A robot control method, system, terminal and medium for cleaning photovoltaic panels

Through dynamic planning and intelligent monitoring technology, the area is divided and priority is set according to the dust accumulation amount and power generation efficiency of photovoltaic panels, which solves the problem of low efficiency of existing photovoltaic panel cleaning robots and achieves efficient and low-cost cleaning effects.

CN115446841BActive Publication Date: 2024-11-08XIAN WANFEI CONTROL TECH CO LTD
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
CN202211318491.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-10-26
Publication Date
2024-11-08
Estimated Expiration
2042-10-26

AI Technical Summary

Technical Problem

The existing photovoltaic panel cleaning robots are inefficient and cannot complete the cleaning tasks adaptively. Their intelligence is not high, resulting in high cost and the advantages of cleaning robots cannot be fully utilized.

Method used

By obtaining photovoltaic panel cleaning task information, setting initial task parameters, and regional division and priority settings are made based on the dust accumulation amount and power generation efficiency. Improved genetic algorithms and Hamiltonian graphs are used to plan the cleaning path, and combined with wavelet neural network to predict power generation loss. Dynamically adjust the cleaning cycle to realize multi-level planning and automatic monitoring.

Benefits of technology

It improves the cleaning efficiency of photovoltaic panels, reduces costs, achieves the optimal cleaning efficiency, and gives full play to the advantages of cleaning robots.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115446841B_ABST
    Figure CN115446841B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of photovoltaic panel cleaning, and discloses a robot control method, system, terminal and medium for cleaning photovoltaic panels. The method obtains photovoltaic panel cleaning task information, sets initialization task parameters according to the cleaning task information, and plans cleaning tasks according to the photovoltaic panel cleaning task information. The method divides the photovoltaic panels into regions according to the dust accumulation and power generation efficiency, and sets priorities for the regions. The proposed method dynamically calculates cleaning cycles and multi-level planning of cleaning tasks reduces manual operations, has a high degree of intelligence, greatly improves photovoltaic panel cleaning efficiency, achieves optimal cleaning cost and cleaning benefit, has low comprehensive cost, and gives full play to the advantages of the cleaning robot.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of photovoltaic panel cleaning, and in particular to a robot control method, system, terminal and medium for cleaning photovoltaic panels. Background Art

[0002] Photovoltaic energy is an important part of new energy and has received strong support from the country. More and more photovoltaic power station projects have been put into operation. The photovoltaic panels in the photovoltaic power station are arranged in the open air. After a period of operation, the dust and other dirt accumulated on the photovoltaic panels will affect the normal operation of the photovoltaic panels and reduce the power generation efficiency. Therefore, the photovoltaic panels need to be cleaned regularly. At present, the common methods of cleaning photovoltaic panels include manual cleaning, cleaning machine cleaning and robot cleaning. Among them, manual cleaning has low efficiency and high cost; large cleaning equipment is limited by the terrain of photovoltaic panels and the narrow arrangement gap; cleaning robots can adapt to various types of photovoltaic power stations, and at the same time have high cleaning efficiency and low comprehensive cost, so it is an effective way to clean photovoltaic panels.

[0003] Currently, most photovoltaic panel cleaning robots are used for single-row photovoltaic panels. A large number of robots need to be deployed in the entire photovoltaic power station to complete the cleaning task, which is costly. At the same time, the cleaning robot system has a single function and cannot complete the cleaning task adaptively. It is not intelligent enough and cannot give full play to the advantages of the cleaning robot. Summary of the invention

[0004] In order to overcome the defects of the above-mentioned prior art, the purpose of the present invention is to provide a robot control method, system, terminal and medium for cleaning photovoltaic panels, so as to solve the technical problem of low photovoltaic panel cleaning efficiency in the prior art.

[0005] The present invention is achieved through the following technical solutions:

[0006] A robot control method for cleaning photovoltaic panels comprises the following steps:

[0007] Step 1, obtaining photovoltaic panel cleaning task information, and setting initialization task parameters according to the cleaning task information;

[0008] Step 2: Plan the cleaning tasks according to the photovoltaic panel cleaning task information, divide the photovoltaic panels into different areas according to the amount of dust accumulation and power generation efficiency, and set priorities for the areas;

[0009] Step 3: Perform global path planning according to the cleaning task planning, locate the initial position, establish navigation points, and plan the operation trajectory;

[0010] Step 4, sending a cleaning instruction according to the running trajectory;

[0011] Step 5, monitor the dust accumulation and power generation efficiency of the photovoltaic panel; when the dust accumulation and power generation efficiency do not reach the threshold, re-plan the cleaning task, perform local path planning, establish navigation points, plan the operation trajectory, and send a cleaning instruction; otherwise, complete the cleaning and send a recycling instruction.

[0012] Preferably, in step 1, the cleaning mode is set according to the photovoltaic panel cleaning task information, and the initialization task parameters are set, wherein the initialization task parameters include the number of cleaning times, task time and running speed.

[0013] Preferably, in step 2, the cleaning task planning method steps are as follows:

[0014] Step 21, dividing the photovoltaic panels in the photovoltaic power station into regions according to the amount of dust accumulation and power generation efficiency of the photovoltaic panels;

[0015] Step 22, setting a priority for each area, wherein priority is set for areas with a large amount of dust in the environment, which are prone to dust accumulation and result in reduced power generation, and areas with sufficient light and high power generation efficiency;

[0016] Step 23, after dividing the regions, mark the geometric center of each region in the regional coordinate system, locate the initial position, and traverse all regions.

[0017] Furthermore, in step 22, a priority is set for each area, and the area with a high priority is cleaned first. The areas with the same priority are cleaned using an improved genetic algorithm, wherein the steps are as follows:

[0018] Step 221, sorting the regions according to priority, determining the priority sorting and the sequence to be sorted using the genetic algorithm;

[0019] Step 222, generating an initial population for the sequence to be sorted using the genetic algorithm, setting parameters such as the fitness function, population size, crossover threshold Q, crossover probability, heuristic mutation probability, and maximum number of iterations;

[0020] Step 223, dynamically linearly calibrate the distances between the regions and convert them into a fitness function for finding the maximum value;

[0021] Step 224, screening out individuals that directly enter the next generation, and selecting the parent generation that participates in the crossover;

[0022] Step 225, perform a crossover operation on the parent generation. When the optimal path of this iteration is greater than the threshold Q, perform a sequential crossover, otherwise perform a self-crossover;

[0023] Step 226, performing a heuristic mutation operation on the generated offspring;

[0024] Step 227, determine whether the termination condition is met, if so, output the optimal solution, otherwise return to execute step 223.

[0025] Furthermore, in step 23, the order of traversing all areas is solved by constructing a Hamiltonian graph, in which the vertices are photovoltaic panel areas, the edges are Manhattan distances between the areas, and the hierarchical planning of photovoltaic panel cleaning tasks is completed in all areas through a shortest Hamiltonian circuit.

[0026] Preferably, in step 5, the dust accumulation and power generation efficiency of the photovoltaic panels are monitored, and the dust accumulation of the photovoltaic panels and the power generation efficiency of cleaning the photovoltaic panels are quantified by the power generation loss and power generation capacity of the photovoltaic modules: by obtaining the power generation of the photovoltaic panels working normally under the current meteorological conditions, and comparing the power generation of the clean photovoltaic modules in the sample under similar meteorological conditions, the power generation loss is calculated.

[0027] Furthermore, the power generation loss is predicted by wavelet neural network. The input variables of the wavelet neural network are single-day weather parameters, irradiation, average temperature, weather conditions, wind speed, and the output variable is the power generation loss. The training set and test set are selected based on the power generation loss caused by dust and the corresponding single-day weather parameters, and then the wavelet neural network prediction model is trained and tested. After the wavelet neural network prediction model is established, the power generation loss caused by daily dust in the next few days is predicted based on weather forecast data.

[0028] A robot control system for cleaning photovoltaic panels, comprising:

[0029] The first processing module is used to obtain photovoltaic panel cleaning task information and set initialization task parameters according to the cleaning task information;

[0030] A setting module is used to plan cleaning tasks according to the photovoltaic panel cleaning task information, divide the areas according to the amount of dust accumulation and power generation efficiency of the photovoltaic panels, and set priorities for the areas;

[0031] The second processing module is used to perform global path planning according to the cleaning task planning, locate the initial position, establish navigation points, and plan the operation trajectory;

[0032] An instruction sending module, used for sending cleaning instructions according to the running trajectory;

[0033] The third processing module monitors the dust accumulation and power generation efficiency of the photovoltaic panels. When the dust accumulation and power generation efficiency do not reach the threshold, the cleaning task is re-planned, local path planning is performed, navigation points are established, the operation trajectory is planned, and cleaning instructions are sent. Otherwise, the cleaning is completed and a recycling instruction is sent.

[0034] A mobile terminal comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the robot control method for cleaning photovoltaic panels as described above are implemented.

[0035] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the robot control method for cleaning photovoltaic panels as described above are implemented.

[0036] Compared with the prior art, the present invention has the following beneficial technical effects:

[0037] The present invention provides a robot control method for cleaning photovoltaic panels, which obtains photovoltaic panel cleaning task information, sets initialization task parameters according to the cleaning task information, plans cleaning tasks according to the photovoltaic panel cleaning task information, divides regions according to the dust accumulation and power generation efficiency of the photovoltaic panels, and sets priorities for the regions. The proposed dynamic calculation of cleaning cycles and multi-level planning of cleaning tasks reduce manual operations, have a high degree of intelligence, greatly improve the cleaning efficiency of the photovoltaic panels, achieve optimal cleaning costs and cleaning benefits, have low overall costs, and give full play to the advantages of the cleaning robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 is a flow chart of a robot control method for cleaning photovoltaic panels in the present invention;

[0039] Figure 2 Schematic diagram of system control in an embodiment of the present invention. DETAILED DESCRIPTION

[0040] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0041] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0042] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0043] The purpose of the present invention is to provide a robot control method, system, terminal and medium for cleaning photovoltaic panels, so as to solve the technical problem of low photovoltaic panel cleaning efficiency in the prior art.

[0044] Specifically, according to Figure 1 As shown, the robot control method for cleaning photovoltaic panels includes the following steps:

[0045] Step 1, obtaining photovoltaic panel cleaning task information, and setting initialization task parameters according to the cleaning task information;

[0046] Specifically, the cleaning mode is set according to the photovoltaic panel cleaning task information, and the initialization task parameters are set, wherein the initialization task parameters include the number of cleaning times, task time, and running speed.

[0047] Step 2: Plan the cleaning tasks according to the photovoltaic panel cleaning task information, divide the photovoltaic panels into different areas according to the amount of dust accumulation and power generation efficiency, and set priorities for the areas;

[0048] Specifically, the steps of the cleaning task planning method are as follows:

[0049] Step 21, dividing the photovoltaic panels in the photovoltaic power station into regions according to the amount of dust accumulation and power generation efficiency of the photovoltaic panels;

[0050] Step 22, setting a priority for each area, wherein priority is set for areas with a large amount of dust in the environment, which are prone to dust accumulation and result in reduced power generation, and areas with sufficient light and high power generation efficiency;

[0051] Among them, the priority is set for each area, and the area with high priority is cleaned first. The areas with the same priority are cleaned using an improved genetic algorithm. The steps are as follows:

[0052] Step 221, sorting the regions according to priority, determining the priority sorting and the sequence to be sorted using the genetic algorithm;

[0053] Step 222, generating an initial population for the sequence to be sorted using the genetic algorithm, setting parameters such as the fitness function, population size, crossover threshold Q, crossover probability, heuristic mutation probability, and maximum number of iterations;

[0054] Step 223, dynamically linearly calibrate the distances between the regions and convert them into a fitness function for finding the maximum value;

[0055] Step 224, screening out individuals that directly enter the next generation, and selecting the parent generation that participates in the crossover;

[0056] Step 225, perform a crossover operation on the parent generation. When the optimal path of this iteration is greater than the threshold Q, perform a sequential crossover, otherwise perform a self-crossover;

[0057] Step 226, performing a heuristic mutation operation on the generated offspring;

[0058] Step 227, determine whether the termination condition is met, if so, output the optimal solution, otherwise return to execute step 223.

[0059] Step 23, after dividing the regions, mark the geometric center of each region in the regional coordinate system, locate the initial position, and traverse all regions.

[0060] The order of traversing all areas is solved by constructing a Hamiltonian graph, in which the vertices are the photovoltaic panel areas and the edges are the Manhattan distances between the areas. The hierarchical planning of the photovoltaic panel cleaning tasks is completed in all areas through a shortest Hamiltonian circuit.

[0061] Step 3: Perform global path planning according to the cleaning task planning, locate the initial position, establish navigation points, and plan the operation trajectory;

[0062] Step 4, sending a cleaning instruction according to the running trajectory;

[0063] Step 5, monitor the dust accumulation and power generation efficiency of the photovoltaic panel; when the dust accumulation and power generation efficiency do not reach the threshold, re-plan the cleaning task, perform local path planning, establish navigation points, plan the operation trajectory, and send a cleaning instruction; otherwise, complete the cleaning and send a recycling instruction.

[0064] Specifically, the dust accumulation and power generation efficiency of photovoltaic panels are monitored. The dust accumulation of photovoltaic panels and the power generation efficiency of cleaning photovoltaic panels are quantified through the power generation loss and power generation capacity of photovoltaic modules: by obtaining the power generation of photovoltaic panels working normally under current meteorological conditions, comparing the power generation of clean photovoltaic modules in the sample under similar meteorological conditions, the power generation loss is calculated.

[0065] Among them, the power generation loss is predicted by wavelet neural network. The input variables of the wavelet neural network are single-day weather parameters, irradiation, average temperature, weather conditions, wind speed, and the output variable is the power generation loss. The training set and test set are selected based on the power generation loss caused by dust and the corresponding single-day weather parameters, and then the wavelet neural network prediction model is trained and tested. After the wavelet neural network prediction model is established, the power generation loss caused by daily dust in the next few days is predicted according to the weather forecast data.

[0066] To calculate the dynamic cleaning cycle, the automatic monitoring system monitors the power generation of different photovoltaic modules in real time. When the cumulative value of dust impact on the module reaches the preset dust impact threshold M, the system refers to the rainfall forecast for the next few days and considers the economic benefits of the increased photovoltaic power generation efficiency after cleaning and the cost of a single cleaning to determine whether to clean the module.

[0067] Example

[0068] In this embodiment, the robot includes an upper mobile cleaning robot, a ground transfer robot, a collaborative cleaning control system, and a cleaning task planning system. Figure 2 As shown; the on-board mobile robot cleans the photovoltaic panels in rows, the ground transfer robot docks with the mobile robot, and transfers to the target photovoltaic panel according to the current task status of the mobile robot; the cleaning task planning system determines the dynamic cleaning cycle according to the dust accumulation and power generation loss of the photovoltaic panel, and plans the cleaning tasks in a hierarchical manner.

[0069] The sensors installed in the mobile robot system include ultrasonic ranging sensors, ambient light sensors, visible light cameras, IMUs and pressure sensors. The ultrasonic ranging sensors measure the distance between the bottom of the robot and the photovoltaic panel, and between the robot periphery and the photovoltaic panel frame, identify the gap between the photovoltaic panels and prevent the robot from falling from the edge; the IMU is used to estimate the position of the mobile robot, integrate the encoder and the odometer to achieve the positioning of the robot, and record the robot's movement trajectory to determine whether the robot's movement deviates from the predetermined cleaning route; the ambient light sensor is used to compare the reflected light intensity on the surface of the photovoltaic wafer before and after cleaning to determine the cleaning effect. If the reflected light intensity does not change much and the cleaning effect does not meet expectations, the mobile robot replans the local cleaning route and cleans the photovoltaic panel again; the visible light camera is used to distinguish between attachments that are difficult to clean and defects in the photovoltaic panel; the pressure sensor monitors the pressure applied by the robot to the photovoltaic panel, and adjusts the pressure of the cleaning components on the photovoltaic panel through the vacuum device to ensure the cleaning effect and efficiency, and avoid damage to the photovoltaic panel.

[0070] The cleaning device combines multiple cleaning methods and consists of a dry brush, a dust suction device and a silicone brush. The dry brush is used to sweep away the dust adsorbed on the photovoltaic panel; the dust suction device is used to suck away the dust swept by the dry brush and send it into the dust collection box, while providing a certain downward pressure to keep the cleaning device away from the photovoltaic panel; the silicone brush is used to clean and collect trace residual dust on the photovoltaic panel.

[0071] In order to enable the cleaning robot to cross the gaps between photovoltaic panels and cover all photovoltaic panels without manual operation, a cleaning mode in which the onboard mobile robot and the ground transfer robot collaborate is adopted. The onboard mobile robot and the ground transfer robot transmit and interact with each other, and work together under different actual scene working conditions.

[0072] The on-board mobile robot cleans the photovoltaic panels in rows. When the cleaning robot completes the cleaning of a row of photovoltaic panels and reaches the edge of the photovoltaic panels, the mobile robot reports the current positioning and status information to the background scheduling system. The scheduling system sends the positioning of the mobile robot on the floor to the ground transfer robot. The transfer robot moves to the position of the on-board robot, uses the ultrasonic positioning method, and completes the docking with the mobile robot through the electromagnetic docking mechanism. According to the current task status of the mobile robot, it is transferred to the next row of photovoltaic panels or transported to the transfer station.

[0073] The on-board mobile cleaning robot adopts two power supply modes, photovoltaic and battery, so that the robot can work in multiple working conditions throughout the day; after the mobile robot starts the cleaning task, it checks the battery power to ensure that the robot can complete the cleaning of a row of photovoltaic panels; after the mobile robot completes the cleaning of a row of photovoltaic panels, it triggers the photoelectric sensor on the edge photovoltaic panel, the robot stops cleaning, uploads the status data to the background server, and waits to establish communication and docking with the ground transfer robot; the ground transfer robot is dispatched by the background server, and after arriving at the designated location, it attempts to establish communication and docking with the mobile cleaning robot, and transfers to the next destination according to the cleaning robot's power and task status.

[0074] Dust accumulation on photovoltaic panels will lead to a decrease in the power generation of photovoltaic power stations. The dispatching system determines the amount of dust accumulation on photovoltaic modules and calculates the dynamic cleaning cycle of photovoltaic modules. The amount of dust accumulated on the photovoltaic modules is quantified by the power generation loss and power generation capacity of the photovoltaic modules. The power generation of the photovoltaic panels working normally under the current meteorological conditions is obtained and compared with the power generation of the clean photovoltaic modules in the sample under similar meteorological conditions. The power generation difference is caused by the current amount of dust accumulation. The power generation capacity is further defined as the ratio of the daily ideal power generation to the daily actual power generation under the same photovoltaic module state under the same environment. The optimal cleaning effect cycle of the photovoltaic module is Tl, and the general cycle is T2. During the optimal cleaning effect cycle, the photovoltaic panel is basically free of dust. N groups of irradiance values ​​I and the corresponding power generation E are sampled and recorded. The irradiance and ideal power generation curves are obtained by fitting the scatter plot of the optimal cleaning cycle data. The actual power generation and the optimal cleaning power generation under the same solar radiation are integrated respectively to obtain the power generation capacity of the photovoltaic module. The performance of the photovoltaic module will decay with the increase of service life. The power generation of the clean module under the same irradiance will also be different. The actual attenuation rate of the module is obtained according to the relationship between the irradiance and the ideal power generation of the photovoltaic panel laboratory, and the influence of the module attenuation on the power generation is eliminated.

[0075] The dust accumulation of photovoltaic modules is predicted based on wavelet neural network. The input variables of wavelet neural network are daily weather parameters, irradiation, average temperature, weather conditions, wind speed, and the output variable is the loss of power generation. The training set and test set are selected based on the power generation loss caused by dust and the corresponding daily weather parameters. The neural network model is trained and tested, and the power generation loss caused by daily dust in the next few days is predicted according to the weather forecast data.

[0076] Determine the dynamic cleaning cycle of the photovoltaic panels, and monitor the power generation of different photovoltaic modules in real time through the automatic monitoring system. If the cumulative value of the dust impact on the photovoltaic panels reaches the pre-set dust impact threshold, and refer to the rainfall forecast in the next few days, consider the economic benefits of the increased photovoltaic power generation efficiency after cleaning and the cost of a single cleaning to determine the cleaning cycle.

[0077] The cleaning tasks of photovoltaic power stations are planned in a hierarchical manner. First, the photovoltaic power station is divided into regions. The regional division standards are dust accumulation and power generation efficiency. Priorities are set for each region. Higher priorities are set for areas with high dust content and easy dust accumulation in the environment and areas with sufficient light and high power generation efficiency. After the regions are divided, the geometric center of each region is marked in the coordinate system. The cleaning robot starts from the starting point and traverses all regions. The traversal order is solved by constructing a Hamiltonian graph. The vertices of the Hamiltonian graph are photovoltaic panel regions, and the edges are Manhattan distances between regions. The hierarchical planning of photovoltaic panel cleaning tasks is completed by finding the shortest Hamiltonian circuit. First, the regions are sorted by priority, and the regions with high priority are cleaned first. For regions with the same priority, an improved genetic algorithm is used to plan and solve the cleaning tasks.

[0078] The on-board mobile cleaning robot cleans the photovoltaic panels in rows. A ground transfer robot and a robot transfer system are set at the edge of the photovoltaic array. The ground transfer robot is used to transfer the on-board mobile cleaning robot to other photovoltaic panels to be cleaned; the transfer system includes an infrared positioning system, a robot charging station and a bracket; the on-board mobile cleaning robot is powered by light and battery, so that the robot can work in multiple working conditions throughout the day, and the photovoltaic panel cleaning task can be arranged when the power generation efficiency is low or at night.

[0079] The present invention also provides a robot control system for cleaning photovoltaic panels, comprising a first processing module, a setting module, a second processing module, an instruction sending module and a third processing module;

[0080] The first processing module is used to obtain photovoltaic panel cleaning task information and set initialization task parameters according to the cleaning task information;

[0081] A setting module is used to plan cleaning tasks according to the photovoltaic panel cleaning task information, divide the areas according to the amount of dust accumulation and power generation efficiency of the photovoltaic panels, and set priorities for the areas;

[0082] The second processing module is used to perform global path planning according to the cleaning task planning, locate the initial position, establish navigation points, and plan the operation trajectory;

[0083] An instruction sending module, used for sending cleaning instructions according to the running trajectory;

[0084] The third processing module monitors the dust accumulation and power generation efficiency of the photovoltaic panels. When the dust accumulation and power generation efficiency do not reach the threshold, the cleaning task is re-planned, local path planning is performed, navigation points are established, the operation trajectory is planned, and cleaning instructions are sent. Otherwise, the cleaning is completed and a recycling instruction is sent.

[0085] The present invention also provides a mobile terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, such as a robot control program for cleaning photovoltaic panels.

[0086] When the processor executes the computer program, the steps of the robot control method for cleaning photovoltaic panels are implemented, for example:

[0087] Step 1, obtaining photovoltaic panel cleaning task information, and setting initialization task parameters according to the cleaning task information;

[0088] Step 2: Plan the cleaning tasks according to the photovoltaic panel cleaning task information, divide the photovoltaic panels into different areas according to the amount of dust accumulation and power generation efficiency, and set priorities for the areas;

[0089] Step 3: Perform global path planning according to the cleaning task planning, locate the initial position, establish navigation points, and plan the operation trajectory;

[0090] Step 4, sending a cleaning instruction according to the running trajectory;

[0091] Step 5, monitor the dust accumulation and power generation efficiency of the photovoltaic panel; when the dust accumulation and power generation efficiency do not reach the threshold, re-plan the cleaning task, perform local path planning, establish navigation points, plan the operation trajectory, and send a cleaning instruction; otherwise, complete the cleaning and send a recycling instruction.

[0092] Alternatively, when the processor executes the computer program, the functions of each module in the above system are realized, for example:

[0093] The first processing module is used to obtain photovoltaic panel cleaning task information and set initialization task parameters according to the cleaning task information;

[0094] A setting module is used to plan cleaning tasks according to the photovoltaic panel cleaning task information, divide the areas according to the amount of dust accumulation and power generation efficiency of the photovoltaic panels, and set priorities for the areas;

[0095] The second processing module is used to perform global path planning according to the cleaning task planning, locate the initial position, establish navigation points, and plan the operation trajectory;

[0096] An instruction sending module, used for sending cleaning instructions according to the running trajectory;

[0097] The third processing module monitors the dust accumulation and power generation efficiency of the photovoltaic panels. When the dust accumulation and power generation efficiency do not reach the threshold, the cleaning task is re-planned, local path planning is performed, navigation points are established, the operation trajectory is planned, and cleaning instructions are sent. Otherwise, the cleaning is completed and a recycling instruction is sent.

[0098] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the mobile terminal. For example, the computer program may be divided into a first processing module, a setting module, a second processing module, an instruction sending module, and a third processing module;

[0099] The first processing module is used to obtain photovoltaic panel cleaning task information and set initialization task parameters according to the cleaning task information;

[0100] A setting module is used to plan cleaning tasks according to the photovoltaic panel cleaning task information, divide the areas according to the amount of dust accumulation and power generation efficiency of the photovoltaic panels, and set priorities for the areas;

[0101] The second processing module is used to perform global path planning according to the cleaning task planning, locate the initial position, establish navigation points, and plan the operation trajectory;

[0102] An instruction sending module, used for sending cleaning instructions according to the running trajectory;

[0103] The third processing module monitors the dust accumulation and power generation efficiency of the photovoltaic panels. When the dust accumulation and power generation efficiency do not reach the threshold, the cleaning task is re-planned, local path planning is performed, navigation points are established, the operation trajectory is planned, and cleaning instructions are sent. Otherwise, the cleaning is completed and a recycling instruction is sent.

[0104] The mobile terminal may be a computing device such as a desktop computer, a notebook, a palm computer, a cloud server, etc. The mobile terminal may include, but is not limited to, a processor and a memory.

[0105] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the mobile terminal, and uses various interfaces and lines to connect various parts of the entire mobile terminal.

[0106] The memory may be used to store the computer programs and / or modules, and the processor implements various functions of the mobile terminal by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory.

[0107] The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0108] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the robot control method for cleaning photovoltaic panels are implemented.

[0109] If the module / unit integrated in the mobile terminal is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0110] Based on such understanding, the present invention implements all or part of the processes in the above method, and can also be completed by instructing related hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the robot control method for cleaning photovoltaic panels can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc.

[0111] The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0112] It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media does not include electrical carrier signals and telecommunication signals.

[0113] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A robot control method for cleaning photovoltaic panels, characterized in that: The steps include: Step 1, obtaining photovoltaic panel cleaning task information, and setting initialization task parameters according to the cleaning task information; Step 2: Plan the cleaning tasks according to the photovoltaic panel cleaning task information, divide the photovoltaic panels into different areas according to the amount of dust accumulation and power generation efficiency, and set priorities for the areas; The steps of cleaning task planning method are as follows: Step 21, dividing the photovoltaic panels in the photovoltaic power station into regions according to the amount of dust accumulation and power generation efficiency of the photovoltaic panels; Step 22, setting a priority for each area, wherein a higher priority is set for an area with a high amount of dust in the environment and easy to accumulate dust, and an area with sufficient light and high power generation efficiency; Set priorities for each area, clean the areas with high priorities first, and use the improved genetic algorithm to clean the areas with the same priority. The steps are as follows: Step 221, sorting the regions according to priority, determining the priority sorting and the sequence to be sorted using the genetic algorithm; Step 222, generating an initial population for the sequence to be sorted using the genetic algorithm, setting the fitness function, population size, crossover threshold Q, crossover probability, heuristic mutation probability, and maximum number of iterations parameters; Step 223, dynamically linearly calibrate the distances between the regions and convert them into a fitness function for finding the maximum value; Step 224, screening out individuals that directly enter the next generation, and selecting the parent generation that participates in the crossover; Step 225, perform a crossover operation on the parent generation. When the optimal path of this iteration is greater than the threshold Q, perform a sequential crossover, otherwise perform a self-crossover; Step 226, performing a heuristic mutation operation on the generated offspring; Step 227, determine whether the termination condition is met, if so, output the optimal solution, otherwise return to step 223; Step 23, after dividing the regions, mark the geometric center of each region in the regional coordinate system, locate the initial position, and traverse all regions; Step 3: Perform global path planning according to the cleaning task planning, locate the initial position, establish navigation points, and plan the operation trajectory; Step 4, sending a cleaning instruction according to the running trajectory; Step 5, monitor the dust accumulation and power generation efficiency of the photovoltaic panel; when the dust accumulation and power generation efficiency do not reach the threshold, re-plan the cleaning task, perform local path planning, establish navigation points, plan the operation trajectory, and send cleaning instructions; Otherwise, the cleaning is completed and a recycling instruction is sent.

2. A robot control method for cleaning photovoltaic panels according to claim 1, characterized in that: In step 1, the cleaning mode is set according to the photovoltaic panel cleaning task information, and the initialization task parameters are set, wherein the initialization task parameters include the number of cleaning times, task time and running speed.

3. A robot control method for cleaning photovoltaic panels according to claim 1, characterized in that: In step 23, the order of traversing all areas is solved by constructing a Hamiltonian graph, where the vertices are photovoltaic panel areas, the edges are the Manhattan distances between the areas, and the hierarchical planning of photovoltaic panel cleaning tasks is completed in all areas through a shortest Hamiltonian circuit.

4. A robot control method for cleaning photovoltaic panels according to claim 1, characterized in that: In step 5, the dust accumulation and power generation efficiency of the photovoltaic panels are monitored. The dust accumulation of the photovoltaic panels and the power generation efficiency of cleaning the photovoltaic panels are quantified by the power generation loss and power generation capacity of the photovoltaic modules: by obtaining the power generation of the photovoltaic panels under normal working conditions under the current meteorological conditions, and comparing the power generation of the clean photovoltaic modules in the sample under similar meteorological conditions, the power generation loss is calculated.

5. A robot control method for cleaning photovoltaic panels according to claim 4, characterized in that: The power generation loss is predicted by wavelet neural network. The input variables of the wavelet neural network are single-day weather parameters, irradiation, average temperature, weather conditions, and wind speed. The output variable is the power generation loss. The training set and test set are selected based on the power generation loss caused by dust and the corresponding single-day weather parameters, and then the wavelet neural network prediction model is trained and tested. After the wavelet neural network prediction model is established, the power generation loss caused by daily dust in the next few days is predicted based on weather forecast data.

6. A robot control system for cleaning photovoltaic panels, characterized in that: include The first processing module is used to obtain photovoltaic panel cleaning task information and set initialization task parameters according to the cleaning task information; A setting module is used to plan cleaning tasks according to the photovoltaic panel cleaning task information, divide the areas according to the amount of dust accumulation and power generation efficiency of the photovoltaic panels, and set priorities for the areas; The steps of cleaning task planning method are as follows: The photovoltaic panels in the photovoltaic power station are divided into regions according to the amount of dust accumulation and power generation efficiency of the photovoltaic panels; Set priorities for each area, with higher priorities given to areas with high dust content and easy dust accumulation, and areas with sufficient light and high power generation efficiency; After dividing the regions, mark the geometric center of each region in the regional coordinate system, locate the initial position, and traverse all regions; Among them, the priority is set for each area, and the area with high priority is cleaned first. The areas with the same priority are cleaned using an improved genetic algorithm. The steps are as follows: Each area is sorted by priority, and the priority order and the sequence to be sorted using the genetic algorithm are determined; Generate an initial population for the sequence to be sorted using a genetic algorithm, set the fitness function, population size, crossover threshold Q, crossover probability, heuristic mutation probability, and maximum number of iterations parameters; The distance between each area is dynamically linearly calibrated and converted into a fitness function to find the maximum value; Screen out individuals that directly enter the next generation and select the parents who participate in the crossover; Perform a crossover operation on the parent generation. When the optimal path of this iteration is greater than the threshold Q, perform a sequential crossover, otherwise perform a self-crossover. Perform heuristic mutation operations on the generated offspring; Determine whether the termination condition is met. If it is met, output the optimal solution. Otherwise, return to execute dynamic linear calibration of the distance between each area and convert it into a fitness function for finding the maximum value. The second processing module is used to perform global path planning according to the cleaning task planning, locate the initial position, establish navigation points, and plan the operation trajectory; An instruction sending module, used for sending cleaning instructions according to the running trajectory; The third processing module monitors the dust accumulation and power generation efficiency of the photovoltaic panels. When the dust accumulation and power generation efficiency do not reach the threshold, the cleaning task is re-planned, local path planning is performed, navigation points are established, the operation trajectory is planned, and cleaning instructions are sent. Otherwise, the cleaning is completed and a recycling instruction is sent.

7. A mobile terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the robot control method for cleaning photovoltaic panels as described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of a robot control method for cleaning photovoltaic panels as described in any one of claims 1 to 5 are implemented.

Citation Information

Patent Citations

  • Intelligent control system and control method for cleaning of solar photovoltaic panel

    CN109546954A

  • Self-adaptive solar photovoltaic power generation equipment intelligent cleaning robot and control system

    CN109571472A

  • Cleaning method and device, and computer equipment

    CN110649883A

  • Cleaning method and device for photovoltaic module and medium

    CN113695295A

  • Intelligent control method of photovoltaic module cleaning robot

    CN113888559A