A photovoltaic power station power generation area inspection control system and an inspection control method

Abstract

The application discloses a kind of photovoltaic power station power generation area inspection control system, the inspection control system includes: unmanned aerial vehicle, for collecting photovoltaic module's thermal infrared image and visible light image;Weather station, for real-time acquisition photovoltaic power station's irradiance, ambient temperature and wind speed, and send inspection request to monitoring device;Analog map, for recording the geographical location of photovoltaic module string and the correspondence of photovoltaic module string and inverter;IV detection device based on inverter, for scanning photovoltaic module string and obtaining the IV curve of corresponding photovoltaic module string;Monitoring device, including IV diagnosis module, route planning module, inspection instruction module, image diagnosis module and defect processing module.The photovoltaic power station power generation area inspection control system of the application, the advantages of inverter I-V wide range fast diagnosis and the advantages of unmanned aerial vehicle accurate positioning and identifying defect ability are combined, and the operation and maintenance workload and operation and maintenance technical difficulty are reduced by the combination and running of data.

Description

Technical Field

[0001] This invention relates to the field of solar power generation technology, specifically to an inspection control system and method that integrates photovoltaic power plant inverter monitoring with drone inspection, and accurately locates and identifies defective photovoltaic modules. Background Technology

[0002] Photovoltaic modules, the core equipment for photovoltaic power generation, are typically installed in arrays in open areas. Due to issues with equipment manufacturing and installation quality, and limitations in operation and maintenance management, photovoltaic modules are exposed to a constantly changing natural environment for extended periods. This makes them prone to various types of damage and deterioration of photovoltaic cell characteristics. Furthermore, during long-term use, dust accumulation, fallen leaves, tree shading, bird droppings, and other factors can cause localized shadows on the surface of the photovoltaic modules, leading to the "hot spot effect."

[0003] Currently, for defective equipment in photovoltaic power plant areas, methods include monitoring and diagnosing the IV performance of photovoltaic strings via inverters, or conducting full-site scanning inspections using drones to locate and determine defective modules. However, inverter monitoring and diagnosis of photovoltaic string IV performance can only pinpoint a few major defects in the photovoltaic strings, not the location of defective photovoltaic modules, and it cannot identify equipment defects when photovoltaic modules are open-circuited. Drone inspection and scanning suffers from limitations such as short drone flight time, weak targeted inspection capabilities, and the time required to complete a full-site scan, making autonomous inspection impossible in the absence of technical personnel. Furthermore, there is no mature solution for planning drone flight and imaging parameters based on the geographical information of photovoltaic modules. Summary of the Invention

[0004] In view of this, in order to overcome the shortcomings of the prior art, the purpose of this invention is to provide a photovoltaic power plant power generation area inspection control system and inspection control method.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] A photovoltaic power plant power generation area inspection and control system, the inspection and control system comprising:

[0007] Drones are used to collect thermal infrared and visible light images of photovoltaic modules.

[0008] The weather station is used to collect real-time data on the irradiance, ambient temperature, and wind speed of the photovoltaic power station, and to send inspection requests to the monitoring device.

[0009] A simulated map is used to record the geographical location of photovoltaic strings and the correspondence between photovoltaic strings and inverters;

[0010] An inverter-based IV detection device is used to scan photovoltaic strings and obtain the IV curve of the corresponding photovoltaic strings.

[0011] The monitoring device includes an IV diagnostic module, a route planning module, an inspection command module, an image diagnostic module, and a defect processing module.

[0012] According to some preferred embodiments of the present invention, the simulated map stores the serial number and geographical location information of each photovoltaic string and the serial number of the photovoltaic string corresponding to each inverter, wherein the geographical location information includes the longitude and latitude (x, y) of the center point of the photovoltaic string. n y n ) and the width and height (w) of the photovoltaic string. n , l n ).

[0013] According to some preferred embodiments of the present invention, the IV diagnostic module is used to acquire the photovoltaic string IV curve generated by the inverter-based IV detection device, and to diagnose the photovoltaic string according to the IV curve image characteristics, generate a defect prompt and give the string defect type after discovering string defects.

[0014] According to some preferred embodiments of the present invention, the route planning module is used to plan the route of the UAV and set the flight parameters of the UAV.

[0015] According to some preferred embodiments of the present invention, the inspection command module is used to automatically acquire the defect prompts generated by the IV diagnostic module and issue inspection commands to the UAV.

[0016] According to some preferred embodiments of the present invention, the inspection command module finds the photovoltaic string number with defect indication based on the correspondence between inverters and photovoltaic strings in the simulation map, and then calls the route planning module to automatically plan an inspection route containing all defective strings. Based on the inspection route, an inspection task is generated accordingly to control the UAV to collect images of the defective strings.

[0017] According to some preferred embodiments of the present invention, the image diagnostic module is used to read the thermal infrared and visible light images collected by the UAV, use a target detection algorithm to screen out photovoltaic modules with defects in the defect string, compare and analyze them with the defect types in the image knowledge base, and combine the IV curve diagnostic results to determine and identify the defect type and defect location of the defective module.

[0018] According to some preferred embodiments of the present invention, the defect processing module is used to obtain the results generated by the image diagnosis module and provide the location coordinates of the defective component and the defect type.

[0019] According to some preferred embodiments of the present invention, the system also includes a drone airport. Upon receiving an inspection task from the inspection command module, the drone airport automatically completes the pre-operation preparations for the drone, downloads the inspection task from the inspection command module, automatically completes the take-off operation of the drone, and uploads the images collected during the operation to the image defect module of the monitoring device. After the drone completes the inspection task, the drone airport automatically completes the landing and entry of the drone, and completes the entry inspection and battery charging of the drone.

[0020] The present invention also provides an inspection control method based on the inspection control system described above, comprising the following steps:

[0021] S1. The meteorological station detects that the irradiance, ambient temperature and wind speed of the photovoltaic power station are within the range suitable for automatic inspection operations, and submits an inspection request to the monitoring device. The monitoring device then activates the inverter-based IV detection device.

[0022] S2. The inverter-based IV detection device scans the photovoltaic strings to obtain the IV curves of each photovoltaic string;

[0023] S3. Based on the characteristic information of the IV curve, the monitoring device identifies whether there is a defect in the string through the IV diagnostic module, gives the type of defect and generates a defect prompt, and gives the sequence number of the defective string according to the correspondence between the inverter and the photovoltaic string in the simulation map.

[0024] S4. Based on the sequence number of the defect string, the monitoring device sets the UAV flight parameters and plans the UAV inspection route through the route planning module; based on the inspection route, it generates an inspection task and issues an inspection command.

[0025] S5. After receiving the inspection command, the UAV flies according to the planned route and collects infrared and visible light images of the defective photovoltaic string, and uploads the collected images to the monitoring device.

[0026] S6. The monitoring device uses a target detection algorithm to filter out the defective components in the defective string, and combines the IV curve diagnostic results to make a comprehensive judgment and give the location coordinates and defect type of the defective component.

[0027] According to some preferred embodiments of the present invention, in step S3, the IV curve diagnosis method includes: comparing the IV curves of different defective photovoltaic strings in the database according to the performance parameters of the corresponding photovoltaic module, and the monitoring device determining the type of defective string based on the identification of IV curve features.

[0028] In some embodiments, the types of defective strings include (1) current mismatch within the string; (2) open circuit in the string; (3) abnormal string current; (4) abnormal string voltage; (5) excessively low parallel resistance of the string; (6) excessively high series resistance of the string; (7) low short-circuit current of the string; and (8) low string power.

[0029] According to some preferred embodiments of the present invention, in step S4, the UAV flight parameters include the latitude and longitude (x′) of each waypoint of the UAV. n y′ n ), the drone's flight altitude h and the drone's gimbal camera's pitch angle α.

[0030] According to some preferred embodiments of the present invention, in step S4, the planning of the inspection route includes the following steps:

[0031] In the simulated map, based on the serial number of the defective photovoltaic string, the longitude and latitude (x, y, y) of the center point of the corresponding photovoltaic string are obtained. n y n ) and the width and height (w) of the photovoltaic string. n , l n ), calculate the longitude and latitude (x′) of the waypoint system of the UAV that took the picture of the photovoltaic string. n y′ n The formula is as follows:

[0032] y′ n =y n -h×tan(90°-α)

[0033] x′ n =x n

[0034] To ensure the drone can fully capture images of the photovoltaic string, the flight path planning module sets the drone's flight parameters h and α according to the following constraint formulas:

[0035]

[0036] Where W and L represent the width and height of the image captured by the drone, respectively.

[0037] According to some preferred embodiments of the present invention, W and L are respectively calculated by the following formulas:

[0038] L=h÷sinα×l c ÷f×μ1

[0039] W = h ÷ sinα × w c ÷f×μ2

[0040] In the formula, w c It is the width of the camera's target surface, lc Here, μ1 is the target height of the camera, f is the camera focal length, and μ2 are the image distortion coefficients. These parameters are inherent to both the drone and the gimbal camera.

[0041] According to some preferred embodiments of the present invention, in step S5, after the monitoring device issues an inspection command, the UAV airport receives the inspection command, automatically completes the pre-operation preparation of the UAV, downloads the inspection task from the inspection command module, automatically completes the take-off operation of the UAV, and uploads the images collected during the operation to the monitoring device; after the UAV completes the inspection task, the UAV airport will automatically complete the landing and entry of the UAV, and complete the entry inspection and battery charging and swapping of the UAV.

[0042] According to some preferred embodiments of the present invention, the monitoring device uses a target detection algorithm to filter out the location and size of abnormal image features from the thermal infrared and visible light image information of the defect cluster, and identifies the location and defect type of the defect component based on the correspondence between image features and defect types.

[0043] In some embodiments, the types of defective components include (1) component smudges; (2) defective cell components; (3) dust accumulation on the component surface; (4) faulty or poorly soldered diode components; (5) PID degradation in components; (6) broken glass in components; (7) open circuit in components; (8) short circuit in components; and (9) abnormal component position.

[0044] Due to the adoption of the above technical solutions, the advantages of the present invention compared with the prior art are as follows: The photovoltaic power station power generation area inspection and control system of the present invention combines the advantages of inverter IV's wide-range rapid diagnosis and the advantages of UAV's precise positioning and defect identification capabilities, and reduces the workload and technical difficulty of operation and maintenance through data combination and mobile operation. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a schematic diagram of the structure of the photovoltaic power station power generation area inspection and control system in a preferred embodiment of the present invention;

[0047] Figure 2 This is a logic flowchart of the photovoltaic power plant power generation area inspection and control method in a preferred embodiment of the present invention;

[0048] Figure 3This is a schematic diagram illustrating the identification of defective photovoltaic strings using IV curve features in a preferred embodiment of the present invention.

[0049] Figure 4 This is a schematic diagram of a photovoltaic string simulation map in a preferred embodiment of the present invention;

[0050] Figure 5 This is a schematic diagram illustrating the identification of photovoltaic module defects using visible light images in a preferred embodiment of the present invention.

[0051] Figure 6 This is a schematic diagram of identifying photovoltaic module defects using thermal infrared images in a preferred embodiment of the present invention. Detailed Implementation

[0052] To enable those skilled in the art to better understand the technical solutions of the present invention, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0053] Example 1: Photovoltaic Power Plant Power Generation Area Inspection and Control System

[0054] like Figure 1 As shown, the photovoltaic power plant power generation area inspection and control system in this embodiment includes the following components:

[0055] 1) Drones

[0056] It is used to acquire thermal infrared and visible light images of photovoltaic modules.

[0057] 2) Weather station

[0058] It is used to collect real-time data on the irradiance, ambient temperature, and wind speed of photovoltaic power plants, and to send inspection requests to the monitoring device.

[0059] 3) Simulated map

[0060] like Figure 4 As shown, it is used to record the geographical location of photovoltaic strings and the correspondence between photovoltaic strings and inverters.

[0061] The simulated map stores the serial number and geographical location information of each photovoltaic string, as well as the serial number of the photovoltaic string corresponding to each inverter. The geographical location information includes the longitude and latitude (x, y) of the center point of the photovoltaic string. n y n ) and the width and height (w) of the photovoltaic string. n , l n ).

[0062] 4) Inverter-based IV detection device

[0063] It is used to scan photovoltaic strings and obtain the IV curve of the corresponding photovoltaic string.

[0064] 5) Unmanned Aerial Vehicle (UAV) Airport

[0065] When the UAV airport receives an inspection task from the inspection command module, it will automatically complete the pre-operation preparation of the UAV, download the inspection task from the inspection command module, automatically complete the take-off operation of the UAV, and upload the images collected during the operation to the image defect module of the monitoring device. After the UAV completes the inspection task, the UAV airport will automatically complete the landing and entry of the UAV, and complete the entry inspection and battery charging of the UAV.

[0066] 6) Monitoring devices

[0067] It includes an IV diagnostic module, a route planning module, an inspection command module, an image diagnostic module, and a defect handling module.

[0068] 6.1) IV Diagnostic Module

[0069] It is used to obtain the IV curve of the photovoltaic string generated by the inverter-based IV detection device, and to diagnose the photovoltaic string according to the characteristics of the IV curve image. After discovering string defects, it generates defect prompts and gives the string defect type.

[0070] The defect types of defective strings are: (1) current mismatch within the string; (2) open circuit in the string; (3) abnormal current in the string; (4) abnormal voltage in the string; (5) excessively low parallel resistance in the string; (6) excessively high series resistance in the string; (7) low short-circuit current in the string; and (8) low power in the string.

[0071] 6.2) Route Planning Module

[0072] It is used to plan drone flight paths and set drone flight parameters.

[0073] 6.3) Inspection Instruction Module

[0074] It is used to automatically acquire defect alerts generated by the IV diagnostic module and issue inspection commands to the drone.

[0075] The inspection command module finds the photovoltaic string number with the defect indication based on the correspondence between inverters and photovoltaic strings in the simulation map. Then, it calls the route planning module to automatically plan an inspection route that includes all defective strings. Based on the inspection route, the module generates an inspection task to control the drone to collect images of the defective strings.

[0076] 6.4) Image Diagnostic Module

[0077] It is used to read thermal infrared and visible light images collected by drones, use artificial intelligence target detection algorithms to screen out photovoltaic modules with defects in defect strings, compare and analyze them with the defect types in the image knowledge base, and combine the IV curve diagnostic results to determine and identify the defect type and defect location of the defective module.

[0078] 6.5) Defect Handling Module

[0079] This is used to obtain the results generated by the image diagnostic module, automatically publish photovoltaic module defect diagnostic reports, provide the location coordinates and defect type of the defective module, and provide different operation and maintenance suggestions for different defect types.

[0080] The types of defective modules include (1) module dirt obstruction; (2) module cell defects; (3) module surface dust accumulation; (4) module diode failure or poor soldering; (5) module PID attenuation; (6) module glass breakage; (7) module open circuit; (8) module short circuit; (9) module abnormal position.

[0081] Example 2

[0082] like Figure 2 As shown, this embodiment provides an inspection control method based on the photovoltaic power plant power generation area inspection control system in Embodiment 1, including the following steps:

[0083] Step S1: Submit an inspection request

[0084] The meteorological station detects that the irradiance, ambient temperature, and wind speed of the photovoltaic power station are within the suitable range for automatic inspection operations, and sends an inspection request to the monitoring device. The monitoring device then activates the inverter-based IV detection device.

[0085] Step S2: Obtain the IV curve

[0086] An inverter-based IV detection device scans all photovoltaic strings in the station to obtain the IV curves of each photovoltaic string.

[0087] Step S3: Obtain defect information

[0088] like Figure 3 As shown, based on the characteristic information of the IV curve, the monitoring device identifies whether there are defects in the string through the IV diagnostic module, gives the type of defect and generates a defect prompt, and gives the sequence number of the defective string according to the correspondence between the inverter and the photovoltaic string in the simulation map.

[0089] The IV curve diagnostic method includes: based on the performance parameters of the corresponding photovoltaic module, comparing the IV curves of different defective photovoltaic strings in the database, and identifying the type of defective string based on the characteristics of the IV curve.

[0090] The defect types of defective strings are: (1) current mismatch within the string; (2) open circuit in the string; (3) abnormal current in the string; (4) abnormal voltage in the string; (5) excessively low parallel resistance in the string; (6) excessively high series resistance in the string; (7) low short-circuit current in the string; and (8) low power in the string.

[0091] Step S4: Issue inspection command

[0092] Based on the sequence number of the defect sequence, the monitoring device sets the UAV flight parameters and plans the UAV inspection route through the route planning module; based on the inspection route, it generates the inspection task and issues the inspection command.

[0093] The drone flight parameters include the latitude and longitude (x′) of each waypoint. n y′ n ), the drone's flight altitude h and the drone's gimbal camera's pitch angle α.

[0094] The planning of inspection routes includes the following steps:

[0095] In the simulated map, based on the serial number of the defective photovoltaic string, the longitude and latitude (x, y, y) of the center point of the corresponding photovoltaic string are obtained. n y n ) and the width and height (w) of the photovoltaic string. n , l n ), calculate the longitude and latitude (x′) of the waypoint system of the UAV that took the picture of the photovoltaic string. n y′ n The formula is as follows:

[0096] y′ n =y n -h×tan(90°-α)

[0097] x′ n =x n

[0098] To ensure the drone can fully capture images of the photovoltaic string, the flight path planning module sets the drone's flight parameters h and α according to the following constraint formulas:

[0099]

[0100] Where W and L represent the width and height of the image captured by the drone, respectively.

[0101] W and L are calculated using the following formulas:

[0102] L=h÷sinα×l c ÷f×μ1

[0103] W = h ÷ sinα × w c ÷f×μ2

[0104] In the formula, w c It is the width of the camera's target surface, l c Here, μ1 is the target height of the camera, f is the camera focal length, and μ2 are the image distortion coefficients. These parameters are inherent to both the drone and the gimbal camera.

[0105] Step S5: Acquire images of defective photovoltaic strings.

[0106] After receiving the inspection command, the drone flies along the planned route and collects infrared and visible light images of the defective photovoltaic strings, and then uploads the collected images to the monitoring device.

[0107] After the monitoring device issues an inspection command, the drone airport receives the command, automatically completes the pre-operation preparations for the drone, downloads the inspection task from the inspection command module, automatically completes the take-off operation of the drone, and uploads the images collected during the operation to the monitoring device. After the drone completes the inspection task, the drone airport will automatically complete the landing and entry of the drone, and complete the entry inspection and battery charging / recharging.

[0108] Step S6: Determine the location coordinates and defect type of the defective component.

[0109] The monitoring device uses artificial intelligence target detection algorithms to filter out defective components in the defect string, and combines the IV curve diagnostic results to make a comprehensive judgment and give the location coordinates and defect type of the defective component, and give different operation and maintenance suggestions for different defect types.

[0110] like Figure 5 and 6 As shown, the monitoring device uses an artificial intelligence target detection algorithm to filter out the location and size of abnormal image features from the thermal infrared and visible light image information of the defect cluster, and identifies the location and type of defective components based on the correspondence between image features and defect types.

[0111] Based on thermal infrared and visible light images, the types of defective components that can be identified are: (1) component dirt obscuring; (2) component cell defects; (3) component surface dust; (4) component diode failure or poor soldering; (5) component PID attenuation; (6) component glass breakage; (7) component open circuit; (8) component short circuit; (9) component abnormal position.

[0112] Corresponding handling suggestions are provided for different defect types. For example: If the module is obstructed by dirt or dust, check the module surface for bird droppings, dust, fallen leaves, or other obstructions and remove them promptly. If the cell is defective and the temperature difference between the hot spot and a normal module is greater than 20°C, consider replacing the module immediately. For diode failures or poor soldering, first eliminate any obstructions on the module surface, then check for faulty bypass diodes. If a diode is faulty, replace the diode or the entire module immediately. For open-circuit defects, check if the module's connector is properly connected. Short circuits may cause internal damage; disconnect the defective module immediately and find the cause of the short circuit. If the module is flipped or detached, check if the module's frame support is damaged and reinstall the module promptly. If the module glass is broken, replace the module immediately.

[0113] This invention discloses an automatic inspection control system and method for photovoltaic power plant equipment. The inspection system includes a drone, a weather station, a simulated map, an inverter-based IV detection device, and a monitoring device. The monitoring device includes an IV diagnostic module, a flight path planning module, an inspection command module, an image diagnostic module, and a defect processing module. The drone is used to collect thermal infrared and visible light images of the photovoltaic modules; the weather station is used to collect real-time data on the irradiance, ambient temperature, and wind speed of the photovoltaic power plant. The simulated map records the geographical locations of the photovoltaic strings and the correspondence between the photovoltaic strings and the inverter. The inverter-based IV detection device scans the photovoltaic strings to obtain their IV curves. The IV diagnostic module diagnoses the IV curves of the strings and provides defect warnings; the flight path planning module locates the defective strings based on the defect warnings and plans the drone flight path for the defective strings. The inspection command module issues inspection commands to the drone, instructing it to collect thermal infrared and visible light images of the defective strings. The image diagnostic module combines IV curve diagnostic results and UAV-acquired image information to identify defect types and filter out defective components in defective strings; the defect processing module provides the location and type of the defective photovoltaic module and offers processing suggestions. Compared with existing technologies, this invention has the following advantages: it realizes the linkage between inverter monitoring and UAV inspection in photovoltaic power plants; it overcomes the problem that inverter monitoring and diagnosis of photovoltaic string IV performance can only locate the location of the photovoltaic string, but not the location of defective photovoltaic modules; it overcomes the problem of weak targeting of UAV inspections and the need for a large amount of time for full-site scanning; it realizes fully automatic monitoring of photovoltaic modules in photovoltaic power plants; and it implements a method for setting flight parameters for UAV inspection of photovoltaic strings using a simulated map.

[0114] The above embodiments are only for illustrating the technical concept and features of the present invention, and are intended to enable those skilled in the art to understand the content of the present invention and implement it accordingly. They should not be construed as limiting the scope of protection of the present invention. All equivalent changes or modifications made in accordance with the spirit and essence of the present invention should be covered within the scope of protection of the present invention.

Claims

1. An inspection control method, which performs inspections of the power generation area of ​​a photovoltaic power station based on an inspection control system, characterized in that, The inspection and control system includes: Drones are used to collect thermal infrared and visible light images of photovoltaic modules. The weather station is used to collect real-time data on the irradiance, ambient temperature, and wind speed of the photovoltaic power station, and to send inspection requests to the monitoring device. A simulated map is used to record the geographical location of photovoltaic strings and the correspondence between photovoltaic strings and inverters; An inverter-based IV detection device is used to scan photovoltaic strings and obtain the IV curve of the corresponding photovoltaic strings. The monitoring device includes an IV diagnostic module, a route planning module, an inspection command module, an image diagnostic module, and a defect processing module; The inspection control method is characterized by comprising the following steps: S1. The meteorological station detects that the irradiance, ambient temperature and wind speed of the photovoltaic power station are within the range suitable for automatic inspection operations, and submits an inspection request to the monitoring device. The monitoring device then activates the inverter-based IV detection device. S2. The inverter-based IV detection device scans the photovoltaic strings to obtain the IV curves of each photovoltaic string; S3. Based on the characteristic information of the IV curve, the monitoring device identifies whether there is a defect in the string through the IV diagnostic module, gives the type of defect and generates a defect prompt, and gives the sequence number of the defective string according to the correspondence between the inverter and the photovoltaic string in the simulation map. S4. Based on the sequence number of the defect string, the monitoring device sets the UAV flight parameters and plans the UAV inspection route through the route planning module; based on the inspection route, it generates an inspection task and issues an inspection command. S5. After receiving the inspection command, the UAV flies according to the planned route and collects infrared and visible light images of the defective photovoltaic strings, and uploads the collected images to the monitoring device. S6. The monitoring device uses a target detection algorithm to filter out the defective components in the defective string, and combines the IV curve diagnostic results to make a comprehensive judgment and give the location coordinates and defect type of the defective component. In step S4, the planning of the inspection route includes the following steps: In the simulated map, the longitude and latitude of the center point of the corresponding defective photovoltaic string are obtained according to its serial number. and the width and height of the photovoltaic string Calculate the longitude and latitude of the waypoint system of the drone that captured the photovoltaic string. The formula is as follows: ； ； To ensure the drone can capture complete images of the photovoltaic string, the flight path planning module sets the drone's flight parameters according to the following constraint formula. h and α : ； in W, L These represent the width and height of the image captured by the drone, respectively. The W, L The results are obtained using the following formulas: ； ； In the formula, It is the width of the camera's target surface. It is the height of the camera's target surface. f It's the camera's focal length. μ 1. μ 2 is the image distortion coefficient; The IV diagnostic module is used to acquire the photovoltaic string IV curve generated by the inverter-based IV detection device, and to diagnose the photovoltaic string according to the IV curve image characteristics. After discovering string defects, it generates a defect prompt and gives the string defect type. The inspection command module is used to automatically obtain the defect prompts generated by the IV diagnostic module and issue inspection commands to the UAV. The inspection command module finds the photovoltaic string number with the defect indication based on the correspondence between inverters and photovoltaic strings in the simulation map, and then calls the route planning module to automatically plan an inspection route that includes all defective strings. Based on the inspection route, an inspection task is generated to control the UAV to collect images of the defective strings.

2. The inspection control method according to claim 1, characterized in that, The simulated map stores the serial number and geographical location information of each photovoltaic string, as well as the serial number of the photovoltaic string corresponding to each inverter. The geographical location information includes the longitude and latitude of the center point of the photovoltaic string. and the width and height of the photovoltaic string. .

3. The inspection control method according to claim 1, characterized in that, The route planning module is used to plan the UAV route and set the UAV flight parameters.

4. The inspection control method according to claim 1, characterized in that, The image diagnostic module is used to read the thermal infrared and visible light images collected by the UAV, use a target detection algorithm to filter out photovoltaic modules with defects in the defect string, compare and analyze them with the defect types in the image knowledge base, and combine the IV curve diagnostic results to determine and identify the defect type and defect location of the defective module.

5. The inspection control method according to claim 1, characterized in that, The defect processing module is used to obtain the results generated by the image diagnosis module, and to provide the location coordinates and defect type of the defective component.

6. The inspection control method according to claim 1, characterized in that, It also includes a drone airport. When the drone airport receives an inspection task from the inspection command module, it will automatically complete the pre-operation preparation of the drone, download the inspection task from the inspection command module, automatically complete the take-off operation of the drone, and upload the images collected during the operation to the image defect module of the monitoring device. After the drone completes the inspection task, the drone airport will automatically complete the landing and entry of the drone, and complete the entry inspection and battery charging of the drone.

7. The inspection control method according to claim 1, characterized in that, In step S3, the IV curve diagnosis method includes: comparing the IV curves of different defective photovoltaic strings in the database according to the performance parameters of the corresponding photovoltaic module, and identifying the type of defective string based on the identification of IV curve features.

8. The inspection control method according to claim 1, characterized in that, In step S4, the UAV flight parameters include the latitude and longitude of each waypoint of the UAV. Drone flight altitude h and the pitch angle of the drone gimbal camera α .

9. The inspection control method according to claim 1, characterized in that, The monitoring device uses a target detection algorithm to filter out the location and size of abnormal image features from the thermal infrared and visible light image information of the defect clusters, and identifies the location and type of the defective component based on the correspondence between image features and defect types.

Images