidate work points based on their operational costs and the drone's working radius includes: selecting multiple target work points from the multiple candidate work points according to a target mathematical model, as follows:

[0049] ;

[0050] in, Indicates alternative work sites. , This represents the operating cost of the candidate work points. The task point refers to the center point of each photovoltaic array in the target photovoltaic power station. ,and The value of is determined based on the working radius of the drone. Represents the set of task points. Indicates that it can cover The set of alternative work sites.

[0051] It should be noted that the objective of the mathematical model is to determine the fewest possible objective task points so that all task points are satisfied. All of them can be executed successfully. Among them, The method for determining the value is as follows: based on the alternative work points A circular area is defined centered on the drone's operating radius, encompassing the task points within this circular area. This refers to the alternative work sites. The task points that can be covered. If alternative task points are available... Able to cover mission points ,but If alternative work sites Cannot cover mission points ,but .

[0052] This solution, through its configuration, can quickly determine multiple optimal target work points based on the target mathematical model, which helps improve the efficiency of photovoltaic inspection.

[0053] S130 determines multiple target operation areas based on multiple target operation points and the working radius of the UAV, and divides each target operation area into multiple target sub-areas.

[0054] In this embodiment, after determining multiple target work points, each target work point can be used as a center point, and the working radius of the UAV can be used as the radius, thereby determining multiple circular areas. Then, the areas containing each photovoltaic array within these circular areas are determined as the target work areas. For example, Figure 6 This is a schematic diagram of a target operation area provided in Embodiment 1 of the present invention. The corresponding UAV operating radius is 2 kilometers, and it includes a total of 3 target operation points and corresponding target operation areas. Figure 6 In the diagram, photovoltaic arrays of the same color represent a target work area, and each dot represents a target work point.

[0055] After identifying multiple target work areas, each target work area can be further divided into multiple target sub-areas. Optionally, dividing each target work area into multiple target sub-areas includes: for each target work area, determining the number of target drones and the number of target photovoltaic arrays included in the target work area; determining the target distances between each target photovoltaic array in the target work area based on the photovoltaic array distribution information of the target work area; and dividing the target work area into multiple target sub-areas based on the number of target drones, the number of target photovoltaic arrays, and the target distances.

[0056] The target number of drones can refer to the number of drones expected to be allocated to the target operational area. The target number of photovoltaic arrays can refer to the number of photovoltaic arrays included in the target operational area. The target distance can refer to the distance between any two target photovoltaic arrays in the target operational area.

[0057] For example, the target operating area can be divided into multiple target sub-regions based on the MTSP (Multiple Traveling Salesman Problem) algorithm, according to the number of target drones, the number of target photovoltaic arrays, and the target distances. MTSP is a classic problem in combinatorial optimization, referring to dividing a city cluster into M groups, and using TSP to find the shortest travel route for each group. Therefore, the key to the problem is how to determine the grouping of the city clusters; the MTSP algorithm can be understood as an algorithm capable of solving the MTSP (Multiple Traveling Salesman Problem). TSP (Traveling Salesman Problem) is a well-known problem in operations research, which can be used to describe the following problem: A traveling salesman starts from city 1 and needs to go to cities 2, 3, ..., n to sell goods, and finally returns to city 1. If the distance between any two cities is known, how should the traveling salesman choose his / her optimal route?

[0058] It should be noted that MTSP is a multi-objective problem, and the equal distribution of tasks among the traveling salesmen is a crucial step in the Multi-Traveling Salesman Problem (MTSP) algorithm. Its objectives generally fall into two categories: 1. Minimize the total travel distance while evenly distributing the number of visiting nodes (number of different cities) among the multiple traveling salesmen; 2. Minimize the total travel distance while evenly distributing the visiting distance. In this embodiment, MTSP with evenly distributed visiting nodes can be used to divide the target operating area into multiple target sub-regions. The objective function of MTSP with evenly distributed visiting nodes minimizes the total travel distance while simultaneously achieving the goal of evenly distributing the visiting nodes among the M traveling salesmen. Based on this, it can be understood that the number of target drones is equivalent to the number of traveling salesmen M, the number of target photovoltaic arrays is equivalent to the total number of visiting nodes, and the target distance is equivalent to the distance between visiting nodes.

[0059] For example, let's take one target work area as an example, and assume that the number of target photovoltaic arrays in that target work area is 50. Figure 7 As shown, if the number of target drones is 5, the target operation area can be divided into 5 target sub-regions, with each drone allocated 10, 10, 10, 10, and 10 photovoltaic arrays respectively. The red dots represent the target operation points (i.e., the drone takeoff points and landing points) corresponding to the target operation areas, and each color area represents one target sub-region. Furthermore, the number of target drones can also be other values, such as 10 or 12.

[0060] This solution, through this configuration, can divide the target work area into multiple target sub-areas based on the number of photovoltaic arrays in the target work area, so that drone scheduling can be realized subsequently based on the target sub-areas.

[0061] S140, determine the target task type of each photovoltaic array in each target sub-region, and determine the target inspection route of the target sub-region according to the target task type.

[0062] The target task type describes the type of photovoltaic (PV) inspection task that the UAV needs to perform on each PV array in the target sub-region. For example, the task type can include: 1. Ordinary inspection task: this refers to PV inspection tasks in centralized PV power plants; 2. Crack detection task: this detects whether the PV panels in the PV array are cracked; 3. Distributed task: this refers to PV inspection tasks in distributed PV power plants. It should be noted that the target task types for each PV array in the target sub-region can be the same or different, depending on the actual inspection requirements. In this embodiment, after determining the target task type for each PV array in each target sub-region, UAV path planning can be performed on the target sub-region based on the target task type, thereby determining the target inspection route for the target sub-region. The target inspection route can be understood as the actual flight path of the UAV for inspecting the PV arrays in the target sub-region. It should be noted that different target task types correspond to different UAV path planning methods, therefore different target task types correspond to different target inspection routes.

[0063] In this embodiment, optionally, determining the target inspection route for the target sub-region based on the target task type includes: if the target task type is a fragmentation task, generating a first inspection route within the photovoltaic strings of the photovoltaic array based on a preset method, and generating a second inspection route between the photovoltaic strings based on the traveling salesman algorithm; wherein, the photovoltaic array includes multiple photovoltaic strings, each photovoltaic string includes multiple photovoltaic panels, and the fragmentation task is used to detect whether there is any fragmentation in the photovoltaic panels of the photovoltaic array; the first inspection route and the second inspection route are integrated to obtain the target inspection route for the target sub-region.

[0064] The preset method refers to the pre-defined method for generating inspection routes within the photovoltaic strings based on actual inspection needs. For example, the preset method can be set to generate inspection routes in an S-shape. The first and second inspection routes can refer to the inspection routes generated within the photovoltaic strings and between photovoltaic strings, respectively. The Traveling Salesman Algorithm (TSP) is an algorithm that can solve the TSP (Traveling Salesman Problem).

[0065] Specifically, if the target task type is determined to be a fragmentation task, a first inspection route is first generated within the photovoltaic strings of the photovoltaic array based on a preset method (such as an S-shape). Then, a second inspection route is generated between the photovoltaic strings based on the traveling salesman algorithm. Finally, the first and second inspection routes are integrated to obtain the target inspection route for the target sub-region.

[0066] This solution, through such a setting, can generate corresponding target inspection routes for fragmentation tasks, so that UAVs can efficiently inspect the photovoltaic arrays in the target sub-regions for fragmentation tasks based on the target inspection routes.

[0067] In this embodiment, optionally, determining the target inspection route for the target sub-region based on the target task type includes: if the target task type is a normal inspection task, generating an inspection route between the photovoltaic strings of the photovoltaic array based on the traveling salesman algorithm as the target inspection route for the target sub-region; wherein, the photovoltaic array includes multiple photovoltaic strings, and the normal inspection task refers to the photovoltaic inspection task under a centralized photovoltaic power station.

[0068] In this embodiment, if the target task type is determined to be a normal inspection task, route planning is performed on a per-photovoltaic string basis. Specifically, based on the traveling salesman algorithm, inspection routes are generated between the photovoltaic strings of the photovoltaic array as the target inspection routes for the target sub-region.

[0069] This solution, through such a setting, can generate corresponding target inspection routes for ordinary inspection tasks, so that UAVs can efficiently inspect photovoltaic arrays in target sub-regions according to the target inspection routes.

[0070] In this embodiment, optionally, determining the target inspection route for the target sub-region based on the target task type includes: if the target task type is a distributed task, determining the minimum bounding rectangle of each distributed region; wherein, a distributed task refers to a photovoltaic inspection task under a distributed photovoltaic power station; generating multiple candidate operation lines in the minimum bounding rectangle based on a preset spacing, and determining the candidate operation lines located inside the distributed region as target operation lines; connecting the target operation lines to obtain the candidate inspection routes for the distributed region, and connecting each candidate inspection route to obtain the target inspection route for the target sub-region.

[0071] The distribution area can refer to the area where the photovoltaic array is located, such as the rooftop area. It's understood that a distributed task includes multiple distribution areas. Specifically, if the target task type is determined to be a distributed task, firstly, the minimum bounding rectangle of each distribution area is determined. Then, based on a preset spacing, multiple candidate work lines are generated within the minimum bounding rectangle, and the candidate work lines located within the distribution area are determined as the target work lines. The preset spacing can refer to the distance between two adjacent candidate work lines pre-set according to actual inspection requirements. Connecting each target work line sequentially yields the candidate inspection routes for the distribution area. Finally, connecting all the candidate inspection routes yields the target inspection route for the target sub-area.

[0072] This solution, through this configuration, can generate corresponding target inspection routes for distributed tasks, enabling UAVs to perform efficient distributed inspections of photovoltaic arrays in target sub-regions based on the target inspection routes.

[0073] S150 assigns a drone to each target sub-region and, based on the assignment result, schedules the drone to inspect the photovoltaic array in the target sub-region according to the target inspection route.

[0074] In this embodiment, after dividing each target work area into multiple target sub-areas, a corresponding drone can be assigned to each target sub-area. For example, if the target work area is divided into multiple target sub-areas based on the number of photovoltaic arrays in the target work area, a drone can be assigned to each target sub-area. Then, based on the allocation results, multiple drones can be scheduled to perform parallel inspections of the photovoltaic arrays in the target sub-areas according to the target inspection route, thereby effectively improving the photovoltaic inspection efficiency.

[0075] The technical solution of this invention involves acquiring photovoltaic array distribution information of a target photovoltaic power station, determining multiple candidate work points based on the photovoltaic array distribution information, wherein the target photovoltaic power station includes multiple photovoltaic arrays; determining multiple target work points from the multiple candidate work points based on the operating cost of the candidate work points and the working radius of the drones; determining multiple target work areas based on the multiple target work points and the working radius of the drones, and dividing each target work area into multiple target sub-areas; determining the target task type of each photovoltaic array in each target sub-area, and determining the target inspection route for the target sub-area based on the target task type; allocating drones to each target sub-area, and scheduling drones to inspect the photovoltaic arrays in the target sub-area according to the target inspection route based on the allocation results. This technical solution can schedule drones for photovoltaic inspection based on the optimal work point and inspection task type, improving the accuracy and efficiency of photovoltaic inspection, thereby ensuring the safe and stable operation of the photovoltaic power station.

[0076] In this embodiment, optionally, multiple candidate work points are determined based on the photovoltaic array distribution information, including: determining the enclosing contour information corresponding to the photovoltaic array in the target photovoltaic power station based on the photovoltaic array distribution information; determining the target interference area based on the map information of the target photovoltaic power station; wherein, the target interference area includes non-road areas and areas with abnormal elevation changes; determining the other areas in the enclosing area corresponding to the enclosing contour information, excluding the target interference area, as the target division area; dividing the target division area at equal intervals to obtain multiple dividing lines, and taking points at equal intervals on each dividing line to obtain multiple candidate work points.

[0077] It should be noted that, considering the differences in terrain and topography of different target photovoltaic power stations, it is sometimes necessary to impose some restrictions on the drone operation points according to the actual terrain and topography. For example, the operation points can only be set up on roads or flat areas. This restriction ensures that the drone can land and take off safely at the starting point. In this case, non-road areas (such as mud pits) and high-altitude areas (such as hillsides) should be excluded to ensure the safety of the drone.

[0078] In this embodiment, firstly, the surrounding contour information of the photovoltaic arrays in the target photovoltaic power station is determined based on the photovoltaic array distribution information. This surrounding contour information can be the convex hull information or contour information formed by the outer photovoltaic arrays of the target photovoltaic power station. Then, map information of the target photovoltaic power station is acquired. This map information can be satellite remote sensing imagery of the target photovoltaic power station obtained by a drone or electronic map information of the target photovoltaic power station. Based on the map information of the target photovoltaic power station, non-road areas and areas with abnormal elevation changes are extracted as target interference areas. Areas with abnormal elevation changes can be understood as areas with a sudden increase in altitude. Then, target interference areas are removed from the surrounding areas corresponding to the surrounding contour information to obtain one or more target division areas. Finally, each target division area is divided at equal intervals to obtain multiple dividing lines, and points are taken at equal intervals on each dividing line to obtain multiple candidate operation points.

[0079] This solution, through this setup, can quickly identify multiple alternative work sites based on constraints, thereby better ensuring the safety of the drone at the starting point.

[0080] Example 2

[0081] Figure 8 This is a flowchart of a photovoltaic power station inspection method based on unmanned aerial vehicles (UAVs) according to Embodiment 2 of the present invention. This embodiment is based on the above embodiment with optimizations. Specifically, the optimizations include: dividing each target operation area into multiple target sub-regions, including: for each target operation area, determining the target cost matrix of the target photovoltaic array according to the task type of each target photovoltaic array in the target operation area; dividing the target operation area into multiple target sub-regions according to the UAV's range and the target cost matrix.

[0082] like Figure 8 As shown, the method in this embodiment specifically includes the following steps:

[0083] S210, Obtain the photovoltaic array distribution information of the target photovoltaic power station, and determine multiple alternative operation points based on the photovoltaic array distribution information; wherein, the target photovoltaic power station includes multiple photovoltaic arrays.

[0084] S220 determines multiple target work points from multiple candidate work points based on the operating costs of alternative work points and the working radius of the drone.

[0085] The S230 determines multiple target operation areas based on multiple target operation points and the working radius of the UAV.

[0086] S240, for each target work area, determine the target cost matrix of the target photovoltaic array based on the task type of each target photovoltaic array in the target work area.

[0087] The target cost matrix describes the overall cost required for a UAV to perform a specific task on a target photovoltaic array. It's important to note that the method for determining the target cost matrix differs for different task types; that is, different task types correspond to different target cost matrices.

[0088] In this embodiment, optionally, the target cost matrix of the target photovoltaic array is determined according to the task type of each target photovoltaic array in the target operation area, including: if the task type of the target photovoltaic array is a normal inspection task, the distance between the target photovoltaic array and other photovoltaic arrays is determined as a reference distance; wherein, a normal inspection task refers to a photovoltaic inspection task under a centralized photovoltaic power station; the target cost matrix of the target photovoltaic array is determined according to the reference distance.

[0089] Specifically, if the task type of the target photovoltaic array is determined to be a routine inspection task, the distances between the target photovoltaic array and other photovoltaic arrays in the target work area are calculated as reference distances. These reference distances are then arranged sequentially to obtain the target cost matrix of the target photovoltaic array. For routine inspection tasks, the target cost matrix can be simply understood as the distance matrix from the current task point to other task points in the target work area.

[0090] In this embodiment, optionally, the target cost matrix of the target photovoltaic array is determined according to the task type of each target photovoltaic array in the target operation area, including: if the task type of the target photovoltaic array is a fragmentation task or a distributed task, the self-operation cost of the target photovoltaic array is determined according to the task type of the target photovoltaic array; wherein, the fragmentation task is used to detect whether there is fragmentation in the photovoltaic panels in the photovoltaic array, and the distributed task refers to the photovoltaic inspection task under the distributed photovoltaic power station; the distance between the target photovoltaic array and other photovoltaic arrays is determined as a reference distance; the target cost matrix of the target photovoltaic array is determined according to the reference distance and its own operation cost.

[0091] Specifically, if the target photovoltaic array's task type is determined to be either a fragmentation task or a distributed task, the self-operation cost of the target photovoltaic array corresponding to the task type needs to be determined first. This self-operation cost can be preset according to the task type. Then, the distances between the target photovoltaic array and other photovoltaic arrays in the target operation area are calculated as reference distances. Each reference distance is then added to its self-operation cost to obtain multiple comprehensive costs. Arranging these comprehensive costs in order yields the target cost matrix for the target photovoltaic array. For fragmentation tasks, the target cost matrix can be simply understood as the sum of the distance matrix from the current task point to other task points in the target operation area and the preset self-cost matrix for fragmentation tasks. For distributed tasks, the target cost matrix can be simply understood as the sum of the distance matrix from the current task point to other task points in the target operation area and the preset self-cost matrix for distributed tasks. The self-cost matrix and the distance matrix have the same number of rows and columns, and each element of the self-cost matrix represents the self-operation cost corresponding to the task type.

[0092] The S250 divides the target operation area into multiple target sub-areas based on the drone's range and target cost matrix.

[0093] In this embodiment, after determining the target cost matrix of the target photovoltaic array, the target operation area can be divided into multiple target sub-regions based on the UAV's flight range and the target cost matrix. Specifically, firstly, the total time required to complete the photovoltaic array inspection task in the target operation area is determined based on the target cost matrix. Then, the maximum single flight time that the UAV can fly is determined based on the UAV's flight range. Finally, the number of target sub-regions to be divided into is determined based on the ratio of the total time to the maximum single flight time. Based on this, it can be understood that the flight range of one UAV can successfully support the photovoltaic inspection task in one target sub-region. Finally, the target operation area can be divided into target sub-regions based on the number of target sub-regions using the CVRP (Capacitated Vehicle Routing Problem) algorithm. The CVRP algorithm can be understood as an algorithm capable of solving the CVRP (Capacitated Vehicle Routing Problem).

[0094] For example, let's take one target work area as an example, assuming that the number of target photovoltaic arrays in this target work area is 50. Figure 9 As shown, if the target sub-region is divided into 5 sub-regions, the target operation area can be divided into 5 target sub-regions. Among them, the red dots represent the target operation points (i.e., the drone take-off points and landing points) corresponding to the target operation areas, and each color area represents 1 target sub-region.

[0095] S260, determine the target task type of each photovoltaic array in each target sub-region, and determine the target inspection route of the target sub-region based on the target task type.

[0096] S270 assigns drones to each target sub-region and, based on the assignment results, schedules the drones to inspect the photovoltaic arrays in the target sub-regions according to the target inspection route.

[0097] It should be noted that since the range of a single drone can adequately support the photovoltaic inspection task of one target sub-area, the allocation of drones to each target sub-area can be flexibly adjusted based on the actual number of drones available for dispatch. When the actual number of available drones is sufficient, to improve photovoltaic inspection efficiency, one drone can be allocated to each target sub-area, with one drone responsible for the photovoltaic inspection of one target sub-area. Conversely, when the actual number of available drones is insufficient, multiple target sub-areas can be assigned to one drone, which can then fly multiple times, performing the photovoltaic inspection task of one target sub-area per flight, thus enabling one drone to be responsible for the photovoltaic inspection of multiple target sub-areas.

[0098] The technical solution of this invention, for each target operating area, determines the target cost matrix of the target photovoltaic array based on the task type of each target photovoltaic array in the target operating area; and divides the target operating area into multiple target sub-areas based on the UAV's range and the target cost matrix. This technical solution can divide the target operating area into multiple target sub-areas based on the task type and UAV flight capability, so that when scheduling UAVs based on the target sub-areas, the UAV task load in each target sub-area is kept as consistent as possible.

[0099] Example 3

[0100] Figure 10 This is a schematic diagram of a drone-based photovoltaic power station inspection device provided in Embodiment 3 of the present invention. This device can execute the drone-based photovoltaic power station inspection method provided in any embodiment of the present invention, and possesses the corresponding functional modules and beneficial effects for executing the method. For example... Figure 10 As shown, the device includes:

[0101] The alternative work site determination module 310 is used to acquire photovoltaic array distribution information of the target photovoltaic power station and determine multiple alternative work sites based on the photovoltaic array distribution information; wherein, the target photovoltaic power station includes multiple photovoltaic arrays;

[0102] The target operation point determination module 320 is used to determine multiple target operation points from the multiple candidate operation points based on the operation cost of the candidate operation points and the working radius of the UAV;

[0103] The target sub-region determination module 330 is used to determine multiple target operation areas based on the multiple target operation points and the working radius of the UAV, and to divide each target operation area into multiple target sub-regions;

[0104] The target inspection route determination module 340 is used to determine the target task type of each photovoltaic array in each target sub-region, and determine the target inspection route of the target sub-region according to the target task type.

[0105] The photovoltaic array inspection module 350 is used to allocate drones to each target sub-region and, based on the allocation result, schedule drones to inspect the photovoltaic arrays in the target sub-regions according to the target inspection route.

[0106] Optionally, the alternative work point determination module 310 is used for:

[0107] Based on the photovoltaic array distribution information, determine the enclosing contour information corresponding to the photovoltaic array in the target photovoltaic power station;

[0108] The bounding region corresponding to the bounding contour information is divided into multiple dividing lines at equal intervals.

[0109] Points are taken at equal intervals along each of the aforementioned dividing lines to obtain multiple candidate operation points.

[0110] Optionally, the alternative work point determination module 310 is used for:

[0111] Based on the photovoltaic array distribution information, determine the enclosing contour information corresponding to the photovoltaic array in the target photovoltaic power station;

[0112] The target interference area is determined based on the map information of the target photovoltaic power station; wherein, the target interference area includes non-road areas and areas with abnormal elevation changes;

[0113] The regions other than the target interference region within the bounding region corresponding to the bounding contour information are defined as the target division region;

[0114] The target area is divided into multiple dividing lines at equal intervals, and multiple candidate operation points are obtained by taking points at equal intervals on each dividing line.

[0115] Optionally, the target work point determination module 320 is used for:

[0116] Multiple target work points are determined from the plurality of candidate work points based on the target mathematical model, which is as follows:

[0117] ;

[0118] in, Indicates alternative work sites. , This represents the operating cost of the candidate work points. The task point refers to the center point of each photovoltaic array in the target photovoltaic power station. ,and The value of is determined based on the working radius of the drone. Represents the set of task points. Indicates that it can cover The set of alternative work sites.

[0119] Optionally, the target sub-region determination module 330 is used for:

[0120] For each target work area, determine the number of target drones in the target work area and the number of target photovoltaic arrays included in the target work area;

[0121] The target distance between each target photovoltaic array in the target work area is determined based on the photovoltaic array distribution information of the target work area.

[0122] Based on the number of target drones, the number of target photovoltaic arrays, and the target distance, the target operating area is divided into multiple target sub-regions.

[0123] Optionally, the target sub-region determination module 330 includes:

[0124] The target cost matrix determination unit is used to determine the target cost matrix of the target photovoltaic array for each target operation area based on the task type of each target photovoltaic array in the target operation area.

[0125] The target sub-region determination unit is used to divide the target operation area into multiple target sub-regions based on the UAV's flight range and the target cost matrix.

[0126] Optionally, the target cost matrix determination unit is used for:

[0127] If the task type of the target photovoltaic array is a normal inspection task, the distance between the target photovoltaic array and other photovoltaic arrays is determined as a reference distance; wherein, the normal inspection task refers to the photovoltaic inspection task under a centralized photovoltaic power station;

[0128] The target cost matrix of the target photovoltaic array is determined based on the reference distance.

[0129] Optionally, the target cost matrix determination unit is used for:

[0130] If the task type of the target photovoltaic array is a fragmentation task or a distributed task, the operating cost of the target photovoltaic array is determined according to the task type of the target photovoltaic array; wherein, the fragmentation task is used to detect whether there is any fragmentation in the photovoltaic panels of the photovoltaic array, and the distributed task refers to the photovoltaic inspection task under the distributed photovoltaic power station;

[0131] The distance between the target photovoltaic array and other photovoltaic arrays is determined as a reference distance;

[0132] The target cost matrix of the target photovoltaic array is determined based on the reference distance and its own operating cost.

[0133] Optionally, the target inspection route determination module 340 is used for:

[0134] If the target task type is a fragmentation task, a first inspection route is generated within the photovoltaic strings of the photovoltaic array based on a preset method, and a second inspection route is generated between the photovoltaic strings based on the traveling salesman algorithm; wherein, the photovoltaic array includes multiple photovoltaic strings, the photovoltaic strings include multiple photovoltaic panels, and the fragmentation task is used to detect whether there is any fragmentation in the photovoltaic panels of the photovoltaic array.

[0135] The first inspection route and the second inspection route are integrated to obtain the target inspection route for the target sub-area.

[0136] Optionally, the target inspection route determination module 340 is used for:

[0137] If the target task type is a normal inspection task, an inspection route is generated between the photovoltaic strings of the photovoltaic array based on the traveling salesman algorithm as the target inspection route of the target sub-region.

[0138] The photovoltaic array includes multiple photovoltaic strings, and the ordinary inspection task refers to the photovoltaic inspection task under the centralized photovoltaic power station.

[0139] Optionally, the target inspection route determination module 340 is used for:

[0140] If the target task type is a distributed task, determine the minimum bounding rectangle of each distribution area; wherein, the distributed task refers to the photovoltaic inspection task under a distributed photovoltaic power station;

[0141] Multiple candidate work lines are generated in the minimum bounding rectangle based on a preset spacing, and the candidate work lines located inside the distribution area are determined as the target work lines.

[0142] Connect the target work lines to obtain candidate inspection routes for the distribution area, and connect each candidate inspection route to obtain the target inspection route for the target sub-area.

[0143] The photovoltaic power plant inspection device based on UAV provided in this embodiment of the invention can execute the photovoltaic power plant inspection method based on UAV provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0144] Example 4

[0145] According to embodiments of the present invention, the present invention also provides an electronic device, a readable storage medium, and a computer program product.

[0146] Figure 11 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0147] like Figure 11 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0148] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0149] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the drone-based photovoltaic power station inspection method.

[0150] In some embodiments, the drone-based photovoltaic (PV) power plant inspection method can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the drone-based PV power plant inspection method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the drone-based PV power plant inspection method by any other suitable means (e.g., by means of firmware).

[0151] In some embodiments, the drone-based photovoltaic (PV) power plant inspection method can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the drone-based PV power plant inspection method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the drone-based PV power plant inspection method by any other suitable means (e.g., by means of firmware).

[0152] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0153] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0154] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0155] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0156] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0157] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0158] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0159] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for inspecting photovoltaic power stations based on unmanned aerial vehicles (UAVs), characterized in that, The method includes: Obtain photovoltaic array distribution information of the target photovoltaic power station, and determine multiple candidate operation points based on the photovoltaic array distribution information; wherein, the target photovoltaic power station includes multiple photovoltaic arrays; Based on the operating costs of the candidate work sites and the working radius of the UAV, multiple target work sites are determined from the multiple candidate work sites; Multiple target operation areas are determined based on the multiple target operation points and the working radius of the UAV, and each target operation area is divided into multiple target sub-regions; Determine the target task type for each photovoltaic array in each target sub-region, and determine the target inspection route for the target sub-region based on the target task type; A drone is assigned to each target sub-region, and based on the assignment result, the drone is scheduled to inspect the photovoltaic array in the target sub-region according to the target inspection route; Among them, based on the operating costs of the candidate operation points and the working radius of the UAV, multiple target operation points are determined from the multiple candidate operation points, including: Multiple target work points are determined from the plurality of candidate work points based on the target mathematical model, which is as follows: ； in, Indicates alternative work sites. , This represents the operating cost of the candidate work points. The task point refers to the center point of each photovoltaic array in the target photovoltaic power station. ,and The value of is determined based on the working radius of the drone. Represents the set of task points. Indicates that it can cover The set of alternative work sites.

2. The method according to claim 1, characterized in that, Based on the photovoltaic array distribution information, multiple candidate work sites are determined, including: Based on the photovoltaic array distribution information, determine the enclosing contour information corresponding to the photovoltaic array in the target photovoltaic power station; The bounding region corresponding to the bounding contour information is divided into multiple dividing lines at equal intervals. Points are taken at equal intervals along each of the aforementioned dividing lines to obtain multiple candidate operation points.

3. The method according to claim 1, characterized in that, Based on the photovoltaic array distribution information, multiple candidate work sites are determined, including: Based on the photovoltaic array distribution information, determine the enclosing contour information corresponding to the photovoltaic array in the target photovoltaic power station; The target interference area is determined based on the map information of the target photovoltaic power station; wherein, the target interference area includes non-road areas and areas with abnormal elevation changes; The regions other than the target interference region within the bounding region corresponding to the bounding contour information are defined as the target division region; The target area is divided into multiple dividing lines at equal intervals, and multiple candidate operation points are obtained by taking points at equal intervals on each dividing line.

4. The method according to claim 1, characterized in that, Each target work area is divided into multiple target sub-regions, including: For each target work area, determine the number of target drones in the target work area and the number of target photovoltaic arrays included in the target work area; The target distance between each target photovoltaic array in the target work area is determined based on the photovoltaic array distribution information of the target work area. Based on the number of target drones, the number of target photovoltaic arrays, and the target distance, the target operating area is divided into multiple target sub-regions.

5. The method according to claim 1, characterized in that, Each target work area is divided into multiple target sub-regions, including: For each target work area, the target cost matrix of the target photovoltaic array is determined according to the task type of each target photovoltaic array in the target work area; Based on the drone's flight range and the target cost matrix, the target operating area is divided into multiple target sub-regions.

6. The method according to claim 5, characterized in that, The target cost matrix of the target photovoltaic array is determined based on the task type of each target photovoltaic array in the target operating area, including: If the task type of the target photovoltaic array is a normal inspection task, the distance between the target photovoltaic array and other photovoltaic arrays is determined as a reference distance; wherein, the normal inspection task refers to the photovoltaic inspection task under a centralized photovoltaic power station; The target cost matrix of the target photovoltaic array is determined based on the reference distance.

7. The method according to claim 5, characterized in that, The target cost matrix of the target photovoltaic array is determined based on the task type of each target photovoltaic array in the target operating area, including: If the task type of the target photovoltaic array is a fragmentation task or a distributed task, the operating cost of the target photovoltaic array is determined according to the task type of the target photovoltaic array; wherein, the fragmentation task is used to detect whether there is any fragmentation in the photovoltaic panels of the photovoltaic array, and the distributed task refers to the photovoltaic inspection task under the distributed photovoltaic power station; The distance between the target photovoltaic array and other photovoltaic arrays is determined as a reference distance; The target cost matrix of the target photovoltaic array is determined based on the reference distance and its own operating cost.

8. The method according to claim 1, characterized in that, Determine the target inspection route for the target sub-area based on the target task type, including: If the target task type is a fragmentation task, a first inspection route is generated within the photovoltaic strings of the photovoltaic array based on a preset method, and a second inspection route is generated between the photovoltaic strings based on the traveling salesman algorithm; wherein, the photovoltaic array includes multiple photovoltaic strings, the photovoltaic strings include multiple photovoltaic panels, and the fragmentation task is used to detect whether there is any fragmentation in the photovoltaic panels of the photovoltaic array. The first inspection route and the second inspection route are integrated to obtain the target inspection route for the target sub-area.

9. The method according to claim 1, characterized in that, Determine the target inspection route for the target sub-area based on the target task type, including: If the target task type is a normal inspection task, an inspection route is generated between the photovoltaic strings of the photovoltaic array based on the traveling salesman algorithm as the target inspection route of the target sub-region. The photovoltaic array includes multiple photovoltaic strings, and the ordinary inspection task refers to the photovoltaic inspection task under the centralized photovoltaic power station.

10. The method according to claim 1, characterized in that, Determine the target inspection route for the target sub-area based on the target task type, including: If the target task type is a distributed task, determine the minimum bounding rectangle of each distribution area; wherein, the distributed task refers to the photovoltaic inspection task under a distributed photovoltaic power station; Multiple candidate work lines are generated in the minimum bounding rectangle based on a preset spacing, and the candidate work lines located inside the distribution area are determined as the target work lines. Connect the target work lines to obtain candidate inspection routes for the distribution area, and connect each candidate inspection route to obtain the target inspection route for the target sub-area.

11. A photovoltaic power station inspection device based on unmanned aerial vehicles (UAVs), characterized in that, The device includes: The alternative work site determination module is used to acquire photovoltaic array distribution information of the target photovoltaic power station and determine multiple alternative work sites based on the photovoltaic array distribution information; wherein, the target photovoltaic power station includes multiple photovoltaic arrays; The target operation point determination module is used to determine multiple target operation points from the multiple candidate operation points based on the operation cost of the candidate operation points and the working radius of the UAV; The target sub-region determination module is used to determine multiple target operation regions based on the multiple target operation points and the working radius of the UAV, and to divide each target operation region into multiple target sub-regions; The target inspection route determination module is used to determine the target task type of each photovoltaic array in each target sub-region, and determine the target inspection route of the target sub-region according to the target task type. The photovoltaic array inspection module is used to allocate drones to each target sub-region and, based on the allocation results, schedule drones to inspect the photovoltaic arrays in the target sub-regions according to the target inspection route; The target work point determination module is used for: Multiple target work points are determined from the plurality of candidate work points based on the target mathematical model, which is as follows: ； in, Indicates alternative work sites. , This represents the operating cost of the candidate work points. The task point refers to the center point of each photovoltaic array in the target photovoltaic power station. ,and The value of is determined based on the working radius of the drone. Represents the set of task points. Indicates that it can cover The set of alternative work sites.

12. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the UAV-based photovoltaic power station inspection method according to any one of claims 1-10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the unmanned aerial vehicle-based photovoltaic power station inspection method according to any one of claims 1-10.

14. A computer program product comprising a computer program that, when executed by a processor, implements the UAV-based photovoltaic power station inspection method according to any one of claims 1-10.

Images