Photovoltaic panel cleaning path planning method and system

Abstract

A photovoltaic panel cleaning path planning method, comprising: collecting the dust accumulation level of each photovoltaic panel; marking a photovoltaic panel with level-1 dust accumulation as Mandatory To Clean, marking a photovoltaic panel with level-2 dust accumulation as Optional To Clean, and marking a photovoltaic panel with level-3 dust accumulation as No Cleaning Required; selecting two photovoltaic panels from the photovoltaic array and respectively setting same as a start point and an end point; and planning a shortest path between the start point and the end point as an optimal cleaning path, wherein the shortest path covers all photovoltaic panels marked as Mandatory To Clean and no less than q% of photovoltaic panels marked as Optional To Clean.

Description

Photovoltaic panel cleaning path planning method and system TECHNICAL FIELD

[0001] The present application relates to the technical field of photovoltaic panel cleaning, in particular to a photovoltaic panel cleaning path planning method and system. BACKGROUND

[0002] A photovoltaic panel, also known as a solar panel or a solar photovoltaic panel, is a device used to convert solar light into electrical energy. It is composed of multiple solar cells that use the photoelectric effect to convert light energy into electrical energy.

[0003] Cleaning of photovoltaic panels often involves high-altitude work risks and personal safety hazards. Therefore, many fields have begun to develop cleaning robots to replace manual cleaning. However, frequent cleaning can also cause damage to photovoltaic panels. Therefore, it is necessary to reasonably control the cleaning frequency, and not all photovoltaic panels need to be cleaned each time. In this case, if the inherent full coverage route is still used for cleaning, it will be a waste of time and will cause excessive consumption of robots.

[0004] Therefore, when cleaning photovoltaic panels, it is necessary to consider the cleaning necessity of each photovoltaic panel and plan the cleaning path to achieve fast, efficient, and moderate photovoltaic panel cleaning.

[0005] SUMMARY

[0006] The purpose of the present application is to provide a photovoltaic panel cleaning path planning method and system that can achieve fast, efficient, and moderate photovoltaic panel cleaning.

[0007] Embodiments of the present application are implemented by the following technical solutions:

[0008] A photovoltaic panel cleaning path planning method, comprising the following steps:

[0009] Collecting the dust accumulation level of each photovoltaic panel, the dust accumulation level being divided according to the amount of dust accumulation, the dust accumulation level being divided into first-level dust accumulation, second-level dust accumulation, and third-level dust accumulation from more to less;

[0010] Marking photovoltaic panels with first-level dust accumulation as must be cleaned, marking photovoltaic panels with second-level dust accumulation as optionally cleaned, and marking photovoltaic panels with third-level dust accumulation as not needing to be cleaned;

[0011] Selecting two photovoltaic panels in a photovoltaic array to be set as a starting point and an ending point, respectively;

[0012] Planning a shortest path between the starting point and the ending point as the best cleaning path, the shortest path covering all photovoltaic panels marked as must be cleaned and no less than q% of photovoltaic panels marked as optionally cleaned.

[0013] Preferably, the method for collecting the dust level of each photovoltaic panel is:

[0014] setting a first degree threshold and a second degree threshold for the dust degree, the first degree threshold being greater than the second degree threshold;

[0015] collecting the dust degree of each photovoltaic panel;

[0016] defining the dust level of the photovoltaic panel with a dust degree greater than the first degree threshold as first-level dust;

[0017] defining the dust level of the photovoltaic panel with a dust degree less than the second degree threshold as third-level dust;

[0018] defining the dust level of the photovoltaic panel in other cases as second-level dust.

[0019] Preferably, the method for collecting the dust degree of each photovoltaic panel is:

[0020] collecting an image of a clean photovoltaic panel as a reference image, and performing grayscale and equalization processing on the reference image;

[0021] extracting a reference feature vector of the reference image, the reference feature matrix including elements of the gray level co-occurrence matrix of the reference image at multiple angles;

[0022] collecting an image of the photovoltaic panel as a measurement image, and performing grayscale and equalization processing on the measurement image;

[0023] extracting a measurement feature vector of the measurement image, the measurement feature matrix including elements of the gray level co-occurrence matrix of the measurement image at multiple angles;

[0024] obtaining a similarity f based on the measurement feature vector and the reference feature vector through a pre-trained comparison model;

[0025] obtaining the dust degree g:

[0026] Preferably, the method for selecting two photovoltaic panels in the photovoltaic array as the starting point and the ending point is:

[0027] selecting a photovoltaic panel located at the edge of the photovoltaic array and marked as having to be cleaned as the starting point, and selecting a photovoltaic panel located at the edge of the photovoltaic array and marked as having to be cleaned as the ending point.

[0028] Preferably, the leftmost or rightmost photovoltaic panel in the first row of photovoltaic panels marked as having to be cleaned in the photovoltaic array is selected as the starting point;

[0029] The leftmost or rightmost photovoltaic panel in the last row of the photovoltaic array marked as having to be cleaned is selected as the end point.

[0030] Preferably, the method of planning the shortest path between the start point and the end point is:

[0031] The number x of photovoltaic panels marked as selected for cleaning is obtained;

[0032] The minimum number y of photovoltaic panels marked as selected for cleaning covered by the shortest path is obtained:

[0033] where, is a rounding up operation;

[0034] A set of selected cleaning A is constructed: A = [m i ], i = 1, 2, …, n, n being the total number of m i ;

[0035] where m i is a set of y photovoltaic panels randomly selected from the x photovoltaic panels marked as selected for cleaning;

[0036] The optimal cleaning path is obtained according to the set of selected cleaning A and the set of photovoltaic panels marked as having to be cleaned.

[0037] Preferably, the method of obtaining the optimal cleaning path is:

[0038] Initialize the mark k = 1;

[0039] A traversal set B is constructed: B = [m k , U], where U is the set of photovoltaic panels marked as having to be cleaned;

[0040] The kth optimal path covering all elements of the traversal set is directly found by the optimal path construction algorithm between the start point and the end point, and the path length is denoted as l k ;

[0041] Change the value of the mark k: k = k + 1;

[0042] Repeat the above steps until k = n;

[0043] The minimum path in the path length l i of the ith optimal path is obtained, i = 1, 2, …, n;

[0044] The optimal path corresponding to the minimum path is selected as the optimal cleaning path.

[0045] Preferably, the shortest path covers all photovoltaic panels marked as must be cleaned and no less than q% of the photovoltaic panels marked as optional cleaning, and the value of q is selected from the range of 75≤q≤85.

[0046] To solve the above problems, the application further provides a photovoltaic panel cleaning path planning system, which is applied to the photovoltaic panel cleaning path planning method in any one of the above, and comprises:

[0047] Dust accumulation condition acquisition module: used for acquiring the dust accumulation level of each photovoltaic panel, wherein the dust accumulation level is divided according to the dust accumulation amount, and the dust accumulation level is divided into first-level dust accumulation, second-level dust accumulation and third-level dust accumulation from more to less according to the dust accumulation amount;

[0048] Cleaning condition marking module: used for marking the photovoltaic panel with first-level dust accumulation as must be cleaned, marking the photovoltaic panel with second-level dust accumulation as optional cleaning, and marking the photovoltaic panel with third-level dust accumulation as no need to be cleaned;

[0049] Starting point and ending point setting module: used for selecting two photovoltaic panels in the photovoltaic array to set as a starting point and an ending point respectively;

[0050] Path planning module: used for planning a shortest path between the starting point and the ending point as the best cleaning path, wherein the shortest path covers all photovoltaic panels marked as must be cleaned and no less than q% of the photovoltaic panels marked as optional cleaning.

[0051] The technical scheme of the embodiment of the application has at least the following advantages and beneficial effects:

[0052] The application judges the cleaning necessity of each photovoltaic panel before cleaning, avoids over cleaning and too frequent cleaning to cause abrasion of the photovoltaic panel, and helps to improve the service life of the photovoltaic panel;

[0053] The application calculates the similarity by taking the normal clean photovoltaic panel as a reference, takes the reciprocal of the similarity as the dust accumulation degree, and is convenient for calculation and data acquisition, easy to implement, and has high reliability;

[0054] The application fully cleans the photovoltaic panel with excessive dust accumulation, partially cleans the photovoltaic panel with moderate dust accumulation according to the principle of optimal path, and directly does not need to clean the photovoltaic panel with light dust accumulation, which takes into account cost saving, efficient cleaning and moderate cleaning.

[0055] The application has reasonable and simple design, and can be applied to cleaning of any photovoltaic array, and is convenient for popularization and implementation. BRIEF DESCRIPTION OF DRAWINGS

[0056] Fig. 1 is a flowchart of the photovoltaic panel cleaning path planning method provided by the embodiment 1 of the application. DETAILED DESCRIPTION

[0057] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will be combined with the drawings in the embodiments of the present application to make a clear and complete description of the technical solutions in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations.

[0058] Embodiment 1

[0059] The embodiment provides a photovoltaic panel cleaning path planning method, referring to FIG. 1, comprising the following steps:

[0060] Marking the cleaning type: collecting the dust accumulation level of each photovoltaic panel, the dust accumulation level is divided according to the dust accumulation amount, and the dust accumulation level is divided into first-level dust accumulation, second-level dust accumulation and third-level dust accumulation from more to less according to the dust accumulation amount;

[0061] Marking the photovoltaic panel with first-level dust accumulation as must be cleaned, marking the photovoltaic panel with second-level dust accumulation as selected to be cleaned, and marking the photovoltaic panel with third-level dust accumulation as unnecessary to be cleaned;

[0062] Selecting two photovoltaic panels in the photovoltaic array to be set as a starting point and an ending point respectively;

[0063] Planning a shortest path between the starting point and the ending point as an optimal cleaning path, and the shortest path covers all the photovoltaic panels marked as must be cleaned and no less than q % of the photovoltaic panels marked as selected to be cleaned.

[0064] The embodiment mainly plans the cleaning path of the photovoltaic panel in the photovoltaic array. In order to prevent excessive cleaning from causing abrasion, the embodiment first judges the dust accumulation level of the photovoltaic panel, then judges the cleaning necessity degree of each photovoltaic panel according to the dust accumulation level, and can exclude the photovoltaic panel that does not need to be cleaned at all when planning the path, and ensures that the photovoltaic panel marked as must be cleaned and no less than q % of the photovoltaic panel marked as selected to be cleaned will be cleaned.

[0065] In this way, the optimal cleaning path is obtained, which not only can improve the speed and efficiency of cleaning, reduce the cleaning cost, but also can prevent damage caused by excessive cleaning of the photovoltaic panel.

[0066] Embodiment 2

[0067] The embodiment is based on the technical solution of embodiment 1, and further describes the dust accumulation level calibration method.

[0068] In the embodiment, the method for collecting the dust accumulation level of each photovoltaic panel is:

[0069] A first degree threshold and a second degree threshold are set for the dust accumulation degree, and the first degree threshold is greater than the second degree threshold;

[0070] collecting a degree of dust accumulation of each of the photovoltaic panels;

[0071] defining a dust accumulation level of the photovoltaic panel with a dust accumulation degree greater than the first degree threshold as a first-level dust accumulation;

[0072] defining a dust accumulation level of the photovoltaic panel with a dust accumulation degree less than the second degree threshold as a third-level dust accumulation;

[0073] defining a dust accumulation level of the photovoltaic panel in other cases as a second-level dust accumulation.

[0074] Further, the method for collecting the degree of dust accumulation of each of the photovoltaic panels is as follows:

[0075] collecting an image of a clean photovoltaic panel as a reference image, and performing grayscale and equalization processing on the reference image;

[0076] extracting a reference feature vector of the reference image, wherein the reference feature matrix includes elements of the gray level co-occurrence matrix of the reference image at multiple angles;

[0077] collecting an image of the photovoltaic panel as a measurement image, and performing grayscale and equalization processing on the measurement image;

[0078] extracting a measurement feature vector of the measurement image, wherein the measurement feature matrix includes elements of the gray level co-occurrence matrix of the measurement image at multiple angles;

[0079] obtaining a similarity f based on the measurement feature vector and the reference feature vector through a pre-trained comparison model;

[0080] obtaining the degree of dust accumulation g:

[0081] In this embodiment, the dust accumulation is determined by detecting the similarity between the image of the current photovoltaic panel and the image of the clean photovoltaic panel as the reference image. By default, the higher the similarity, the cleaner the photovoltaic panel, and the lower the similarity, the more dust accumulation. Therefore, the reciprocal of the similarity f is selected as the description of the degree of dust accumulation g. The greater the value of the degree of dust accumulation g, the more dust accumulation and the greater the need for cleaning.

[0082] When calculating the similarity through the pre-trained comparison model, the gray level co-occurrence matrix at multiple angles is used to construct the feature vector. The use of the gray level co-occurrence matrix can reflect various image features, such as contrast and uniformity.

[0083] The dimension of the gray level co-occurrence matrix is determined by the gray image corresponding to the image, and the gray level in the gray image is N, so the dimension of the gray level co-occurrence matrix is N*N. Generally, four different angles of the gray level co-occurrence matrix, 0 degrees, 45 degrees, 90 degrees and 135 degrees, can be used to build the feature vector in this embodiment. The feature vector can be written in the order of 0 degrees, 45 degrees, 90 degrees and 135 degrees, and each element of the gray level co-occurrence matrix is written in the feature vector in the order from top to bottom and from left to right. After determining the distance d, the dimension of the gray level co-occurrence matrix N*N and the angle, the construction of the gray level co-occurrence matrix can be performed. In short, the value of the element at position (i, j) in the gray level co-occurrence matrix represents the number of gray pairs formed by elements at a distance of d in the set angle direction starting from the element with a gray value of b i The element value of the gray level co-occurrence matrix at position (i, j) represents the number of gray pairs formed by elements at a distance of d in the set angle direction starting from the element with a gray value of b i , where b j , b i , and b j are the i-th and j-th gray values in all gray values in the gray image.

[0084] Embodiment 3

[0085] This embodiment is based on the technical solution of embodiment 1, and further illustrates the setting of the starting point and the ending point when planning the path.

[0086] In this embodiment, the method of selecting two photovoltaic panels in the photovoltaic array as the starting point and the ending point is:

[0087] Selecting a photovoltaic panel located at the edge of the photovoltaic array and marked as having to be cleaned as the starting point, and selecting a photovoltaic panel located at the edge of the photovoltaic array and marked as having to be cleaned as the ending point.

[0088] Further, the leftmost or rightmost photovoltaic panel in the first row of the photovoltaic array marked as having to be cleaned is selected as the starting point.

[0089] The leftmost or rightmost photovoltaic panel in the last row of the photovoltaic array marked as having to be cleaned is selected as the ending point.

[0090] Embodiment 4

[0091] This embodiment is based on the technical solution of embodiment 1, and further illustrates the method of planning the shortest path.

[0092] As a preferred solution of this embodiment, the method of planning the shortest path between the starting point and the ending point is:

[0093] Obtaining the number x of photovoltaic panels marked as selected for cleaning;

[0094] Obtaining the minimum number y of photovoltaic panels marked for selective cleaning that the shortest path covers:

[0095] wherein, is a rounding up operation;

[0096] Constructing the selective cleaning set A: A = [m i ], i = 1, 2, …, n, n being the total number of m i ;

[0097] wherein m i is a set of y photovoltaic panels randomly selected from the x photovoltaic panels marked for selective cleaning, and n can be set as the total number of selection possibilities of y from the x photovoltaic panels marked for selective cleaning in specific settings;

[0098] Obtaining the optimal cleaning path according to the selective cleaning set A and the set of photovoltaic panels marked for mandatory cleaning.

[0099] In the present embodiment, the method for obtaining the optimal cleaning path is:

[0100] Initializing the mark k = 1;

[0101] Constructing the traversal set: B = [m k , U], wherein U is the set of photovoltaic panels marked for mandatory cleaning;

[0102] Directly finding the kth optimal path covering all elements of the traversal set by the optimal path construction algorithm between the starting point and the ending point, and the path length is denoted as l k ;

[0103] Changing the value of the mark k: k = k + 1;

[0104] Repeating the above steps until k = n;

[0105] Obtaining the minimum path in the path length l i of the ith optimal path, i = 1, 2, …, n;

[0106] Selecting the optimal path corresponding to the minimum path as the optimal cleaning path.

[0107] On the other hand, when the shortest path covers all photovoltaic panels marked for mandatory cleaning and no less than q% of photovoltaic panels marked for selective cleaning, the value of q is selected in the range of 75 ≤ q ≤ 85.

[0108] In the construction of the route, the target is covered to cover all the photovoltaic panels marked as must be cleaned and q% of the photovoltaic panels marked as optional cleaning, and the lower limit of the photovoltaic panels marked as optional cleaning is q%. Therefore, in the actual operation of cleaning, the cleaning path can be set to cover all the photovoltaic panels marked as must be cleaned and the photovoltaic panels marked as optional cleaning, and the photovoltaic panels marked as no need to be cleaned are not cleaned, because the actual planned path cannot only cover all the photovoltaic panels marked as must be cleaned and q% of the photovoltaic panels marked as optional cleaning.

[0109] Embodiment 5

[0110] The embodiment provides a photovoltaic panel cleaning path planning system, applied to the photovoltaic panel cleaning path planning method of any one of the above embodiments, and comprising:

[0111] The dust accumulation condition acquisition module is configured to acquire the dust accumulation level of each photovoltaic panel, wherein the dust accumulation level is divided according to the dust accumulation amount, and the dust accumulation level is divided into first-level dust accumulation, second-level dust accumulation and third-level dust accumulation from more to less according to the dust accumulation amount.

[0112] The cleaning condition marking module is configured to mark the photovoltaic panel with first-level dust accumulation as must be cleaned, mark the photovoltaic panel with second-level dust accumulation as optional cleaning, and mark the photovoltaic panel with third-level dust accumulation as no need to be cleaned.

[0113] The start point and end point setting module is configured to select two photovoltaic panels in the photovoltaic array as a start point and an end point, respectively.

[0114] The path planning module is configured to plan a shortest path between the start point and the end point as a best cleaning path, and the shortest path covers all the photovoltaic panels marked as must be cleaned and no less than q% of the photovoltaic panels marked as optional cleaning.

[0115] The above is only a preferred embodiment of the present application and is not used to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method of photovoltaic panel cleaning path planning, characterized in that, The method comprises the following steps: Collecting the dust level of each photovoltaic panel, the dust level being divided according to the amount of dust, the dust level being divided into first dust, second dust and third dust from more to less according to the amount of dust; Marking the photovoltaic panel with first dust as must be cleaned, marking the photovoltaic panel with second dust as optional cleaning, and marking the photovoltaic panel with third dust as no need to be cleaned; Selecting two photovoltaic panels in the photovoltaic array as the starting point and the ending point respectively; Planning the shortest path between the starting point and the ending point as the best cleaning path, the shortest path covering all the photovoltaic panels marked as must be cleaned and no less than q% of the photovoltaic panels marked as optional cleaning.

2. A method of cleaning path planning for a photovoltaic panel according to claim 1, wherein, The method for collecting the dust level of each photovoltaic panel is: Setting a first degree threshold and a second degree threshold for the dust level, the first degree threshold being greater than the second degree threshold; Collecting the dust level of each photovoltaic panel; Defining the dust level of the photovoltaic panel with the dust level greater than the first degree threshold as first dust; Defining the dust level of the photovoltaic panel with the dust level less than the second degree threshold as third dust; Defining the dust level of the photovoltaic panel in other cases as second dust.

3. A method of cleaning path planning for a photovoltaic panel according to claim 2, wherein, The method for collecting the dust level of each photovoltaic panel is: Collecting the image of the clean photovoltaic panel as a reference image, and performing grayscale and equalization processing on the reference image; Extracting the reference feature vector of the reference image, the reference feature matrix including the elements of the gray level co-occurrence matrix of the reference image at multiple angles; Collecting the image of the photovoltaic panel as a measurement image, and performing grayscale and equalization processing on the measurement image; Extracting the measurement feature vector of the measurement image, the measurement feature matrix including the elements of the gray level co-occurrence matrix of the measurement image at multiple angles; Obtaining the similarity f based on the measurement feature vector and the reference feature vector through a pre-trained comparison model; The method for selecting two photovoltaic panels in the photovoltaic array as the starting point and the ending point is: acquiring the degree of soot accumulation g:

4. The method of claim 1, wherein, Selecting a photovoltaic panel located at the edge of the photovoltaic array and marked as must be cleaned as the starting point, and selecting a photovoltaic panel located at the edge of the photovoltaic array and marked as must be cleaned as the ending point. Selecting the leftmost or rightmost photovoltaic panel in the first row of the photovoltaic array and marked as must be cleaned as the starting point; 5. A method of cleaning path planning for a photovoltaic panel according to claim 4, wherein, Selecting the leftmost or rightmost photovoltaic panel in the last row of the photovoltaic array and marked as must be cleaned as the ending point. The method for planning the shortest path between the starting point and the ending point is:

6. The method of claim 1, wherein, Obtaining the number x of the photovoltaic panels marked as optional cleaning; Performing the upward rounding operation; acquiring a marking of the shortest path coverage as a minimum number y of photovoltaic panels to be selected for cleaning: wherein Obtaining the best cleaning path according to the optional cleaning set A and the set of photovoltaic panels marked as must be cleaned. Constructing the selection sweeping set A: A = [m i ], i = 1, 2, …, n, n is the total number of m i ​ wherein m i is a set of y of the photovoltaic panels randomly selected among x of the photovoltaic panels marked for selective cleaning; The method for obtaining the best cleaning path is:

7. A method of cleaning path planning for a photovoltaic panel according to claim 6, wherein, Initializing the mark k = 1; Changing the value of the mark k: k = k + 1; Build the set of traversed sets: B = [m k , U], where U is the set of the photovoltaic panels marked as to be cleaned. directly finding a kth best path covering all elements of the traversal set by an optimal path construction algorithm, and the path length is recorded as l k ; Repeating the above steps until k = n; Selecting the best path corresponding to the minimum path as the best cleaning path. the minimum path length in the set of paths l i , i = 1, 2, …, n; When the shortest path covers all the photovoltaic panels marked as must be cleaned and no less than q% of the photovoltaic panels marked as optional cleaning, the value of q is selected in the range of 75 ≤ q ≤ 85.

8. The method of claim 1, wherein, ​ 9. A photovoltaic panel cleaning path planning system, applied to the photovoltaic panel cleaning path planning method of any one of claims 1-8, characterized in that, Comprise: Dust accumulation acquisition module: for collecting the dust accumulation level of each photovoltaic panel, the dust accumulation level is divided according to the dust accumulation amount, the dust accumulation level is divided into first dust accumulation, second dust accumulation and third dust accumulation from more to less according to the dust accumulation amount; Scrubbing condition marking module: for marking the photovoltaic panel with first dust accumulation as must be cleaned, marking the photovoltaic panel with second dust accumulation as optional cleaning, and marking the photovoltaic panel with third dust accumulation as unnecessary cleaning; Starting point and ending point setting module: for selecting two photovoltaic panels in the photovoltaic array as starting point and ending point respectively; Path planning module: for planning the shortest path between the starting point and the ending point as the best cleaning path, the shortest path covers all photovoltaic panels marked as must be cleaned and no less than q% of photovoltaic panels marked as optional cleaning. ​

Images