Inspection control method and system for photovoltaic cleaning robot

Abstract

The invention relates to the technical field of photovoltaic cleaning robots, and discloses an inspection control method and system for a photovoltaic cleaning robot, and the method comprises the steps: obtaining the image data of a photovoltaic module, and determining the pollution degree of a polluted photovoltaic panel according to the image data of the photovoltaic module; acquiring meteorological data of the photovoltaic power station, and predicting the pollution degree change value of the polluted photovoltaic panel according to the meteorological data of the photovoltaic power station; determining a photovoltaic panel cleaning strategy according to the pollution degree change value of the polluted photovoltaic panel, and determining an inspection path of the photovoltaic cleaning robot according to the photovoltaic panel cleaning strategy; and performing secondary inspection on the polluted photovoltaic panel after the inspection is finished, determining an abnormal photovoltaic panel according to the pollution degree of the polluted photovoltaic panel subjected to the secondary inspection, and performing early warning on the abnormal photovoltaic panel. According to the photovoltaic cleaning robot, the pollution degree change value of the photovoltaic panel can be predicted and inspected in time, meanwhile, the abnormal photovoltaic panel is recognized, and the cleaning efficiency of the photovoltaic cleaning robot is effectively improved.

Description

Technical Field

[0001] The present application relates to the technical field of photovoltaic cleaning robots, and more specifically, to an inspection control method and system for a photovoltaic cleaning robot. Background Art

[0002] Photovoltaic power generation refers to the conversion of solar energy into electrical energy and storage through photovoltaic panels. Photovoltaic power generation is still a green energy use method strongly supported by many countries. During the use of photovoltaic panels, when dirt adheres to the photovoltaic panels, the power generation efficiency will decrease, so they need to be cleaned. The conventional cleaning methods mainly include manual cleaning, high-pressure water gun cleaning, large-scale cleaning equipment cleaning, and photovoltaic cleaning robot cleaning.

[0003] The photovoltaic cleaning robots in the prior art are of a single type and a single function, and are unable to inspect photovoltaic power stations, resulting in the failure to promptly detect seriously polluted photovoltaic panels. In addition, the cleaning method is single and the cleaning efficiency is low, which affects the power generation efficiency of the photovoltaic power station. Summary of the invention

[0004] The present invention provides a patrol control method and system for a photovoltaic cleaning robot, which is used to solve the problem of low cleaning efficiency of photovoltaic cleaning robots in the prior art. The method comprises:

[0005] Acquire photovoltaic module image data, and determine the degree of contamination of the contaminated photovoltaic panel according to the photovoltaic module image data;

[0006] Obtain meteorological data of the photovoltaic power station, and predict the change value of the pollution degree of the polluted photovoltaic panels based on the meteorological data of the photovoltaic power station;

[0007] Determine a photovoltaic panel cleaning strategy according to the change in the degree of contamination of the contaminated photovoltaic panel, and determine an inspection path of the photovoltaic cleaning robot according to the photovoltaic panel cleaning strategy;

[0008] After the inspection, a second inspection is carried out on the polluted photovoltaic panels. The abnormal photovoltaic panels are determined according to the degree of pollution of the polluted photovoltaic panels in the second inspection, and early warning is issued for the abnormal photovoltaic panels.

[0009] Further, determining the degree of contamination of the contaminated photovoltaic panel according to the photovoltaic component image data includes:

[0010] Grayscale processing is performed on the photovoltaic module image data to obtain a photovoltaic module grayscale image;

[0011] Determine the pixel points of the photovoltaic panel region of the photovoltaic module grayscale image based on a preset grayscale interval, and perform regional growth on the pixel points of the photovoltaic panel region based on a region growing algorithm to obtain a photovoltaic panel region;

[0012] The photovoltaic panel area is detected based on the Canny algorithm to obtain the edge of the suspected contaminated area of ​​the photovoltaic panel area;

[0013] Obtain the center point of the edge of the suspected contaminated area, and generate several radial lines with a preset angle from the center point as the starting point and the edge of the suspected contaminated area as the end point;

[0014] Obtaining the length value of each radiation line in the suspected contaminated area, and normalizing each radiation line according to the length value of each radiation line in the suspected contaminated area to obtain the normalized radiation line;

[0015] Calculating the variance of the normalized radiation line length values ​​in the suspected contaminated area, and determining the suspected contaminated area with a variance greater than a first preset threshold as a contaminated area;

[0016] A grayscale image of the polluted area is obtained, and the degree of contamination of the polluted photovoltaic panel is determined according to the grayscale image of the polluted area.

[0017] Furthermore, determining the degree of contamination of the contaminated photovoltaic panel according to the grayscale image of the contaminated area includes:

[0018] Obtain a standard photovoltaic panel area, calculate the difference between the area value of the standard photovoltaic panel area and the area value of the polluted area, and obtain a first pollution parameter;

[0019] Obtaining an average grayscale value of pixels in the grayscale image of the polluted area, and determining the average grayscale value of pixels in the grayscale image of the polluted area as a second pollution parameter;

[0020] Obtaining the proportion of pixels whose grayscale values ​​of the grayscale image of the polluted area are less than the average grayscale value, and determining the proportion of pixels whose grayscale values ​​of the grayscale image of the polluted area are less than the average grayscale value as a third pollution parameter;

[0021] The first pollution parameter, the second pollution parameter, and the third pollution parameter are normalized respectively, and the sum of the first pollution parameter, the second pollution parameter, and the third pollution parameter after the normalization is calculated to obtain the pollution degree of the polluted photovoltaic panel.

[0022] Furthermore, the prediction of the change value of the pollution degree of the polluted photovoltaic panels according to the meteorological data of the photovoltaic power station includes:

[0023] Determine the meteorological type of the photovoltaic power station within a preset period of time according to the meteorological data of the photovoltaic power station, and determine the pollution degree change parameter according to the meteorological type of the photovoltaic power station within the preset period of time;

[0024] The pollution degree change value is determined based on the pollution degree calculation formula according to the pollution degree change parameter. The pollution degree calculation formula is specifically as follows:

[0025]

[0026] Among them, p is the change value of pollution degree, Q is the current pollution degree, W i is the pollution degree variation parameter, i=1, 2, 3, t is the preset time period, and R is the preset range coefficient.

[0027] Furthermore, the determining of the pollution degree change parameter according to the meteorological type of the photovoltaic power station within a preset period of time includes:

[0028] If the weather type of the photovoltaic power station during the preset period is rainy weather, the pollution degree change parameter is set to W1;

[0029] If the weather type of the photovoltaic power station during the preset period is sunny, the pollution degree change parameter is set to W2;

[0030] If the weather type of the photovoltaic power station in the preset time period is windy weather, the pollution degree change parameter is set to W3, where W1<0<W2<W3.

[0031] Furthermore, the photovoltaic panel cleaning strategy is determined according to the change value of the contamination degree of the contaminated photovoltaic panel, including:

[0032] Obtain a preset pollution degree tolerance threshold, screen out polluted photovoltaic panels whose pollution degree change value within a preset period is greater than the preset pollution degree tolerance threshold, and obtain the photovoltaic panels to be cleaned and the corresponding position coordinates;

[0033] Calculate the difference between the change in pollution level of the photovoltaic panel to be cleaned within a preset period of time and the pollution level tolerance threshold, determine the cleaning time according to the difference between the change in pollution level of the photovoltaic panel to be cleaned within the preset period of time and the pollution level tolerance threshold, and determine the photovoltaic panel cleaning strategy according to the position coordinates of the photovoltaic panel to be cleaned and the cleaning time.

[0034] Further, the determining of the inspection path of the photovoltaic cleaning robot according to the photovoltaic panel cleaning strategy includes:

[0035] Obtain the arrangement positions of each photovoltaic panel in the photovoltaic power station, establish a photovoltaic panel distribution topology map according to the arrangement positions of each photovoltaic panel in the photovoltaic power station, and mark the position coordinates of the photovoltaic panels to be cleaned in the photovoltaic panel distribution topology map according to the photovoltaic panel cleaning strategy;

[0036] Obtain the cleaning time of any two photovoltaic panels to be cleaned, and calculate the cleaning time difference between any two photovoltaic panels to be cleaned;

[0037] The cleaning time difference is multiplied by the distance between the two photovoltaic panels to be cleaned to obtain the difference between the two photovoltaic panels to be cleaned, and the photovoltaic panels to be cleaned whose difference is less than a second preset threshold are merged into the same area to be cleaned;

[0038] All photovoltaic panels to be cleaned are merged to obtain several areas to be cleaned;

[0039] All inspection paths of the photovoltaic cleaning robot are determined according to all areas to be cleaned, and the inspection path with the shortest time consumption is selected as the inspection path of the photovoltaic cleaning robot.

[0040] Furthermore, the method of determining the inspection path of the photovoltaic cleaning robot according to the photovoltaic panel cleaning strategy also includes:

[0041] Sorting the cleaning time of each photovoltaic panel to be cleaned in the area to be cleaned, assigning a cleaning weight to each photovoltaic panel to be cleaned according to the sorting result, and determining a first fine inspection path according to the cleaning weight of each photovoltaic panel to be cleaned;

[0042] Acquire a second fine inspection path in the area to be cleaned that takes less time than a third preset threshold, select the second fine inspection path with the highest overlap with the first fine inspection path, and obtain a fine inspection path;

[0043] The refined inspection path is added to the inspection path of the photovoltaic cleaning robot to obtain the final inspection path.

[0044] Furthermore, the determining of abnormal photovoltaic panels according to the contamination degree of the contaminated photovoltaic panels inspected for the second time includes:

[0045] The difference between the pollution degree of the polluted photovoltaic panels inspected for the second time and the pollution degree of the polluted photovoltaic panels before the inspection is calculated, and the polluted photovoltaic panels whose pollution degree difference is greater than the fourth preset threshold are screened out, and the polluted photovoltaic panels whose pollution degree difference is greater than the fourth preset threshold are determined as abnormal photovoltaic panels.

[0046] In order to achieve the above object, the present invention also provides a patrol control system for a photovoltaic cleaning robot, comprising:

[0047] The first module is used to obtain the photovoltaic module image data and determine the degree of contamination of the photovoltaic panel according to the photovoltaic module image data;

[0048] The second module is used to obtain the meteorological data of the photovoltaic power station and predict the change value of the pollution degree of the polluted photovoltaic panels according to the meteorological data of the photovoltaic power station;

[0049] The third module is used to determine the photovoltaic panel cleaning strategy according to the change value of the pollution degree of the polluted photovoltaic panel, and determine the inspection path of the photovoltaic cleaning robot according to the photovoltaic panel cleaning strategy;

[0050] The fourth module is used to conduct a second inspection on the polluted photovoltaic panels after the inspection is completed, determine abnormal photovoltaic panels according to the degree of pollution of the polluted photovoltaic panels in the second inspection, and issue an early warning for the abnormal photovoltaic panels.

[0051] The beneficial effects of the present invention are:

[0052] By applying the above technical scheme, the present invention collects photovoltaic component image data to detect the pollution degree of each photovoltaic panel, and predicts the change value of the pollution degree of the photovoltaic panel based on meteorological data, thereby realizing the prediction of the pollution trend of the photovoltaic panel, and formulating a cleaning strategy for the photovoltaic panel according to the prediction results, thereby determining the inspection path of the photovoltaic cleaning robot, effectively improving the cleaning efficiency, and through secondary inspection of contaminated photovoltaic panels, abnormal photovoltaic panels are discovered in time and early warnings are issued, thereby ensuring the normal operation of the photovoltaic power station. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0054] Figure 1 A schematic flow chart of a patrol control method of a photovoltaic cleaning robot proposed in an embodiment of the present invention is shown;

[0055] Figure 2 The figure shows the overall structure of a patrol control system of a photovoltaic cleaning robot proposed in an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0057] The present application embodiment provides a patrol control method for a photovoltaic cleaning robot, such as Figure 1 As shown, the method includes:

[0058] S101, obtaining photovoltaic module image data, and determining the degree of contamination of the contaminated photovoltaic panel according to the photovoltaic module image data;

[0059] In some embodiments of the present application, the method of determining the degree of contamination of a contaminated photovoltaic panel based on photovoltaic module image data includes: grayscale processing the photovoltaic module image data to obtain a photovoltaic module grayscale image; determining the photovoltaic panel area pixel points of the photovoltaic module grayscale image based on a preset grayscale interval, and performing regional growth on the photovoltaic panel area pixel points based on a regional growing algorithm to obtain a photovoltaic panel area; performing edge detection on the photovoltaic panel area based on a canny algorithm to obtain an edge of a suspected contaminated area of ​​the photovoltaic panel area; obtaining a center point of the edge of the suspected contaminated area, and generating a plurality of radiation lines from the center point as a starting point at a preset angle and the edge of the suspected contaminated area as an end point; obtaining a length value of each radiation line in the suspected contaminated area, and normalizing each radiation line according to the length value of each radiation line in the suspected contaminated area to obtain the normalized radiation line; calculating the variance of the normalized radiation line length value in the suspected contaminated area, and determining the suspected contaminated area whose variance is greater than a first preset threshold as a contaminated area; obtaining a grayscale image of the contaminated area, and determining the degree of contamination of the contaminated photovoltaic panel according to the grayscale image of the contaminated area.

[0060] In this embodiment, the photovoltaic module image data of the photovoltaic power station is collected by a drone, and the pixel points whose grayscale values ​​are in the preset grayscale interval are screened out by the preset grayscale interval, and the photovoltaic panel area is obtained by performing regional growth on the screened pixel points. The photovoltaic panel area is edge detected based on the canny algorithm, and the edge of the photovoltaic panel area is detected. The non-photovoltaic panel area of ​​the photovoltaic module image data is determined as the edge of the suspected contaminated area. The radiation lines in the suspected contaminated area are normalized based on the maximum length value and the minimum length value of each radiation line in the suspected contaminated area. The regularity of the suspected contaminated area is obtained by the variance of the normalized radiation line length value in the suspected contaminated area, so that the irregular suspected contaminated area is determined as the contaminated area.

[0061] In some embodiments of the present application, determining the degree of contamination of a contaminated photovoltaic panel based on a grayscale image of a contaminated area includes: obtaining a standard photovoltaic panel area, calculating the difference between an area value of the standard photovoltaic panel area and an area value of the contaminated area, and obtaining a first pollution parameter; obtaining an average grayscale value of pixels in the grayscale image of the contaminated area, and determining the average grayscale value of pixels in the grayscale image of the contaminated area as a second pollution parameter; obtaining the proportion of pixels in the grayscale image of the contaminated area whose grayscale value is less than the average grayscale value, and determining the proportion of pixels in the grayscale image of the contaminated area whose grayscale value is less than the average grayscale value as a third pollution parameter; normalizing the first pollution parameter, the second pollution parameter, and the third pollution parameter, respectively, and calculating the sum of the first pollution parameter, the second pollution parameter, and the third pollution parameter after normalization to obtain the degree of contamination of the contaminated photovoltaic panel.

[0062] In this embodiment, the pollution degree of the polluted photovoltaic panel is obtained by calculating the sum of the first pollution parameter, the second pollution parameter and the third pollution parameter, and the pollution degree, pollution depth and pollution uniformity of the polluted area are comprehensively evaluated to obtain a comprehensive pollution degree evaluation index.

[0063] S102, obtaining meteorological data of the photovoltaic power station, and predicting the change value of the pollution degree of the polluted photovoltaic panels according to the meteorological data of the photovoltaic power station;

[0064] In some embodiments of the present application, the prediction of the pollution degree change value of the polluted photovoltaic panel according to the meteorological data of the photovoltaic power station includes: determining the meteorological type of the photovoltaic power station within a preset period of time according to the meteorological data of the photovoltaic power station, and determining the pollution degree change parameter according to the meteorological type of the photovoltaic power station within the preset period of time; determining the pollution degree change value according to the pollution degree change parameter based on the pollution degree calculation formula, and the pollution degree calculation formula is specifically,

[0065]

[0066] Among them, P is the change value of pollution degree, Q is the current pollution degree, and W is i is the pollution degree variation parameter, i=1, 2, 3, t is the preset time period, and R is the preset range coefficient.

[0067] In some embodiments of the present application, the pollution degree change parameter is determined according to the meteorological type of the photovoltaic power station within a preset time period, including: if the meteorological type of the photovoltaic power station within the preset time period is rainy weather, the pollution degree change parameter is set to W1; if the meteorological type of the photovoltaic power station within the preset time period is clear weather, the pollution degree change parameter is set to W2; if the meteorological type of the photovoltaic power station within the preset time period is windy weather, the pollution degree change parameter is set to W3, wherein W1<0<W2<W3.

[0068] In this embodiment, when the rainfall amount is greater than the preset standard rainfall amount, the meteorological type of the photovoltaic power station is determined to be rainy weather; when the wind force is greater than the preset standard wind force, the meteorological type of the photovoltaic power station is determined to be windy weather; the rest of the weather is clear weather, and the corresponding pollution degree change parameters are set for each weather type, thereby realizing the prediction of the pollution degree change value within the preset time period.

[0069] S103, determining a photovoltaic panel cleaning strategy according to a change in the degree of contamination of the contaminated photovoltaic panel, and determining an inspection path of a photovoltaic cleaning robot according to the photovoltaic panel cleaning strategy;

[0070] In some embodiments of the present application, the photovoltaic panel cleaning strategy is determined based on the pollution degree change value of the contaminated photovoltaic panel, including: obtaining a preset pollution degree tolerance threshold, screening out the contaminated photovoltaic panels whose pollution degree change values ​​within a preset time period are greater than the preset degree tolerance threshold, and obtaining the photovoltaic panels to be cleaned and the corresponding position coordinates; calculating the difference between the pollution degree change value of the photovoltaic panels to be cleaned within the preset time period and the pollution degree tolerance threshold, determining the cleaning time based on the difference between the pollution degree change value of the photovoltaic panels to be cleaned within the preset time period and the pollution degree tolerance threshold, and determining the photovoltaic panel cleaning strategy based on the position coordinates and the cleaning time of the photovoltaic panels to be cleaned.

[0071] In this embodiment, the cleaning time is determined by the difference between the change in the pollution level of the photovoltaic panel to be cleaned within a preset time period and the pollution level tolerance threshold. The larger the difference, the longer the corresponding cleaning time. The position coordinates and cleaning time of each photovoltaic panel to be cleaned are counted to obtain the photovoltaic panel cleaning strategy.

[0072] In some embodiments of the present application, the inspection path of the photovoltaic cleaning robot is determined according to the photovoltaic panel cleaning strategy, including: obtaining the arrangement position of each photovoltaic panel in the photovoltaic power station, establishing a photovoltaic panel distribution topology map according to the arrangement position of each photovoltaic panel in the photovoltaic power station, and marking the position coordinates of the photovoltaic panels to be cleaned in the photovoltaic panel distribution topology map according to the photovoltaic panel cleaning strategy; obtaining the cleaning time of any two photovoltaic panels to be cleaned, and calculating the cleaning time difference between any two photovoltaic panels to be cleaned; multiplying the cleaning time difference by the distance value of the two photovoltaic panels to be cleaned to obtain the difference between the two photovoltaic panels to be cleaned, and merging the photovoltaic panels to be cleaned whose difference is less than a second preset threshold into the same area to be cleaned; merging all the photovoltaic panels to be cleaned to obtain several areas to be cleaned; determining all the inspection paths of the photovoltaic cleaning robot according to all the areas to be cleaned, and screening out the inspection path with the lowest time consumption as the inspection path of the photovoltaic cleaning robot.

[0073] In this embodiment, the photovoltaic panels to be cleaned are marked in the photovoltaic panel distribution topology map, and the photovoltaic panels to be cleaned are merged by cleaning time difference and distance value to obtain several areas to be cleaned. The inspection path with the shortest time is screened out by traversing the inspection path through each area to be cleaned, and the photovoltaic cleaning robot is controlled to clean the photovoltaic panels through the inspection path with the shortest time.

[0074] In some embodiments of the present application, the inspection path of the photovoltaic cleaning robot is determined according to the photovoltaic panel cleaning strategy, and further includes: sorting the cleaning time of each photovoltaic panel to be cleaned in the area to be cleaned, assigning a cleaning weight to each photovoltaic panel to be cleaned according to the sorting result, and determining a first fine inspection path according to the cleaning weight of each photovoltaic panel to be cleaned; obtaining a second fine inspection path in the area to be cleaned that takes less than a third preset threshold value, screening out the second fine inspection path with the highest degree of overlap with the first fine inspection path, and obtaining a fine inspection path; adding the fine inspection path to the inspection path of the photovoltaic cleaning robot to obtain a final inspection path.

[0075] In this embodiment, a cleaning weight is allocated according to the cleaning time of each photovoltaic panel to be cleaned. The longer the cleaning time, the greater the corresponding cleaning weight is allocated. The first fine inspection path is determined by the order of the cleaning weights. The second fine inspection path whose time consumption is less than a third preset threshold is screened out by traversing the inspection paths of each photovoltaic panel to be cleaned. The first fine inspection path and the second fine inspection path are overlapped, and the second fine inspection path with the highest overlap is screened out as the fine inspection path. The fine inspection path is merged into the inspection path of the photovoltaic cleaning robot to obtain the final inspection path.

[0076] S104, performing a secondary inspection on the polluted photovoltaic panels after the inspection, determining abnormal photovoltaic panels according to the degree of pollution of the polluted photovoltaic panels in the secondary inspection, and issuing an early warning for the abnormal photovoltaic panels.

[0077] In some embodiments of the present application, determining abnormal photovoltaic panels based on the degree of contamination of the contaminated photovoltaic panels inspected for the second time includes: calculating the difference between the degree of contamination of the contaminated photovoltaic panels inspected for the second time and the degree of contamination of the contaminated photovoltaic panels before the inspection, screening out the contaminated photovoltaic panels whose difference in degree of contamination is greater than a fourth preset threshold, and determining the contaminated photovoltaic panels whose difference in degree of contamination is greater than the fourth preset threshold as abnormal photovoltaic panels.

[0078] In this embodiment, the abnormal photovoltaic panel is located by the difference between the pollution degree of the polluted photovoltaic panel in the second inspection and the pollution degree of the polluted photovoltaic panel before the inspection. When the difference is 0 or the difference becomes larger, the corresponding polluted photovoltaic panel is determined as an abnormal photovoltaic panel.

[0079] Based on the same technical concept, such as Figure 2 As shown, the present invention also provides a patrol control system for a photovoltaic cleaning robot, comprising:

[0080] The first module is used to obtain the image data of photovoltaic modules, and determine the pollution degree of the polluted photovoltaic panels according to the image data of the photovoltaic modules; the second module is used to obtain the meteorological data of the photovoltaic power station, and predict the change value of the pollution degree of the polluted photovoltaic panels according to the meteorological data of the photovoltaic power station; the third module is used to determine the photovoltaic panel cleaning strategy according to the change value of the pollution degree of the polluted photovoltaic panels, and determine the inspection path of the photovoltaic cleaning robot according to the photovoltaic panel cleaning strategy; the fourth module is used to conduct a secondary inspection of the polluted photovoltaic panels after the inspection, determine the abnormal photovoltaic panels according to the pollution degree of the polluted photovoltaic panels in the secondary inspection, and issue early warnings for the abnormal photovoltaic panels.

[0081] By applying the above technical solutions, the present invention obtains the image data of photovoltaic modules, determines the degree of contamination of the contaminated photovoltaic panels according to the image data of photovoltaic modules; obtains the meteorological data of the photovoltaic power station, predicts the change value of the degree of contamination of the contaminated photovoltaic panels according to the meteorological data of the photovoltaic power station; determines the photovoltaic panel cleaning strategy according to the change value of the degree of contamination of the contaminated photovoltaic panels, and determines the inspection path of the photovoltaic cleaning robot according to the photovoltaic panel cleaning strategy; conducts a secondary inspection on the contaminated photovoltaic panels after the inspection, determines the abnormal photovoltaic panels according to the degree of contamination of the contaminated photovoltaic panels in the secondary inspection, and issues an early warning for the abnormal photovoltaic panels. It is possible to predict the change value of the degree of contamination of the photovoltaic panels and conduct inspections in a timely manner, while identifying abnormal photovoltaic panels, and effectively improve the cleaning efficiency of the photovoltaic cleaning robot.

[0082] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present invention can be implemented by hardware, or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present invention.

[0083] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A patrol control method for a photovoltaic cleaning robot, characterized in that: The method comprises: Acquire photovoltaic module image data, and determine the degree of contamination of the contaminated photovoltaic panel according to the photovoltaic module image data; Obtain meteorological data of the photovoltaic power station, and predict the change value of the pollution degree of the polluted photovoltaic panels based on the meteorological data of the photovoltaic power station; Determine a photovoltaic panel cleaning strategy according to the change in the degree of contamination of the contaminated photovoltaic panel, and determine an inspection path of the photovoltaic cleaning robot according to the photovoltaic panel cleaning strategy; After the inspection, a second inspection is carried out on the polluted photovoltaic panels. The abnormal photovoltaic panels are determined according to the degree of pollution of the polluted photovoltaic panels in the second inspection, and early warning is issued for the abnormal photovoltaic panels.

2. The inspection control method of the photovoltaic cleaning robot according to claim 1, characterized in that: The step of determining the degree of contamination of the photovoltaic panel according to the photovoltaic component image data comprises: Grayscale processing is performed on the photovoltaic module image data to obtain a photovoltaic module grayscale image; Determine the pixel points of the photovoltaic panel region of the photovoltaic module grayscale image based on a preset grayscale interval, and perform regional growth on the pixel points of the photovoltaic panel region based on a region growing algorithm to obtain a photovoltaic panel region; The photovoltaic panel area is detected based on the Canny algorithm to obtain the edge of the suspected contaminated area of ​​the photovoltaic panel area; Obtain the center point of the edge of the suspected contaminated area, and generate several radial lines with a preset angle from the center point as the starting point and the edge of the suspected contaminated area as the end point; Obtaining the length value of each radiation line in the suspected contaminated area, and normalizing each radiation line according to the length value of each radiation line in the suspected contaminated area to obtain the normalized radiation line; Calculating the variance of the normalized radiation line length values ​​in the suspected contaminated area, and determining the suspected contaminated area with a variance greater than a first preset threshold as a contaminated area; A grayscale image of the polluted area is obtained, and the degree of contamination of the polluted photovoltaic panel is determined according to the grayscale image of the polluted area.

3. The inspection control method of the photovoltaic cleaning robot according to claim 2, characterized in that: Determining the degree of contamination of the photovoltaic panel according to the grayscale image of the contaminated area includes: Obtain a standard photovoltaic panel area, calculate the difference between the area value of the standard photovoltaic panel area and the area value of the polluted area, and obtain a first pollution parameter; Obtaining an average grayscale value of pixels in the grayscale image of the polluted area, and determining the average grayscale value of pixels in the grayscale image of the polluted area as a second pollution parameter; Obtaining the proportion of pixels whose grayscale values ​​of the grayscale image of the polluted area are less than the average grayscale value, and determining the proportion of pixels whose grayscale values ​​of the grayscale image of the polluted area are less than the average grayscale value as a third pollution parameter; The first pollution parameter, the second pollution parameter, and the third pollution parameter are normalized respectively, and the sum of the first pollution parameter, the second pollution parameter, and the third pollution parameter after the normalization is calculated to obtain the pollution degree of the polluted photovoltaic panel.

4. The inspection control method of the photovoltaic cleaning robot according to claim 1, characterized in that: The prediction of the change value of the pollution degree of the polluted photovoltaic panels according to the meteorological data of the photovoltaic power station includes: Determine the meteorological type of the photovoltaic power station within a preset period of time according to the meteorological data of the photovoltaic power station, and determine the pollution degree change parameter according to the meteorological type of the photovoltaic power station within the preset period of time; The pollution degree change value is determined based on the pollution degree calculation formula according to the pollution degree change parameter. The pollution degree calculation formula is specifically as follows: Among them, P is the change value of pollution degree, Q is the current pollution degree, and W is i is the pollution degree variation parameter, i=1, 2, 3, t is the preset time period, and R is the preset range coefficient.

5. The inspection control method of the photovoltaic cleaning robot according to claim 4, characterized in that: The step of determining the pollution degree change parameter according to the meteorological type of the photovoltaic power station within a preset period of time includes: If the weather type of the photovoltaic power station during the preset period is rainy weather, the pollution degree change parameter is set to W1; If the weather type of the photovoltaic power station during the preset period is sunny, the pollution degree change parameter is set to W2; If the weather type of the photovoltaic power station in the preset time period is windy weather, the pollution degree change parameter is set to W3, where W1<0<W2<W3.

6. The inspection control method of the photovoltaic cleaning robot according to claim 1, characterized in that: The step of determining a photovoltaic panel cleaning strategy according to a change in the degree of contamination of the contaminated photovoltaic panel comprises: Obtain a preset pollution degree tolerance threshold, screen out polluted photovoltaic panels whose pollution degree change value within a preset period is greater than the preset pollution degree tolerance threshold, and obtain the photovoltaic panels to be cleaned and the corresponding position coordinates; Calculate the difference between the change in pollution level of the photovoltaic panel to be cleaned within a preset period of time and the pollution level tolerance threshold, determine the cleaning time according to the difference between the change in pollution level of the photovoltaic panel to be cleaned within the preset period of time and the pollution level tolerance threshold, and determine the photovoltaic panel cleaning strategy according to the position coordinates of the photovoltaic panel to be cleaned and the cleaning time.

7. The inspection control method of the photovoltaic cleaning robot according to claim 6, characterized in that: Determining the inspection path of the photovoltaic cleaning robot according to the photovoltaic panel cleaning strategy includes: Obtain the arrangement positions of each photovoltaic panel in the photovoltaic power station, establish a photovoltaic panel distribution topology map according to the arrangement positions of each photovoltaic panel in the photovoltaic power station, and mark the position coordinates of the photovoltaic panels to be cleaned in the photovoltaic panel distribution topology map according to the photovoltaic panel cleaning strategy; Obtain the cleaning time of any two photovoltaic panels to be cleaned, and calculate the cleaning time difference between any two photovoltaic panels to be cleaned; The cleaning time difference is multiplied by the distance between the two photovoltaic panels to be cleaned to obtain the difference between the two photovoltaic panels to be cleaned, and the photovoltaic panels to be cleaned whose difference is less than a second preset threshold are merged into the same area to be cleaned; All photovoltaic panels to be cleaned are merged to obtain several areas to be cleaned; All inspection paths of the photovoltaic cleaning robot are determined according to all areas to be cleaned, and the inspection path with the shortest time consumption is selected as the inspection path of the photovoltaic cleaning robot.

8. The inspection control method of the photovoltaic cleaning robot according to claim 7, characterized in that: The step of determining the inspection path of the photovoltaic cleaning robot according to the photovoltaic panel cleaning strategy further includes: Sorting the cleaning time of each photovoltaic panel to be cleaned in the area to be cleaned, assigning a cleaning weight to each photovoltaic panel to be cleaned according to the sorting result, and determining a first fine inspection path according to the cleaning weight of each photovoltaic panel to be cleaned; Acquire a second fine inspection path in the area to be cleaned that takes less time than a third preset threshold, select the second fine inspection path with the highest overlap with the first fine inspection path, and obtain a fine inspection path; The refined inspection path is added to the inspection path of the photovoltaic cleaning robot to obtain the final inspection path.

9. The inspection control method of the photovoltaic cleaning robot according to claim 1, characterized in that: The method of determining an abnormal photovoltaic panel according to the contamination degree of the contaminated photovoltaic panel obtained through the secondary inspection includes: The difference between the pollution degree of the polluted photovoltaic panels inspected for the second time and the pollution degree of the polluted photovoltaic panels before the inspection is calculated, and the polluted photovoltaic panels whose pollution degree difference is greater than the fourth preset threshold are screened out, and the polluted photovoltaic panels whose pollution degree difference is greater than the fourth preset threshold are determined as abnormal photovoltaic panels.

10. A patrol control system for a photovoltaic cleaning robot, characterized in that: include: The first module is used to obtain the photovoltaic module image data and determine the degree of contamination of the photovoltaic panel according to the photovoltaic module image data; The second module is used to obtain the meteorological data of the photovoltaic power station and predict the change value of the pollution degree of the polluted photovoltaic panels according to the meteorological data of the photovoltaic power station; The third module is used to determine the photovoltaic panel cleaning strategy according to the change value of the pollution degree of the polluted photovoltaic panel, and determine the inspection path of the photovoltaic cleaning robot according to the photovoltaic panel cleaning strategy; The fourth module is used to conduct a second inspection on the polluted photovoltaic panels after the inspection is completed, determine abnormal photovoltaic panels according to the degree of pollution of the polluted photovoltaic panels in the second inspection, and issue an early warning for the abnormal photovoltaic panels.

Images