Intelligent safety inspection method, device and equipment for unattended photovoltaic station and storage medium

Abstract

The invention discloses an intelligent safety inspection method, device and equipment for an unattended photovoltaic station and a storage medium, and the method comprises the steps: generating a space model of the photovoltaic station according to the three-dimensional scanning data of an unmanned plane group for the photovoltaic station and a two-dimensional station base map of the photovoltaic station, and building a three-dimensional space coordinate system based on the space model; marshalling information of the unmanned aerial vehicle group is determined, the space model of the photovoltaic station is segmented based on the marshalling information, inspection partitions are obtained, and a safety inspection path is determined based on the inspection partitions and the marshalling information; multispectral image information collected based on the safety inspection path is obtained, fault identification is carried out on the multispectral image, and fault features of the multispectral image information are determined; when the fault feature is the target fault feature, determining the position information of the fault feature in the multispectral image information, obtaining the fault positioning information based on the position information and the three-dimensional space coordinate system, and outputting the fault positioning information, thereby improving the inspection efficiency and accuracy, and achieving the safety inspection of the photovoltaic station.

Description

Technical Field

[0001] The present application relates to the technical field of automatic inspection of photovoltaic power stations, and in particular to methods, devices, equipment and storage media for intelligent safety inspection of unmanned photovoltaic stations. Background Art

[0002] With the transformation of the global energy structure and the increasing demand for clean energy, the photovoltaic industry has ushered in an opportunity for rapid development. Photovoltaic stations are one of the components of clean energy. Inspection of photovoltaic stations is a daily work content, while the traditional inspection method of photovoltaic power stations mainly relies on manual labor, which is inefficient, costly, and difficult to cover large areas of power stations. Manual inspection is not only time-consuming and labor-intensive, but also difficult to ensure the accuracy and consistency of the inspection due to human factors. At the same time, for installations in complex terrain or other difficult-to-access locations, manual inspection methods have safety risks. Therefore, traditional manual inspection methods cannot adapt to the safe and efficient inspection of photovoltaic stations.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide an unmanned photovoltaic station intelligent safety inspection method, device, equipment and storage medium, aiming to solve the technical problems of high cost and low efficiency of manual inspection in the prior art.

[0005] To achieve the above objectives, the present application proposes an unmanned photovoltaic station intelligent safety inspection method, the unmanned photovoltaic station intelligent safety inspection method comprising: Generate a spatial model of the photovoltaic station according to the three-dimensional scanning data of the photovoltaic station by the drone group and the two-dimensional station base map of the photovoltaic station, and establish a three-dimensional spatial coordinate system based on the spatial model; Determine the grouping information of the drone group, segment the spatial model of the photovoltaic station based on the grouping information to obtain a plurality of inspection partitions, and determine a safe inspection path based on the inspection partitions and the grouping information; Acquire multispectral image information collected based on the safety inspection path, perform fault identification on the multispectral image, and determine fault features in the multispectral image information; When the fault feature is a target fault feature, position information of the fault feature in the multispectral image information is determined, fault location information is obtained based on the position information and the three-dimensional space coordinate system, and the fault location information is output.

[0006] In one embodiment, the step of generating a spatial model of the photovoltaic power station based on the three-dimensional scan data of the unmanned aerial vehicle (UAV) group and the two-dimensional bottom map of the photovoltaic power station, and establishing a three-dimensional space coordinate system based on the spatial model includes: Match the three-dimensional scan data of the photovoltaic power station by the UAV group with the scan formation information of the UAV group, and add scan marks to the three-dimensional scan data; Match the two-dimensional bottom map of the photovoltaic power station with the three-dimensional scan data corresponding to the scan marks to obtain a matching result, and rewrite the scan marks according to the matching result to obtain model fragment marks; Arrange the model fragment marks in order, and generate a spatial model from the three-dimensional description data corresponding to the model fragment marks and the two-dimensional bottom map of the photovoltaic power station; Establish a three-dimensional space coordinate system based on the spatial model.

[0007] In one embodiment, the step of determining the formation information of the UAV group and dividing the spatial model of the photovoltaic power station based on the formation information to obtain multiple inspection zones includes: Determine the formation information of the UAVs, where the formation information includes grouping information and member identity information; Determine the number of members in each formation according to the grouping information and the member identity information; Determine the inspection division weight based on the number of members in each formation; Divide the spatial model of the photovoltaic power station according to the inspection division weight to obtain multiple inspection zones consistent with the number of formations.

[0008] In one embodiment, the step of determining a safe inspection path based on the inspection zones and the formation information includes: Determine the number of formation members according to the formation information, and divide the formation members into a first detachment formation and a second detachment formation, where the difference in the number of formation members between the first detachment formation and the second detachment formation is no more than one; Divide the inspection zones into an inspection matrix with an even number of rows and columns, and determine a first inspection starting point and a second inspection starting point of the inspection matrix, where the first inspection starting point corresponds to the first detachment formation and the second inspection starting point corresponds to the second detachment formation; Generate a first safe inspection path from the first inspection starting point and a first inspection direction, and generate a second safe inspection path from the second inspection starting point and a second inspection direction. Specifically, the formation members can obtain the position information of other formation members in real time, determine the flight interval according to the position information, and when the flight interval is less than a preset safe interval, determine the ascending / descending height of the formation members according to the safe interval; Combining the plurality of the first safety inspection paths in sequence to obtain a first target safety inspection path; A plurality of the second safety inspection paths are sequentially combined to obtain a second target safety inspection path.

[0009] In one embodiment, the step of acquiring multispectral image information collected based on the safety inspection path, performing fault identification on the multispectral image, and determining fault features in the multispectral image information includes: Obtaining visible light image information and infrared image information collected by the drone group based on the safety inspection path; fusing the visible light image with the infrared image to obtain a multispectral image; Performing feature recognition on the multispectral image to determine physical object features and temperature features in the spectral image; Performing feature fusion on the physical feature and the temperature feature to obtain a fused image of the photovoltaic station; Perform hot spot detection and occlusion detection on the fused image to obtain hot spot detection results and foreign body occlusion results, and determine fault characteristics based on the hot spot detection results and foreign body occlusion detection results.

[0010] In one embodiment, the step of performing hot spot detection and occlusion detection on the fused image to obtain hot spot detection results and foreign body occlusion detection results, and determining fault features according to the hot spot detection results and foreign body occlusion detection results includes: Performing hot spot detection on the fused image to determine a temperature-differentiated area in the fused image, and determining a temperature difference between the temperature-differentiated area and the highest temperature of other temperature areas; When the temperature difference is greater than a preset temperature difference, determining the temperature-differentiated area as a target hot spot area, and generating a hot spot detection result according to the target hot spot area; performing occlusion detection on the fused image in parallel to determine a shadow area in the fused image; When the shadow area has a preset shadow feature, determining that the shadow area is a target shadow area, and generating a foreign body occlusion detection result according to the target shadow area; When any one of the hot spot detection result and the foreign object obstruction detection result is a fault characteristic result, the fault characteristic is determined according to the hot spot detection result and / or the foreign object obstruction detection result.

[0011] In one embodiment, when the fault feature is a target fault feature, determining position information of the fault feature in the multispectral image information, obtaining fault location information based on the position information and the three-dimensional space coordinate system, and outputting the fault location information comprises: When the fault feature is the target fault feature, determine the fault type of the fault feature; When the fault type is a single hot spot fault type or an occlusion fault type, based on the position information of the fault feature in the multi-spectral image information, obtain the target single type fault location information based on the position information and the three-dimensional space coordinate system; When the fault type includes both the hot spot fault type and the occlusion fault type, based on the position information of the fault feature in the multi-spectral image information, obtain the multi-type fault location information based on the position information and the three-dimensional space coordinate system; Perform duplicate removal processing on the multi-type fault location information, and remove duplicate position information in the fault location information corresponding to the hot spot fault type and the occlusion fault type to obtain the target multi-type fault location information; Output the target single type fault location information or the target multi-type fault location information.

[0012] In addition, to achieve the above object, the present application also proposes an unattended photovoltaic power station intelligent safety inspection device, and the unattended photovoltaic power station intelligent safety inspection device includes: A field modeling module, configured to generate a spatial model of the photovoltaic power station according to the three-dimensional scan data of the photovoltaic power station by the unmanned aerial vehicle group and the two-dimensional field base map of the photovoltaic power station, and establish a three-dimensional space coordinate system based on the spatial model; A path planning module, configured to determine the formation information of the unmanned aerial vehicle group, divide the spatial model of the photovoltaic power station based on the formation information to obtain a plurality of inspection zones, and determine a safety inspection path based on the inspection zones and the formation information; A fault identification module, configured to obtain multi-spectral image information collected based on the safety inspection path, perform fault identification on the multi-spectral image, and determine the fault features in the multi-spectral image information; A fault location module, configured to, when the fault feature is the target fault feature, determine the position information of the fault feature in the multi-spectral image information, obtain the fault location information based on the position information and the three-dimensional space coordinate system, and output the fault location information.

[0013] In addition, to achieve the above object, the present application also proposes an unattended photovoltaic power station intelligent safety inspection device, and the device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the unattended photovoltaic power station intelligent safety inspection method as described above.

[0014] In addition, to achieve the above object, the present application also provides a storage medium, which is a computer-readable storage medium. A computer program is stored on the storage medium, and when the computer program is executed by a processor, the steps of the unattended photovoltaic power station intelligent safety inspection method described above are implemented.

[0015] In addition, to achieve the above object, the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the unattended photovoltaic power station intelligent safety inspection method described above are implemented.

[0016] One or more technical solutions proposed by the present application have at least the following technical effects: generating a spatial model of the photovoltaic power station according to the three-dimensional scan data of the photovoltaic power station by the unmanned aerial vehicle (UAV) group and the two-dimensional bottom map of the photovoltaic power station, establishing a three-dimensional space coordinate system based on the spatial model, determining the formation information of the UAV group, dividing the spatial model of the photovoltaic power station based on the formation information to obtain a plurality of inspection zones, determining a safety inspection path based on the inspection zones and the formation information, acquiring multi-spectral image information collected based on the safety inspection path, performing fault identification on the multi-spectral image, determining the fault features in the multi-spectral image information, when the fault features are target fault features, determining the position information of the fault features in the multi-spectral image information, obtaining fault location information based on the position information and the three-dimensional space coordinate system, and outputting the fault location information. It is possible to model the photovoltaic power station through the UAV formation, plan a safety inspection path based on the modeling result, obtain multi-spectral information collected on the safety inspection path for fault identification and location, improve the inspection efficiency and fault identification accuracy of the photovoltaic power station, and thus achieve the safety inspection of the photovoltaic power station. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present application and used together with the specification to explain the principles of the present application.

[0018] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 It is a schematic flowchart provided for the first embodiment of the unattended photovoltaic power station intelligent safety inspection method of the present application; Figure 2Schematic diagram of the safety inspection path of the drone provided by an embodiment of the unattended photovoltaic power station intelligent safety inspection method of the present application; Figure 3 Schematic diagram of multi-spectral image fusion provided by an embodiment of the unattended photovoltaic power station intelligent safety inspection method of the present application; Figure 4 Schematic diagram of the module structure of the unattended photovoltaic power station intelligent safety inspection device according to an embodiment of the present application; Figure 5 Schematic diagram of the device structure of the hardware operating environment involved in the unattended photovoltaic power station intelligent safety inspection method according to an embodiment of the present application.

[0020] The realization of the purpose, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. Detailed implementation manners

[0021] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0022] In order to better understand the technical solutions of the present application, the following will be described in detail in combination with the specification drawings and specific implementation manners.

[0023] The main solution of the embodiment of the present application is: generating a spatial model of the photovoltaic power station according to the three-dimensional scan data of the photovoltaic power station by the drone group and the two-dimensional bottom map of the photovoltaic power station, and establishing a three-dimensional space coordinate system based on the spatial model; determining the grouping information of the drone group, dividing the spatial model of the photovoltaic power station based on the grouping information to obtain a plurality of inspection areas, and determining a safety inspection path based on the inspection areas and the grouping information; acquiring multi-spectral image information collected based on the safety inspection path, performing fault identification on the multi-spectral image to determine the fault characteristics in the multi-spectral image information; when the fault characteristics are target fault characteristics, determining the position information of the fault characteristics in the multi-spectral image information, obtaining fault location information based on the position information and the three-dimensional space coordinate system, and outputting the fault location information.

[0024] In this embodiment, for the convenience of description, the following will be described with the unattended photovoltaic power station intelligent safety inspection device as the execution subject.

[0025] Since the current photovoltaic power station inspection method mainly relies on manual labor, this method is inefficient, costly, and difficult to cover large areas of the power station. Manual inspection not only consumes time and effort, but also due to human factors, the accuracy and consistency of inspection are difficult to guarantee. At the same time, for installations in complex terrains or other inaccessible locations, there are safety risks in the manual inspection method. Therefore, the traditional manual inspection method cannot adapt to the safe and efficient inspection of photovoltaic power stations.

[0026] This application provides a solution that can replace manual inspection with a drone group, can perform three-dimensional modeling on a photovoltaic power station, determine the layout structure of the photovoltaic power station, group the drones based on the layout structure of the photovoltaic power station, enable the drones to simultaneously inspect the photovoltaic power station from multiple angles, plan a suitable safe inspection path, quickly and accurately obtain multi-spectral acquisition images of the unmanned photovoltaic power station, identify faults in the multi-spectral acquisition images, and determine the type and location of the faults in a way that combines visible light and infrared light images. Compared with manual inspection, it can not only improve the inspection efficiency, but also discover potential faults and accurately obtain the fault location to achieve precise positioning.

[0027] As can be seen from the above embodiments, this application generates the spatial model of the photovoltaic power station based on the three-dimensional scan data of the drone group for the photovoltaic power station and the two-dimensional power station base map of the photovoltaic power station, establishes a three-dimensional space coordinate system based on the spatial model, determines the grouping information of the drone group, divides the spatial model of the photovoltaic power station based on the grouping information to obtain multiple inspection zones, determines a safe inspection path based on the inspection zones and the grouping information, obtains multi-spectral image information collected based on the safe inspection path, identifies faults in the multi-spectral images, determines the fault characteristics in the multi-spectral image information, when the fault characteristics are target fault characteristics, determines the position information of the fault characteristics in the multi-spectral image information, obtains fault location information based on the position information and the three-dimensional space coordinate system, and outputs the fault location information. It can model the photovoltaic power station through drone grouping, plan a safe inspection path based on the modeling result, obtain multi-spectral information collected on the safe inspection path for fault identification and location, improve the inspection efficiency and fault identification accuracy of the photovoltaic power station, and thus achieve the safe inspection of the photovoltaic power station.

[0028] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device, an intelligent safety inspection device for unmanned photovoltaic power stations, etc. that can implement the above functions. Hereinafter, the intelligent safety inspection device for unmanned photovoltaic power stations will be taken as an example to illustrate this embodiment and the following embodiments.

[0029] Based on this, an intelligent safety inspection method for unmanned photovoltaic power stations is provided in an embodiment of the present application. Refer to Figure 1 , Figure 1 which is a schematic flow chart of the first embodiment of the intelligent safety inspection method for the unmanned photovoltaic power station of the present application.

[0030] In this embodiment, the intelligent safety inspection method for the unmanned photovoltaic power station includes steps S10 to S40: Step S10, generate a spatial model of the photovoltaic power station according to the three-dimensional scanning data of the photovoltaic power station by the unmanned aerial vehicle group and the two-dimensional site base map of the photovoltaic power station, and establish a three-dimensional space coordinate system based on the spatial model.

[0031] It should be noted that the unmanned aerial vehicle group generally refers to a set composed of multiple unmanned aerial vehicles. In this embodiment, it can be used for the inspection work of the photovoltaic power station. And because multiple unmanned aerial vehicles work together, the data collected has redundancy, which can ensure the accuracy of the data. The photovoltaic power station refers to a power generation facility that directly converts solar energy into electrical energy using solar cell modules.

[0032] It should be understood that the three-dimensional scanning data is a set of data obtained by a three-dimensional scanning device (such as a lidar LiDAR or a photogrammetry system) carried by an unmanned aerial vehicle. These data can describe the three-dimensional shape and structure of the photovoltaic power station in detail. They usually include a large amount of point cloud data, and each point contains its X, Y, and Z coordinates in space. These data can accurately reflect the physical characteristics and spatial layout of the photovoltaic power station. The two-dimensional site base map refers to the projection map of the photovoltaic power station on the horizontal plane, usually a plan obtained by means of surveying or satellite images. This map contains the plane layout information of the photovoltaic power station, such as the position relationship of component arrangements, roads, buildings, etc. The three-dimensional space coordinate system is established based on the spatial model of the photovoltaic power station, which can accurately describe each point in the spatial model and is established with three mutually perpendicular X-axis, Y-axis, and Z-axis, and each axis represents a dimension in space.

[0033] In a specific implementation, an unmanned aerial vehicle (UAV) group is deployed in a photovoltaic power station for safety inspection of the photovoltaic power station. First, the UAV group can perform three-dimensional scanning on the photovoltaic power station to obtain structural information of the photovoltaic power station, including contour information of the photovoltaic power station, orientation information of the photovoltaic panels, etc. The UAV group can freely perform omnidirectional scanning on the photovoltaic panels of the photovoltaic power station to obtain scanning information of the photovoltaic power station. Each UAV can obtain certain acquisition data, and the flight trajectories of the UAVs are also stored. Therefore, the data of each UAV can be aggregated and fused, and the data of multiple UAVs can be stitched together to form complete scanning information of the photovoltaic power station. At the same time, a two-dimensional base map of the photovoltaic power station is obtained, and the complete scanning information of the photovoltaic power station and the two-dimensional base map of the photovoltaic power station are used to generate the spatial model of the photovoltaic power station, and a three-dimensional space coordinate system is constructed with a preset point in the spatial model as the origin of the three-dimensional coordinate system.

[0034] In a feasible implementation manner, the step of generating the spatial model of the photovoltaic power station according to the three-dimensional scanning data of the UAV group for the photovoltaic power station and the two-dimensional base map of the photovoltaic power station, and establishing a three-dimensional space coordinate system based on the spatial model includes: Match the three-dimensional scanning data of the UAV group for the photovoltaic power station with the scanning formation information of the UAV group, and add scanning marks to the three-dimensional scanning data; Match the two-dimensional base map of the photovoltaic power station with the three-dimensional scanning data corresponding to the scanning marks to obtain a matching result, and rewrite the scanning marks according to the matching result to obtain model fragment marks; Arrange the model fragment marks in order, and generate a spatial model from the three-dimensional description data corresponding to the model fragment marks and the two-dimensional base map of the power station; Establish a three-dimensional space coordinate system based on the spatial model.

[0035] It should be noted that the scanning marks are used to identify the correspondence between the three-dimensional scanning data and the UAVs. Each UAV can mark the collected three-dimensional scanning data to facilitate matching with the two-dimensional base map of the power station.

[0036] In a specific implementation, for the convenience of managing the UAV group, the UAVs in the UAV group can be grouped and managed. In this embodiment, the UAV group is divided into two teams, and the UAV with the best performance in each of the two UAV formations is selected as the UAV leader. In the same formation, other UAVs can transmit data to and from the leader UAV, and the leader UAV can collect and process the acquisition information of other UAVs in the same formation. Therefore, in order to manage the UAV formation, all UAVs can be numbered. For example, the numbers of the first UAV formation can be A00~An, and the numbers of the second UAV formation can be B00~Bm, where A and B are used to distinguish the formation groups, 00 represents the leader UAV, and m and n are the numbers of UAVs in the UAV formation. When the UAV formation performs the three-dimensional scanning task of modeling the photovoltaic power station, the three-dimensional scanning data of the photovoltaic power station by the UAV group can be matched with the scanning formation information of the UAV group, and scanning marks are added to the three-dimensional scanning data. Then, the two-dimensional site base map of the photovoltaic power station is matched with the three-dimensional scanning data corresponding to the scanning marks to obtain a matching result, and the scanning marks are rewritten according to the matching result to obtain model fragment marks. Then, the model fragment marks can be arranged in the order shown in the two-dimensional site base map, and the three-dimensional description data corresponding to the corresponding model fragment marks and the two-dimensional site base map are used to generate a spatial model, and a three-dimensional space coordinate system is established on the basis of the spatial model to describe each point in the spatial model.

[0037] Step S20, determine the grouping information of the UAV group, divide the spatial model of the photovoltaic power station based on the grouping information to obtain a plurality of inspection sub-areas, and determine a safe inspection path based on the inspection sub-areas and the grouping information.

[0038] It should be noted that the grouping information refers to the organization and allocation information of the UAVs when performing tasks. This includes the number of UAVs and their respective task roles. The inspection sub-areas refer to dividing the spatial model of the photovoltaic power station into multiple areas, and each area is used as an independent inspection unit. This kind of partitioning is usually based on the geographical layout, equipment distribution, risk level or other relevant factors of the photovoltaic power station. The safe inspection path refers to the specific flight route followed by the UAV when performing the inspection task. This path is determined based on the inspection sub-areas and the grouping information, aiming to ensure that the UAV can efficiently and comprehensively cover all inspection areas.

[0039] In the specific implementation, the drone group's grouping information is parsed to determine the current drone group's formation status and the composition of each formation. After understanding the composition of the drone group, the spatial model of the photovoltaic station is divided according to the drone grouping status to obtain multiple inspection zones, where each inspection zone is directly related to the number of drones. After the drone inspection zones are divided, the number of drone formations or the number of drones included in the inspection zone can be determined, and the safe inspection path is determined by combining the number of drones and the size of the inspection zone.

[0040] In a feasible implementation manner, the step of determining the grouping information of the drone group, and segmenting the spatial model of the photovoltaic station based on the grouping information to obtain a plurality of inspection partitions includes: Determine the grouping information of the drone, wherein the grouping information includes grouping information and group member identity information; Determine the number of members in each group according to the grouping information and the member identity information; Determining inspection division weights based on the number of members of each group; The spatial model of the photovoltaic station is segmented according to the inspection division weights to obtain a plurality of inspection partitions that are consistent with the number of the groups.

[0041] It should be noted that the inspection division weight refers to the ratio of the drone member information in the drone formation to the total number of drones corresponding to all drone groups when dividing the inspection zones, which reflects the formation's ability to undertake tasks.

[0042] In a specific implementation, the grouping information of the drones is determined, where the grouping information includes grouping information and member identity information. The grouping information is the formation number of the current drone grouping, and the member identity information is the information of the drones that make up the drone formation. That is, multiple drone sets are obtained from the drones, where different drone sets include several drone members, and each drone can only exist in one drone group. In the drone grouping information, it can be stored in the format of <grouping, group number, drone identity information>, for example<C,02,3DH87MKA98W1> Therefore, the number of members in each group can be determined based on the grouping information and the identity information of the members, and the inspection division weight can be obtained based on the proportion of each group to the total number of drones. The weight division formula is:

[0043] in, Assign weights to inspections. For the The number of drones in a group, is the total number of drones in the drone group, is the total number of groups.

[0044] When dividing the photovoltaic power station space model according to the inspection weight, it is possible to divide the area according to the weight of each UAV group, which is expressed as: , where is the total area of the space model, is the th inspection sub-area of the UAV group. The grouping information of the UAVs is consistent with the number of inspection sub-areas. Therefore, it can be determined that when the number of UAVs in the UAV group changes, the inspection area can be dynamically changed. It should be noted that when dividing the inspection area, the integrity of the inspection area can be ensured as much as possible. Therefore, the UAV group with a larger weight can be preferentially allocated.

[0045] In a feasible implementation manner, the step of determining the safe inspection path based on the inspection sub-area and the grouping information includes: Determine the number of group members according to the grouping information, and divide the group members into a first detachment group and a second detachment group. The difference in the number of group members between the first detachment group and the second detachment group is not greater than one; Divide the inspection sub-area into an inspection matrix with even rows and columns, and determine the first inspection starting point and the second inspection starting point of the inspection matrix. The first inspection starting point corresponds to the first detachment group, and the second inspection starting point corresponds to the second detachment group; Generate a first safe inspection path with the first inspection starting point and the first inspection direction, and generate a second safe inspection path with the second inspection starting point and the second inspection direction. Specifically, the group members can obtain the position information of other group members in real time, determine the flight interval according to the position information, and when the flight interval is less than the preset safe interval, determine the height at which the group members rise / fall according to the safe interval; Sequentially combine multiple first safe inspection paths to obtain a first target safe inspection path; Sequentially combine multiple second safe inspection paths to obtain a second target safe inspection path.

[0046] It should be noted that the first detachment formation and the second detachment formation are refined groupings within the same formation. That is, the UAVs in the original formation are divided into multiple detachment formations according to certain rules. When allocating, the average principle can be followed to make the number of UAVs in the first detachment formation and the second detachment formation the same or differ by 1. For example, when the number of UAV formations is 9, the numbers in the first detachment formation and the second detachment formation are 4 and 5 respectively. If the number of UAV formations is 10, the numbers in both the first detachment formation and the second detachment formation are 5. At the same time, the safety inspection path of the first detachment formation is the first safety inspection path, and the safety inspection path of the second detachment formation is the second safety inspection path. The first safety inspection path and the second safety inspection path are different safety inspection paths.

[0047] In the specific implementation, first, determine the number of formation members according to the formation information, divide the formation members into the first detachment formation and the second detachment formation, and at the same time divide the inspection area into an inspection matrix with even rows and columns. Determine the first inspection starting point and the second inspection starting point of the inspection matrix. The first inspection starting point corresponds to the first detachment formation, and the second inspection starting point corresponds to the second detachment formation. Generate the first safety inspection path with the first inspection starting point and the first inspection direction, and generate the second safety inspection path with the second inspection starting point and the second inspection direction. Refer to Figure 2 , Figure 2 is a schematic diagram of the UAV safety inspection path. In the figure, the UAV inspection area is divided into inspection matrix. The red area and the blue area are the first inspection starting point and the second inspection starting point respectively, and the green area is the inspection end point of the first safety inspection path and the second safety inspection path. Since each detachment formation includes multiple UAVs, the safety inspection paths of each UAV in each detachment formation are sequentially combined to obtain the target safety inspection path. Therefore, multiple first safety inspection paths can be sequentially combined to obtain the first target safety inspection path; multiple second safety inspection paths can be sequentially combined to obtain the second target safety inspection path.

[0048] When determining the safety inspection path, the formation members in the UAV formation can obtain the flight positions of other UAV formation members around them in real time. Since the UAV will disturb the local air flow during flight, if the UAV is in the disturbed air flow, it will get out of control, threatening the photovoltaic panels below. Therefore, when determining the safety inspection path, the flight altitude of the UAV can be adjusted in real time according to the distance from other UAVs. That is to say, when the distance between the UAV and other UAVs is less than the set safety interval, the flight altitude of the UAV can be changed to ensure the distance between UAVs, and choose to increase or decrease the flight altitude to ensure the flight safety of the UAV.

[0049] Step S30: Obtain the multi-spectral image information collected based on the safe inspection path, perform fault identification on the multi-spectral image, and determine the fault features in the multi-spectral image information.

[0050] It should be noted that the multi-spectral image information refers to visible spectral images and infrared spectral images. The visible spectral images and infrared spectral images can form a multi-spectral image, enabling an image to include both visible light information and infrared information simultaneously, and being able to reflect the texture details and thermal information of the photovoltaic panel at the same time. The fault features include externally induced faults and internally native faults. Externally induced faults are faults caused by external occlusion resulting in uneven heating of the photovoltaic panel, and internally native faults refer to abnormal heating faults of electronic components inside the photovoltaic panel due to short circuits or overloads.

[0051] In a specific implementation, the unmanned aerial vehicle (UAV) can carry visible light image acquisition equipment and infrared image acquisition equipment according to mission requirements. To improve the performance of the UAV, a single UAV includes one of the visible light image acquisition equipment and the infrared image acquisition equipment. In a team formation, the difference in equipment between the visible light image acquisition equipment and the infrared image acquisition equipment is not greater than 1. After obtaining the visible spectral images and infrared spectral images collected by the visible light image acquisition equipment and the infrared image acquisition equipment, fault identification can be performed on the visible spectral images and infrared spectral images to determine the fault types in the photovoltaic power station and the corresponding fault features.

[0052] In a feasible implementation manner, the step of obtaining the multi-spectral image information collected based on the safe inspection path, performing fault identification on the multi-spectral image, and determining the fault features in the multi-spectral image information includes: Obtain the visible light image information and infrared image information collected by the UAV group based on the safe inspection path; Fuse the visible light image and the infrared image to obtain a multi-spectral image; Perform feature identification on the multi-spectral image to determine the physical features and temperature features in the spectral image; Fuse the physical features and the temperature features to obtain the fused image of the photovoltaic power station; Perform hot spot detection and occlusion detection on the fused image to obtain the hot spot detection result and the foreign object occlusion result, and determine the fault features according to the hot spot detection result and the foreign object occlusion detection result.

[0053] In a specific implementation, the UAV flies along a preset safe inspection path, collects the visible light image and the infrared image of the photovoltaic power station, fuses the collected visible light image and infrared image to obtain a multi-spectral image, referring to Figure 3 , Figure 3It is a schematic diagram of multi - spectral image fusion. When performing fusion, it can be based on , where is the fused multi - spectral image, is the visible - light image, is the infrared image, is the fusion weight, which is used to balance the contributions of the visible - light and infrared images. Feature recognition is performed on the fused multi - spectral image to determine the physical features and temperature features in the image. The physical image and infrared image of the photovoltaic panel are feature - fused to obtain the temperature - distribution feature image of the photovoltaic panel, and hot - spot detection and occlusion detection are performed on the fused image to obtain the hot - spot detection result and foreign - object occlusion result, and the fault feature is determined according to the hot - spot detection result and foreign - object occlusion detection result. When performing foreign - object occlusion detection, it can detect the gray - scale value in the image. This process can judge the gray - scale values of adjacent regions and determine the region with a higher gray - scale value as the occluded region. While hot - spot detection is based on the temperature - curve graph formed by the infrared image, and the region with temperature mutation is determined as the hot - spot region.

[0054] In a feasible implementation manner, the step of performing hot - spot detection and occlusion detection on the fused image, obtaining the hot - spot detection result and foreign - object occlusion detection result, and determining the fault feature according to the hot - spot detection result and foreign - object occlusion detection result includes: Performing hot - spot detection on the fused image to determine the temperature - dissimilarity region in the fused image, and determining the temperature difference between the highest temperature of the temperature - dissimilarity region and other temperature regions; When the temperature difference is greater than the preset temperature difference, determining the temperature - dissimilarity region as the target hot - spot region, and generating the hot - spot detection result according to the target hot - spot region; Performing occlusion detection on the fused image in parallel to determine the shadow region in the fused image; When the shadow region has the preset shadow feature, determining the shadow region as the target shadow region, and generating the foreign - object occlusion detection result according to the target shadow region; When any one of the hot - spot detection result and the foreign - object occlusion detection result is the fault - feature result, determining the fault feature according to the hot - spot detection result and / or the foreign - object occlusion detection result.

[0055] In a specific implementation, through infrared - image analysis, we can determine the temperature - dissimilarity region in the fused image. According to the formula: , where is the set of temperature - dissimilarity regions, is the temperature value of point , is the preset temperature threshold. Determine the temperature difference between the highest temperature in the temperature alienation region and that in other temperature regions. When the temperature difference is greater than the preset temperature difference, determine the temperature alienation region as the target hot spot region, and generate a hot spot detection result based on the target hot spot region. The temperature difference is the maximum temperature difference, that is, the difference between the highest temperature in the alienation region and the lowest temperature in the remaining regions, expressed as: , where is the maximum temperature difference, is the highest temperature in the temperature alienation region, is the lowest temperature in other regions. When determining the hot spot region, the formula:

[0056] is the set of target hot spot regions, is the preset temperature threshold.

[0057] Similarly, when determining the occlusion region, according to the formula:

[0058] , where is the target shadow region, is the preset shadow region threshold.

[0059] When any one of the hot spot detection result and the foreign object occlusion detection result is a fault feature result, determine the fault feature according to the hot spot detection result and / or the foreign object occlusion detection result.

[0060] Step S40, when the fault feature is the target fault feature, determine the position information of the fault feature in the multi-spectral image information, obtain the fault location information based on the position information and the three-dimensional space coordinate system, and output the fault location information.

[0061] It should be noted that the target fault feature refers to the fault feature of local hot spots or shadow occlusions on the photovoltaic panel. The position information is the positioning coordinates of the corresponding position, and the fault location information refers to the comprehensive information of the type and position information of the output fault.

[0062] In specific implementation, when the fault feature is the target fault feature, determine the fault type of the fault feature; when the fault type is a single hot spot fault type or occlusion fault type, based on the position information of the fault feature in the multi-spectral image information and with reference to the position information and the three-dimensional space coordinate system, obtain the target single-type fault location information; when the fault type includes both the hot spot fault type and the occlusion fault type, based on the position information of the fault feature in the multi-spectral image information and with reference to the position information and the three-dimensional space coordinate system, obtain the multi-type fault location information; perform a duplicate removal process on the multi-type fault location information, remove the overlapping position information in the fault location information corresponding to the hot spot fault type and the occlusion fault type, and obtain the target multi-type fault location information; output the target single-type fault location information or the target multi-type fault location information.

[0063] When the fault feature is the target fault feature, the fault type of the fault feature can be determined. After determining the fault feature, the position information in the multi-spectral image information can be obtained, and combined with the three-dimensional space coordinate system to obtain the location information in the three-dimensional model. Since when a fault occurs, there may be an occlusion feature and a hot spot feature at the same position, when it is determined that there are both an occlusion area and a hot spot feature at the same position, the two types of fault features can be combined and classified as multi-type fault location information, and the positions corresponding to the corresponding occlusion feature and hot spot feature are calibrated to obtain the multi-type fault location information. If it is only a single fault type, the fault type and position information can be combined to obtain the single-type fault location information. Finally, the obtained single-type fault location information and multi-type fault location information are output to provide guidance for the maintenance of the photovoltaic power station.

[0064] This embodiment provides an intelligent security inspection method for an unattended photovoltaic power station. By generating the spatial model of the photovoltaic power station according to the three-dimensional scanning data of the photovoltaic power station by the unmanned aerial vehicle (UAV) group and the two-dimensional bottom map of the photovoltaic power station, establishing a three-dimensional space coordinate system based on the spatial model, determining the grouping information of the UAV group, dividing the spatial model of the photovoltaic power station based on the grouping information to obtain multiple inspection zones, determining the safe inspection path based on the inspection zones and the grouping information, acquiring the multi-spectral image information collected based on the safe inspection path, performing fault identification on the multi-spectral image, determining the fault feature in the multi-spectral image information, when the fault feature is the target fault feature, determining the position information of the fault feature in the multi-spectral image information, obtaining the fault location information based on the position information and the three-dimensional space coordinate system, and outputting the fault location information, it is possible to model the photovoltaic power station through the UAV group, plan the safe inspection path based on the modeling result, acquire the multi-spectral information collected on the safe inspection path for fault identification and location, and improve the inspection efficiency and fault identification accuracy of the photovoltaic power station.

[0065] It should be noted that the above examples are only for understanding the present application and do not constitute a limitation on the unattended photovoltaic power station intelligent safety inspection method of the present application. Based on this technical concept, more forms of simple transformation are within the protection scope of the present application.

[0066] The present application also provides an unattended photovoltaic power station intelligent safety inspection device. Please refer to Figure 4 The unattended photovoltaic power station intelligent safety inspection device includes: A site modeling module 10, configured to generate a spatial model of the photovoltaic power station according to the three-dimensional scan data of the photovoltaic power station by the unmanned aerial vehicle (UAV) group and the two-dimensional site base map of the photovoltaic power station, and establish a three-dimensional space coordinate system based on the spatial model; A path planning module 20, configured to determine the formation information of the UAV group, divide the spatial model of the photovoltaic power station based on the formation information to obtain a plurality of inspection zones, and determine a safety inspection path based on the inspection zones and the formation information; A fault identification module 30, configured to obtain multi-spectral image information collected based on the safety inspection path, perform fault identification on the multi-spectral image, and determine fault features in the multi-spectral image information; A fault location module 40, configured to, when the fault feature is a target fault feature, determine the position information of the fault feature in the multi-spectral image information, obtain fault location information based on the position information and the three-dimensional space coordinate system, and output the fault location information.

[0067] In one embodiment, the site modeling module 10 is further configured to match the three-dimensional scan data of the photovoltaic power station by the UAV group with the scan formation information of the UAV group, and add scan marks to the three-dimensional scan data; match the two-dimensional site base map of the photovoltaic power station with the three-dimensional scan data corresponding to the scan marks to obtain a matching result, and rewrite the scan marks according to the matching result to obtain model fragment marks; arrange the model fragment marks in sequence, generate a spatial model from the three-dimensional description data corresponding to the model fragment marks and the two-dimensional site base map; and establish a three-dimensional space coordinate system based on the spatial model.

[0068] In one embodiment, the path planning module 20 is further configured to determine the formation information of the UAVs, where the formation information includes grouping information and crew member identity information; determine the number of crew members in each formation according to the grouping information and the crew member identity information; determine an inspection division weight based on the number of crew members in each formation; and divide the spatial model of the photovoltaic power station according to the inspection division weight to obtain a plurality of inspection zones consistent with the number of formations.

[0069] In one embodiment, the path planning module 20 is also used to determine the number of grouping members according to the grouping information, and divide the grouping members into a first squad grouping and a second squad grouping, the difference in the number of grouping members between the first squad grouping and the second squad grouping is not greater than one; divide the inspection partition into an inspection matrix of even rows and columns, determine the first inspection starting point and the second inspection starting point of the inspection matrix, the first inspection starting point corresponds to the first squad grouping, and the second inspection starting point corresponds to the second squad grouping; generate a first safety inspection path with the first inspection starting point and the first inspection direction, and generate a second safety inspection path with the second inspection starting point and the second inspection direction; sequentially combine multiple first safety inspection paths to obtain a first target safety inspection path; sequentially combine multiple second safety inspection paths to obtain a second target safety inspection path.

[0070] In one embodiment, the fault identification module 30 is further used to obtain visible light image information and infrared image information collected by the drone group based on the safety inspection path; fuse the visible light image with the infrared image to obtain a multispectral image; perform feature recognition on the multispectral image to determine the physical features and temperature features in the spectral image; perform feature fusion on the physical features and the temperature features to obtain a fused image of the photovoltaic station; perform hot spot detection and occlusion detection on the fused image to obtain hot spot detection results and foreign object occlusion results, and determine fault features based on the hot spot detection results and foreign object occlusion detection results.

[0071] In one embodiment, the fault identification module 30 is also used to perform hot spot detection on the fused image, determine the temperature differentiation area in the fused image, and determine the temperature difference between the temperature differentiation area and the highest temperature of other temperature areas; when the temperature difference is greater than a preset temperature difference, determine the temperature differentiation area as a target hot spot area, and generate a hot spot detection result based on the target hot spot area; perform occlusion detection on the fused image in parallel to determine the shadow area in the fused image; when the shadow area is a preset shadow feature, determine the shadow area as a target shadow area, and generate a foreign body occlusion detection result based on the target shadow area; when any one of the hot spot detection result and the foreign body occlusion detection result is a fault feature result, determine the fault feature based on the hot spot detection result and / or the foreign body occlusion detection result.

[0072] In one embodiment, the fault location module 40 is further configured to determine the fault type of the fault feature when the fault feature is a target fault feature; when the fault type is a single hot spot fault type or an occlusion fault type, based on the position information of the fault feature in the multi-spectral image information and the position information and the three-dimensional space coordinate system, obtain target single-type fault location information; when the fault type includes both the hot spot fault type and the occlusion fault type, based on the position information of the fault feature in the multi-spectral image information and the position information and the three-dimensional space coordinate system, obtain multi-type fault location information; perform duplicate removal processing on the multi-type fault location information, remove duplicate position information in the fault location information corresponding to the hot spot fault type and the occlusion fault type, and obtain target multi-type fault location information; output the target single-type fault location information or the target multi-type fault location information.

[0073] The unattended photovoltaic power station intelligent safety inspection device provided by the present application adopts the unattended photovoltaic power station intelligent safety inspection method in the above embodiment, and can solve the technical problems of high cost and low efficiency in manual inspection in the prior art. Compared with the prior art, the beneficial effects of the unattended photovoltaic power station intelligent safety inspection device provided by the present application are the same as those of the unattended photovoltaic power station intelligent safety inspection method provided by the above embodiment, and other technical features in the unattended photovoltaic power station intelligent safety inspection device are the same as the features disclosed in the above embodiment method, and will not be described in detail here.

[0074] The present application provides an unattended photovoltaic power station intelligent safety inspection device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the unattended photovoltaic power station intelligent safety inspection method in the first embodiment above.

[0075] Next, refer to Figure 5, which shows a schematic structural diagram of an unattended intelligent safety inspection device for a photovoltaic power station suitable for implementing the embodiments of the present application. The unattended intelligent safety inspection device in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The shown unattended intelligent safety inspection device for a photovoltaic power station is merely an example and should not impose any limitations on the functions and scope of use of the embodiments of the present application.

[0076] As Figure 5 shown, the unattended intelligent safety inspection device for a photovoltaic power station may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 into the random access memory (RAM: Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the unattended intelligent safety inspection device are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, magnetic tapes, hard disks, etc.; and a communication device 1009. The communication device 1009 can allow the unattended intelligent safety inspection device for a photovoltaic power station to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows an unattended intelligent safety inspection device with various systems, it should be understood that it is not required to implement or have all the shown systems. More or fewer systems may be alternatively implemented or had.

[0077] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product that includes a computer program carried on a computer-readable medium, and the computer program contains program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by a processing device 1001, the above functions defined in the methods of the embodiments disclosed in the present application are executed.

[0078] The unattended intelligent safety inspection device for a photovoltaic power station provided by the present application adopts the unattended intelligent safety inspection method in the above embodiments, and can solve the technical problems of high cost and low efficiency existing in manual inspection in the prior art. Compared with the prior art, the beneficial effects of the unattended intelligent safety inspection device for a photovoltaic power station provided by the present application are the same as those of the unattended intelligent safety inspection method provided by the above embodiments, and other technical features in the unattended intelligent safety inspection device are the same as the features disclosed in the method of the previous embodiment, which will not be elaborated here.

[0079] It should be understood that each part disclosed in the present application can be implemented by hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0080] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all of them should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claimed rights.

[0081] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the unattended intelligent safety inspection method in the above embodiments.

[0082] The computer-readable storage medium provided by this application can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with 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 of the above. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. The program code contained on the computer-readable storage medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0083] The above computer-readable storage medium can be included in the unattended photovoltaic power station intelligent safety inspection device; or it can exist independently without being assembled into the unattended photovoltaic power station intelligent safety inspection device.

[0084] The above computer-readable storage medium carries one or more programs. When the one or more programs are executed by the unattended photovoltaic power station intelligent safety inspection device, the unattended photovoltaic power station intelligent safety inspection device is caused to: Generate a spatial model of the photovoltaic power station based on the three-dimensional scan data of the photovoltaic power station by the unmanned aerial vehicle (UAV) group and the two-dimensional base map of the photovoltaic power station, and establish a three-dimensional space coordinate system based on the spatial model; Determine the grouping information of the UAV group, divide the spatial model of the photovoltaic power station based on the grouping information to obtain multiple inspection zones, and determine a safe inspection path based on the inspection zones and the grouping information; Obtain multi-spectral image information collected based on the safe inspection path, perform fault identification on the multi-spectral image, and determine the fault features in the multi-spectral image information; When the fault feature is a target fault feature, determine the position information of the fault feature in the multi-spectral image information, obtain fault location information based on the position information and the three-dimensional space coordinate system, and output the fault location information.

[0085] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The above-mentioned programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN: Local Area Network) or a wide area network (WAN: Wide Area Network), or it can be connected to an external computer (for example, by connecting through an Internet service provider via the Internet).

[0086] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0087] The modules involved in the embodiments of this application can be implemented in software or in hardware. Among them, the name of the module does not constitute a limitation on the unit itself in some cases.

[0088] The readable storage medium provided by this application is a computer-readable storage medium. The computer-readable storage medium stores computer-readable program instructions (i.e., computer programs) for performing the above-mentioned unattended intelligent safety inspection method for photovoltaic power stations, and can solve the technical problems of high cost and low efficiency in manual inspection in the prior art. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by this application are the same as those of the unattended intelligent safety inspection method for photovoltaic power stations provided in the above embodiments, and will not be elaborated here.

[0089] The present application also provides a computer program product, including a computer program which, when executed by a processor, implements the steps of the unattended intelligent safety inspection method for a photovoltaic power station as described above.

[0090] The computer program product provided by the present application can solve the technical problems of high cost and low efficiency existing in manual inspection in the prior art. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the unattended intelligent safety inspection method for a photovoltaic power station provided in the above embodiments, and will not be elaborated herein.

[0091] The above are only partial embodiments of the present application, and thus do not limit the patent scope of the present application. Any equivalent structural transformation made by using the content of the specification and drawings of the present application under the technical concept of the present application, or any direct / indirect application in other related technical fields, is included in the patent protection scope of the present application.

Claims

1. An intelligent safety inspection method for unattended photovoltaic power stations, characterized in that, The intelligent safety inspection method for unattended photovoltaic power stations includes: Generating a spatial model of the photovoltaic power station based on the three-dimensional scanning data of the photovoltaic power station by the unmanned aerial vehicle (UAV) group and the two-dimensional power station base map of the photovoltaic power station, and establishing a three-dimensional space coordinate system based on the spatial model; Determining the formation information of the UAV group, dividing the spatial model of the photovoltaic power station based on the formation information to obtain multiple inspection zones, and determining a safety inspection path based on the inspection zones and the formation information; Obtaining multi-spectral image information collected based on the safety inspection path, performing fault identification on the multi-spectral image, and determining fault features in the multi-spectral image information; When the fault feature is a target fault feature, determining the position information of the fault feature in the multi-spectral image information, obtaining fault location information based on the position information and the three-dimensional space coordinate system, and outputting the fault location information.

2. The method according to claim 1, characterized in that, The step of generating a spatial model of the photovoltaic power station based on the three-dimensional scanning data of the photovoltaic power station by the UAV group and the two-dimensional power station base map of the photovoltaic power station, and establishing a three-dimensional space coordinate system based on the spatial model includes: Matching the three-dimensional scanning data of the photovoltaic power station by the UAV group with the scanning formation information of the UAV group, and adding scanning marks to the three-dimensional scanning data; Matching the two-dimensional power station base map of the photovoltaic power station with the three-dimensional scanning data corresponding to the scanning marks to obtain a matching result, and rewriting the scanning marks according to the matching result to obtain model fragment marks; Arranging the model fragment marks in order, and generating a spatial model from the three-dimensional description data corresponding to the model fragment marks and the two-dimensional power station base map; Establishing a three-dimensional space coordinate system based on the spatial model.

3. The method according to claim 1, characterized in that The step of determining the formation information of the UAV group, dividing the spatial model of the photovoltaic power station based on the formation information to obtain multiple inspection zones includes: Determining the formation information of the UAVs, where the formation information includes grouping information and member identity information; Determining the number of members in each formation according to the grouping information and the member identity information; Determining an inspection division weight based on the number of members in each formation; Dividing the spatial model of the photovoltaic power station according to the inspection division weight to obtain multiple inspection zones equal in number to the number of formations.

4. The method according to claim 1, characterized in that, The step of determining a safety inspection path based on the inspection zones and the formation information includes: Determining the number of formation members according to the formation information, and dividing the formation members into a first detachment formation and a second detachment formation, where the difference in the number of formation members between the first detachment formation and the second detachment formation is not greater than one; Dividing the inspection zones into an inspection matrix with an even number of rows and columns, determining a first inspection starting point and a second inspection starting point of the inspection matrix, where the first inspection starting point corresponds to the first detachment formation and the second inspection starting point corresponds to the second detachment formation; The first inspection starting point and the first inspection direction are used to generate a first safety inspection path, and the second inspection starting point and the second inspection direction are used to generate a second safety inspection path, specifically including: the team members can obtain the position information of other team members in real time, determine the flight interval according to the position information, and when the flight interval is less than a preset safety interval, determine the ascent / descent height of the team members according to the safety interval; Combining the plurality of the first safety inspection paths in sequence to obtain a first target safety inspection path; A plurality of the second safety inspection paths are sequentially combined to obtain a second target safety inspection path.

5. The method according to claim 1, wherein The step of acquiring multispectral image information collected based on the safety inspection path, performing fault identification on the multispectral image, and determining fault features in the multispectral image information comprises: Obtaining visible light image information and infrared image information collected by the drone group based on the safety inspection path; fusing the visible light image with the infrared image to obtain a multispectral image; Performing feature recognition on the multispectral image to determine physical object features and temperature features in the spectral image; Performing feature fusion on the physical feature and the temperature feature to obtain a fused image of the photovoltaic station; Perform hot spot detection and occlusion detection on the fused image to obtain hot spot detection results and foreign body occlusion results, and determine fault characteristics based on the hot spot detection results and foreign body occlusion detection results.

6. The method according to claim 5, characterized in that, The step of performing hot spot detection and occlusion detection on the fused image to obtain hot spot detection results and foreign body occlusion detection results, and determining fault features according to the hot spot detection results and foreign body occlusion detection results comprises: Performing hot spot detection on the fused image to determine a temperature-differentiated area in the fused image, and determining a temperature difference between the temperature-differentiated area and the highest temperature of other temperature areas; When the temperature difference is greater than a preset temperature difference, determining the temperature-differentiated area as a target hot spot area, and generating a hot spot detection result according to the target hot spot area; performing occlusion detection on the fused image in parallel to determine a shadow area in the fused image; When the shadow area has a preset shadow feature, determining that the shadow area is a target shadow area, and generating a foreign body occlusion detection result according to the target shadow area; When any one of the hot spot detection result and the foreign object obstruction detection result is a fault characteristic result, the fault characteristic is determined according to the hot spot detection result and / or the foreign object obstruction detection result.

7. The method according to claim 1, characterized in that, When the fault feature is a target fault feature, determining position information of the fault feature in the multispectral image information, obtaining fault location information based on the position information and the three-dimensional space coordinate system, and outputting the fault location information comprises: When the fault feature is a target fault feature, determining a fault type of the fault feature; When the fault type is a single hot spot fault type or an occlusion fault type, according to the position information of the fault feature in the multispectral image information, target single type fault location information is obtained based on the position information and the three-dimensional space coordinate system; When the fault types simultaneously include the hot spot fault type and the occlusion fault type, based on the position information of the fault characteristics in the multi-spectral image information, multi-type fault location information is obtained according to the position information and the three-dimensional space coordinate system; Deduplicate the multi-type fault location information, and deduplicate the overlapping position information in the fault location information corresponding to the hot spot fault type and the occlusion fault type to obtain target multi-type fault location information; Output the target single-type fault location information or the target multi-type fault location information.

8. An intelligent safety inspection device for unattended photovoltaic power stations, characterized in that, The device includes: A station yard modeling module, configured to generate a spatial model of the photovoltaic station yard according to the three-dimensional scan data of the photovoltaic station yard by the unmanned aerial vehicle group and the two-dimensional station yard base map of the photovoltaic station yard, and establish a three-dimensional space coordinate system based on the spatial model; A path planning module, configured to determine the formation information of the unmanned aerial vehicle group, divide the spatial model of the photovoltaic station yard based on the formation information to obtain a plurality of inspection zones, and determine a safe inspection path based on the inspection zones and the formation information; A fault identification module, configured to obtain multi-spectral image information collected based on the safe inspection path, perform fault identification on the multi-spectral image, and determine the fault characteristics in the multi-spectral image information; A fault location module, configured to, when the fault characteristics are target fault characteristics, determine the position information of the fault characteristics in the multi-spectral image information, obtain fault location information according to the position information and the three-dimensional space coordinate system, and output the fault location information.

9. An intelligent security inspection device for unattended photovoltaic power stations, characterized in that, The device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the computer program is configured to implement the steps of the unmanned photovoltaic station intelligent safety inspection method according to any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the unmanned photovoltaic station intelligent safety inspection method according to any one of claims 1 to 7 are implemented.

Images