A method, device, equipment and storage medium for fault location of a photovoltaic module

Abstract

The present invention discloses a method, device, equipment and storage medium for fault location of a photovoltaic module. The method includes: obtaining a target fault infrared photo containing a target fault module and a duplicate-removed fault infrared photo associated with the target fault infrared photo, and determining the duplicate-removed fault module in the duplicate-removed fault infrared photo; determining a reprojection error parameter according to the target shooting parameters of the target fault infrared photo, the duplicate-removed shooting parameters of the duplicate-removed fault infrared photo, the first pixel coordinates of the target fault module and the second pixel coordinates of the duplicate-removed fault module; when the reprojection error parameter does not meet the preset reprojection threshold condition, determining a target fault module shooting line and a target fault string plane based on the target shooting parameters and the first pixel coordinates; and determining the three-dimensional coordinates of the target fault module according to the target fault module shooting line and the target fault string plane. The present invention realizes the effect of effectively removing duplicate fault photovoltaic module information and quickly and accurately locating the fault photovoltaic module.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of photovoltaic module inspection, and in particular, to a method, device, equipment and storage medium for fault location of photovoltaic modules. Background Art

[0002] With the development of unmanned aerial vehicle (UAV) technology, the operation and maintenance of photovoltaic power stations tend to be intelligent. The fault detection operation of photovoltaic modules has gradually changed from manual inspection in the past to collecting photos through visible light and infrared cameras carried by UAVs, which greatly improves the operation and maintenance efficiency of photovoltaic power stations and saves a large amount of human resources. After the fault detection of photovoltaic modules is completed, it is necessary to accurately locate the faulty photovoltaic modules and mark the located results on the global electronic map to guide the maintenance personnel for repair. The existing methods for fault location of photovoltaic modules mainly include the following several types:

[0003] 1. Using the visible light photos and infrared photos taken simultaneously during UAV inspection for image registration, determining the pixel coordinate conversion relationship between the visible light photos and the infrared photos, converting the pixel coordinates of the faults detected on the infrared photos into the pixel coordinates of the visible light photos, and then performing the registration of the visible light photos and the power station electronic map, and finally completing the calibration of the photovoltaic module faults on the power station electronic map.

[0004] 2. According to the GPS coordinates and camera poses of all the photos taken during UAV inspection, using the SFM (Structure from motion) three-dimensional reconstruction method to generate sparse point cloud data, and establishing the correspondence between the three-dimensional coordinates of the point cloud and the two-dimensional pixel points of the photos, and finally interpolating the three-dimensional coordinates corresponding to the pixel coordinates of the fault points.

[0005] For the first positioning method, its disadvantage is that due to the different imaging methods of the visible light photos and the infrared photos, there are large differences in the resolution, shooting range, etc. between the visible light photos and the infrared photos, while the texture differences between photovoltaic strings are small. Therefore, in many UAV photovoltaic inspection scenarios, it is very difficult to perform accurate registration of visible light and infrared images or impossible to perform registration. In the second method, when there is not enough sparse point cloud or no sparse point cloud within a certain range around the pixel coordinates of the fault point, it will cause problems of unstable interpolation and uncontrollable errors, and this situation is very common in the photovoltaic scenario. Summary of the Invention

[0006] The present invention provides a method, device, equipment and storage medium for fault location of photovoltaic modules to achieve accurate location of faulty photovoltaic modules.

[0007] According to one aspect of the present invention, a method for fault location of photovoltaic modules is provided, and the method includes:

[0008] Obtain a target fault infrared photo containing a target fault component, as well as a duplicate-removed fault infrared photo associated with the target fault infrared photo, and determine a duplicate-removed fault component in the duplicate-removed fault infrared photo that has the same fault type as the target fault component;

[0009] Determine a reprojection error parameter based on the target shooting parameters corresponding to the target fault infrared photo, the duplicate-removed shooting parameters corresponding to the duplicate-removed fault infrared photo, the first pixel coordinates of the target fault component, and the second pixel coordinates of the duplicate-removed fault component;

[0010] When the reprojection error parameter does not meet the preset reprojection threshold condition, determine a target fault component shooting line and a target fault string plane based on the target shooting parameters and the first pixel coordinates;

[0011] Determine the three-dimensional coordinates of the target fault component according to the target fault component shooting line and the target fault string plane

[0012] According to another aspect of the present invention, there is provided a photovoltaic module fault location device, which includes:

[0013] A duplicate-removed component combination determination module, configured to obtain a target fault infrared photo containing a target fault component, as well as a duplicate-removed fault infrared photo associated with the target fault infrared photo, and determine a duplicate-removed fault component in the duplicate-removed fault infrared photo that has the same fault type as the target fault component;

[0014] A reprojection error parameter determination module, configured to determine a reprojection error parameter based on the target shooting parameters corresponding to the target fault infrared photo, the duplicate-removed shooting parameters corresponding to the duplicate-removed fault infrared photo, the first pixel coordinates of the target fault component, and the second pixel coordinates of the duplicate-removed fault component;

[0015] A shooting line and string plane determination module, configured to determine a target fault component shooting line and a target fault string plane based on the target shooting parameters and the first pixel coordinates when the reprojection error parameter does not meet the preset reprojection threshold condition;

[0016] A target three-dimensional coordinate determination module, configured to determine the three-dimensional coordinates of the target fault component according to the target fault component shooting line and the target fault string plane.

[0017] According to another aspect of the present invention, there is provided an electronic device, which includes:

[0018] At least one processor; and

[0019] A memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores a computer program executable by the at least one processor. When executed by the at least one processor, the computer program enables the at least one processor to execute the photovoltaic module fault location method according to any embodiment of the present invention.

[0021] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for implementing the photovoltaic module fault location method according to any embodiment of the present invention when executed by a processor.

[0022] The technical solution of the embodiment of the present invention obtains a target fault infrared photo including a target fault module and a deduplicated fault infrared photo associated with the target fault infrared photo, and determines a deduplicated fault module in the deduplicated fault infrared photo with the same fault type as the target fault module; according to the target shooting parameters corresponding to the target fault infrared photo, the deduplicated shooting parameters corresponding to the deduplicated fault infrared photo, the first pixel coordinates of the target fault module, and the second pixel coordinates of the deduplicated fault module, determines a reprojection error parameter; when the reprojection error parameter does not meet the preset reprojection threshold condition, based on the target shooting parameters and the first pixel coordinates, determines a target fault module shooting line and a target fault string plane; according to the target fault module shooting line and the target fault string plane, determines the three-dimensional coordinates of the target fault module, solving the problems of inaccurate positioning and high shooting requirements of existing faulty photovoltaic modules, and achieving the effect of effectively removing duplicate faulty photovoltaic module information and quickly and accurately locating faulty photovoltaic modules.

[0023] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings without creative efforts based on these drawings.

[0025] Figure 1 is a flowchart of a photovoltaic module fault location method provided in Embodiment 1 of the present invention;

[0026] Figure 2 is a schematic diagram of a photovoltaic module fault location method provided in Embodiment 1 of the present invention;

[0027] Figure 3It is a flowchart of a method for fault location of a photovoltaic module according to Embodiment 2 of the present invention;

[0028] Figure 4a It is a first schematic diagram of a method for fault location of a photovoltaic module according to Embodiment 2 of the present invention;

[0029] Figure 4b It is a second schematic diagram of a method for fault location of a photovoltaic module according to Embodiment 2 of the present invention;

[0030] Figure 4c It is a third schematic diagram of a method for fault location of a photovoltaic module according to Embodiment 2 of the present invention;

[0031] Figure 5 It is a structural block diagram of a device for fault location of a photovoltaic module according to Embodiment 3 of the present invention;

[0032] Figure 6 It is a structural block diagram of an electronic device according to Embodiment 4 of the present invention. Detailed Embodiments

[0033] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0034] It should be noted that the terms "first", "second", "target", "alternative", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0035] Embodiment 1

[0036] Figure 1The figure is a flowchart of a method for fault location of a photovoltaic module provided in the first embodiment of the present invention. This embodiment is applicable to the situation of locating a faulty photovoltaic module. This method can be executed by a photovoltaic module fault location device, which can be implemented by software and / or hardware.

[0037] As Figure 1 shown, the method includes:

[0038] S110. Obtain a target fault infrared photo including a target fault component and a duplicate-removed fault infrared photo associated with the target fault infrared photo, and determine a duplicate-removed fault component in the duplicate-removed fault infrared photo that has the same fault type as the target fault component.

[0039] In this embodiment, a drone can be used to inspect the photovoltaic modules, and a certain number of infrared photos are taken for the photovoltaic strings within a preset positioning range. Before executing the photovoltaic module fault location method of this embodiment, photovoltaic fault detection can be performed on the infrared photos, and the faulty photovoltaic modules captured in the infrared photos can be marked, and the detected fault types can also be marked. For example, the fault types are divided into "Type A1", "Type B", etc. Figure 2 is a schematic diagram of a method for fault location of a photovoltaic module provided in the first embodiment of the present invention. As Figure 2 shown, the position marked A1 in the figure is the photovoltaic fault component with the fault type of "Type A1" marked by the photovoltaic fault detection.

[0040] Specifically, one photo with a faulty photovoltaic module can be selected from the captured infrared photos as the target fault infrared photo, and one of the faulty photovoltaic modules can be selected as the target fault component. Other infrared photos taken near the geographical location where the target fault infrared photo is taken can be selected as the duplicate-removed fault infrared photos, and the fault points in the duplicate-removed fault infrared photos that have the same fault type as the target fault component can be selected as the duplicate-removed fault components.

[0041] S120. Determine a reprojection error parameter according to the target shooting parameters corresponding to the target fault infrared photo, the duplicate-removed shooting parameters corresponding to the duplicate-removed fault infrared photo, the first pixel coordinates of the target fault component, and the second pixel coordinates of the duplicate-removed fault component.

[0042] Among them, the shooting parameters may include the three-dimensional coordinates of the camera, the camera attitude parameters, and the camera internal parameters. The three-dimensional coordinates of the camera can be understood as the three-dimensional spatial coordinates of the UAV when taking infrared photos. The camera attitude parameters may include the three angular attitudes of the UAV when taking infrared photos. The camera internal parameters may include the focal length of the camera and the pixel coordinates of the camera photography center when the UAV takes infrared photos. The target shooting parameters can be understood as the shooting parameters of the camera when taking infrared photos of the target fault, and the duplicate-removing shooting parameters can be understood as the shooting parameters of the camera when taking infrared photos of the duplicate-removing fault. The first pixel coordinates can be understood as the pixel coordinates of the target fault component in the target fault infrared photo, and the second pixel coordinates can be understood as the pixel coordinates of the duplicate-removing fault component in the duplicate-removing fault infrared photo.

[0043] Specifically, the reprojection error parameter can be determined according to the target shooting parameters of the target fault infrared photo, the duplicate-removing shooting parameters of the duplicate-removing fault infrared photo, the first pixel coordinates, and the second pixel coordinates, so as to determine whether the target fault component captured in the target fault infrared photo and the duplicate-removing fault component captured in the duplicate-removing fault infrared photo are the same faulty photovoltaic component.

[0044] Optionally, S120 can be implemented through the following specific steps:

[0045] S1201. Determine the target coordinate expression satisfied by the three-dimensional coordinates of the target fault component according to the target shooting parameters corresponding to the target fault infrared photo and the first pixel coordinates of the target fault component; determine the duplicate-removing coordinate expression satisfied by the three-dimensional coordinates of the duplicate-removing fault component according to the duplicate-removing shooting parameters corresponding to the duplicate-removing fault infrared photo and the second pixel coordinates of the duplicate-removing fault component.

[0046] In practical applications, the coordinate position of the fault component in the fault infrared photo can be recorded as (u, v), and the shooting parameters corresponding to the fault infrared photo can be recorded as the three-dimensional coordinates of the camera (X a , Y a , Z a ), the camera attitude parameters and the camera internal parameters (f, c x , c y ), where the camera attitude parameters can represent that the camera rotates by angle around the Y axis, rotates by ω angle around the X axis, and rotates by k angle around the Z axis. In the camera internal parameters (f, c x , c y ), f can represent the focal length of the camera, and c x and c y can represent the pixel coordinates of the camera photography center. Assuming that the three-dimensional coordinates of the fault component are (X, Y, Z), then the shooting line of the fault component can be expressed by the following expression:

[0047]

[0048]

[0049] Among them, a 11 , a 12 , a 13 , a 21 , a 22 , a 23 , a 31 , a 32 , a 33 can be regarded as known values, which can be calculated using the camera pose parameters and satisfy the following relational expressions:

[0050]

[0051] In this embodiment, the first pixel coordinates of the target faulty component can be denoted as (u0, v0), and the target shooting parameters of the target faulty infrared photo can be denoted as (X a0 , Y a0 , Z a0 ), (f0, c x0 , c y0 ). Substituting them into the above expressions as the coordinates of the faulty component and the shooting parameters respectively, two target coordinate expressions containing X, Y, and Z in the three-dimensional coordinates of the faulty component can be obtained.

[0052] The second pixel coordinates of the duplicate-removed faulty component can be denoted as (ui, vi), and the duplicate-removed shooting parameters of the duplicate-removed faulty infrared photo can be denoted as (X ai , Y ai , Z ai ). (fi, c xi , c yi ). Substituting them into the above expressions as the coordinates of the faulty component and the shooting parameters respectively, two duplicate-removed coordinate expressions containing X, Y, and Z in the three-dimensional coordinates of the faulty component can be obtained.

[0053] S1202. Determine the alternative three-dimensional coordinates that satisfy the target coordinate expressions and the duplicate-removed coordinate expressions.

[0054] Specifically, since X, Y, and Z in the three-dimensional coordinates of the faulty component satisfy both the two target coordinate expressions and the two duplicate-removed coordinate expressions, X, Y, and Z can be solved. For example, X, Y, and Z can be solved by the least squares method, and the three-dimensional coordinates (X, Y, Z) are used as the alternative three-dimensional coordinates.

[0055] S1203. Determine the target projected pixel coordinates according to the alternative three-dimensional coordinates and the target shooting parameters; determine the duplicate-removed projected pixel coordinates according to the alternative three-dimensional coordinates and the duplicate-removed shooting parameters.

[0056] In practical applications, when the shooting parameters corresponding to the fault infrared photo are recorded as the three-dimensional coordinates of the camera (X a , Y a , Z a ), the attitude parameters of the camera and the internal parameters of the camera (f, c x , c y ), when the three-dimensional coordinates of the located fault component are (X, Y, Z), the projection pixel coordinates (up, vp) can be obtained through the following formula:

[0057]

[0058]

[0059] In this embodiment, the target shooting parameters can be used as the shooting parameters, and the alternative three-dimensional coordinates can be used as the three-dimensional coordinates of the fault component and substituted into the above two formulas to obtain the target projection pixel coordinates (up0, vp0). (up0, vp0) can represent the projection pixel coordinates of the alternative three-dimensional coordinates (X, Y, Z) on the target fault infrared photo according to the imaging principle.

[0060] The deduplicated shooting parameters can be used as the shooting parameters, and the alternative three-dimensional coordinates can be used as the three-dimensional coordinates of the fault component and substituted into the above two formulas to obtain the deduplicated projection pixel coordinates (upi, vpi). (upi, vpi) can represent the projection pixel coordinates of the alternative three-dimensional coordinates (X, Y, Z) on the deduplicated fault infrared photo according to the imaging principle.

[0061] S1204. Determine the alternative height coordinate value in the alternative three-dimensional coordinates, and determine the target projection pixel coordinates, the deduplicated projection pixel coordinates, and the alternative height coordinate value as the reprojection error parameters.

[0062] In this embodiment, when Z in the alternative three-dimensional coordinates (X, Y, Z) represents the height in the three-dimensional space, Z can be used as the alternative height coordinate value, and the target projection pixel coordinates (up0, vp0), the deduplicated projection pixel coordinates (upi, vpi), and the alternative height coordinate value Z can be determined as the reprojection error parameters.

[0063] S130. When the reprojection error parameters do not meet the preset reprojection threshold condition, determine the target fault component shooting line and the target fault string plane based on the target shooting parameters and the first pixel coordinates.

[0064] In this embodiment, the target fault component imaging line can be understood as a line composed of the possible position points of the target fault component in space determined based on the imaging position of the target fault component in the target fault infrared photo. The target fault string plane can be understood as the plane of the string area where the target fault component is located fitted according to the sparse three-dimensional point cloud.

[0065] Optionally, the following steps can be used to determine whether the reprojection error parameter meets the preset reprojection threshold condition:

[0066] S1301. Determine the reprojection error value based on the first pixel coordinate, the second pixel coordinate, the target projection pixel coordinate, and the de-duplicated projection pixel coordinate.

[0067] In this embodiment, the reprojection error value Perror can be calculated in the following manner:

[0068] Perror = [(u0 - up0) 2 + (v0 - vp0) 2 + (ui - upi) 2 + (vi - vpi) 2 / 2.

[0069] S1302. Determine whether the reprojection error value is greater than the preset reprojection error threshold and whether the alternative height coordinate value is within the preset elevation threshold range.

[0070] Specifically, it can be determined whether the reprojection error value Perror is greater than the preset reprojection error threshold and whether the alternative height coordinate value Z is within the preset elevation threshold range. When the reprojection error value Perror is greater than the preset reprojection error threshold or the alternative height coordinate value Z is not within the preset elevation threshold range, S1303 can be performed; otherwise, S1304 can be performed. The preset reprojection error threshold can be set according to the actual scenario, for example, set to 1. Similarly, the preset elevation threshold range can also be set according to the actual scenario, for example, set to [0, 2]. That is to say, when Perror > 1, or perform S1303. Among them, the preset elevation threshold range can be understood as the reasonable height range of the photovoltaic module from the ground.

[0071] S1303. When the reprojection error value is greater than the preset reprojection error threshold or the alternative height coordinate value is not within the preset elevation threshold range, determine that the reprojection error parameter does not meet the preset reprojection threshold condition.

[0072] Specifically, when the reprojection error value is greater than the preset reprojection error threshold, it can be considered that the target fault component in the target fault infrared photo and the de-duplicated fault component in the de-duplicated fault infrared photo are not the same component; when the alternative height coordinate value is not within the preset elevation threshold range, it can be considered that the spatial three-dimensional coordinates of the fault photovoltaic component located based on the two infrared photos are inaccurate and not within a reasonable range. As long as one of the two conditions is met, it can be determined that the reprojection error parameter does not meet the preset reprojection threshold condition.

[0073] S1304. When the reprojection error value is less than or equal to the preset reprojection error threshold and the alternative height coordinate value is within the preset elevation threshold range, determine that the reprojection error parameter meets the preset reprojection threshold condition.

[0074] Specifically, when the reprojection error value is less than or equal to the preset reprojection error threshold and the alternative height coordinate value is within the preset elevation threshold range, it can be considered that the target fault component in the target fault infrared photo and the de-duplicated fault component in the de-duplicated fault infrared photo are the same component. At the same time, the spatial three-dimensional coordinates of the fault photovoltaic component located based on the two infrared photos are relatively accurate and within a reasonable range. When both conditions are met, it can be determined that the reprojection error parameter meets the preset reprojection threshold condition.

[0075] Furthermore, when the reprojection error parameter meets the preset reprojection threshold condition, determine that the target fault component and the de-duplicated fault component are the same fault component, and determine the alternative three-dimensional coordinates as the three-dimensional coordinates of the target fault component.

[0076] In this embodiment, when the reprojection error parameter meets the preset reprojection threshold condition, it can be considered that the fault photovoltaic components corresponding to the target fault component in the target fault infrared photo and the de-duplicated fault component in the de-duplicated fault infrared photo are the same component. At the same time, the spatial three-dimensional coordinates of the fault photovoltaic component located based on the two infrared photos are relatively accurate and within a reasonable range. Therefore, the calculated alternative three-dimensional coordinates can be determined as the three-dimensional coordinates of the target fault component in the three-dimensional space.

[0077] S140. Determine the three-dimensional coordinates of the target fault component according to the shooting line of the target fault component and the plane of the target fault string.

[0078] Optionally, step 140 can be specifically implemented in the following way: determine the line-plane intersection coordinates of the shooting line of the target fault component and the plane of the target fault string, and determine the line-plane intersection coordinates as the three-dimensional coordinates of the target fault component.

[0079] Specifically, the spatial position where the target faulty component is located exists on the shooting line of the target faulty component. At the same time, the spatial position where the target faulty component is located exists in the plane of the target faulty string. Therefore, by calculating the line-plane intersection coordinates of the shooting line of the target faulty component and the plane of the target faulty string, the spatial position where the target faulty component is located can be determined.

[0080] In the embodiment of the present invention, by obtaining a target faulty infrared photo containing the target faulty component and a duplicate-removed faulty infrared photo associated with the target faulty infrared photo, and determining the duplicate-removed faulty component in the duplicate-removed faulty infrared photo whose fault type is the same as that of the target faulty component; according to the target shooting parameters corresponding to the target faulty infrared photo, the duplicate-removed shooting parameters corresponding to the duplicate-removed faulty infrared photo, the first pixel coordinates of the target faulty component, and the second pixel coordinates of the duplicate-removed faulty component, the reprojection error parameter is determined; when the reprojection error parameter does not meet the preset reprojection threshold condition, based on the target shooting parameters and the first pixel coordinates, the shooting line of the target faulty component and the plane of the target faulty string are determined; according to the shooting line of the target faulty component and the plane of the target faulty string, the three-dimensional coordinates of the target faulty component are determined, solving the problems of inaccurate positioning and high shooting requirements of existing faulty photovoltaic components, and achieving the effect of effectively removing duplicate faulty photovoltaic component information and quickly and accurately positioning faulty photovoltaic components.

[0081] Embodiment 2

[0082] Figure 3 It is a flowchart of a method for positioning faults of photovoltaic components provided in Embodiment 2 of the present invention. On the basis of the above embodiment, the method for positioning faults of the above photovoltaic components is further optimized. As Figure 3 shown, the method includes:

[0083] S210. Obtain a target faulty infrared photo containing the target faulty component and a duplicate-removed faulty infrared photo associated with the target faulty infrared photo, and determine the duplicate-removed faulty component in the duplicate-removed faulty infrared photo whose fault type is the same as that of the target faulty component.

[0084] S220. Determine the reprojection error parameter according to the target shooting parameters of the target faulty infrared photo, the duplicate-removed shooting parameters of the duplicate-removed faulty infrared photo, the first pixel coordinates of the target faulty component, and the second pixel coordinates of the duplicate-removed faulty component.

[0085] S230. When the reprojection error parameter does not meet the preset reprojection threshold condition, obtain all the infrared photos taken by the unmanned aerial vehicle within the preset positioning range, and establish a sparse three-dimensional point cloud within the preset positioning range according to each infrared photo and its corresponding shooting parameters.

[0086] Among them, the preset positioning range can be understood as the regional range where fault positioning of photovoltaic components needs to be carried out.

[0087] In practical applications, after the UAV takes infrared photos within a preset positioning range, based on these infrared photos and the shooting parameters when the UAV takes these infrared photos, a sparse three-dimensional point cloud within the preset positioning range can be established using a three-dimensional reconstruction model. For example, the SFM three-dimensional reconstruction technology can be used to establish the sparse three-dimensional point cloud.

[0088] Optionally, the reconstruction of the sparse three-dimensional point cloud can be specifically implemented in the following way:

[0089] Extract three-dimensional reconstruction pixel points from each infrared photo, and perform three-dimensional reconstruction based on each three-dimensional reconstruction pixel point and its corresponding shooting parameters to obtain the three-dimensional point cloud data corresponding to each three-dimensional reconstruction pixel point, forming a sparse three-dimensional point cloud within the preset positioning range.

[0090] Specifically, a certain number of three-dimensional reconstruction pixel points can be determined in each infrared photo, and three-dimensional reconstruction can be performed in combination with the shooting parameters corresponding to the infrared photo where each three-dimensional reconstruction pixel point is located, forming a sparse three-dimensional point cloud within the preset positioning range. In the sparse three-dimensional point cloud, each three-dimensional point cloud has corresponding three-dimensional reconstruction pixel points in at least one infrared photo.

[0091] Furthermore, when establishing a sparse three-dimensional point cloud within the preset positioning range based on each infrared photo and its corresponding shooting parameters, it can also include: correcting the shooting parameters corresponding to each infrared photo.

[0092] In this embodiment, when performing three-dimensional reconstruction, the three-dimensional reconstruction model can also correct the shooting parameters of each infrared photo and output the corrected shooting parameters.

[0093] S240. Determine the shooting line of the target faulty component according to the target shooting parameters and the first pixel coordinates.

[0094] Exemplarily, the first pixel coordinates can be denoted as (u0, v0), and the target shooting parameters corresponding to the target faulty infrared photo can be denoted as the camera three-dimensional coordinates (X a , Y a , Z a ), the camera attitude parameters and the camera internal parameters (f, c x , c y ). Assuming that the three-dimensional coordinates of the target faulty component are (X, Y, Z), then the shooting line of the target faulty component can be expressed by the following expression:

[0095]

[0096]

[0097] In the above formula, a 11 , a 12,a 13 ,a 21 ,a 22 ,a 23 ,a 31 ,a 32 ,a 33 It can be regarded as a known value and can be calculated using the camera pose parameters in the target shooting parameters, satisfying the following relational expressions:

[0098]

[0099] S250. Divide the target fault string area where the target fault component is located from the target fault infrared photo, and combine the sparse three-dimensional point cloud to determine the target fault string plane.

[0100] In practical applications, generally multiple photovoltaic components are arranged in an orderly manner to form a photovoltaic string. In this embodiment, the first pixel coordinate represents the position where the target fault component is located, then the string area where the first pixel coordinate is located can be determined as the target fault string area. The target fault string plane can be understood as the plane of the string area where the target fault component is located fitted according to the sparse three-dimensional point cloud.

[0101] Specifically, the string area in the target fault infrared photo can be divided, the string area where the first pixel coordinate is located can be determined as the target fault string area, and then according to the sparse three-dimensional point cloud, the spatial plane of the target fault string area is fitted as the target fault string plane.

[0102] Optionally, S250 can be specifically implemented through the following steps:

[0103] S2501. Divide at least one photovoltaic string area according to the pixel values of each pixel point in the target fault infrared photo.

[0104] Furthermore, S2501 can be specifically implemented in the following way: perform pixel threshold segmentation on the target fault infrared photo to determine the string information area; divide the string information area according to the regional connectivity of each pixel point in the string information area to obtain at least one photovoltaic string area.

[0105] In this embodiment, the temperature information of each pixel point in the infrared photo can be extracted according to the RGB information of the target fault infrared photo, perform OTSU threshold segmentation on the temperature values, and divide the area containing the photovoltaic string, that is, the string information area. Perform 8-connected region tracking on the pixel points in the extracted string information area, and the string information area can be divided into at least one photovoltaic string area.

[0106] Figure 4a is the first schematic diagram of a photovoltaic component fault location method provided in the second embodiment of the present invention. AsFigure 4a As shown in the figure, multiple light-colored areas in the figure are respectively divided photovoltaic string areas. After obtaining multiple photovoltaic string areas, in order to distinguish different photovoltaic string areas, each photovoltaic string area can also be marked. Figure 4b This is the second schematic diagram of a photovoltaic module fault location method provided in the second embodiment of the present invention. As Figure 4b shown, different photovoltaic string areas can be marked as different pixel degrees.

[0107] S2502. Determine the photovoltaic string area where the first pixel coordinate is located as the target fault string area.

[0108] S2503. Determine the three-dimensional reconstruction pixel points included in the target fault string area as plane fitting pixel points, and determine the three-dimensional point cloud data corresponding to each plane fitting pixel point as plane fitting point cloud data.

[0109] Specifically, since there is a corresponding relationship between the sparse three-dimensional point cloud and the three-dimensional reconstruction pixel points, the three-dimensional reconstruction pixel points included in the target fault string area can be determined as plane fitting pixel points, and the three-dimensional point cloud data corresponding to each plane fitting pixel point is extracted from the sparse three-dimensional point cloud, and the extracted three-dimensional point cloud data is determined as plane fitting point cloud data.

[0110] S2504. Perform plane fitting on each plane fitting point cloud data to obtain the target fault string plane.

[0111] Specifically, a plane can be fitted according to each plane fitting point cloud data as the target fault string plane.

[0112] Before fitting the target fault string plane, it is also possible to check whether there is a target fault string plane of the target fault component in the target fault string area that has been fitted in the database. For example, there are two fault components in the same fault string area. When performing spatial positioning on the first fault component, the fault string plane of the fault string area has been fitted. Then, when performing spatial positioning on the second fault component, the fault string plane fitted during the spatial positioning of the first fault component can be directly used.

[0113] Exemplarily, the plane fitting pixel points included in the target fault string area can be denoted as (X i , Y i , Z i ), and the target fault string plane obtained by fitting can be expressed as a*X + b*Y + c*Z = 1, where a, b, and c are the coefficients of the plane equation, and a, b, and c can be determined by the following relational expressions:

[0114]

[0115]

[0116]

[0117] S260. Determine the three-dimensional coordinates of the target faulty component based on the line of the target faulty component and the plane of the target faulty string.

[0118] As can be seen from the above example, the coordinates of the intersection point of the line of the target faulty component and the plane of the target faulty string satisfy both the equation of the line of the target faulty component and the equation of the plane of the target faulty string. Therefore, the coordinates of the intersection point of the line and the plane can be solved according to the equation of the line of the target faulty component and the equation of the plane of the target faulty string, and the coordinates of the intersection point of the line and the plane are the spatial position where the target faulty component is located.

[0119] Figure 4c It is the third schematic diagram of a method for locating photovoltaic module faults provided in the second embodiment of the present invention. As Figure 4c shown, there is a target faulty component A1 in the target faulty infrared photo. The S point contains the target shooting parameter information when taking the target faulty infrared photo. According to the target shooting parameters contained in the S point and the first pixel coordinates A1 of the target faulty component, a line of the target faulty component can be determined. The triangular marked points in the figure are the plane fitting point cloud data, and the plane of the target faulty string can be fitted according to these plane fitting point cloud data. The intersection point of the line of the target faulty component and the plane of the target faulty string is the coordinate point of the intersection of the line and the plane, and the three-dimensional coordinates of the coordinate point of the intersection of the line and the plane are the three-dimensional coordinates of the target faulty component.

[0120] The technical solution of this embodiment, after removing duplicates from the faulty components in two infrared photos, obtains all the infrared photos taken by the drone within the preset positioning range, and establishes a sparse three-dimensional point cloud within the preset positioning range according to each infrared photo and its corresponding shooting parameters; determines the line of the target faulty component according to the target shooting parameters corresponding to the target faulty infrared photo and the first pixel coordinates of the target faulty component; divides the target faulty string area where the target faulty component is located from the target faulty infrared photo, and combines the sparse three-dimensional point cloud to determine the plane of the target faulty string; determines the three-dimensional coordinates of the target faulty component according to the line of the target faulty component and the plane of the target faulty string. This embodiment solves the problems of inaccurate positioning and high shooting requirements of existing faulty photovoltaic modules, and realizes the effect of quickly and accurately locating faulty photovoltaic modules while effectively removing duplicate faulty photovoltaic module information.

[0121] Embodiment Three

[0122] Figure 5 It is a schematic structural diagram of a device for locating photovoltaic module faults provided in the third embodiment of the present invention. As Figure 5 shown, the device includes:

[0123] The duplicate removal component combination determination module 310 is configured to obtain a target fault infrared photo including a target fault component, and a duplicate removal fault infrared photo associated with the target fault infrared photo, and determine a duplicate removal fault component in the duplicate removal fault infrared photo whose fault type is the same as that of the target fault component.

[0124] The reprojection error parameter determination module 320 is configured to determine a reprojection error parameter according to the target shooting parameters corresponding to the target fault infrared photo, the duplicate removal shooting parameters corresponding to the duplicate removal fault infrared photo, the first pixel coordinates of the target fault component, and the second pixel coordinates of the duplicate removal fault component.

[0125] The shooting line and string plane determination module 330 is configured to, when the reprojection error parameter does not meet the preset reprojection threshold condition, determine a target fault component shooting line and a target fault string plane based on the target shooting parameters and the first pixel coordinates.

[0126] The target three-dimensional coordinate determination module 340 is configured to determine the three-dimensional coordinates of the target fault component according to the target fault component shooting line and the target fault string plane.

[0127] In an embodiment of the present invention, by obtaining a target fault infrared photo including a target fault component, and a duplicate removal fault infrared photo associated with the target fault infrared photo, and determining a duplicate removal fault component in the duplicate removal fault infrared photo whose fault type is the same as that of the target fault component; according to the target shooting parameters corresponding to the target fault infrared photo, the duplicate removal shooting parameters corresponding to the duplicate removal fault infrared photo, the first pixel coordinates of the target fault component, and the second pixel coordinates of the duplicate removal fault component, determining a reprojection error parameter; when the reprojection error parameter does not meet the preset reprojection threshold condition, determining a target fault component shooting line and a target fault string plane based on the target shooting parameters and the first pixel coordinates; and determining the three-dimensional coordinates of the target fault component according to the target fault component shooting line and the target fault string plane, the problems of inaccurate positioning of existing faulty photovoltaic components and high shooting requirements are solved, and the effect of effectively removing duplicate faulty photovoltaic component information and quickly and accurately positioning faulty photovoltaic components is achieved.

[0128] Optionally, the reprojection error parameter determination module 320 includes:

[0129] The coordinate expression determination unit is configured to determine a target coordinate expression satisfied by the three-dimensional coordinates of the target fault component according to the target shooting parameters corresponding to the target fault infrared photo and the first pixel coordinates of the target fault component; and determine a duplicate removal coordinate expression satisfied by the three-dimensional coordinates of the duplicate removal fault component according to the duplicate removal shooting parameters corresponding to the duplicate removal fault infrared photo and the second pixel coordinates of the duplicate removal fault component.

[0130] An alternative three-dimensional coordinate determination unit for determining alternative three-dimensional coordinates that satisfy the target coordinate expression and the duplicate-removing coordinate expression;

[0131] A projection pixel coordinate determination unit for determining target projection pixel coordinates according to the alternative three-dimensional coordinates and the target shooting parameters; and determining duplicate-removing projection pixel coordinates according to the alternative three-dimensional coordinates and the duplicate-removing shooting parameters;

[0132] A reprojection error parameter determination unit for determining an alternative height coordinate value in the alternative three-dimensional coordinates, and determining the target projection pixel coordinates, the duplicate-removing projection pixel coordinates, and the alternative height coordinate value as reprojection error parameters.

[0133] Optionally, the step of determining that the reprojection error parameter does not satisfy the preset reprojection threshold condition includes:

[0134] Determining a reprojection error value according to the first pixel coordinate, the second pixel coordinate, the target projection pixel coordinate, and the duplicate-removing projection pixel coordinate;

[0135] When the reprojection error value is greater than a preset reprojection error threshold, or the alternative height coordinate value is not within a preset elevation threshold range, it is determined that the reprojection error parameter does not satisfy the preset reprojection threshold condition.

[0136] Optionally, the device further includes a pixel point duplicate-removing positioning module for:

[0137] When the reprojection error parameter satisfies the preset reprojection threshold condition, determining that the target faulty component and the duplicate-removing faulty component are the same faulty component, and determining the alternative three-dimensional coordinates as the three-dimensional coordinates of the target faulty component.

[0138] Optionally, the device further includes a three-dimensional point cloud reconstruction module for:

[0139] Before determining the target faulty component shooting line and the target faulty string plane, acquiring all infrared photos taken by the unmanned aerial vehicle within a preset positioning range, and establishing a sparse three-dimensional point cloud within the preset positioning range according to each of the infrared photos and their corresponding shooting parameters.

[0140] Optionally, the shooting line and string plane determination module 330 includes:

[0141] A faulty component shooting line determination unit for determining a target faulty component shooting line according to the target shooting parameters and the first pixel coordinate when the reprojection error parameter does not satisfy the preset reprojection threshold condition;

[0142] A fault string plane determination unit, configured to divide a target fault string area where the target fault component is located from the target fault infrared photo, and determine a target fault string plane in combination with the sparse three-dimensional point cloud.

[0143] Optionally, the fault string plane determination unit includes:

[0144] A photovoltaic string area division sub-unit, configured to divide at least one photovoltaic string area according to the pixel values of each pixel point in the target fault infrared photo;

[0145] A target fault string area determination sub-unit, configured to determine the photovoltaic string area where the first pixel coordinate is located as the target fault string area;

[0146] A fitting pixel point data determination sub-unit, configured to determine the three-dimensional reconstructed pixel points included in the target fault string area as plane fitting pixel points, and determine the three-dimensional point cloud data corresponding to each of the plane fitting pixel points as plane fitting point cloud data;

[0147] A fault string plane determination sub-unit, configured to perform plane fitting on each of the plane fitting point cloud data to obtain a target fault string plane.

[0148] Optionally, the photovoltaic string area division sub-unit is specifically configured to:

[0149] Perform pixel threshold segmentation on the target fault infrared photo to determine a string information area;

[0150] Divide the string information area according to the regional connectivity of each pixel point in the string information area to obtain at least one photovoltaic string area.

[0151] The photovoltaic module fault location device provided by the embodiments of the present invention can execute the photovoltaic module fault location method provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.

[0152] Embodiment 4

[0153] Figure 6The structural schematic diagram of the electronic device 10 that can be used to implement the embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0154] As Figure 6 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. The memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0155] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0156] The processor 11 can be various general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the photovoltaic component fault location method.

[0157] In some embodiments, the photovoltaic module fault location method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the photovoltaic module fault location method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the photovoltaic module fault location method by any other suitable means (e.g., by means of firmware).

[0158] The various embodiments of the systems and techniques described above in this document may be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), systems on a chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that may be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a special-purpose or general-purpose programmable processor that receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0159] The computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs may be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0160] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0161] To provide for interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide for interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0162] The systems and techniques described herein can be implemented in a computing system that includes backend components (such as, for example, a data server), or a computing system that includes middleware components (such as, for example, an application server), or a computing system that includes frontend components (such as, for example, a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (such as, for example, a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0163] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0164] It should be understood that various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is imposed herein.

[0165] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for fault location of a photovoltaic module, characterized in that, Including: Obtain a target fault infrared photo including a target fault component, as well as a duplicate-removed fault infrared photo associated with the target fault infrared photo, and determine a duplicate-removed fault component in the duplicate-removed fault infrared photo with the same fault type as the target fault component, where the duplicate-removed fault infrared photo is other infrared photos taken near the geographical location where the target fault infrared photo is taken; Determine a reprojection error parameter according to the target shooting parameters corresponding to the target fault infrared photo, the duplicate-removed shooting parameters corresponding to the duplicate-removed fault infrared photo, the first pixel coordinates of the target fault component, and the second pixel coordinates of the duplicate-removed fault component; When the reprojection error parameter does not meet the preset reprojection threshold condition, based on the target shooting parameters and the first pixel coordinates, determine a target fault component shooting line and a target fault string plane, where the target fault component shooting line is a line segment composed of possible position points of the target fault component in space, and the target fault string plane is the plane of the string area where the target fault component is located; Determine the three-dimensional coordinates of the target fault component according to the target fault component shooting line and the target fault string plane.

2. The photovoltaic module fault location method according to claim 1, wherein The step of determining a reprojection error parameter according to the target shooting parameters corresponding to the target fault infrared photo, the duplicate-removed shooting parameters corresponding to the duplicate-removed fault infrared photo, the first pixel coordinates of the target fault component, and the second pixel coordinates of the duplicate-removed fault component includes: According to the target shooting parameters corresponding to the target fault infrared photo and the first pixel coordinates of the target fault component, determine a target coordinate expression satisfied by the three-dimensional coordinates of the target fault component; according to the duplicate-removed shooting parameters corresponding to the duplicate-removed fault infrared photo and the second pixel coordinates of the duplicate-removed fault component, determine a duplicate-removed coordinate expression satisfied by the three-dimensional coordinates of the duplicate-removed fault component; Determine alternative three-dimensional coordinates that satisfy the target coordinate expression and the duplicate-removed coordinate expression; According to the alternative three-dimensional coordinates and the target shooting parameters, determine target projected pixel coordinates; according to the alternative three-dimensional coordinates and the duplicate-removed shooting parameters, determine duplicate-removed projected pixel coordinates; Determine an alternative height coordinate value in the alternative three-dimensional coordinates, and determine the target projected pixel coordinates, the duplicate-removed projected pixel coordinates, and the alternative height coordinate value as the reprojection error parameter.

3. The photovoltaic module fault location method according to claim 2, wherein, The step of determining that the reprojection error parameter does not meet the preset reprojection threshold condition includes: Determine a reprojection error value according to the first pixel coordinates, the second pixel coordinates, the target projected pixel coordinates, and the duplicate-removed projected pixel coordinates; When the reprojection error value is greater than the preset reprojection error threshold, or the alternative height coordinate value is not within the preset elevation threshold range, determine that the reprojection error parameter does not meet the preset reprojection threshold condition.

4. The photovoltaic module fault location method according to claim 2, characterized in that After determining the reprojection error parameter, it further includes: When the reprojection error parameter meets the preset reprojection threshold condition, determine that the target fault component and the duplicate-removed fault component are the same fault component, and determine the alternative three-dimensional coordinates as the three-dimensional coordinates of the target fault component.

5. The photovoltaic module fault location method according to claim 1, wherein Before determining the shooting line of the target faulty component and the plane of the target faulty string, it further includes: Obtain all infrared photos taken by the drone within the preset positioning range, and establish a sparse three-dimensional point cloud within the preset positioning range according to each of the infrared photos and their corresponding shooting parameters.

6. The photovoltaic module fault location method according to claim 5, characterized in that, The determining the shooting line of the target faulty component and the plane of the target faulty string according to the target shooting parameters and the first pixel coordinates includes: Determine the shooting line of the target faulty component according to the target shooting parameters and the first pixel coordinates; Divide the target faulty string area where the target faulty component is located from the target faulty infrared photo, and combine with the sparse three-dimensional point cloud to determine the plane of the target faulty string.

7. The photovoltaic module fault location method according to claim 6, wherein, The dividing the target faulty string area where the target faulty component is located from the target faulty infrared photo and combining with the sparse three-dimensional point cloud to determine the plane of the target faulty string includes: Divide at least one photovoltaic string area according to the pixel values of each pixel point in the target faulty infrared photo; Determine the photovoltaic string area where the first pixel coordinate is located as the target faulty string area; Determine the three-dimensional reconstruction pixel points included in the target faulty string area as plane fitting pixel points, and determine the three-dimensional point cloud data corresponding to each of the plane fitting pixel points as plane fitting point cloud data; Perform plane fitting on each of the plane fitting point cloud data to obtain the plane of the target faulty string.

8. The photovoltaic module fault location method according to claim 7, wherein, The dividing at least one photovoltaic string area according to the pixel values of each pixel point in the target faulty infrared photo includes: Perform pixel threshold segmentation on the target faulty infrared photo to determine the string information area; Divide the string information area according to the regional connectivity of each pixel point in the string information area to obtain at least one photovoltaic string area.

9. A photovoltaic module fault location device, characterized in that, It includes: A duplicate removal component combination determination module, configured to obtain a target faulty infrared photo including a target faulty component, and a duplicate removal faulty infrared photo associated with the target faulty infrared photo, and determine a duplicate removal faulty component in the duplicate removal faulty infrared photo whose fault type is the same as that of the target faulty component, where the duplicate removal faulty infrared photo is other infrared photos taken near the geographical location where the target faulty infrared photo is taken; A reprojection error parameter determination module, configured to determine a reprojection error parameter according to the target shooting parameters corresponding to the target faulty infrared photo, the duplicate removal shooting parameters corresponding to the duplicate removal faulty infrared photo, the first pixel coordinates of the target faulty component, and the second pixel coordinates of the duplicate removal faulty component; A shooting line and string plane determination module, configured to determine the shooting line of the target faulty component and the plane of the target faulty string based on the target shooting parameters and the first pixel coordinates when the reprojection error parameter does not meet the preset reprojection threshold condition, where the shooting line of the target faulty component is a line segment composed of possible position points of the target faulty component in space, and the plane of the target faulty string is the plane of the string area where the target faulty component is located; A target three-dimensional coordinate determination module, configured to determine the three-dimensional coordinates of a target faulty component according to the line for photographing the target faulty component and the plane of the target faulty string.

10. An electronic device, characterized in that, The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to execute the photovoltaic component fault location method according to any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the photovoltaic component fault location method according to any one of claims 1-8 is implemented.

Images