Photovoltaic cleaning robot, self-adaptive control method thereof and readable medium

Abstract

The invention provides a photovoltaic cleaning robot, a self-adaptive control method thereof and a readable medium, and the self-adaptive control method comprises the steps: determining a to-be-cleaned photovoltaic module according to the generating capacity of the photovoltaic module; the photovoltaic cleaning robot moves to the coordinate position of the to-be-cleaned assembly and collects a surface image of the to-be-cleaned photovoltaic assembly; extracting feature information of the surface image, and determining a dust area based on the feature information; and calculating dust space distribution data according to the dust area, and planning a cleaning path according to the dust space distribution data. According to the method, part of the photovoltaic modules can be selectively cleaned, the optimal path can be planned according to the image information, the cleaning efficiency can be improved, and resource waste can be reduced.

Description

Technical Field

[0001] The present invention mainly relates to the technical field of new energy, and particularly relates to a photovoltaic cleaning robot, an adaptive control method thereof, and a readable medium. Background Art

[0002] With the rapid development of renewable energy, photovoltaic power generation, as an important clean energy, has been widely used. However, during the long-term operation of photovoltaic modules, they will be affected by environmental factors such as dust and bird droppings. These impurities will accumulate on the surface of the modules, thereby reducing the power generation efficiency. Therefore, regular cleaning and inspection of photovoltaic modules are necessary means to maintain their efficient operation and stable performance.

[0003] The cleaning of traditional photovoltaic modules is generally manually completed. However, for large-scale photovoltaic module scenarios, manual cleaning has low efficiency, high cleaning costs, and certain safety hazards. Nowadays, some photovoltaic cleaning robots have emerged, which to a certain extent replace manual labor for the inspection and surface cleaning of photovoltaic modules. However, existing photovoltaic cleaning robots usually use one-way or two-way fixed cleaning paths for cleaning work, lacking detection of the cleaning environment and the state of the modules. The pollution degrees on the surfaces of different modules may vary. Fixed-time cleaning may cause some modules to be not cleaned in time, reducing the power generation efficiency; on the other hand, it may cause over-cleaning, resulting in waste of water resources. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a photovoltaic cleaning robot, an adaptive control method thereof, and a readable medium, so as to solve the problems of unsatisfactory cleaning effect and resource waste of existing cleaning methods.

[0005] To solve the above technical problem, the present invention provides an adaptive control method for a photovoltaic cleaning robot, including: determining the photovoltaic modules to be cleaned according to the power generation of the photovoltaic modules; moving the photovoltaic cleaning robot to the coordinate position of the to-be-cleaned module, and collecting a surface image of the to-be-cleaned photovoltaic module; extracting feature information of the surface image, and determining a dust area based on the feature information; calculating dust spatial distribution data according to the dust area, and planning a cleaning path according to the dust spatial distribution data.

[0006] Optionally, it further includes: calculating a cleaning satisfaction function based on a dust cleaning degree factor and a power generation growth rate on the surface of the photovoltaic module; determining whether the cleaning satisfaction function is greater than or equal to a first preset threshold. If not, re-plan the cleaning path or add a cleaning mode.

[0007] Optionally, the cleaning satisfaction function is calculated by the following formula:

[0008] Among them, is the cleaning satisfaction function, is the dust cleaning degree factor, is the power generation growth rate, and are weight coefficients.

[0009] Optionally, the dust cleaning degree factor is calculated by the following formula:

[0010] Among them, is the dust cleaning degree factor, represents the dust amount before cleaning, represents the dust amount after cleaning.

[0011] Optionally, planning the cleaning path according to the dust spatial distribution data includes: Judging the dust distribution of the photovoltaic modules according to the dust spatial distribution data; When the dust at the middle or edge position of the photovoltaic module is greater than that of other parts, the planned cleaning path is that the photovoltaic cleaning robot moves forward to the middle part of the photovoltaic module for cleaning. After walking one robot body position, it rotates counterclockwise by 90° and continues to clean. At this time, after moving one body position, it rotates counterclockwise by 90° again, and so on until the edge of the photovoltaic module is cleaned; When the dust on the surface of the photovoltaic module is evenly distributed, the planned cleaning path is: when the photovoltaic cleaning robot moves to the position to be cleaned, it first rotates clockwise by 90°, moves towards the edge of the photovoltaic module. After reaching the edge of the photovoltaic module, it rotates counterclockwise by 90°, moves one body position and then rotates counterclockwise by 90°. At this time, it continues to move towards the edge of the photovoltaic module, and so on. When it reaches the corner of the photovoltaic module, it returns to the initial cleaning position along the edge of the module.

[0012] Optionally, determining the photovoltaic modules to be cleaned according to the power generation of the photovoltaic modules includes: obtaining the power generation of the photovoltaic modules per unit time; calculating the difference between the power generation of the photovoltaic modules per unit time and the rated power generation of the photovoltaic modules. When the difference is greater than the second preset threshold, the photovoltaic module is set as the photovoltaic module to be cleaned.

[0013] Optionally, the rated power generation of the photovoltaic module is determined by the following formula:

[0014] Among them, is the rated daily power generation of the photovoltaic module, is the equivalent daily solar irradiance, A is the installation area of the photovoltaic module, is the power generation efficiency of the photovoltaic module.

[0015] Optionally, extracting the feature information of the surface image includes: extracting the shape feature of the surface image using morphological operations; extracting the texture feature of the surface image using Gabor filters; extracting the color feature of the surface image using the HSV color space; extracting the local feature of the surface image using feature descriptors.

[0016] Optionally, determining the dust area based on the feature information includes: inputting the shape feature, the texture feature, the color feature, and the local feature into a dust recognition model, and the dust recognition model outputs the dust area.

[0017] Optionally, the dust spatial distribution data includes dust distribution density, and calculating the dust distribution density includes: dividing the number of pixels of the dust area by the number of pixels of the photovoltaic module to obtain the dust distribution density.

[0018] Optionally, it further includes: establishing a robot movement coordinate system according to the arrangement order of the photovoltaic modules; determining the coordinate position of the component to be cleaned based on the robot movement coordinate system.

[0019] To solve the above technical problems, the present invention provides a photovoltaic cleaning robot, which is controlled by the above-mentioned adaptive control method.

[0020] To solve the above technical problems, the present invention provides a computer-readable medium storing computer program code, and the computer program code realizes the above-mentioned adaptive control method when executed by a processor.

[0021] Compared with the prior art, the present invention has the following advantages: The adaptive control method of the photovoltaic cleaning robot of the present invention can selectively clean some photovoltaic modules by combining the power generation of the photovoltaic modules and the image information of the photovoltaic modules, and can plan the optimal path according to the image information, which can not only improve the cleaning efficiency, but also reduce resource waste, extend the service life of the photovoltaic modules, and improve the power generation efficiency. Description of the Drawings

[0022] The accompanying drawings are provided to provide a further understanding of the present application, and they are incorporated and constitute a part of the present application. The accompanying drawings illustrate the embodiments of the present application and, together with the description of the present application, serve to explain the principles of the present application. In the accompanying drawings: Figure 1 is a flowchart of the adaptive control method of the photovoltaic cleaning robot according to an embodiment of the present invention.

[0023] Figure 2 is a schematic diagram of the robot movement coordinate system according to an embodiment of the present invention.

[0024] Figure 3It is a flowchart for extracting feature information of a surface image according to an embodiment of the present invention.

[0025] Figure 4 and Figure 5 It is a schematic diagram of two cleaning paths according to an embodiment of the present invention.

[0026] Figure 6 It is a system block diagram of a photovoltaic cleaning robot according to an embodiment of the present invention. Detailed implementation manners

[0027] To more clearly illustrate the technical solutions of the embodiments of the present application, the accompanying drawings required for description in the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some examples or embodiments of the present application. For those of ordinary skill in the art, without creative efforts, the present application can also be applied to other similar scenarios based on these drawings. Unless obvious from the language context or otherwise stated, the same reference numerals in the drawings represent the same structure or operation.

[0028] Flowcharts are used in the present application to illustrate the operations performed by the systems according to the embodiments of the present application. It should be understood that the operations before or below do not necessarily need to be precisely executed in sequence. On the contrary, they can be executed in reverse order or simultaneously, and various steps can be processed. At the same time, other operations can be added to these processes, or one or several operations can be removed from these processes.

[0029] The main objective of the present invention is to solve the problem that the single-mode cleaning method of existing cleaning robots cannot combine photovoltaic module and cleaning environment information, resulting in unsatisfactory cleaning effects and resource waste.

[0030] By combining image processing, machine learning, path planning, and motion control technologies, the present invention can effectively analyze the distribution of dust and dirt on the surface of photovoltaic modules, and set the cleaning direction and motion trajectory for the cleaning robot. This can not only improve the cleaning efficiency, but also reduce energy waste, extend the service life of photovoltaic modules, and improve the power generation efficiency.

[0031] Figure 1 It is a flowchart of an adaptive control method for a photovoltaic cleaning robot according to an embodiment of the present invention. As Figure 1 shown, the adaptive control method 100 of the photovoltaic cleaning robot includes the following steps: Step S1: Determine the photovoltaic modules to be cleaned according to the power generation of the photovoltaic modules.

[0032] Optionally, determining the photovoltaic modules to be cleaned according to the power generation of the photovoltaic modules includes: Step S11: Obtain the power generation per unit time of the photovoltaic modules.

[0033] Optionally, the electric power formula can be used, combined with measuring the current and voltage of the photovoltaic module, to calculate the current power generation of the photovoltaic module.

[0034] P = I × V × coefficient Where, P is power (watt, W); I is current (ampere, A); V is voltage (volt, V).

[0035] Calculate the power generation within a unit time: The power generation is usually the integral (or accumulation) of power within a unit time. If the average value of power or the instantaneous power data within a certain time period is available, the total power generation can be calculated by multiplying the power by the time. Assuming the time period is Δt (in hours or seconds), the power generation E (unit: watt-hour, Wh) within a unit time can be calculated by the following formula:

[0036] is the instantaneous power at the i-th time point, Δt is the time interval, and n is the number of time points.

[0037] Step S12: Calculate the difference between the power generation per unit time of the photovoltaic module and the rated power generation of the photovoltaic module. When the difference is greater than the second preset threshold, set the photovoltaic module as the photovoltaic module to be cleaned.

[0038] Optionally, the unit time refers to one day. The rated power generation of the photovoltaic module refers to the rated daily power generation of the photovoltaic module. The rated power generation of the photovoltaic module is determined by the following formula:

[0039] Where, is the rated daily power generation of the photovoltaic module, is the equivalent daily irradiance, A is the installation area of the photovoltaic module, is the power generation efficiency of the photovoltaic module, usually taking values between 0.15 and 0.22, depending on the technology of the photovoltaic module.

[0040] The equivalent daily irradiance refers to the "converted value" of the total solar irradiance received by the photovoltaic module within a day, usually expressed as "equivalent sun hours", that is, the total energy of solar radiation received by the photovoltaic module within a day, assuming it is calculated at the intensity under standard conditions (usually 1000 W / m²). The equivalent daily irradiance usually uses kWh / m²·day (kilowatt-hour per square meter per day) as the unit. The value of the equivalent daily irradiance Usually provided by meteorological data, it can be estimated through local irradiance data and historical records. The equivalent daily irradiance varies greatly in different regions. Generally, the values in tropical and subtropical regions are relatively high, while those in high-latitude regions are relatively low. Relevant meteorological data can be consulted or a specialized solar radiation database (such as PVGIS, NASA, meteorological websites, etc.) can be used to obtain the equivalent daily irradiance of the region where you are located.

[0041] Optionally, when calculating the rated daily power generation of the photovoltaic module, system losses are also considered. The rated daily power generation of the photovoltaic module is calculated by the following formula:

[0042] If there are certain system losses in the photovoltaic system (such as inverter efficiency, connection losses, shading, etc.), the loss coefficient needs to be multiplied. Generally, the loss coefficient is between 0.75 and 0.85.

[0043] Dust and dirt on the surface of the photovoltaic module will cause a decrease in power generation. In the present invention, the difference between the actual power generation and the rated daily power generation is used to determine which photovoltaic modules have more dust and dirt, and then they are set as the photovoltaic modules to be cleaned. In other words, the present invention does not clean all photovoltaic modules, which can avoid waste of resources.

[0044] Step S2: The photovoltaic cleaning robot moves to the coordinate position of the component to be cleaned and acquires the surface image of the photovoltaic module to be cleaned.

[0045] Optionally, before step S2, it further includes: establishing a robot movement coordinate system according to the arrangement order of the photovoltaic modules, and determining the coordinate position of the component to be cleaned based on the robot movement coordinate system.

[0046] Figure 2 is a schematic diagram of the robot movement coordinate system according to an embodiment of the present invention. As Figure 2 shown, the photovoltaic modules are arranged in order, fixedly installed on the photovoltaic support, and the gaps between adjacent two photovoltaic modules are the same. According to the arrangement order of the components, a robot movement coordinate system is established. The middle position on the side of the first photovoltaic module is set as the coordinate origin, the direction of the arrangement order of the photovoltaic modules is the x-axis direction, and the side line of the photovoltaic module is the y-axis direction. Taking the positive direction of the x-axis as the initial direction, the photovoltaic modules are sorted. For example, the first photovoltaic module is X1, the second is X2, and so on, and the last one is Xn. The sizes of photovoltaic modules from different manufacturers and models may vary. Here, L is used to represent the short side dimension of the photovoltaic module, and a is the gap between adjacent two photovoltaic modules.

[0047] The coordinate position of the component to be cleaned can be calculated by the following formula:

[0048] S is the coordinate position of the component to be cleaned (unit: centimeter, cm); L is the side dimension of the photovoltaic module (unit: centimeter, cm); a is the distance between two adjacent photovoltaic modules (unit: centimeter, cm); n is the serial number of the photovoltaic module to be cleaned.

[0049] Start and release the photovoltaic cleaning robot at the starting position, control the photovoltaic cleaning robot to move along the central axis of the photovoltaic module (the middle line of the photovoltaic module), and stop when it moves to the coordinate position of the component to be cleaned.

[0050] Optionally, collect the surface image data of the photovoltaic module through the image acquisition module of the photovoltaic cleaning robot.

[0051] Optionally, before identifying dust, it is first necessary to perform some preprocessing on the image to enhance the characteristics of the dust and reduce the influence of noise on the identification. The preprocessing includes but is not limited to: Denosing: Use filters (such as Gaussian filtering, median filtering) to reduce the noise in the image, especially small spots similar to dust and cluttered background noise.

[0052] Contrast enhancement: Through methods such as histogram equalization and local contrast enhancement, improve the contrast between the dust area and the background in the image to make the dust more obvious.

[0053] Edge detection: Use algorithms such as Canny edge detection to extract the edge information in the image, which helps to identify the contour of the dust area.

[0054] Image normalization: Adjust the brightness and color balance of the image to make the dust area easier to distinguish.

[0055] Step S3: Extract the feature information of the surface image, and determine the dust area based on the feature information.

[0056] Figure 3 is a flowchart for extracting the feature information of the surface image according to an embodiment of the present invention. Extracting the feature information in the image is the core step of dust recognition. Because dust usually has some specific visual features, such as small and irregular shapes, low texture complexity, etc., as Figure 3 shown, the features can be extracted in the following ways: Step S31: Morphological operations. Dust usually appears as small spots or tiny objects. Using morphological operations (such as dilation, erosion, opening operation, and closing operation) can help highlight these small areas and extract shape features. The erosion operation helps to remove noise, while the dilation operation helps to highlight the presence of dust.

[0057] Step S32: Extract texture features. Dust often has texture features different from those of the background. Methods such as Gabor filters and LBP (Local Binary Pattern) can be used to extract the texture features of dust.

[0058] Step S33: Extract color features. The color of dust is usually slightly different from the surface of the background. Especially on certain backgrounds, dust can be identified through color distribution. The HSV color space can be used for color feature extraction to help separate the dust area from the background.

[0059] Step S34: Extract local features. Feature descriptors such as SIFT (Scale-Invariant Feature Transform) and SURF (Speeded-Up Robust Features) can help identify small objects in the image.

[0060] After feature extraction, the shape features, texture features, color features, and local features are input into the dust recognition model, and the dust recognition model outputs the dust area. Optionally, the dust recognition model is trained based on machine learning or deep learning.

[0061] Optionally, after identifying the dust area, some post-processing operations are also included to improve the recognition accuracy and robustness. The post-processing operations include but are not limited to: Region merging and filtering: Merge the detected small regions into larger regions to avoid detecting multiple tiny noise points or mis-identified regions.

[0062] Judgment of the shape and size of dust: Further filter out the regions that do not conform to the dust characteristics according to the characteristics such as the shape, size, and distribution of dust.

[0063] Connected region analysis: By analyzing the connectivity of the dust area, remove isolated small regions and retain the actual dust area.

[0064] Step S4: Calculate the dust spatial distribution data based on the dust area, and plan the cleaning path according to the dust spatial distribution data.

[0065] The dust spatial distribution data includes but is not limited to dust distribution density and dust intensity mapping. The dust distribution density refers to the proportion of the pixels of each dust area to the pixels of the photovoltaic module. The dust intensity mapping refers to generating a dust intensity heat map on the entire surface.

[0066] After obtaining the dust distribution, a path planning algorithm can be used to generate the optimal cleaning route for the cleaning robot. Using a greedy algorithm and a dynamic adjustment path planning method, the robot starts cleaning from the area with more dust according to the dust distribution density, and gradually cleans to the area with less dust. At the same time, if some areas of the robot have been cleaned during the cleaning process, the direction and path of the robot's movement can be dynamically adjusted according to the real-time feedback to ensure no missed cleaning.

[0067] When the photovoltaic cleaning robot arrives at the designated location, it generates two optional cleaning path plans based on the distribution of dust and dirt on the surface of the photovoltaic components. Figure 4 and Figure 5 Schematic diagram of two cleaning paths according to an embodiment of the present invention.

[0068] The first cleaning path, such as Figure 4 As shown in the figure, when there is a lot of dust in the middle or edge of the photovoltaic module, the photovoltaic cleaning robot will first clean this area. At this time, the photovoltaic cleaning robot continues to move forward to the middle of the photovoltaic module to clean it. After moving one robot body position, it rotates 90° counterclockwise to continue cleaning. At this time, after moving one robot body position, it rotates 90° counterclockwise again, and so on. In this cleaning scheme, the photovoltaic cleaning robot moves in a "U"-shaped trajectory until it cleans the edge of the photovoltaic module.

[0069] The second cleaning path, such as Figure 5 As shown in the figure, when the dust on the surface of the photovoltaic module is evenly distributed, when the photovoltaic cleaning robot moves to the position to be cleaned, it first rotates 90° clockwise and moves to the edge of the photovoltaic module. After reaching the edge of the photovoltaic module, it rotates 90° counterclockwise, moves one body position and then rotates 90° counterclockwise. At this time, it continues to move to the edge of the photovoltaic module, and so on. In this cleaning scheme, the photovoltaic cleaning robot moves in a "J"-shaped trajectory. When cleaning the corner of the photovoltaic module, it returns to the initial cleaning position along the edge of the module.

[0070] Optionally, the adaptive control method of the photovoltaic cleaning robot further includes: Step S5: Evaluate the cleaning results, calculate the cleaning satisfaction function based on the dust cleaning degree factor on the surface of the photovoltaic module and the power generation growth rate of the photovoltaic module after cleaning, and determine whether the cleaning satisfaction function is greater than or equal to a first preset threshold. If not, re-plan the cleaning path or add a cleaning mode.

[0071] Satisfaction is defined as a comprehensive factor that includes both the degree of dust cleaning and the increase in power generation. Assume that the cleaning satisfaction function S can be expressed as:

[0072] in, and are weight coefficients, representing the influence of dust cleaning degree and power generation increment on the final satisfaction, and , which can be adjusted according to specific needs.

[0073] is the dust cleaning degree factor, which can be expressed by the following formula:

[0074] Among them, is the dust cleaning degree factor, represents the amount of dust before cleaning, represents the amount of dust after cleaning, where the amount of dust can be represented by measuring the dust coverage or pollution index on the surface of the photovoltaic module. The larger the value, the more dust there is.

[0075] represents the power generation growth rate. The higher it is, the more obvious the improvement in power generation after cleaning. is the power generation before cleaning, is the power generation increment after cleaning.

[0076] If the S value is high, it indicates good cleaning effect, sufficient dust removal, and obvious improvement in power generation. If the S value is low, it may mean poor dust cleaning effect or insignificant improvement in power generation after cleaning.

[0077] The present invention monitors the cleaning progress through image processing and sensor feedback. The system can evaluate which areas have been cleaned and which areas need to be cleaned again according to the cleaning effect. At this time, the movement trajectory of the robot can be dynamically adjusted, or the cleaning efficiency can be further improved by adding cleaning modes.

[0078] In the embodiment of the present invention, the robot movement control and execution control the movement of the robot on the surface of the photovoltaic module according to the planned cleaning route. Technologies such as lidar and visual SLAM are used for positioning to ensure that the robot can accurately track the path and perform the cleaning task. Appropriate cleaning actions are set, such as longitudinal cleaning, transverse cleaning, or spiral cleaning, etc., to maximize the cleaning effect. The robot should have real-time detection ability during the cleaning process to be able to sense the current dirt cleaning effect. If the dirt in some areas cannot be cleaned cleanly, the movement trajectory and cleaning intensity can be automatically adjusted.

[0079] The adaptive control method of the photovoltaic cleaning robot of the present invention can selectively clean some photovoltaic modules by combining the power generation of the photovoltaic module and the image information of the photovoltaic module, and can plan the optimal path according to the image information, which can not only improve the cleaning efficiency, but also reduce resource waste, extend the service life of the photovoltaic module, and improve the power generation efficiency.

[0080] The present disclosure also provides a distributed photovoltaic cleaning robot. Figure 6 is the system block diagram of the photovoltaic cleaning robot according to an embodiment of the present invention. As Figure 6 shown, the photovoltaic cleaning robot 600 includes: An image acquisition module 61, which is used to acquire the image data of the surface layer of the photovoltaic module in the forward direction of the robot.

[0081] An image preprocessing module 62, which is used to preprocess the image data on the surface of a photovoltaic module to improve the image quality, extract useful information, or prepare for subsequent analysis and model input. It mainly improves the image quality through a series of operations to provide better input for subsequent feature extraction, classification, or other image processing tasks.

[0082] A dust detection and classification module 63, which uses machine learning or deep learning methods to detect and classify dust after feature extraction; A dust area post-processing module 64, which adopts some post-processing operations to improve the accuracy and robustness of recognition after identifying the dust area.

[0083] A path planning module 65, which is used to calculate the dust spatial distribution data according to the dust area and plan the cleaning path according to the dust spatial distribution data.

[0084] This application also includes a computer-readable medium storing computer program code, and when the computer program code is executed by a processor, it implements the adaptive control method of the photovoltaic cleaning robot described above.

[0085] When the adaptive control method of the photovoltaic cleaning robot is implemented as a computer program, it can also be stored in a computer-readable storage medium as an article of manufacture. For example, the computer-readable storage medium may include, but is not limited to, magnetic storage devices (such as hard disks, floppy disks, magnetic strips), optical disks (such as compact discs (CDs), digital versatile discs (DVDs)), smart cards, and flash memory devices (such as electrically erasable programmable read-only memories (EPROMs), cards, sticks, key drives). In addition, the various storage media described herein can represent one or more devices and / or other machine-readable media for storing information. The term "machine-readable medium" may include, but is not limited to, wireless channels and various other media (and / or storage media) that can store, contain, and / or carry code and / or instructions and / or data.

[0086] The basic concepts have been described above. Obviously, for those skilled in the art, the above invention disclosure is only an example and does not constitute a limitation to this application. Although not explicitly stated here, those skilled in the art may make various modifications, improvements, and corrections to this application. Such modifications, improvements, and corrections are proposed in this application, so such modifications, improvements, and corrections still fall within the spirit and scope of the exemplary embodiments of this application.

[0087] Meanwhile, this application uses specific terms to describe the embodiments of this application. For example, "an embodiment", "one embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of this application. Therefore, it should be emphasized and noted that the "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more at different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this application can be appropriately combined.

[0088] Some aspects of this application can be executed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above-mentioned hardware or software can all be referred to as "data blocks", "modules", "engines", "units", "components", or "systems". The processor can be one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DAPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, or a combination thereof. In addition, aspects of this application may be embodied as a computer product located in one or more computer-readable media, which includes computer-readable program code. For example, the computer-readable medium may include, but is not limited to, magnetic storage devices (such as hard disks, floppy disks, magnetic tapes...), optical disks (such as compact disks CD, digital versatile disks DVD...), smart cards, and flash memory devices (such as cards, sticks, key drives...).

[0089] The computer-readable medium may contain a propagated data signal that contains computer program code, for example, on a baseband or as part of a carrier wave. This propagated signal may have various forms of representation, including electromagnetic form, optical form, etc., or a suitable combination of forms. The computer-readable medium can be any computer-readable medium other than a computer-readable storage medium, and this medium can be connected to an instruction execution system, device, or equipment to implement communication, propagation, or transmission for use of the program. The program code located on the computer-readable medium can be propagated through any suitable medium, including radio, cable, fiber optic cable, radio frequency signal, or similar media, or any combination of the above media.

[0090] Similarly, it should be noted that, in order to simplify the presentation of this application disclosure and thus help the understanding of one or more embodiments of the invention, in the previous description of the embodiments of this application, sometimes multiple features are grouped into one embodiment, drawing, or description thereof. However, this disclosure method does not mean that the features required by the object of this application are more than the features mentioned. In fact, the features of the embodiment are less than all the features of the single embodiment disclosed above.

[0091] As shown in this application, unless the context clearly indicates otherwise, words such as "a", "an", "one", and / or "the" are not specifically singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of the clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0092] Unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions, and numerical values set forth in these embodiments do not limit the scope of this application. At the same time, it should be understood that, for the sake of convenience of description, the dimensions of the various parts shown in the drawings are not drawn in actual proportional relationships. Technologies, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, such technologies, methods, and devices should be regarded as part of the specification. In all the examples shown and discussed here, any specific value should be interpreted as merely exemplary and not as a limitation. Therefore, other examples of the exemplary embodiments may have different values. It should be noted that like reference numerals and letters denote like items in the following drawings, and thus, once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0093] In the description of this application, it should be understood that the orientation or positional relationships indicated by orientation words such as "front, back, up, down, left, right", "lateral, vertical, perpendicular, horizontal", and "top, bottom" are generally based on the orientation or positional relationships shown in the drawings. These are only for the convenience of describing this application and simplifying the description. Without contrary description, these orientation words do not indicate and imply that the device or element referred to must have a specific orientation or be constructed and operated in a specific orientation. Therefore, they should not be construed as limiting the scope of protection of this application; the orientation words "inside, outside" refer to the inside and outside relative to the contour of each component itself.

[0094] For the convenience of description, spatial relative terms such as "above", "over", "on the upper surface", "above" can be used here to describe the spatial positional relationships of one device or feature with other devices or features as shown in the drawings. It should be understood that the spatial relative terms are intended to include different orientations in use or operation in addition to the orientation described in the drawings for the device. For example, if the device in the drawing is inverted, the device described as "above" or "over" other devices or structures will then be positioned "below" or "under" other devices or structures. Thus, the exemplary term "above" can include both "above" and "below". The device can also be positioned in other different ways (rotated 90 degrees or in other orientations), and corresponding interpretations will be made for the spatial relative descriptions used here.

[0095] In addition, it should be noted that the use of terms such as "first" and "second" to limit components is only for the convenience of distinguishing the corresponding components. Without further statement, the above terms have no special meaning, and thus should not be construed as a limitation on the protection scope of the present application. In addition, although the terms used in the present application are selected from well-known and commonly used terms, some terms mentioned in the specification of the present application may be selected by the applicant according to his or her judgment, and their detailed meanings are described in the relevant parts of the present description. In addition, it is required to understand the present application not only through the actual terms used, but also through the meaning implied by each term.

[0096] It should be understood that when a component is referred to as "on another component", "connected to another component", "coupled to another component" or "in contact with another component", it can be directly on, connected to, or coupled to, or in contact with the other component, or there may be an intervening component. In contrast, when a component is referred to as "directly on another component", "directly connected to", "directly coupled to" or "directly in contact with" another component, there is no intervening component. Similarly, when the first component is referred to as "electrically contacting" or "electrically coupled to" the second component, there is an electrical path allowing current to flow between the first component and the second component. The electrical path may include capacitors, coupled inductors, and / or other components allowing current to flow, even if there is no direct contact between the conductive components.

[0097] In some embodiments, numbers are used to describe components and attribute quantities. It should be understood that such numbers used for the description of embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the said numbers allow a variation of ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification are approximate values, and such approximate values may change according to the characteristics required by individual embodiments. In some embodiments, the numerical parameters should consider the specified significant digits and adopt the method of retaining general digits. Although the numerical ranges and parameters used to confirm the breadth of the scope in some embodiments of the present application are approximate values, in specific embodiments, the setting of such numerical values is as precise as possible within the feasible range.

[0098] Although the present application has been described with reference to current specific embodiments, those of ordinary skill in the art in this technical field should recognize that the above embodiments are only used to illustrate the present application, and various equivalent changes or substitutions can be made without departing from the spirit of the present application. Therefore, as long as the changes and modifications to the above embodiments are within the scope of the spirit of the present application, they will fall within the scope of the present application.

Claims

1. An adaptive control method for a photovoltaic cleaning robot, characterized in that, Including: Determine the photovoltaic modules to be cleaned according to the power generation of the photovoltaic modules; The photovoltaic cleaning robot moves to the coordinate position of the to-be-cleaned module and acquires the surface image of the to-be-cleaned photovoltaic module; Extract the feature information of the surface image and determine the dust area based on the feature information; Calculate the dust spatial distribution data according to the dust area, and plan the cleaning path according to the dust spatial distribution data.

2. The adaptive control method of the photovoltaic cleaning robot according to claim 1, wherein, It also includes: Calculate the cleaning satisfaction function based on the dust cleaning degree factor and the power generation growth rate on the surface of the photovoltaic module; Judge whether the cleaning satisfaction function is greater than or equal to the first preset threshold. If not, re-plan the cleaning path or add a cleaning mode.

3. The adaptive control method of the photovoltaic cleaning robot according to claim 2, characterized in that Calculate the cleaning satisfaction function through the following formula: Among them, is the cleaning satisfaction function, is the dust cleaning degree factor, is the power generation growth rate, and are weight coefficients.

4. The adaptive control method of the photovoltaic cleaning robot according to claim 3, characterized in that, Calculate the dust cleaning degree factor through the following formula: Among them, is the dust cleaning degree factor, represents the amount of dust before cleaning, represents the amount of dust after cleaning.

5. The adaptive control method of the photovoltaic cleaning robot according to claim 1, characterized in that Planning the cleaning path according to the dust spatial distribution data includes: Judge the dust distribution condition of the photovoltaic module according to the dust spatial distribution data; When the dust in the middle or edge position of the photovoltaic module is greater than the dust in other parts, the planned cleaning path is that the photovoltaic cleaning robot moves forward to the middle part of the photovoltaic module for cleaning. After walking one robot body position, it rotates counterclockwise by 90° and continues to clean. At this time, after moving one body position, it rotates counterclockwise by 90° again, and so on until it cleans to the edge of the photovoltaic module; When the dust on the surface of the photovoltaic module is evenly distributed, the planned cleaning path is: when the photovoltaic cleaning robot moves to the to-be-cleaned position, it first rotates clockwise by 90°, moves towards the edge of the photovoltaic module. After reaching the edge of the photovoltaic module, it rotates counterclockwise by 90°, moves one body position and then rotates counterclockwise by 90° again. At this time, it continues to walk towards the edge of the photovoltaic module, and so on until it cleans to the corner of the photovoltaic module, and then returns to the initial cleaning position along the edge of the module.

6. The adaptive control method of the photovoltaic cleaning robot according to claim 1, characterized in that, Determining the photovoltaic modules to be cleaned according to the power generation of the photovoltaic modules includes: Obtain the power generation per unit time of the photovoltaic module; Calculate the difference between the power generation per unit time of the photovoltaic module and the rated power generation of the photovoltaic module. When the difference is greater than the second preset threshold, set the photovoltaic module as the to-be-cleaned photovoltaic module.

7. The adaptive control method of the photovoltaic cleaning robot according to claim 6, wherein, Determine the rated power generation of the photovoltaic module through the following formula: Among them, is the rated daily power generation of the photovoltaic module, is the equivalent daily irradiance, A is the installation area of the photovoltaic module, is the power generation efficiency of the photovoltaic module.

8. The adaptive control method of the photovoltaic cleaning robot according to claim 1, characterized in that, Extracting the feature information of the surface image includes: Use morphological operations to extract the shape features of the surface image; Use Gabor filters to extract the texture features of the surface image; Use the HSV color space to extract the color features of the surface image; Use feature descriptors to extract the local features of the surface image.

9. The adaptive control method of the photovoltaic cleaning robot according to claim 8, wherein Determining the dust area based on the feature information includes: Input the shape features, the texture features, the color features and the local features into the dust recognition model, and the dust recognition model outputs the dust area.

10. The adaptive control method of the photovoltaic cleaning robot according to claim 1, wherein The dust spatial distribution data includes dust distribution density. Calculating the dust distribution density includes: dividing the number of pixels of the dust area by the number of pixels of the photovoltaic module to obtain the dust distribution density.

11. The adaptive control method of the photovoltaic cleaning robot according to claim 1, wherein, It also includes: Establish a robot movement coordinate system according to the arrangement order of the photovoltaic modules; Determine the coordinate position of the to-be-cleaned module based on the robot movement coordinate system.

12. A photovoltaic cleaning robot, characterized in that, It is controlled by the adaptive control method described in any one of claims 1 to 11.

13. A computer-readable medium storing computer program code, characterized in that, The computer program code, when executed by a processor, implements the adaptive control method described in claims 1 to 11.

Images