IV&CV Fusion Diagnostic System

Abstract

The present invention discloses an IV&CV fusion diagnosis system, including: a fusion diagnosis server, an IV diagnosis server and an unmanned aerial vehicle, wherein the fusion diagnosis server is respectively connected to the IV diagnosis server and the unmanned aerial vehicle in communication, and is used to execute a diagnosis task in response to a diagnosis task request, including: triggering the IV diagnosis server to perform IV diagnosis analysis on the current data and voltage data of the photovoltaic components in the target photovoltaic power station, and receiving the IV diagnosis analysis results sent by the IV diagnosis server; controlling the flight of the unmanned aerial vehicle, performing image acquisition on the photovoltaic components in the target photovoltaic power station, obtaining the photovoltaic component images, and identifying the photovoltaic component images to obtain the CV diagnosis analysis results; matching and fusing the IV diagnosis analysis results and the CV diagnosis analysis results to obtain the final diagnosis analysis results. The IV&CV fusion diagnosis system of the embodiment of the present invention can improve the fault diagnosis rate of photovoltaic components by diagnosing photovoltaic components through IV and CV fusion.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an IV&CV fusion diagnosis system. Background Art

[0002] With the development of the photovoltaic industry, the inspection scheme for photovoltaic components has entered the era of inspection and diagnosis using a variety of equipment from manual inspection. Such as IV diagnostic instruments, drones, etc. The emergence of such equipment has improved the pain points of manual inspection in the photovoltaic inspection industry, which is time-consuming and labor-intensive, and has improved the efficiency of photovoltaic inspection to a certain extent and reduced the labor cost. At present, manual inspection, traditional manual drone inspection and IV diagnosis still have the following shortcomings: 1. It takes several days to inspect all components of a photovoltaic station of a certain scale, and it is necessary to judge whether the components are faulty based on experience. The equipment fault detection rate is low, which greatly affects the efficiency of the power station. 2. The IV diagnosis results can only locate the string. When the operation and maintenance personnel are eliminating the fault, they need to manually identify one by one, analyze and determine the specific faulty components, and cannot accurately locate the faulty components. 3. Traditional drone inspection can improve the pain points of manual inspection, but it will be affected by factors such as the number of pilots and the different technical levels of pilots, resulting in the inability of traditional drone inspection to form a standardized, normalized and procedural operation form. Summary of the invention

[0003] The present invention aims to solve one of the technical problems in the related art at least to a certain extent. To this end, the purpose of the present invention is to propose an IV&CV fusion diagnosis system to improve the fault diagnosis rate of photovoltaic modules.

[0004] To achieve the above-mentioned purpose, an embodiment of the present invention proposes an IV&CV fusion diagnosis system, which includes: a fusion diagnosis server, an IV diagnosis server and a drone, wherein the fusion diagnosis server is respectively communicated with the IV diagnosis server and the drone, and is used to execute a diagnosis task in response to a diagnosis task request, including: triggering the IV diagnosis server to perform IV diagnosis analysis on the current data and voltage data of the photovoltaic components in the target photovoltaic power station, and receiving the IV diagnosis analysis results sent by the IV diagnosis server; controlling the drone to fly, capturing images of the photovoltaic components in the target photovoltaic power station, obtaining images of the photovoltaic components, and identifying the images of the photovoltaic components to obtain CV diagnosis analysis results; matching and fusing the IV diagnosis analysis results and the CV diagnosis analysis results to obtain the final diagnosis analysis results.

[0005] In addition, the IV&CV fusion diagnostic system of the embodiment of the present invention may also have the following additional technical features:

[0006] According to one embodiment of the present invention, the fusion diagnosis server is also used to: determine a target area based on the IV diagnostic analysis results, wherein the target area is an area where candidate faulty photovoltaic components are located; control the drone to fly to the target area to capture images of the photovoltaic components in the target area; identify the images of the photovoltaic components in the target area to determine the final diagnostic analysis results from the candidate faulty photovoltaic components.

[0007] According to one embodiment of the present invention, the system further includes: an acquisition server, a forward isolation device and a reverse isolation device, the acquisition server being communicatively connected to the fusion diagnosis server via the forward isolation device and the reverse isolation device, and being used for: receiving the diagnosis task request sent by the fusion diagnosis server via the reverse isolation device; triggering the IV diagnosis server to perform IV diagnosis analysis on the current data and voltage data of the photovoltaic components in the target photovoltaic power station according to the diagnosis task request; and transmitting the IV diagnosis analysis results sent by the IV diagnosis server to the fusion diagnosis server via the forward isolation device.

[0008] According to one embodiment of the present invention, the fusion diagnosis server includes: an image memory, a relational database, a message queue and a data processing module; the image memory is used to store the photovoltaic component image; the relational database is used to store the IV diagnosis analysis result and the CV diagnosis analysis result, as well as the storage path of the photovoltaic component image fed back by the image memory; the message queue is used to receive the diagnosis task request and the CV diagnosis analysis result; the data processing module is used to identify the photovoltaic component image using a pre-trained AI model after monitoring that the message queue receives the diagnosis task request, obtain the CV diagnosis analysis result, and transmit the CV diagnosis analysis result to the relational database through the message queue for storage, and match and fuse the IV diagnosis analysis result and the CV diagnosis analysis result to obtain the final diagnosis analysis result.

[0009] According to one embodiment of the present invention, the photovoltaic component image includes a visible light image and an infrared image. When the data processing module uses a pre-trained AI model to identify the photovoltaic component image, it is specifically used to: calculate the actual size of the infrared image according to the infrared camera parameters corresponding to the infrared image, recorded as the first actual size, and calculate the actual size of the visible light image according to the visible light camera parameters corresponding to the visible light image, recorded as the second actual size; obtain the position information of the drone, and determine the position of the center point of the infrared image in the visible light image according to the position information, the first actual size, and the second actual size, recorded as the first position; obtain the position of the faulty photovoltaic component in the visible light image according to the first position and the position of the faulty photovoltaic component in the infrared image, recorded as the second position; establish an image field of view coordinate system according to the yaw angle of the drone; in the image field of view coordinate system, obtain the viewing angle of the faulty photovoltaic component relative to the drone according to the second position and the viewing angle of the visible light camera, and complete the positioning of the faulty photovoltaic component.

[0010] According to one embodiment of the present invention, the system also includes: a client, which is communicatively connected to the fusion diagnostic server, and is used to send the diagnostic task request to the fusion diagnostic server, and receive a fault diagnosis report transmitted by the fusion diagnostic server, wherein the fault diagnosis report is generated by the fusion diagnostic server based on the final faulty photovoltaic component.

[0011] According to one embodiment of the present invention, before executing the diagnostic task, the fusion diagnostic server is further used to: obtain weather information of the environment in which the target photovoltaic power station is located; determine whether the weather information meets the preset diagnostic task conditions; if so, execute the diagnostic task.

[0012] According to one embodiment of the present invention, the fusion diagnosis server is also used to perform one of the following actions when the weather information does not meet the preset diagnosis task conditions: perform task waiting, and execute the diagnosis task when the weather information meets the preset diagnosis task conditions within a preset time; use historical IV diagnostic analysis results and historical photovoltaic component images collected by the drone to perform fault fusion diagnosis.

[0013] According to one embodiment of the present invention, the preset diagnostic task conditions include: wind speed less than 10 m / s and irradiance greater than 600 W / m2.

[0014] According to one embodiment of the present invention, the IV diagnostic server communicates with the acquisition server through an intranet firewall.

[0015] The IV&CV fusion diagnosis system of the embodiment of the present invention can improve the fault diagnosis rate of photovoltaic components through IV and CV fusion diagnosis of photovoltaic components, accurately identify and mark the location of the fault, and at the same time, reduce labor costs and improve operation and maintenance efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a schematic diagram of the structure of an IV&CV fusion diagnostic system according to an embodiment of the present invention;

[0017] Figure 2 is a schematic diagram of the workflow of a fusion diagnosis server according to an embodiment of the present invention;

[0018] Figure 3 is a schematic structural diagram of an IV&CV fusion diagnostic system according to another embodiment of the present invention;

[0019] Figure 4 is a structural diagram of a fusion diagnosis server according to an embodiment of the present invention;

[0020] Figure 5 It is a schematic diagram of a flow chart of a data processing module according to an embodiment of the present invention identifying a photovoltaic module image using a pre-trained AI model;

[0021] Figure 6 is an example diagram of an infrared image coordinate system and a visible light image coordinate system according to an embodiment of the present invention;

[0022] Figure 7 is an example diagram of an image field of view coordinate system according to an embodiment of the present invention;

[0023] Figure 8 is an example diagram of a fault location and the corresponding x and y viewing angles of a drone according to an embodiment of the present invention;

[0024] Fig. 9 It is a schematic diagram of a specific workflow of an IV&CV fusion diagnostic system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0026] The IV&CV fusion diagnosis system according to an embodiment of the present invention will be described below with reference to the accompanying drawings.

[0027] Figure 1 It is a structural schematic diagram of an IV&CV fusion diagnostic system according to an embodiment of the present invention.

[0028] like Figure 1 As shown, the IV&CV fusion diagnosis system includes: a fusion diagnosis server 10, an IV diagnosis server 20 and an unmanned aerial vehicle 30. The fusion diagnosis server 10 is respectively connected to the IV diagnosis server 20 and the unmanned aerial vehicle 30 for communication, and is used to execute a diagnosis task in response to a diagnosis task request, including: triggering the IV diagnosis server 20 to perform IV diagnosis analysis on the current data and voltage data of the photovoltaic components in the target photovoltaic power station, and receiving the IV diagnosis analysis results sent by the IV diagnosis server 20; controlling the flight of the unmanned aerial vehicle 30 to capture images of the photovoltaic components in the target photovoltaic power station to obtain images of the photovoltaic components, and identifying the images of the photovoltaic components to obtain CV diagnosis analysis results; matching and fusing the IV diagnosis analysis results and the CV diagnosis analysis results to obtain the final diagnosis analysis results.

[0029] It should be noted that IV diagnosis is to detect and diagnose faulty components in photovoltaic modules by analyzing the current-voltage (IV) curve of photovoltaic modules. Specifically, the IV scanning instruction can be sent to the inverter through the data acquisition device, and the inverter completes the complete IV curve data acquisition of the photovoltaic string. Based on the analysis of the typical IV characteristic parameters of the photovoltaic string, the different defect information of the photovoltaic string is identified, and based on the defect information, it is determined whether the photovoltaic string is abnormal. CV diagnosis is to use an algorithm to identify the images collected by the drone 30, so as to determine the type of fault in the photovoltaic module.

[0030] The IV&CV fusion diagnosis system of the embodiment of the present invention can improve the fault diagnosis rate of photovoltaic components through IV and CV fusion diagnosis of photovoltaic components, accurately identify and mark the location of the fault, and at the same time, reduce labor costs and improve operation and maintenance efficiency.

[0031] In some embodiments of the present invention, Figure 2 As shown, the fusion diagnosis server 10 is also used for:

[0032] S11, determining a target area according to the IV diagnostic analysis result, wherein the target area is an area where the candidate faulty photovoltaic modules are located.

[0033] S12, controlling the drone 30 to fly to the target area to collect images of the photovoltaic modules in the target area.

[0034] S13, identifying the photovoltaic module images in the target area to determine the final diagnosis analysis results from the candidate faulty photovoltaic modules.

[0035] As an example, it can be divided into extreme speed mode and fine mode according to actual diagnostic needs. In extreme speed mode, the IV curve of the photovoltaic power station is first fully tested through IV diagnosis to identify the performance problems of the solar panels in the entire photovoltaic module, and CV diagnosis is performed on the faulty strings found. This can not only shorten the flight route of the drone 30, but also make full use of the advantages of IV fast and CV fine. In fine mode, IV and CV are used for comprehensive testing at the same time, and a comprehensive and detailed "physical examination" of the inside and outside of the photovoltaic module can be carried out, which can achieve a more comprehensive and accurate diagnosis.

[0036] In this embodiment, the IV&CV fusion diagnosis system can formulate inspection tasks in a targeted manner and accurately locate the problematic components in the faulty string, thereby reducing unnecessary inspections of the drone 30 and saving power consumption of the drone 30.

[0037] In some embodiments of the present invention, Figure 3 As shown, the IV&CV fusion diagnosis system further includes: an acquisition server 40, a forward isolation device 50 and a reverse isolation device 60. The acquisition server 40 is connected to the fusion diagnosis server 10 through the forward isolation device 50 and the reverse isolation device 60 for:

[0038] S21 , receiving a diagnostic task request sent by the fusion diagnostic server 10 through the reverse isolation device 60 .

[0039] S22, triggering the IV diagnostic server 20 to perform IV diagnostic analysis on the current data and voltage data of the photovoltaic modules in the target photovoltaic power station according to the diagnostic task request.

[0040] S23 , transmitting the IV diagnostic analysis result sent by the IV diagnostic server 20 to the fusion diagnostic server 10 through the forward isolation device 50 .

[0041] Specifically, the IV diagnostic server 20 communicates with the collection server 40 through the intranet firewall 70 .

[0042] As an example, both the acquisition server 40 and the fusion diagnosis server 10 can be communicatively connected to other devices via the switch 80 .

[0043] It should be noted that, in some embodiments, the IV&CV fusion diagnostic system can be divided into a production control area and a management information area, wherein the production control area may include a control area (safety area I) and a non-control area (safety area II), and the management information area may include a safety area III.

[0044] In this embodiment, the forward isolation device 50 can be used to protect the staff and equipment from voltage shock. When the equipment needs to be repaired or overhauled, the forward isolation device 50 is used to cut off the circuit and guide the voltage to the ground through the grounding device, which can ensure the safety of the staff. The reverse isolation device 60 can improve the stability and reliability of the power module.

[0045] In some embodiments of the present invention, Figure 4 As shown, the fusion diagnosis server 10 includes: an image storage 101 , a relational database 102 , a message queue 103 and a data processing module 104 .

[0046] The image storage 101 is used to store the photovoltaic component images.

[0047] As an example, after the drone 30 completes image acquisition of the photovoltaic components in the target photovoltaic power station, the captured photovoltaic component images are uploaded to the image storage 101 through the “air to ground, ground to cloud” transmission process.

[0048] The relational database 102 is used to store the IV diagnostic analysis results and the CV diagnostic analysis results, as well as the storage path of the photovoltaic module image fed back by the image storage 101 .

[0049] The message queue 103 is used to receive diagnostic task requests and CV diagnostic analysis results.

[0050] As an example, the message queue 103 may be a RabbitMQ message queue.

[0051] The data processing module 104 is used to use a pre-trained AI model to identify the photovoltaic component image after monitoring the message queue 103 receiving the diagnostic task request, obtain the CV diagnostic analysis result, and transmit the CV diagnostic analysis result to the relational database 102 for storage through the message queue 103, and match and fuse the IV diagnostic analysis result and the CV diagnostic analysis result to obtain the final diagnostic analysis result.

[0052] As an example, the data processing module 104 may also transmit the final diagnosis and analysis result to the relational database 102 for storage.

[0053] In this embodiment, the reliability and data processing efficiency of the IV&CV fusion diagnosis system can be improved through the image storage 101 , the relational database 102 , the message queue 103 and the data processing module 104 .

[0054] In some embodiments of the present invention, the photovoltaic module image includes a visible light image and an infrared image, such as Figure 5As shown, when the data processing module 104 uses the pre-trained AI model to recognize the photovoltaic component image, it is specifically used to:

[0055] S31, calculating the actual size of the infrared image according to the infrared camera parameters corresponding to the infrared image, recorded as the first actual size, and calculating the actual size of the visible light image according to the visible light camera parameters corresponding to the visible light image, recorded as the second actual size.

[0056] S32, obtaining the position information of the drone 30, and determining the position of the center point of the infrared image in the visible light image according to the position information, the first actual size, and the second actual size, which is recorded as the first position.

[0057] S33, obtaining the position of the faulty photovoltaic assembly in the visible light image according to the first position and the position of the faulty photovoltaic assembly in the infrared image, and recording it as the second position.

[0058] As an example, Figure 6 As shown, the infrared image coordinate system O1X1Y1 and the visible light image coordinate system O2X2Y2 can be established. The registration of the infrared image in the visible light image is obtained through the position information, the first actual size, and the second actual size.

[0059] S34, establishing an image field of view coordinate system according to the yaw angle of the drone 30.

[0060] As an example, Figure 7 As shown, the image field of view coordinate system is established with the drone 30 as the coordinate origin.

[0061] S35, in the image field of view coordinate system, according to the second position and the viewing angle of the visible light camera, the viewing angle of the faulty photovoltaic component relative to the drone 30 is obtained, and the positioning of the faulty photovoltaic component is completed.

[0062] As an example, Figure 8 As shown, the fault position and the x and y corresponding viewing angles of the drone 30 are obtained according to the second position and the viewing angle of the visible light camera, thereby completing the positioning of the faulty photovoltaic component.

[0063] In this embodiment, the data processing module 104 is able to accurately identify and mark the location of the defect in the failed photovoltaic module.

[0064] In some embodiments of the present invention, the IV&CV fusion diagnostic system also includes: a client, which is communicatively connected to the fusion diagnostic server 10, and is used to send a diagnostic task request to the fusion diagnostic server 10, and receive a fault diagnosis report transmitted by the fusion diagnostic server 10, wherein the fault diagnosis report is generated by the fusion diagnostic server 10 based on the final faulty photovoltaic component.

[0065] As an example, the client may send a diagnosis plan via an HTTP request.

[0066] In some embodiments of the present invention, before executing the diagnosis task, the fusion diagnosis server 10 is further used to:

[0067] S41, obtaining weather information of the environment in which the target photovoltaic power station is located.

[0068] S42, determining whether the weather information meets the preset diagnosis task conditions.

[0069] S43: If the conditions are met, the diagnosis task is executed.

[0070] Specifically, the fusion diagnosis server 10 is also used to perform one of the following actions when the weather information does not meet the preset diagnostic task conditions: wait for the task, and execute the diagnostic task when the weather information meets the preset diagnostic task conditions within the preset time; use the historical IV diagnostic analysis results and the historical photovoltaic component images collected by the drone 30 to perform fault fusion diagnosis.

[0071] More specifically, the preset diagnostic task conditions include: wind speed less than 10m / s and irradiance greater than 600W / m2.

[0072] In this embodiment, whether to perform a diagnostic task is selected based on weather information, and when the preset diagnostic task conditions are not met, the historical IV diagnostic analysis results and the historical photovoltaic component images collected by the drone 30 can be used to perform fault fusion diagnosis, which can meet various diagnostic scenarios and facilitate timely and accurate acquisition of diagnostic results.

[0073] As an example, Fig. 9 As shown, the specific workflow of the present invention is described:

[0074] A1, the client sends a plan request to the fusion diagnosis server 10.

[0075] A2, the fusion diagnosis server 10 transmits the diagnosis task request through the reverse isolation device 60.

[0076] A3, the acquisition server 40 sends a diagnostic task request to the IV diagnostic server 20.

[0077] A4, the IV diagnostic server 20 performs IV diagnostic analysis on the current data and voltage data of the photovoltaic components in the target photovoltaic power station according to the diagnostic task request, and responds to the IV diagnostic analysis result to the collection server 40.

[0078] A5, the acquisition server 40 transmits the IV diagnostic analysis results to the fusion diagnostic server 10 through the forward isolation device 50.

[0079] A6, the fusion diagnosis server 10 sends the flight mission to the drone 30 via MQTT.

[0080] A7, the drone 30 collects images of the photovoltaic modules in the target photovoltaic power station, obtains visible light images and infrared images of the photovoltaic modules, and uploads them to the image storage 101.

[0081] A8, the image storage 101 generates a storage path for the photovoltaic assembly image.

[0082] A9, the fusion diagnosis server 10 stores the storage path of the photovoltaic component image in the relational database 102.

[0083] A10, the relational database 102 feeds back a storage response.

[0084] A11 , the fusion diagnosis server 10 puts the diagnosis task request into the message queue 103 .

[0085] A12, the message queue 103 pushes the corresponding request to the data processing module 104.

[0086] A13, after listening to the diagnostic task request, the data processing module 104 uses the pre-trained AI model to identify the photovoltaic component image, obtains the CV diagnostic analysis result, and matches and fuses the IV diagnostic analysis result and the CV diagnostic analysis result to obtain the final diagnostic analysis result.

[0087] A14, the data processing module 104 transmits the final diagnosis and analysis result to the message queue 103.

[0088] A15, the message queue 103 pushes the final diagnosis and analysis results.

[0089] A16, the fusion diagnosis server 10 transmits the final diagnosis analysis result to the relational database 102 for storage.

[0090] A17, the relational database 102 feeds back a storage response.

[0091] A18, the client receives the fault diagnosis report transmitted by the fusion diagnosis server 10.

[0092] It should be understood that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0093] At the same time, the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0094] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0095] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0096] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. An IV&CV fusion diagnostic system, characterized in that: The system includes: a fusion diagnosis server, an IV diagnosis server and a drone, wherein the fusion diagnosis server is respectively connected to the IV diagnosis server and the drone in communication, and is used to execute a diagnosis task in response to a diagnosis task request, including: Triggering the IV diagnostic server to perform IV diagnostic analysis on current data and voltage data of photovoltaic modules in the target photovoltaic power station, and receiving the IV diagnostic analysis results sent by the IV diagnostic server; Controlling the UAV to fly, collecting images of photovoltaic modules in the target photovoltaic power station to obtain photovoltaic module images, and identifying the photovoltaic module images to obtain CV diagnosis and analysis results; Matching and fusing the IV diagnostic analysis result and the CV diagnostic analysis result to obtain a final diagnostic analysis result; The fusion diagnosis server includes: an image storage, a relational database, a message queue and a data processing module; The image storage device is used to store the photovoltaic module image; The relational database is used to store the IV diagnostic analysis result and the CV diagnostic analysis result, and the storage path of the photovoltaic component image fed back by the image storage; The message queue is used to receive the diagnostic task request and the CV diagnostic analysis result; The data processing module is used to, after monitoring that the message queue receives the diagnostic task request, use the pre-trained AI model to identify the photovoltaic component image to obtain the CV diagnostic analysis result, and transmit the CV diagnostic analysis result to the relational database for storage through the message queue, and match and fuse the IV diagnostic analysis result and the CV diagnostic analysis result to obtain the final diagnostic analysis result; wherein the photovoltaic component image includes a visible light image and an infrared image, and when the data processing module uses the pre-trained AI model to identify the photovoltaic component image, it is specifically used to: The actual size of the infrared image is calculated according to the infrared camera parameters corresponding to the infrared image, which is recorded as a first actual size; the actual size of the visible light image is calculated according to the visible light camera parameters corresponding to the visible light image, which is recorded as a second actual size; Acquire the position information of the UAV, and determine the position of the center point of the infrared image in the visible light image according to the position information, the first actual size, and the second actual size, and record it as a first position; According to the first position and the position of the faulty photovoltaic component in the infrared image, the position of the faulty photovoltaic component in the visible light image is obtained, which is recorded as a second position; Establishing an image field of view coordinate system according to the yaw angle of the drone; In the image field of view coordinate system, the viewing angle of the faulty photovoltaic component relative to the drone is obtained according to the second position and the viewing angle of the visible light camera, thereby completing the positioning of the faulty photovoltaic component.

2. The IV&CV fusion diagnostic system according to claim 1, characterized in that: The fusion diagnosis server is also used for: Determine a target area according to the IV diagnostic analysis result, wherein the target area is an area where a candidate faulty photovoltaic module is located; Controlling the UAV to fly to the target area to collect images of the photovoltaic components in the target area; The photovoltaic component images within the target area are identified to determine a final diagnosis analysis result from the candidate faulty photovoltaic components.

3. The IV&CV fusion diagnostic system according to claim 1, characterized in that: The system further includes: a collection server, a forward isolation device and a reverse isolation device, wherein the collection server is communicatively connected with the fusion diagnosis server through the forward isolation device and the reverse isolation device, and is used for: receiving the diagnostic task request sent by the fusion diagnostic server through the reverse isolation device; Triggering the IV diagnostic server to perform IV diagnostic analysis on current data and voltage data of photovoltaic components in the target photovoltaic power station according to the diagnostic task request; The IV diagnostic analysis results sent by the IV diagnostic server are transmitted to the fusion diagnostic server through the forward isolation device.

4. The IV&CV fusion diagnostic system according to claim 1, characterized in that: The system also includes: a client, which is communicatively connected to the fusion diagnostic server and is used to send the diagnostic task request to the fusion diagnostic server and receive a fault diagnosis report transmitted by the fusion diagnostic server, wherein the fault diagnosis report is generated by the fusion diagnostic server according to the final faulty photovoltaic component.

5. The IV&CV fusion diagnostic system according to claim 1, characterized in that: Before executing the diagnosis task, the fusion diagnosis server is further used to: Obtaining weather information of the environment in which the target photovoltaic power station is located; Determining whether the weather information meets the preset diagnostic task conditions; If satisfied, the diagnostic task is executed.

6. The IV&CV fusion diagnostic system according to claim 5, characterized in that: The fusion diagnosis server is further configured to perform one of the following actions when the weather information does not meet the preset diagnosis task condition: Perform task waiting, and execute the diagnostic task when the weather information meets the preset diagnostic task conditions within the preset time; Fault fusion diagnosis is performed using historical IV diagnostic analysis results and historical photovoltaic module images collected by the UAV.

7. The IV&CV fusion diagnostic system according to claim 6, characterized in that: The preset diagnostic task conditions include: wind speed less than 10m / s and irradiance greater than 600W / m2.

8. The IV&CV fusion diagnostic system according to claim 3, characterized in that: The IV diagnostic server communicates with the acquisition server through an intranet firewall.

Images