Method and system for realizing automatic control assembly cleaning based on infrared and appearance of unmanned aerial vehicle

Abstract

The invention relates to a method and a system for automatically controlling component cleaning based on infrared and appearance of an unmanned aerial vehicle. The method comprises the following steps: constructing a three-dimensional model based on actual data of a photovoltaic power station, and collecting an infrared photo and an appearance photo of a photovoltaic power station component; defining a hot spot defect type and an appearance defect type, and constructing and training a hot spot defect model and an appearance defect model; respectively inputting the infrared photo and the appearance photo into a model to obtain a judgment result; and planning a cleaning route based on the judgment result, and cleaning defects on the photovoltaic power station assembly through an unmanned aerial vehicle. The whole-station infrared thermal imaging and appearance testing of the photovoltaic power station are realized by automatically controlling the infrared and appearance of the unmanned aerial vehicle, the conditions of hot spots, component dust, shielding and the like are identified through automatic judgment software, then GPS positions of components such as the hot spots, the component dust, the shielding and the like are identified, a route is automatically planned, and the detection accuracy is improved. The unmanned aerial vehicle or the robot is automatically controlled to mount a water tank or a cleaning brush to achieve assembly cleaning.

Description

Technical Field

[0001] The present invention belongs to the technical field of photovoltaic power generation, and particularly relates to a method and system for automatically controlling the cleaning of components based on the infrared and appearance of an unmanned aerial vehicle (UAV). Background Art

[0002] At present, the cleaning method of a photovoltaic power station uses a cleaning vehicle for cleaning, which has a high cost, and some mountainous areas, water surface photovoltaics, etc. cannot be cleaned; using the cleaning robot method requires installing more cleaning robots, and the cleaning cost is relatively high. Summary of the Invention

[0003] The purpose of the present invention is to provide a method and system for automatically controlling the cleaning of components based on the infrared and appearance of an unmanned aerial vehicle (UAV) to solve the above problems.

[0004] The present invention achieves the above purpose through the following technical solutions:

[0005] A method for automatically controlling the cleaning of components based on the infrared and appearance of an unmanned aerial vehicle (UAV) includes the following steps:

[0006] Performing three-dimensional modeling on the components of the photovoltaic power station based on the actual data of the photovoltaic power station to obtain a three-dimensional model;

[0007] Planning a UAV test flight path based on the three-dimensional model, and collecting infrared photos and appearance photos of the components of the photovoltaic power station;

[0008] Defining hot spot defect types and appearance defect types, constructing and training a hot spot defect model and an appearance defect model to obtain a final hot spot defect model and a final appearance defect model;

[0009] Inputting the infrared photos and appearance photos of the components of the photovoltaic power station into the final hot spot defect model and the final appearance defect model respectively to obtain a determination result;

[0010] Planning a cleaning flight path based on the determination result, and cleaning the defects on the components of the photovoltaic power station through a UAV.

[0011] As a further optimized solution of the present invention, the actual data of the photovoltaic power station includes the components actually used in the photovoltaic power station, inverters, brackets, energy storage, box transformers, and design files and GPS position information.

[0012] As a further optimized solution of the present invention, the three-dimensional model corresponds to the GPS position of the components of the photovoltaic power station, and the data link between the three-dimensional model and the actual components of the photovoltaic power station on site is connected; the three-dimensional model uses equal proportions, the same type of components, and the actual GPS position, and the detailed information and position of each sub-array of the power station can be viewed in real time; the three-dimensional model corresponds one by one to the strings corresponding to each branch of the inverter.

[0013] As a further optimization solution of the present invention, the hot spot defect types include hot spots and short circuits, and the appearance defect types include dust occlusion, bird droppings occlusion, and foreign object occlusion.

[0014] As a further optimization solution of the present invention, the specific process of planning the UAV test route based on the three-dimensional model and collecting the infrared photos and appearance photos of the photovoltaic power station components is as follows:

[0015] Plan the UAV infrared and appearance test routes through the GPS position of the three-dimensional model, and send down the UAV routes;

[0016] The UAV flies according to the route and takes pictures of the photovoltaic power station components on the route to collect infrared photos and appearance photos.

[0017] As a further optimization solution of the present invention, the specific process of planning the cleaning route based on the determination result and cleaning the defects on the photovoltaic power station components by the UAV is as follows:

[0018] Plan the cleaning route based on the defect positions on the photovoltaic power station components shown by the determination result;

[0019] Control the UAV to mount a water tank or a cleaning brush to clean the defect positions on the photovoltaic power station components based on the route.

[0020] A method for automatically controlling component cleaning based on UAV infrared and appearance also includes: real-time monitoring of the string current and power data corresponding to each branch of the inverter, analyzing the power generation loss of the string, establishing a power generation loss and cleaning cost model. If the power generation loss is less than the cleaning cost, no action is taken; if the power generation loss is greater than the cleaning cost, cleaning is performed.

[0021] A system for automatically controlling component cleaning based on UAV infrared and appearance includes:

[0022] A three-dimensional model construction module for performing three-dimensional modeling on the photovoltaic power station components based on the actual data of the photovoltaic power station to obtain a three-dimensional model;

[0023] A photo data collection module for planning the UAV infrared and appearance test routes based on the three-dimensional model and collecting the infrared photos and appearance photos of the photovoltaic power station components;

[0024] A model construction module for defining hot spot defect types and appearance defect types, constructing and training a hot spot defect model and an appearance defect model to obtain a final hot spot defect model and a final appearance defect model;

[0025] A determination module, configured to respectively input the infrared photo and the appearance photo of the photovoltaic power station component into the final hot spot defect model and the final appearance defect model to obtain a determination result;

[0026] A cleaning module, configured to plan a cleaning route based on the determination result, and clean the defects on the photovoltaic power station component by using a drone.

[0027] An electronic device includes a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete communication with each other through the communication bus;

[0028] The memory is used to store a computer program;

[0029] The processor is configured to implement an automatic control component cleaning method based on drone infrared and appearance when executing the program stored in the memory.

[0030] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, an automatic control component cleaning method based on drone infrared and appearance is implemented.

[0031] The beneficial effects of the present invention are as follows:

[0032] The present invention realizes the infrared thermal imaging and appearance testing of the entire photovoltaic power station through automatic control of drone infrared plus appearance. At the same time, through an automatic determination software, it can identify situations such as hot spots, component dust, and occlusion. Then, for the components with identified hot spots, component dust, and occlusion, their GPS positions are determined, and the cleaning route is automatically planned. The drone or robot is automatically controlled to mount a water tank or a cleaning brush to achieve component cleaning. This method can realize the refined operation and maintenance of the photovoltaic power station, realize the positioning and automatic cleaning of component dust, hot spots, etc., and solve the problem of high cost for one-time large-area cleaning of the photovoltaic power station. Description of the Drawings

[0033] Figure 1 is the method flow chart of the present invention;

[0034] Figure 2 is the system structure block diagram of the present invention;

[0035] Figure 3 is the device structure block diagram of the present invention. Detailed Embodiments

[0036] The following further describes the present application in detail with reference to the drawings. It is necessary to point out here that the following specific embodiments are only used to further illustrate the present application and cannot be understood as limiting the protection scope of the present application. Those skilled in the art can make some non-essential improvements and adjustments to the present application based on the above application content.

[0037] AsFigure 1 As shown in Figure 1 , a method for automatically controlling the cleaning of components based on the infrared and appearance of drones includes the following steps:

[0038] Perform three-dimensional modeling on the components of the photovoltaic power station based on the actual data of the photovoltaic power station to obtain a three-dimensional model;

[0039] Based on the three-dimensional model, plan the infrared and appearance test flight routes of the drone, and collect the infrared photos and appearance photos of the components of the photovoltaic power station;

[0040] Define the types of hot spot defects and appearance defects, construct and train the hot spot defect model and the appearance defect model to obtain the final hot spot defect model and the final appearance defect model;

[0041] Input the infrared photos and appearance photos of the components of the photovoltaic power station into the final hot spot defect model and the final appearance defect model respectively to obtain the determination results;

[0042] Based on the determination results, plan the cleaning flight route, and use the drone to clean the defects on the components of the photovoltaic power station.

[0043] The actual data of the photovoltaic power station includes the components actually used in the photovoltaic power station, inverters, brackets, energy storage, box transformers, and design files and GPS location information.

[0044] The three-dimensional model corresponds to the GPS location of the components of the photovoltaic power station, and the data link between the three-dimensional model and the actual components of the photovoltaic power station on site is connected; the three-dimensional model uses equal proportions, the same type of components, and the actual GPS location, and the detailed information and location of each sub-array of the power station can be viewed in real time; the three-dimensional model corresponds one-to-one with each string corresponding to each branch of the inverter.

[0045] The types of hot spot defects include hot spots and short circuits, and the types of appearance defects include dust occlusion, bird droppings occlusion, and foreign object occlusion.

[0046] The specific process of planning the infrared and appearance test flight routes of the drone based on the three-dimensional model and collecting the infrared photos and appearance photos of the components of the photovoltaic power station is as follows:

[0047] Plan the infrared and appearance test flight routes of the drone through the GPS location of the three-dimensional model, and send down the drone flight route;

[0048] The drone flies according to the flight route and takes pictures of the components of the photovoltaic power station on the flight route to collect infrared photos and appearance photos.

[0049] The specific process of planning the cleaning flight route based on the determination results and using the drone to clean the defects on the components of the photovoltaic power station is as follows:

[0050] Planning a cleaning route based on the defect locations on the photovoltaic power station components shown by the determination results;

[0051] Based on the route, the drone is controlled to carry a water tank or a cleaning brush to clean the defective positions on the photovoltaic power station components.

[0052] It also includes: real-time monitoring of the string current and power data corresponding to each branch of the inverter, analyzing the power generation loss of the string, establishing a power generation loss and cleaning cost model, and if the power generation loss is less than the cleaning cost, no action is taken; if the power generation loss is greater than the cleaning cost, cleaning is performed.

[0053] In this embodiment, the specific steps are:

[0054] (1) First, the power station needs to be modeled. The three-dimensional interface corresponds to the GPS location on site, so that the background can monitor the on-site information in real time, and the data link between the virtual power station and the actual power station on site is connected. Collect information such as the components, inverters, brackets, energy storage, box transformers, design files, GPS locations, etc. actually used in the power station to build a three-dimensional model on the computer. The three-dimensional model uses proportional, same-type components and actual GPS locations, and can view the detailed information and location of each sub-array of the power station in real time. In addition, the strings corresponding to each branch of the inverter also correspond one by one in the three-dimensional interface. The three-dimensional interface can realize the data link of each string in the three-dimensional interface by collecting the data of the inverter branches, and realize the real-time display of the string interface data;

[0055] (2) The infrared and appearance test routes of drones for the entire station are automatically planned through the GPS position of the power station's three-dimensional interface, and the drone routes can be issued. The infrared and appearance test of drones for the entire power station can be carried out through the background;

[0056] (3) For the collected component appearance photos, firstly, the appearance defect types are manually defined, including dust occlusion, bird droppings occlusion, foreign body occlusion, etc., and then the appearance defect model is trained by machine learning, so that the appearance photo input can be automatically judged; the infrared defect types are manually defined, including hot spots, short circuits, etc., and then the hot spot defect model is trained by machine learning, so that the hot spot photo input can be automatically judged;

[0057] (4) After the test is completed, the collected infrared and appearance photos can be automatically judged for appearance defects through the developed appearance automatic judgment software, automatically generate test reports, and display defective components in real time in the three-dimensional interface group string;

[0058] (5) According to the location of the defective component displayed on the three-dimensional interface, the cleaning route is automatically planned. The cleaning route is planned to include all defect types, keep the test route as short as possible, and maximize the test efficiency;

[0059] (6) According to the cleaning route, the computer software can start the control of the drone or robot to mount the water tank or cleaning brush with one key to achieve the cleaning of the components. After the cleaning is completed, the task ends.

[0060] (7) Real-time monitor the series current and power data, analyze the power generation loss of the series, establish a power generation loss and cleaning cost model. When the power generation loss < cleaning cost, do not act; when the power generation loss > cleaning cost, the automatic control of the software can be realized, and the above steps are carried out to improve the power generation of the power station.

[0061] The present invention provides a method for automatically controlling the cleaning of components based on the infrared and appearance of drones. First, determine whether cleaning is required according to the dirt degree of the components. Secondly, automatically plan the route and use the drone or robot to mount the water tank or cleaning brush to achieve the cleaning of the components. The whole process realizes automatic control and targeted cleaning, realizes refined management of cleaning, and saves investment costs.

[0062] As Figure 2 shown, the embodiment of the present disclosure provides a system for automatically controlling the cleaning of components based on the infrared and appearance of drones, including:

[0063] A three-dimensional model construction module for three-dimensionally modeling the components of the photovoltaic power station based on the actual data of the photovoltaic power station to obtain a three-dimensional model;

[0064] A photo data acquisition module for planning the infrared and appearance test routes of the drone based on the three-dimensional model and acquiring the infrared photos and appearance photos of the components of the photovoltaic power station;

[0065] A model construction module for defining the types of hot spot defects and appearance defects, constructing and training the hot spot defect model and the appearance defect model to obtain the final hot spot defect model and the final appearance defect model;

[0066] A determination module for respectively inputting the infrared photos and appearance photos of the components of the photovoltaic power station into the final hot spot defect model and the final appearance defect model to obtain a determination result;

[0067] A cleaning module for planning the cleaning route based on the determination result and cleaning the defects on the components of the photovoltaic power station through the drone.

[0068] For the specific implementation process of the functions and roles of each module in the above system, please refer to the implementation process of the corresponding steps in the above method for details, and will not be elaborated here.

[0069] For the system embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial descriptions of the method embodiments. The system embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of the present invention. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0070] In the above embodiments, any number of all the modules can be combined and implemented in one module, or any one of the modules can be split into multiple modules. Or, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. At least one of all the modules can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by any other reasonable way of integrating or packaging circuits, etc., in hardware or firmware, or implemented in any one of the three implementation ways of software, hardware, and firmware, or in an appropriate combination of any several of them. Or, at least one of all the modules can be at least partially implemented as a computer program module, and when the computer program module runs, it can execute the corresponding functions.

[0071] See Figure 3 , the electronic device provided by the embodiments of the present disclosure includes a processor 1110, a communication interface 1120, a memory 1130, and a communication bus 1140. Among them, the processor 1110, the communication interface 1120, and the memory 1130 communicate with each other through the communication bus 1140;

[0072] The memory 1130 is used to store computer programs;

[0073] When the processor 1110 is used to execute the program stored on the memory 1130, it implements the method for automatically controlling the cleaning of components based on the infrared and appearance of the drone as shown below.

[0074] The above communication bus 1140 can be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus 1140 can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0075] The communication interface 1120 is used for communication between the above electronic device and other devices.

[0076] The memory 1130 can include a Random Access Memory (RAM), and can also include a non-volatile memory, such as at least one disk memory. Optionally, the memory 1130 can also be at least one storage device located far from the aforementioned processor 1110.

[0077] The above processor 1110 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0078] An embodiment of the present disclosure also provides a computer-readable storage medium. A computer program is stored on the above computer-readable storage medium, and when the computer program is executed by a processor, it implements the method for automatically controlling component cleaning based on the infrared and appearance of an unmanned aerial vehicle as described above.

[0079] The computer-readable storage medium can be included in the device / device described in the above embodiment; it can also exist alone without being assembled into the device / device. The above computer-readable storage medium carries one or more programs, and when the one or more programs are executed, it implements the method for automatically controlling component cleaning based on the infrared and appearance of an unmanned aerial vehicle according to the embodiments of the present disclosure.

[0080] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, it may include but is not limited to: portable computer disks, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), portable compact disk read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device.

[0081] The above-described embodiments merely represent several implementation manners of the present invention, and the description thereof is relatively specific and detailed. However, it should not be construed as a limitation on the scope of the patent of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention.

Claims

1. A method for automatically controlling the cleaning of components based on UAV infrared and appearance, characterized in that, it includes the following steps: Perform three-dimensional modeling on the components of the photovoltaic power station based on the actual data of the photovoltaic power station to obtain a three-dimensional model; Based on the three-dimensional model, plan the UAV test flight path and collect infrared photos and appearance photos of the components of the photovoltaic power station; Define the types of hot spot defects and appearance defects, construct and train the hot spot defect model and the appearance defect model to obtain the final hot spot defect model and the final appearance defect model; Input the infrared photos and appearance photos of the components of the photovoltaic power station into the final hot spot defect model and the final appearance defect model respectively to obtain the determination results; Based on the determination results, plan the cleaning flight path and use the UAV to clean the defects on the components of the photovoltaic power station.

2. The method for automatically controlling the cleaning of components based on UAV infrared and appearance according to claim 1, characterized in that, the actual data of the photovoltaic power station includes the components actually used in the photovoltaic power station, inverters, brackets, energy storage, box transformers, and design files and GPS position information.

3. The method for automatically controlling the cleaning of components based on UAV infrared and appearance according to claim 2, characterized in that, the three-dimensional model corresponds to the GPS position of the components of the photovoltaic power station, and the data link between the three-dimensional model and the actual components of the photovoltaic power station on site is connected; the three-dimensional model uses the same scale, the same type of components, and the actual GPS position, and the detailed information and position of each sub-array of the power station can be viewed in real time; the three-dimensional model corresponds one by one to the strings corresponding to each branch of the inverter.

4. The method for automatically controlling the cleaning of components based on UAV infrared and appearance according to claim 1, characterized in that, the types of hot spot defects include hot spots and short circuits, and the types of appearance defects include dust occlusion, bird droppings occlusion, and foreign object occlusion.

5. The method for automatically controlling the cleaning of components based on UAV infrared and appearance according to claim 1, characterized in that, the specific process of planning the UAV test flight path based on the three-dimensional model and collecting infrared photos and appearance photos of the components of the photovoltaic power station is as follows: Plan the UAV infrared and appearance test flight paths through the GPS position of the three-dimensional model and send down the UAV flight paths; The UAV flies according to the flight paths and takes pictures of the components of the photovoltaic power station on the flight paths to collect infrared photos and appearance photos.

6. The method for automatically controlling the cleaning of components based on UAV infrared and appearance according to claim 1, characterized in that, the specific process of planning the cleaning flight path based on the determination results and using the UAV to clean the defects on the components of the photovoltaic power station is as follows: Plan the cleaning flight path based on the defect positions on the components of the photovoltaic power station shown by the determination results; Based on the flight paths, control the UAV to carry a water tank or a cleaning brush to clean the defect positions on the components of the photovoltaic power station.

7. The method for automatically controlling the cleaning of components based on UAV infrared and appearance according to claim 1, characterized in that, It further includes: real-time monitoring of the string current and power data corresponding to each branch of the inverter, analyzing the power generation loss of the string, establishing a model of power generation loss and cleaning cost. If the power generation loss is less than the cleaning cost, no action is taken; if the power generation loss is greater than the cleaning cost, cleaning is performed.

8. An automatic control component cleaning system based on UAV infrared and appearance Characterized in that It includes: A three-dimensional model construction module for three-dimensionally modeling the photovoltaic power station components based on the actual data of the photovoltaic power station to obtain a three-dimensional model; A photo data acquisition module for planning the UAV infrared and appearance test flight paths based on the three-dimensional model and acquiring the infrared photos and appearance photos of the photovoltaic power station components; A model construction module for defining the hot spot defect type and appearance defect type, constructing and training the hot spot defect model and appearance defect model to obtain the final hot spot defect model and final appearance defect model; A determination module for respectively inputting the infrared photos and appearance photos of the photovoltaic power station components into the final hot spot defect model and the final appearance defect model to obtain a determination result; A cleaning module for planning the cleaning flight path based on the determination result and cleaning the defects on the photovoltaic power station components by the UAV.

9. An electronic device Characterized in that It includes a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete mutual communication through the communication bus; The memory is used for storing computer programs; The processor, when executing the programs stored in the memory, implements the automatic control component cleaning method based on UAV infrared and appearance described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program Characterized in that When the computer program is executed by the processor, it implements the automatic control component cleaning method based on UAV infrared and appearance described in any one of claims 1-7.

Images