Component fault detection method, device, equipment and storage medium
By using drones to collect infrared and visible light images and combining them with detection models, photovoltaic module faults can be automatically identified, solving the problems of low efficiency and high cost of traditional manual inspections and achieving efficient and safe fault detection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SUNGROW SMART MAINTENANCE TECH CO LTD
- Filing Date
- 2024-12-26
- Publication Date
- 2026-06-26
Smart Images
Figure CN122289112A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of photovoltaic power plant technology, and in particular to a method, apparatus, equipment and storage medium for detecting component faults. Background Technology
[0002] In recent years, energy and environmental issues have constrained socio-economic development, and the emergence of photovoltaic (PV) power generation has brought an opportunity for the large-scale use of new energy sources. However, with the continuous growth of PV installed capacity, the problem of PV module failures has become increasingly prominent. This not only affects the power generation of PV power plants and increases their operation and maintenance costs, but also poses certain safety hazards. Traditional PV power plant operation and maintenance methods mostly rely on manual inspections, depending primarily on the electrical characteristics of the PV power plant equipment. However, the electrical characteristics of PV power plant equipment are greatly affected by environmental factors such as weather, making manual inspections inaccurate in detecting PV faults. Furthermore, manual inspections are limited by factors such as the terrain where PV modules are installed, resulting in low inspection efficiency, high operation and maintenance costs, and significant safety hazards. Therefore, how to automatically and accurately detect PV module faults has become an urgent problem to be solved. Summary of the Invention
[0003] The main objective of this application is to provide a method, apparatus, device, and storage medium for detecting component faults, aiming to solve the technical problem of how to automatically and accurately detect faults in photovoltaic strings.
[0004] To achieve the above objectives, this application provides a component fault detection method, which includes the following steps:
[0005] Inspection images of each photovoltaic string are collected according to the flight route corresponding to the photovoltaic power station. The inspection images include initial infrared images and initial visible light images.
[0006] Component fault detection is performed on the initial infrared image and the initial visible light image respectively to obtain infrared fault detection results and visible light fault detection results;
[0007] The target fault type is determined based on the infrared fault detection results and the visible light fault detection results.
[0008] Optionally, the step of collecting inspection images of each photovoltaic string according to the flight path corresponding to the photovoltaic power station, wherein the inspection images include initial infrared images and initial visible light images, specifically includes:
[0009] The panoramic map corresponding to the photovoltaic power station is segmented into strings to obtain multiple photovoltaic strings;
[0010] The center position of each photovoltaic string is determined, and the path is planned for each center position according to the optimal path planning algorithm to obtain the waypoint route.
[0011] The flight parameters for each waypoint are determined based on the parameters of the photovoltaic power station and the string arrangement parameters.
[0012] Based on the flight parameters, inspection images of each photovoltaic string are collected along the waypoint route. The inspection images include initial infrared images and initial visible light images.
[0013] Optionally, the step of performing component fault detection on the initial infrared image and the initial visible light image respectively to obtain infrared fault detection results and visible light fault detection results specifically includes:
[0014] Extract the target infrared image from the initial infrared image, and extract the target visible light image from the initial visible light image;
[0015] The target infrared image is input into the infrared fault detection model to obtain the infrared fault detection result;
[0016] The target visible light image is input into the visible light fault detection model to obtain the visible light fault detection result.
[0017] Optionally, the steps of extracting the target infrared image from the initial infrared image and extracting the target visible light image from the initial visible light image specifically include:
[0018] The initial infrared image and the initial visible light image are segmented into strings using a string segmentation algorithm to obtain the infrared strings in the initial infrared image and the visible light strings in the initial visible light image.
[0019] The target infrared image is extracted from the initial infrared image based on the position of the infrared string corresponding to the string, and the target visible light image is extracted from the initial visible light image based on the position of the visible light string corresponding to the string.
[0020] Optionally, the step of determining the target fault type based on the infrared fault detection result and the visible light fault detection result specifically includes:
[0021] Determine the infrared fault type and the corresponding initial infrared fault confidence level in the infrared fault detection results;
[0022] Determine the visible light fault type and the corresponding initial visible light fault confidence level in the visible light detection results;
[0023] The infrared fault type and the visible light fault type are fused based on the initial infrared fault confidence level and the initial visible light fault confidence level to obtain the target fault type.
[0024] Optionally, the step of fusing the infrared fault type and the visible light fault type based on the initial infrared fault confidence and the initial visible light fault confidence to obtain the target fault type specifically includes:
[0025] Identify multiple identical initial fault types among the infrared fault types and the visible light fault types;
[0026] For each initial fault type, the target infrared fault confidence level corresponding to the initial fault type is selected from the initial infrared fault confidence level, and the target visible light fault confidence level corresponding to the initial fault type is selected from the initial visible light fault confidence level.
[0027] The target confidence level corresponding to the initial fault type is calculated based on the target infrared fault confidence level, the infrared fault weight corresponding to the initial fault type, the target visible light fault confidence level, and the visible light fault weight corresponding to the initial fault type.
[0028] When the target confidence level is greater than a preset threshold, the initial fault type is taken as the target fault type.
[0029] Optionally, the step of determining the target fault type based on the infrared fault detection result and the visible light fault detection result specifically includes:
[0030] The component fault location is selected from the infrared fault detection results and / or the visible light detection results based on the target fault type;
[0031] The infrared image and / or the visible light image of the target are input into the component segmentation model to obtain multiple components;
[0032] The plurality of components are numbered, and the target component corresponding to the fault location of the component is determined based on the number.
[0033] Furthermore, to achieve the above objectives, this application also provides a component fault detection device, the component fault detection device comprising:
[0034] The image acquisition module is used to acquire inspection images of each photovoltaic string according to the flight route corresponding to the photovoltaic power station. The inspection images include initial infrared images and initial visible light images.
[0035] The fault detection module is used to perform component fault detection on the initial infrared image and the initial visible light image respectively, and obtain infrared fault detection results and visible light fault detection results;
[0036] The fault type determination module is used to determine the target fault type based on the infrared fault detection results and the visible light fault detection results.
[0037] In addition, to achieve the above objectives, this application also proposes a component fault detection device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the component fault detection method as described above.
[0038] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the component fault detection method described above.
[0039] This application collects inspection images of each photovoltaic string based on the flight path corresponding to the photovoltaic power station. These inspection images include initial infrared images and initial visible light images. Then, component fault detection is performed on both the initial infrared and initial visible light images to obtain infrared fault detection results and visible light fault detection results. Finally, the target fault type is determined based on these results. This application first collects clear and complete inspection images of each photovoltaic string based on the flight path corresponding to the photovoltaic power station. Then, component fault detection is performed on both the initial infrared and initial visible light images. Finally, the target fault type is determined based on the infrared and visible light fault detection results. This approach enables automatic fault detection of photovoltaic modules based on the initial infrared and initial visible light images and improves the accuracy of component fault detection and identification. Attached Figure Description
[0040] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0041] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0042] Figure 1 This is a flowchart illustrating the first embodiment of the component fault detection method of this application;
[0043] Figure 2 This is a schematic diagram of the initial infrared image and the initial visible light image of an embodiment of the component fault detection method of this application;
[0044] Figure 3 This is a schematic diagram illustrating the segmentation of panoramic images according to an embodiment of the component fault detection method of this application.
[0045] Figure 4 This is a flowchart illustrating the second embodiment of the component fault detection method of this application;
[0046] Figure 5 This is a schematic diagram of a target infrared image and a target visible light image, representing an embodiment of the component fault detection method of this application.
[0047] Figure 6 This is a flowchart illustrating the third embodiment of the component fault detection method of this application;
[0048] Figure 7 This is a schematic diagram of the component fault location in a target infrared image and the component fault location in a target visible light image, according to an embodiment of the component fault detection method of this application.
[0049] Figure 8 This is a schematic diagram of a target visible light image after component segmentation, which is an embodiment of the component fault detection method of this application.
[0050] Figure 9 This is a structural block diagram of the first embodiment of the component fault detection device of this application;
[0051] Figure 10 This is a schematic diagram of the structure of a component fault detection device for the hardware operating environment involved in the embodiments of this application.
[0052] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0053] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.
[0054] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.
[0055] It should be noted that the executing entity of this application can be a computing service device with data processing, network communication, and program execution functions, such as a computer, or an electronic device or component fault detection device capable of performing the above functions. The following description uses a component fault detection device as an example to illustrate this embodiment and the subsequent embodiments.
[0056] Based on this, embodiments of this application provide a component fault detection method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the component fault detection method of this application.
[0057] In this embodiment, the component fault detection method includes the following steps:
[0058] Step S10: Collect inspection images of each photovoltaic string according to the flight route corresponding to the photovoltaic power station. The inspection images include initial infrared images and initial visible light images.
[0059] Understandably, waypoints can be individual photovoltaic strings within a photovoltaic power station, and waypoint routes refer to the routes taken by drones to collect images on the photovoltaic power station. The center points of all photovoltaic strings can be connected to form waypoint routes, and drones can collect inspection images of each photovoltaic string through these waypoint routes.
[0060] It should be understood that the inspection images may include initial infrared images and initial visible light images. Specifically, the initial infrared image can be acquired by a drone equipped with an infrared camera, and the initial visible light image can be acquired by a drone equipped with a visible light camera. Because infrared and visible light cameras differ in camera angle, zoom level, etc., the information contained in the acquired initial infrared and initial visible light images will differ, such as the number of strings and environmental information. (Refer to...) Figure 2 , Figure 2 This is a schematic diagram of the initial infrared image and the initial visible light image of an embodiment of the component fault detection method of this application. (a) is the initial infrared image, which includes multiple photovoltaic strings, and (b) is the initial visible light image, which only includes strings corresponding to waypoints.
[0061] Furthermore, in order to accurately obtain the waypoint routes corresponding to the UAV, in this embodiment, step S10 includes: segmenting the panoramic map corresponding to the photovoltaic power station into multiple photovoltaic strings; determining the center position corresponding to each photovoltaic string, and performing path planning on each center position according to the optimal path planning algorithm to obtain waypoint routes; determining the flight parameters of each waypoint according to the photovoltaic power station parameters and string arrangement parameters; and collecting inspection images of each photovoltaic string on the waypoint routes based on the flight parameters, wherein the inspection images include initial infrared images and initial visible light images.
[0062] Understandably, this embodiment utilizes drones to inspect and collect modeling images of a photovoltaic power station according to a planned flight path and parameters. The flight path can be manually planned, and parameters may include zoom level, inspection altitude, etc. The modeling images may include all photovoltaic strings within the photovoltaic power station. All modeling images are imported into the intelligent mapping software to generate a panoramic image corresponding to the photovoltaic power station, and then modeling is performed on the panoramic image to obtain a panoramic map. The panoramic map is then input into a pre-set string segmentation algorithm model to segment the panoramic map into strings, obtaining multiple photovoltaic strings within the photovoltaic power station and the corresponding position coordinates of each photovoltaic string, such as... Figure 3 As shown, Figure 3 This is a schematic diagram illustrating the segmentation of panoramic images according to an embodiment of the component fault detection method of this application. Figure 3 It contains multiple photovoltaic strings.
[0063] It should be understood that, since the position coordinates of each photovoltaic string can be obtained during string segmentation, the center position of each photovoltaic string can be obtained, and the center positions of all photovoltaic strings can be connected to form waypoint routes according to the optimal path planning algorithm, with each photovoltaic string serving as a waypoint.
[0064] In practical implementation, due to significant differences in the string arrangement of photovoltaic power stations in different scenarios, using the same parameters for each waypoint may result in inspection images collected at some waypoints not meeting requirements. Therefore, when planning UAV inspection routes, it is necessary to consider both photovoltaic power station parameters and string arrangement parameters. Photovoltaic power station parameters may include terrain type and weather, while string arrangement parameters may include string tilt angle and string type. When setting flight parameters for each waypoint, these parameters can be determined based on the photovoltaic power station parameters and string arrangement parameters at that location. Flight parameters may include the UAV gimbal camera angle, zoom level, and inspection altitude. For example, if the terrain type is steep, the camera angle will be adjusted accordingly. By using the UAV to collect inspection images of each photovoltaic string along the waypoint route based on the flight parameters, complete and clear images of the entire string and module fault characteristics can be captured.
[0065] Step S20: Perform component fault detection on the initial infrared image and the initial visible light image respectively to obtain infrared fault detection results and visible light fault detection results.
[0066] Understandably, component fault detection can be performed on the initial infrared image using an infrared fault detection algorithm to obtain infrared fault detection results, which may include fault type, fault confidence, fault location, etc. Fault confidence refers to the probability that the component in the initial infrared image will produce this type of fault. Similarly, component fault detection can be performed on the initial visible light image using a visible light fault detection algorithm to obtain visible light fault detection results, which may also include fault type, fault confidence, fault location, etc.
[0067] Step S30: Determine the target fault type based on the infrared fault detection results and the visible light fault detection results.
[0068] It should be understood that, since the fault characteristics of different components differ significantly in the initial infrared and visible light images, the infrared fault detection results and the visible light fault detection results can be fused to obtain the target fault type corresponding to the component. Specifically, the confidence levels in the infrared fault detection results and the visible light fault detection results can be compared, and the fault type with the higher confidence level can be taken as the target fault type.
[0069] This embodiment collects inspection images of each photovoltaic string based on the flight path corresponding to the photovoltaic power station. These inspection images include initial infrared images and initial visible light images. Then, component fault detection is performed on both the initial infrared and initial visible light images to obtain infrared fault detection results and visible light fault detection results. Finally, the target fault type is determined based on these results. This embodiment first collects clear and complete inspection images of each photovoltaic string based on the flight path corresponding to the photovoltaic power station. Then, component fault detection is performed on both the initial infrared and initial visible light images. Finally, the target fault type is determined based on the infrared and visible light fault detection results. This method can automatically detect photovoltaic module faults based on the initial infrared and initial visible light images and improves the component fault detection and identification effect.
[0070] refer to Figure 4 , Figure 4 This is a flowchart illustrating the second embodiment of the component fault detection method of this application.
[0071] Based on the first embodiment described above, in this embodiment, step S20 includes:
[0072] Step S201: Extract the target infrared image from the initial infrared image and extract the target visible light image from the initial visible light image.
[0073] Understandably, a target infrared image can be extracted from an initial infrared image, and the target infrared image can contain a complete string. Similarly, a target visible light image can be extracted from an initial visible light image, and the target visible light image can also contain a complete string. The strings contained in the target infrared image and the target visible light image are the same string.
[0074] Furthermore, in order to effectively extract the initial infrared image and the initial visible light image, in this embodiment, step S201 includes: performing string segmentation on the initial infrared image and the initial visible light image respectively using a string segmentation algorithm to obtain infrared strings in the initial infrared image and visible light strings in the initial visible light image; extracting the target infrared image from the initial infrared image according to the string position corresponding to the infrared strings, and extracting the target visible light image from the initial visible light image according to the string position corresponding to the visible light strings.
[0075] It should be understood that this embodiment can perform string segmentation on the initial infrared image to determine all infrared strings in the initial infrared image, and can also perform string segmentation on the initial visible light image to determine all visible light strings in the initial visible light image.
[0076] Understandably, due to the waypoint flight method, each captured sequence should be located in the center area of the image. Therefore, the target infrared image can be extracted from the initial infrared image based on the position of the corresponding infrared sequence. Specifically, the target infrared sequence located at the center can be selected from all infrared sequences based on its position, and then the target infrared image containing this target infrared sequence can be extracted from the initial infrared image. Similarly, the target visible light image can be extracted from the initial visible light image based on the position of the corresponding visible light sequence. (See reference...) Figure 5 , Figure 5 This is a schematic diagram of a target infrared image and a target visible light image according to an embodiment of the component fault detection method of this application. (a) is a target infrared image, and (b) is a target visible light image. Both the target infrared image and the target visible light image can contain a string, and the string in the target infrared image and the string in the target visible light image are the same string.
[0077] Step S202: Input the target infrared image into the infrared fault detection model to obtain the infrared fault detection result.
[0078] It should be understood that the target infrared image corresponding to each waypoint can be input into the infrared fault detection model, and fault identification can be performed on each component in the string in the target infrared image to obtain the infrared fault detection result, which may include fault type, fault confidence, fault location, etc.
[0079] Step S203: Input the target visible light image into the visible light fault detection model to obtain the visible light fault detection result.
[0080] In a practical implementation, the target visible light image corresponding to each waypoint can be input into the visible light fault detection model. Fault identification can be performed on each component in the string of the target visible light image to obtain the visible light fault detection result, which may include fault type, fault confidence, fault location, etc.
[0081] This embodiment extracts a target infrared image from an initial infrared image and a target visible light image from an initial visible light image. The target infrared image is then input into an infrared fault detection model to obtain infrared fault detection results. Similarly, the target visible light image is input into a visible light fault detection model to obtain visible light fault detection results. By extracting the target infrared image from the initial infrared image and the target visible light image from the initial visible light image, this embodiment ensures that the target infrared image and the target visible light image contain the same string. By inputting both the target infrared image and the target visible light image into the infrared fault detection model and the visible light image into the visible light fault detection model, accurate infrared and visible light fault detection results are obtained.
[0082] refer to Figure 6 , Figure 6This is a flowchart illustrating the third embodiment of the component fault detection method of this application.
[0083] Based on the above embodiments, in this embodiment, step S30 includes:
[0084] Step S301: Determine the infrared fault type and the corresponding initial infrared fault confidence level in the infrared fault detection results.
[0085] It is understood that this embodiment can determine the infrared fault type in the infrared fault detection result and determine the initial infrared fault confidence level corresponding to the infrared fault type. The initial infrared fault confidence level refers to the probability that the component in the target infrared image will experience the infrared fault type.
[0086] Step S302: Determine the visible light fault type and the corresponding initial visible light fault confidence level in the visible light detection results.
[0087] It should be understood that this embodiment can determine the visible light fault type in the visible light fault detection result and determine the initial visible light fault confidence level corresponding to the visible light fault type. The initial visible light fault confidence level refers to the probability that the component in the target visible light image will experience the visible light fault type.
[0088] Step S303: Based on the initial infrared fault confidence and the initial visible light fault confidence, fuse the infrared fault type and the visible light fault type to obtain the target fault type.
[0089] Furthermore, in order to effectively fuse infrared fault types and visible light fault types, in this embodiment, step S303 includes: determining multiple identical initial fault types among the infrared fault types and the visible light fault types; for each initial fault type, selecting a target infrared fault confidence level corresponding to the initial fault type from the initial infrared fault confidence levels, and selecting a target visible light fault confidence level corresponding to the initial fault type from the initial visible light fault confidence levels; calculating a target confidence level corresponding to the initial fault type based on the target infrared fault confidence level, the infrared fault weight corresponding to the initial fault type, the target visible light fault confidence level, and the visible light fault weight corresponding to the initial fault type; when the target confidence level is greater than a preset threshold, using the initial fault type as the target fault type.
[0090] Understandably, different component failures exhibit significantly different failure characteristics in the target infrared and visible light images. We can identify common failure types within both infrared and visible light failure types as initial failure types. For each initial failure type, we can determine the corresponding target infrared and visible light failure confidence levels. We can also set the corresponding infrared and visible light failure weights. For example, if the initial failure type is a junction box failure, since this failure can only appear in infrared images and has no features in visible light images, the infrared failure weight can be set to 1, and the visible light failure weight to 0. If the initial failure type is component breakage, since component breakage is not obvious in infrared images but is obvious in visible light images, the infrared failure weight can be set to 0.2, and the visible light failure weight to 0.8.
[0091] It should be understood that the target confidence level can be calculated as: target infrared fault confidence level × infrared fault weight + target visible light fault confidence level + visible light fault weight. For each initial fault type, a corresponding preset threshold can be set. When the target confidence level corresponding to the initial fault type is greater than the preset threshold, it indicates that the component possesses that initial fault type, and this initial fault type is taken as the component's target fault type.
[0092] Furthermore, in order to locate the faulty component, in this embodiment, after step S30, the method further includes: selecting the component fault location from the infrared fault detection results and / or the visible light detection results according to the target fault type; inputting the target infrared image and / or the target visible light image into the component segmentation model to obtain multiple components; numbering the multiple components, and determining the target component corresponding to the component fault location according to the number.
[0093] Understandably, infrared fault results can include the location of component faults, and visible light fault results can also include the location of component faults, as shown in the reference. Figure 7 , Figure 7 This is a schematic diagram showing the component fault location in the target infrared image and the component fault location in the target visible light image, according to an embodiment of the component fault detection method of this application. The red box in (a) represents the component fault location in the target infrared image, and the red box in (b) represents the component fault location in the target visible light image.
[0094] It should be understood that target infrared images and / or target visible light images can be input into the component segmentation model to obtain multiple components, as referenced. Figure 8 , Figure 8 This is a schematic diagram of a target visible light image after component segmentation, as shown in one embodiment of the component fault detection method of this application. Figure 8As shown, the visible light image of the target contains 22 components, each of which is numbered as follows: Figure 8 The component numbers can be 1-1, 1-2, 1-3, 1-4, etc., and are determined. Figure 7 The fault number corresponding to the fault location of the component in the diagram indicates that the component at that fault number is the target component. Figure 8 The components numbered 1-6 are the target components, where 1 represents the first row and 6 represents the sixth component from the left to the right.
[0095] In the specific implementation, after obtaining the position of the faulty component in the string, the faulty component can be further located on the panoramic map. Based on the segmentation results of the string components in the panoramic map, the waypoint routes, the location information of the inspection images, and the heading angle of the UAV, the faulty position of the component is mapped to obtain the position information of the faulty component in the panoramic map.
[0096] This embodiment determines the infrared fault type and corresponding initial infrared fault confidence level in the infrared fault detection results, then determines the visible light fault type and corresponding initial visible light fault confidence level in the visible light detection results, and then fuses the infrared fault type and the visible light fault type based on the initial infrared fault confidence level and the initial visible light fault confidence level to obtain the target fault type. This embodiment can combine infrared images and visible light images to jointly detect faults in photovoltaic modules and can improve the module fault detection and identification effect.
[0097] Reference Figure 9 , Figure 9 This is a structural block diagram of the first embodiment of the component fault detection device of this application.
[0098] like Figure 9 As shown, the component fault detection device proposed in this application includes:
[0099] Image acquisition module 10 is used to acquire inspection images of each photovoltaic string according to the flight route corresponding to the photovoltaic power station. The inspection images include initial infrared images and initial visible light images.
[0100] Fault detection module 20 is used to perform component fault detection on the initial infrared image and the initial visible light image respectively, and obtain infrared fault detection results and visible light fault detection results;
[0101] The fault type determination module 30 is used to determine the target fault type based on the infrared fault detection result and the visible light fault detection result.
[0102] This embodiment collects inspection images of each photovoltaic string based on the flight path corresponding to the photovoltaic power station. These inspection images include initial infrared images and initial visible light images. Then, component fault detection is performed on both the initial infrared and initial visible light images to obtain infrared fault detection results and visible light fault detection results. Finally, the target fault type is determined based on these results. This embodiment first collects clear and complete inspection images of each photovoltaic string based on the flight path corresponding to the photovoltaic power station. Then, component fault detection is performed on both the initial infrared and initial visible light images. Finally, the target fault type is determined based on the infrared and visible light fault detection results. This method can automatically detect photovoltaic module faults based on the initial infrared and initial visible light images and improves the component fault detection and identification effect.
[0103] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this application. In practical applications, those skilled in the art can select some or all of it to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.
[0104] In addition, for technical details not described in detail in this embodiment, please refer to the component fault detection method provided in any embodiment of this application, which will not be repeated here.
[0105] Based on the first embodiment of the component fault detection device described in this application, a second embodiment of the component fault detection device of this application is proposed.
[0106] In this embodiment, the image acquisition module 10 is further used to segment the panoramic map corresponding to the photovoltaic power station into multiple photovoltaic strings; determine the center position corresponding to each photovoltaic string, and perform path planning on each center position according to the optimal path planning algorithm to obtain waypoint routes; determine the flight parameters of each waypoint according to the photovoltaic power station parameters and string arrangement parameters; and acquire inspection images of each photovoltaic string on the waypoint routes based on the flight parameters, wherein the inspection images include initial infrared images and initial visible light images.
[0107] Furthermore, the fault detection module 20 is also used to extract a target infrared image from the initial infrared image and extract a target visible light image from the initial visible light image; input the target infrared image into the infrared fault detection model to obtain an infrared fault detection result; and input the target visible light image into the visible light fault detection model to obtain a visible light fault detection result.
[0108] Furthermore, the fault detection module 20 is also used to perform string segmentation on the initial infrared image and the initial visible light image respectively using a string segmentation algorithm to obtain infrared strings in the initial infrared image and visible light strings in the initial visible light image; to extract the target infrared image from the initial infrared image according to the string position corresponding to the infrared strings, and to extract the target visible light image from the initial visible light image according to the string position corresponding to the visible light strings.
[0109] Furthermore, the fault type determination module 30 is also used to determine the infrared fault type and the corresponding initial infrared fault confidence level in the infrared fault detection result; determine the visible light fault type and the corresponding initial visible light fault confidence level in the visible light detection result; and fuse the infrared fault type and the visible light fault type according to the initial infrared fault confidence level and the initial visible light fault confidence level to obtain the target fault type.
[0110] Furthermore, the fault type determination module 30 is also used to determine multiple identical initial fault types among the infrared fault types and the visible light fault types; for each initial fault type, a target infrared fault confidence level corresponding to the initial fault type is selected from the initial infrared fault confidence levels, and a target visible light fault confidence level corresponding to the initial fault type is selected from the initial visible light fault confidence levels; a target confidence level corresponding to the initial fault type is calculated based on the target infrared fault confidence level, the infrared fault weight corresponding to the initial fault type, the target visible light fault confidence level, and the visible light fault weight corresponding to the initial fault type; when the target confidence level is greater than a preset threshold, the initial fault type is taken as the target fault type.
[0111] Furthermore, the fault detection module 20 is also used to select the component fault location from the infrared fault detection results and / or the visible light detection results according to the target fault type; input the target infrared image and / or the target visible light image into the component segmentation model to obtain multiple components; number the multiple components, and determine the target component corresponding to the component fault location according to the number.
[0112] Other embodiments or specific implementations of the component fault detection device of this application can be found in the above-described method embodiments, and will not be repeated here.
[0113] This application provides a component fault detection device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the component fault detection method in Embodiment 1 above.
[0114] The following is for reference. Figure 10 The diagram illustrates a structural schematic suitable for implementing a component fault detection device according to embodiments of this application. The component fault detection device in embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 10 The component fault detection device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.
[0115] like Figure 10 As shown, the component fault detection device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the component fault detection device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the component fault detection device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows component fault detection devices with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.
[0116] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.
[0117] The component fault detection device provided in this application, employing the component fault detection method in the above embodiments, can solve the technical problem of how to automatically and accurately detect faults in photovoltaic modules. Compared with the prior art, the beneficial effects of the component fault detection device provided in this application are the same as those of the component fault detection method provided in the above embodiments, and other technical features of this component fault detection device are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.
[0118] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.
[0119] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
[0120] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the component fault detection method in the above embodiments.
[0121] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.
[0122] The aforementioned computer-readable storage medium may be included in the component failure detection device; or it may exist independently and not assembled into the component failure detection device.
[0123] The aforementioned computer-readable storage medium carries one or more programs. When the aforementioned one or more programs are executed by the component fault detection device, the component fault detection device causes the following: it collects inspection images of each photovoltaic string according to the flight path corresponding to the photovoltaic power station, the inspection images including initial infrared images and initial visible light images; it performs component fault detection on the initial infrared images and the initial visible light images respectively to obtain infrared fault detection results and visible light fault detection results; and it determines the target fault type based on the infrared fault detection results and the visible light fault detection results.
[0124] Computer program code for performing the operations of this application can be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, and C++, and conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0125] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0126] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.
[0127] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described component fault detection method, thereby solving the technical problem of how to automatically and accurately detect faults in photovoltaic modules. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the component fault detection method provided in the above embodiments, and will not be repeated here.
[0128] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.
Claims
1. A component fault detection method, characterized in that, The component fault detection method includes the following steps: Inspection images of each photovoltaic string are collected according to the flight route corresponding to the photovoltaic power station. The inspection images include initial infrared images and initial visible light images. Component fault detection is performed on the initial infrared image and the initial visible light image respectively to obtain infrared fault detection results and visible light fault detection results; The target fault type is determined based on the infrared fault detection results and the visible light fault detection results.
2. The component fault detection method as described in claim 1, characterized in that, The step of collecting inspection images of each photovoltaic string according to the flight path corresponding to the photovoltaic power station, wherein the inspection images include initial infrared images and initial visible light images, specifically includes: The panoramic map corresponding to the photovoltaic power station is segmented into strings to obtain multiple photovoltaic strings; The center position of each photovoltaic string is determined, and the path is planned for each center position according to the optimal path planning algorithm to obtain the waypoint route. The flight parameters for each waypoint are determined based on the parameters of the photovoltaic power station and the string arrangement parameters. Based on the flight parameters, inspection images of each photovoltaic string are collected along the waypoint route. The inspection images include initial infrared images and initial visible light images.
3. The component fault detection method as described in claim 1, characterized in that, The step of performing component fault detection on the initial infrared image and the initial visible light image respectively, and obtaining infrared fault detection results and visible light fault detection results, specifically includes: Extract the target infrared image from the initial infrared image, and extract the target visible light image from the initial visible light image; The target infrared image is input into the infrared fault detection model to obtain the infrared fault detection result; The target visible light image is input into the visible light fault detection model to obtain the visible light fault detection result.
4. The component fault detection method as described in claim 3, characterized in that, The steps of extracting the target infrared image from the initial infrared image and extracting the target visible light image from the initial visible light image specifically include: The initial infrared image and the initial visible light image are segmented into strings using a string segmentation algorithm to obtain the infrared strings in the initial infrared image and the visible light strings in the initial visible light image. The target infrared image is extracted from the initial infrared image based on the position of the infrared string corresponding to the string, and the target visible light image is extracted from the initial visible light image based on the position of the visible light string corresponding to the string.
5. The component fault detection method as described in claim 1, characterized in that, The step of determining the target fault type based on the infrared fault detection result and the visible light fault detection result specifically includes: Determine the infrared fault type and the corresponding initial infrared fault confidence level in the infrared fault detection results; Determine the visible light fault type and the corresponding initial visible light fault confidence level in the visible light detection results; The infrared fault type and the visible light fault type are fused based on the initial infrared fault confidence level and the initial visible light fault confidence level to obtain the target fault type.
6. The component fault detection method as described in claim 5, characterized in that, The step of fusing the infrared fault type and the visible light fault type based on the initial infrared fault confidence and the initial visible light fault confidence to obtain the target fault type specifically includes: Identify multiple identical initial fault types among the infrared fault types and the visible light fault types; For each initial fault type, the target infrared fault confidence level corresponding to the initial fault type is selected from the initial infrared fault confidence level, and the target visible light fault confidence level corresponding to the initial fault type is selected from the initial visible light fault confidence level. The target confidence level corresponding to the initial fault type is calculated based on the target infrared fault confidence level, the infrared fault weight corresponding to the initial fault type, the target visible light fault confidence level, and the visible light fault weight corresponding to the initial fault type. When the target confidence level is greater than a preset threshold, the initial fault type is taken as the target fault type.
7. The component fault detection method according to any one of claims 3 to 6, characterized in that, The step of determining the target fault type based on the infrared fault detection result and the visible light fault detection result specifically includes: The component fault location is selected from the infrared fault detection results and / or the visible light detection results based on the target fault type; The infrared image and / or the visible light image of the target are input into the component segmentation model to obtain multiple components; The plurality of components are numbered, and the target component corresponding to the fault location of the component is determined based on the number.
8. A component fault detection device, characterized in that, The component fault detection device includes: The image acquisition module is used to acquire inspection images of each photovoltaic string according to the flight route corresponding to the photovoltaic power station. The inspection images include initial infrared images and initial visible light images. The fault detection module is used to perform component fault detection on the initial infrared image and the initial visible light image respectively, and obtain infrared fault detection results and visible light fault detection results; The fault type determination module is used to determine the target fault type based on the infrared fault detection results and the visible light fault detection results.
9. A component fault detection device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the component failure detection method as described in any one of claims 1 to 7.
10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the component fault detection method as described in any one of claims 1 to 7.