Automatic inspection method and device for photovoltaic station, storage medium and electronic equipment
By establishing the correlation between the two-dimensional orthophoto image of the photovoltaic site and the CAD design image, combining power data monitoring and drone inspection, mapping defect string positions into the image, solving the problem of low photovoltaic inspection efficiency and accuracy , achieving more intuitive defect display and more efficient inspection process.
Patent Information
- Application Number
- CN202410984040.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-22
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-07-22
AI Technical Summary
Photovoltaic inspection is low efficiency and accuracy, and the defect strings are presented in two-dimensional orthogonal images for intuitive viewing by operation and maintenance personnel.
By acquiring the two-dimensional orthophotometer and CAD design images of the photovoltaic site, establishing an association relationship, combining power data monitoring to trigger the drone inspection, map the defect string position into the two-dimensional orthophotometer and inspection images for marking and exhibit.
The efficiency and accuracy of photovoltaic station inspection have been improved, and the display of defect strings is more intuitive, making it easier for operation and maintenance personnel to view.
Smart Images

Figure CN118941990A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of photovoltaic technology, and in particular to an automatic inspection method, device, storage medium and electronic equipment for a photovoltaic station. Background Art
[0002] Photovoltaic inspection is to control the drone to fly above the photovoltaic station according to the inspection route, collect visible light images of the photovoltaic station (i.e., inspection images) for defect identification, thereby determining the defective strings in the photovoltaic station, and finally generating a defect detection report. However, drone inspections are inefficient, and can only detect and locate defects through the single dimension of images, resulting in the inability to guarantee the accuracy of inspections. At the same time, defective strings can only be presented in two-dimensional orthophoto images, which is not convenient for operation and maintenance personnel to intuitively view them when conducting on-site verification and processing of defects. Summary of the invention
[0003] The purpose of the embodiments of the present disclosure is to provide a method, device, storage medium and electronic device for automatic inspection of photovoltaic stations, so as to solve the problems of low efficiency, low accuracy and unchanged presentation method of photovoltaic inspection in the prior art.
[0004] The embodiments of the present disclosure adopt the following technical solutions: an automatic inspection method for a photovoltaic station, comprising: obtaining a two-dimensional orthophoto image and a CAD design image of the photovoltaic station, and associating the photovoltaic strings in the two-dimensional orthophoto image with the photovoltaic strings in the CAD design image to obtain a first association relationship; monitoring the power data of the photovoltaic strings in the photovoltaic station, and triggering a drone inspection when there are defective strings with abnormal power data; obtaining an inspection image taken after the drone inspection; mapping the position of the defective string to the two-dimensional orthophoto image according to the first association relationship; mapping the defective string to the inspection image according to a second association relationship between the two-dimensional orthophoto image and the inspection image, and marking and displaying the position of the defective string in the inspection image.
[0005] The disclosed embodiment also provides an automatic inspection device for a photovoltaic station, comprising: a first image acquisition module, used to acquire a two-dimensional orthophoto image and a CAD design image of the photovoltaic station, and associate the photovoltaic strings in the two-dimensional orthophoto image with the photovoltaic strings in the CAD design image to obtain a first association relationship; an inspection module, used to monitor the power data of the photovoltaic strings in the photovoltaic station, and trigger a drone inspection when there are defective strings with abnormal power data; a second image acquisition module, used to acquire an inspection image taken after the drone inspection; a first mapping module, used to map the position of the defective string into the two-dimensional orthophoto image according to the first association relationship; a second mapping module, used to map the defective string into the inspection image according to a second association relationship between the two-dimensional orthophoto image and the inspection image, and mark and display the position of the defective string in the inspection image.
[0006] The embodiment of the present disclosure further provides a storage medium storing a computer program, which implements the steps of the above-mentioned automatic inspection method of photovoltaic stations when executed by a processor.
[0007] The embodiment of the present disclosure further provides an electronic device, comprising at least a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned automatic inspection method of a photovoltaic station when executing the computer program on the memory.
[0008] The beneficial effects of the disclosed embodiments are as follows: the monitoring based on power data and the inspection based on drones are associated to realize real-time monitoring of defective strings in photovoltaic stations and trigger drone inspections, so as to improve the efficiency and accuracy of photovoltaic station inspections; at the same time, combined with the association relationship between photovoltaic strings in CAD design images and two-dimensional orthophoto images, the defective strings are mapped to the two-dimensional orthophoto images, and then based on the association relationship between the two-dimensional orthophoto images and the drone inspection images, the defective strings are mapped to the inspection images for marking and display, so that the display of defective strings is more intuitive and more convenient for operation and maintenance personnel to view. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0010] Figure 1 This is a flow chart of an automatic inspection method for a photovoltaic station in the first embodiment of the present disclosure;
[0011] Figure 2 It is a schematic diagram of the structure of the automatic inspection device of the photovoltaic station in the second embodiment of the present disclosure. DETAILED DESCRIPTION
[0012] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the following will be combined with the drawings in one or more embodiments of this specification to clearly and completely describe the technical solutions in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this document.
[0013] Photovoltaic inspection is to control the drone to fly above the photovoltaic station according to the inspection route, collect visible light images of the photovoltaic station (i.e., inspection images) for defect identification, thereby determining the defective strings in the photovoltaic station, and finally generating a defect detection report. However, drone inspections are inefficient, and can only detect and locate defects through the single dimension of images, resulting in the inability to guarantee the accuracy of inspections. At the same time, defective strings can only be presented in two-dimensional orthophoto images, which is not convenient for operation and maintenance personnel to intuitively view them when conducting on-site verification and processing of defects.
[0014] In order to solve the above problems, the first embodiment of the present disclosure provides an automatic inspection method for a photovoltaic station, and the flow chart thereof is as follows: Figure 1 As shown, it mainly includes steps S10 to S50:
[0015] S10, acquiring a two-dimensional orthophoto image and a CAD design image of the photovoltaic station, and associating the photovoltaic strings in the two-dimensional orthophoto image with the photovoltaic strings in the CAD design image to obtain a first association relationship.
[0016] The 2D orthophoto image (DOM) of a photovoltaic station is the orthophoto image obtained by processing the shooting results through the Zhitu software after shooting the entire photovoltaic station area with a camera mounted on a drone. When the software constructs a 2D orthophoto image, it can also collect 3D point clouds of the photovoltaic station to obtain a digital display of the photovoltaic station. After obtaining the DOM, the DOM can be divided into sub-arrays according to the actual arrangement of each photovoltaic array in the photovoltaic station to obtain the sub-array DOM. The sub-array can be used as the inspection range for subsequent automatic inspections.
[0017] Then, the strings in the DOM are identified, and specifically, the photovoltaic strings can be identified and segmented from the DOM through any image segmentation model, and after segmentation, the first pixel coordinates of each photovoltaic string in the DOM are obtained based on the pixel coordinate system in the DOM image. Specifically, the image segmentation model used in this embodiment can be a deep learning semantic segmentation model deeplapV3+ as an algorithm model for accurately extracting the strings in the DOM. After selecting the model, a training set must be constructed first. Here, the DOM image with the strings extracted is selected as the training set. Since the size of a single DOM is relatively large, in this embodiment, the DOM needs to be cropped into a single small picture for training. Here, a sliding window of 512*512 pixels is used, and the moving step size is set to 400. After obtaining the cropped small image, in order to better train the model, the data needs to be enhanced. First, the canny operator is used to extract the edges of the strings in the image and save it as a single-channel boundary image. Then it is spliced with the original image to turn the image into a 4-channel sub-image, which is conducive to increasing the edge features of the strings in the image, so that the complete strings can be better extracted and the segmentation results can be avoided from sticking. Secondly, the sub-image enhanced by the canny operator is expanded by random inversion, brightness adjustment, color gamut change, noise addition and other data enhancement methods, and then a string segmentation data set is constructed for better string extraction.
[0018] After the algorithm model is trained, the trained model can be used to identify and extract strings in the DOM of the photovoltaic station. For DOMs with larger sizes, the same cropping method as the training set is used here. A sliding window of 512*512 pixels is used, and the moving step size is set to 400. The DOM is cropped into several small pictures, and the small pictures are input into the algorithm model to output the corresponding string recognition results. Specifically, the string part in the small picture will be identified as 1, and the background part will be identified as 0. Then, based on the coordinates of the upper left corner of each small picture, it is restored to the DOM image. After superposition, the background and the background are still 0, and as long as there is a string part, the superposition result is 1 no matter how it is superimposed, and then the string recognition and extraction of the entire DOM is obtained, and the frame coordinates corresponding to the edge of each string in the DOM pixel coordinate system are used as the first pixel coordinates representing the string.
[0019] Furthermore, after obtaining the extraction results of the group string, the group string can be sorted according to the pixel coordinates and encoded in an increasing manner from left to right and from top to bottom based on the sorting results. The encoding rule is: subarray-row-column, so as to obtain the position code of the group string. Since the DOM has its own geographic location information, the position code has the corresponding first pixel coordinate and the first world coordinate.
[0020] The CAD design image is produced when the photovoltaic station is designed, and it records the design information of the station, the design code of each string, and the world coordinates corresponding to the string during the design, that is, the second world coordinates. After obtaining the CAD design image, the CAD design image can also be segmented according to the subarray, and the strings in the CAD design image can be extracted and saved according to the subarray. Subsequently, the second world coordinates of the photovoltaic strings in the CAD design image are mapped to the dom image with the help of the world coordinate system of the dom, and the second pixel coordinates corresponding to the second world coordinates of the photovoltaic strings in the dom image are determined. However, due to the position differences caused by different acquisition tools and actual construction, the first pixel coordinates directly determined in the dom of the same photovoltaic string and the second pixel coordinates obtained by mapping the CAD design image usually cannot overlap, and in order to achieve the matching of the same photovoltaic string, this embodiment adjusts the overall position of the second pixel coordinates of all photovoltaic strings, so that they are matched one-to-one with the strings in the dom, so as to complete the association between the position code and the design code of the photovoltaic string. It should be noted that when matching is actually performed, it can be performed according to the subarray, which helps to improve the matching efficiency and accuracy. Specifically, the above adjustment operation may be performed by the Hungarian algorithm, or may be implemented by other adjustment algorithms, which is not limited in this embodiment.
[0021] S20, monitoring the power data of the photovoltaic strings in the photovoltaic station, and triggering a drone inspection when there is a defective string with abnormal power data.
[0022] When the photovoltaic strings are in normal operation, the corresponding power data is also within the normal range, such as its current value, voltage value, etc. If the photovoltaic strings fail, such as being blocked by pollutants or photovoltaic panel failure, the power data of the corresponding strings will be abnormal. Therefore, this embodiment monitors the power data of the photovoltaic strings in the photovoltaic station in real time, and when there are defective strings with abnormal power data, it can trigger a drone to conduct on-site inspections to help operation and maintenance personnel determine whether the corresponding photovoltaic panels are blocked or faulty.
[0023] Specifically, in the process of real-time monitoring of power data, when it is found that the power data of a certain string is not within the normal range, the photovoltaic string is identified as a defective string, and the design code of the defective string is obtained according to the design code recorded in the CAD design image; then, the corresponding position code and the first world coordinates of the position code presented in the dom, that is, the actual geographical coordinates of the defective string, can be determined according to the design code of the defective string; after determining the first world coordinates of all defective strings, the first world coordinates of all defective strings can be used as inspection points to plan the inspection route of the drone, and the drone can be triggered to perform the inspection operation according to the inspection route, so that the drone can traverse and inspect the locations of all defective strings in one inspection process, and at the same time instruct the drone to take inspection images when inspecting to the inspection points, so as to realize the acquisition of visible light images of the defective strings.
[0024] In some embodiments, when planning the inspection route of the drone, the first world coordinates of all defect groups can be used and integrated to form the least number of cruise points to achieve the formation of the optimal planned path. Specifically, first, the first world coordinates of the center points of all defect groups are used as inspection points to establish an inspection point set; then, any inspection point is selected from the inspection point set as a recording point, and the camera imaging principle is used to calculate the coverage area of the cruise image taken when the drone inspects the recording point. It should be noted that due to the existence of positioning errors, the actual coverage area can be calculated as 90% of the theoretical coverage area to avoid an increase in subsequent waypoint calculation errors due to excessive coverage areas; then, it is detected whether the coverage area contains other inspection points. If the coverage area does not contain other inspection points, the current recording point is placed in the waypoint set as a waypoint. If If the coverage area contains other inspection points, the other inspection points are merged with the current recording point, and the current recording point is placed in the waypoint set as a waypoint. At the same time, other inspection points already included in the coverage area are deleted from the inspection point set; according to the above steps, a inspection point is continuously selected from the inspection point set as a new recording point, and the waypoint is determined and integrated with other inspection points according to its corresponding coverage area, until all inspection points in the inspection point set are traversed and the inspection point set is an empty set. At this time, part of the inspection points are placed in the waypoint set as waypoints, and the other part is located in the coverage area of a certain waypoint and is directly deleted to reduce the number of waypoints, which is convenient for subsequent route planning.
[0025] After the waypoint set is determined, the inspection route of the drone can be planned according to the first world coordinates of all the waypoints in the set. In this embodiment, the inspection route of the drone can be planned by any of the following algorithms: greedy algorithm, ant colony algorithm, backtracking algorithm, divide-and-conquer algorithm, etc. This embodiment does not limit the specific algorithm used in route planning. In actual operation, the appropriate algorithm can be selected according to the number of waypoints, inspection efficiency, time requirements, etc. It should also be noted that if the number of defective strings exceeds the preset percentage of the total number of photovoltaic strings in the current photovoltaic station, such as 60%, it means that most of the strings in the current photovoltaic station are in defective condition. At this time, the drone's full-station inspection can be directly started to determine whether there is a large-scale string failure or photovoltaic panel shading caused by dust.
[0026] S30, obtaining inspection images taken by the drone after the inspection.
[0027] When the drone detects a defective string during the inspection process, it will take images of it. The inspection images taken reflect the actual situation of the station area that currently contains the defective string.
[0028] S40: Mapping the position of the defective string into the two-dimensional orthophoto image according to the first association relationship.
[0029] The first association relationship of this embodiment is the association between the two-dimensional orthophoto image of the photovoltaic station and the CAD design image, that is, the association relationship between the design code and the position code of the photovoltaic string obtained by step S10, and the relationship between the first pixel coordinate and the first world coordinate in the two-dimensional orthophoto image. After the drone inspection, the first world coordinate and the first pixel coordinate of the defective string in the DOM can be determined based on the design code of the defective string based on the first association relationship, that is, the position of the defective string can be mapped to the DOM, and the corresponding marking and display can be performed, so that the operation and maintenance personnel can intuitively understand the position of the defective string through the DOM image.
[0030] S50, mapping the defect group string into the inspection image according to the second association relationship between the two-dimensional orthophoto image and the inspection image, and marking and displaying the position of the defect group string in the inspection image.
[0031] In this embodiment, in addition to displaying the defective strings in the DOM, the defective strings can also be marked and displayed in the inspection image, so that the operation and maintenance personnel can more quickly and directly locate the faulty string position and understand the actual situation of the current string based on the inspection image actually taken. Specifically, the flight altitude Z of the drone during the inspection process is usually fixed, and the intrinsic parameters K and extrinsic parameters T of the camera it carries are also known parameters. Then the mapping relationship between the pixel coordinate system of the inspection image actually taken by the drone and the world coordinate system of the actual geographical location corresponding to the inspection image can be determined, and the world coordinate system of the actual geographical location corresponding to the inspection image is the world coordinate system of the two-dimensional orthophoto image. According to the camera imaging principle, the mapping relationship can be obtained as follows:
[0032]
[0033] Among them, P uv represents the pixel coordinates of the inspection image, Z represents the flight height of the drone in the real world coordinates, and P w is the world coordinate system of the two-dimensional orthophoto image, K is the camera internal parameter, and T is the camera external parameter. w , K, T and Z, we can get P uv The coordinates of the defective string are combined with the first world coordinates of the defective string in DOM, the flight height Z of the UAV, the camera internal parameter K and the external parameter T, and the third pixel coordinates of the defective string in the inspection image can be obtained. At this time, the position of the defective string can be marked and displayed in the inspection image according to the third pixel coordinates.
[0034] In some embodiments, photovoltaic inspections may also include triggering drones to inspect all photovoltaic strings in a photovoltaic station at a scheduled inspection cycle according to a preset period, and extracting defective strings through image recognition of the drone's inspection image, and then marking and displaying the corresponding defective strings in the DOM according to the mapping relationship between the inspection image and the DOM. At the same time, when the drone periodic inspection is triggered, the monitoring of power data can be triggered at the same time. After the results obtained by the two monitoring methods are merged and unified, all defective strings can be marked and displayed on the DOM and the inspection image at the same time, thereby realizing the inspection effect of photovoltaic stations with multi-dimensional data, and improving the inspection efficiency and the accuracy of the recognition effect.
[0035] This embodiment associates the monitoring based on power data with the inspection based on drones, realizes real-time monitoring of defective strings in photovoltaic stations and triggers drone inspections, so as to improve the efficiency and accuracy of photovoltaic station inspections; at the same time, combined with the association between photovoltaic strings in CAD design images and two-dimensional orthophoto images, the defective strings are mapped to the two-dimensional orthophoto images, and then based on the association between the two-dimensional orthophoto images and the drone inspection images, the defective strings are mapped to the inspection images for marking and display, so that the display of defective strings is more intuitive and more conducive to viewing by operation and maintenance personnel.
[0036] Based on the same inventive concept, the second embodiment of the present disclosure provides an automatic inspection device for a photovoltaic station, and its structural schematic diagram is shown as follows: Figure 2 As shown, it mainly includes the following modules coupled in sequence: a first image acquisition module 10, used to acquire a two-dimensional orthophoto image and a CAD design image of a photovoltaic station, and associate the photovoltaic strings in the two-dimensional orthophoto image with the photovoltaic strings in the CAD design image to obtain a first association relationship; an inspection module 20, used to monitor the power data of the photovoltaic strings in the photovoltaic station, and trigger a drone inspection when there are defective strings with abnormal power data; a second image acquisition module 30, used to acquire an inspection image taken after the drone inspection; a first mapping module 40, used to map the position of the defective string into the two-dimensional orthophoto image according to the first association relationship; a second mapping module 50, used to map the defective string into the inspection image according to the second association relationship between the two-dimensional orthophoto image and the inspection image, and mark and display the position of the defective string in the inspection image.
[0037] In some embodiments, the first image acquisition module 10 is specifically used to photograph a photovoltaic station through a drone, and construct a two-dimensional orthophoto image of the photovoltaic station based on the photographing results; segment the two-dimensional orthophoto image through an image segmentation model to obtain the first pixel coordinates of the photovoltaic string in the two-dimensional orthophoto image; assign a position code to the photovoltaic string according to the first pixel coordinate of the photovoltaic string, and associate the position code, first pixel coordinate and first world coordinate of the photovoltaic string; obtain a CAD design image of the photovoltaic station, and determine the second world coordinate and design code of each photovoltaic string in the CAD design image; determine the second pixel coordinate corresponding to the second world coordinate of the photovoltaic string in the two-dimensional orthophoto image; adjust the overall position of the second pixel coordinate so that the second pixel coordinates of all photovoltaic strings match the unique first pixel coordinate to complete the association between the position code and the design code of the photovoltaic string.
[0038] In some embodiments, the inspection module 20 is specifically used to determine that the photovoltaic string is a defective string and obtain the design code of the defective string when the power data of the photovoltaic string is not within the normal range; determine the corresponding position code and first world coordinates according to the design code of the defective string; use the first world coordinates of all defective strings as inspection points to plan the inspection route of the drone; trigger the inspection operation of the drone according to the inspection route, and instruct the drone to take inspection images when it inspects to the inspection point.
[0039] In some embodiments, the inspection module 20 is also specifically used to establish a inspection point set using the first world coordinates of the center points of all defective groups as inspection points; using any inspection point in the inspection point set as a recording point, calculating the coverage area of the cruise image taken when the drone inspects the recording point; detecting whether the coverage area contains other inspection points; if the coverage area does not contain other inspection points, placing the recording point as a waypoint into the waypoint set; if the coverage area contains other inspection points, placing the recording point as a waypoint into the waypoint set, and deleting other inspection points in the coverage area from the inspection point set; traversing all inspection points in the inspection point set until the inspection point set is an empty set; planning the inspection route of the drone according to the first world coordinates of all waypoints in the waypoint set.
[0040] In some embodiments, the inspection module 20 plans the inspection route of the drone using any one of the following algorithms: greedy algorithm, ant colony algorithm, backtracking algorithm, divide-and-conquer algorithm.
[0041] In some embodiments, the second mapping module 50 is specifically used to establish a mapping relationship between the pixel coordinate system of the inspection image and the world coordinate system of the two-dimensional orthophoto image according to the flight altitude of the UAV when shooting the inspection image, the camera intrinsic parameters and camera extrinsic parameters of the UAV; determine the corresponding first world coordinate according to the design code of the defect group string; determine the third pixel coordinate of the defect group string in the inspection image according to the first world coordinate of the defect group string, the flight altitude, the camera intrinsic parameters and camera extrinsic parameters of the UAV and the mapping relationship; mark and display the position of the defect group string in the inspection image according to the third pixel coordinate.
[0042] In some embodiments, the inspection module 20 is also used to trigger the drone to inspect all photovoltaic strings in the photovoltaic station according to a preset period; the second image acquisition module 30 is also used to perform image recognition on the inspection image of the drone to identify defective strings; the second mapping module 50 is also used to map the defective strings into a two-dimensional orthophoto image for marking and display.
[0043] This embodiment associates the monitoring based on power data with the inspection based on drones, realizes real-time monitoring of defective strings in photovoltaic stations and triggers drone inspections, so as to improve the efficiency and accuracy of photovoltaic station inspections; at the same time, combined with the association between photovoltaic strings in CAD design images and two-dimensional orthophoto images, the defective strings are mapped to the two-dimensional orthophoto images, and then based on the association between the two-dimensional orthophoto images and the drone inspection images, the defective strings are mapped to the inspection images for marking and display, so that the display of defective strings is more intuitive and more conducive to viewing by operation and maintenance personnel.
[0044] Based on the same inventive concept, a third embodiment of the present disclosure provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the automatic inspection method of a photovoltaic station of the first embodiment of the present disclosure.
[0045] Based on the same inventive concept, the fourth embodiment of the present disclosure provides an electronic device, comprising at least a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program in the memory, the steps of the automatic inspection method of the photovoltaic station of the first embodiment of the present disclosure are implemented.
[0046] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them. Although the present disclosure has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present disclosure.
Claims
1. An automatic inspection method for a photovoltaic station, characterized in that: include: Acquire a two-dimensional orthophoto image and a CAD design image of a photovoltaic station, and associate the photovoltaic strings in the two-dimensional orthophoto image with the photovoltaic strings in the CAD design image to obtain a first association relationship; The power data of the photovoltaic strings in the photovoltaic station are monitored, and when there are defective strings with abnormal power data, a drone inspection is triggered; Obtain inspection images taken by drones after inspection; According to the first association relationship, mapping the position of the defect group string into the two-dimensional orthophoto image; According to the second association relationship between the two-dimensional orthophoto image and the inspection image, the defect group string is mapped into the inspection image, and the position of the defect group string is marked and displayed in the inspection image.
2. The automatic inspection method according to claim 1, characterized in that: The acquiring of a two-dimensional orthophoto image and a CAD design image of a photovoltaic station, and associating the photovoltaic strings in the two-dimensional orthophoto image with the photovoltaic strings in the CAD design image to obtain a first association relationship includes: photographing the photovoltaic station by using a drone, and constructing a two-dimensional orthophoto image of the photovoltaic station according to the photographing results; Segmenting the two-dimensional orthophoto image using an image segmentation model to obtain first pixel coordinates of the photovoltaic string in the two-dimensional orthophoto image; Assigning a position code to the photovoltaic string according to the first pixel coordinate of the photovoltaic string, and associating the position code, the first pixel coordinate and the first world coordinate of the photovoltaic string; Acquire a CAD design image of the photovoltaic station, and determine a second world coordinate and a design code of each photovoltaic string in the CAD design image; Determining a second pixel coordinate corresponding to a second world coordinate of the photovoltaic string in the two-dimensional orthoimage; The overall position of the second pixel coordinates is adjusted so that the second pixel coordinates of all photovoltaic strings match the unique first pixel coordinates, thereby completing the association between the position code and the design code of the photovoltaic strings.
3. The automatic inspection method according to claim 2, characterized in that: The monitoring of the power data of the photovoltaic strings in the photovoltaic station and triggering the drone inspection when there is a defective string with abnormal power data includes: When the power data of the photovoltaic string is not within a normal range, determining that the photovoltaic string is the defective string, and obtaining a design code of the defective string; Determine the corresponding position code and the first world coordinate according to the design code of the defective string; The first world coordinates of all the defective strings are used as inspection points to plan the inspection route of the drone; The inspection operation of the drone is triggered according to the inspection route, and the drone is instructed to capture inspection images when it inspects the inspection point.
4. The automatic inspection method according to claim 2, characterized in that: The first world coordinates of all the defective strings are used as inspection points to plan the inspection route of the drone, including: Taking the first world coordinates of the center points of all the defective strings as inspection points, a set of inspection points is established; Taking any one of the inspection points in the inspection point set as a recording point, calculating the coverage area of the cruise image taken when the drone inspects the recording point; Detect whether the coverage area contains other inspection points; If no other inspection points are included in the coverage area, the recorded point is placed in the waypoint set as a waypoint; In the case where the coverage area includes other inspection points, the recorded point is placed in a waypoint set as a waypoint, and other inspection points in the coverage area are deleted from the inspection point set; Traversing all inspection points in the inspection point set until the inspection point set is an empty set; The inspection route of the UAV is planned according to the first world coordinates of all the waypoints in the waypoint set.
5. The automatic inspection method according to claim 4, characterized in that: Planning the inspection route of the UAV according to the first world coordinates of all the waypoints in the waypoint set includes: planning the inspection route of the UAV by any one of the following algorithms: greedy algorithm, ant colony algorithm, backtracking algorithm, divide and conquer algorithm.
6. The automatic inspection method according to claim 2, characterized in that: Mapping the defect group string into the inspection image according to the second association relationship between the two-dimensional orthoimage and the inspection image, and marking and displaying the position of the defect group string in the inspection image includes: A mapping relationship between a pixel coordinate system of the inspection image and a world coordinate system of the two-dimensional orthophoto image is established according to the flight altitude of the drone when shooting the inspection image, the camera intrinsic parameters and the camera extrinsic parameters of the drone; Determine the corresponding first world coordinate according to the design code of the defective string; Determine a third pixel coordinate of the defect group string in the inspection image according to the first world coordinate of the defect group string, the flight altitude, the camera intrinsic parameters and camera extrinsic parameters of the drone, and the mapping relationship; The position of the defective string is marked and displayed in the inspection image according to the third pixel coordinate.
7. The automatic inspection method according to any one of claims 1 to 6, characterized in that: Also includes: Triggering the drone to inspect all photovoltaic strings in the photovoltaic station according to a preset period; Performing image recognition on the inspection image of the drone to identify defective strings; The defect group string is mapped into the two-dimensional orthophoto image for marking and display.
8. An automatic inspection device for a photovoltaic station, characterized in that: include: A first image acquisition module is used to acquire a two-dimensional orthophoto image and a CAD design image of the photovoltaic station, and associate the photovoltaic strings in the two-dimensional orthophoto image with the photovoltaic strings in the CAD design image to obtain a first association relationship; An inspection module is used to monitor the power data of the photovoltaic strings in the photovoltaic station, and trigger a drone inspection when there is a defective string with abnormal power data; The second image acquisition module is used to acquire the inspection image taken by the drone after the inspection; A first mapping module, used for mapping the position of the defect group string into the two-dimensional orthophoto image according to the first association relationship; The second mapping module is used to map the defect group string into the inspection image according to the second association relationship between the two-dimensional orthoimage and the inspection image, and mark and display the position of the defect group string in the inspection image.
9. A storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the automatic inspection method of a photovoltaic station according to any one of claims 1 to 7 are implemented.
10. An electronic device comprising at least a memory and a processor, wherein a computer program is stored in the memory, wherein: The processor implements the steps of the automatic inspection method for a photovoltaic station according to any one of claims 1 to 7 when executing the computer program on the memory.
Citation Information
Patent Citations
Photovoltaic power station unmanned aerial vehicle inspection method and system based on photovoltaic string data analysis
CN114898232A
A method and electronic equipment for determining the inspection route of a distributed photovoltaic power station
CN114935942A
Digital method for unmanned aerial vehicle to automatically inspect and position photovoltaic panel defects
CN116773598A
Intelligent inspection method and system for photovoltaic power station based on unmanned aerial vehicle
CN116797206A
Method and device for numbering photovoltaic strings in photovoltaic power station
CN117391049A
Cited By
Photovoltaic station assembly defect positioning method, device, equipment and medium
CN120182287A
Photovoltaic station maintenance path planning method and device and computer readable storage medium
CN120403647A
Unmanned aerial vehicle routing inspection photovoltaic string defect positioning method, system, medium and equipment
CN121190390A
Photovoltaic station intelligent inspection method and system based on object model
CN121502576A
