New energy photovoltaic power station intelligent inspection collaborative operation management method and system

Abstract

The invention provides a new energy photovoltaic power station intelligent inspection collaborative operation management method and system, and the method comprises the steps: collecting a bird's-eye view containing all photovoltaic panels, and determining the outer boundary of the bird's-eye view; obtaining pixel values representing the photovoltaic panels, and dividing the target image into a first area representing a plurality of photovoltaic panels and a second area representing an aisle according to the pixel values; an advancing route of the robot is planned in the second area, the robot is controlled to move to the starting point position of the advancing route, and meanwhile the shooting picture of the robot is controlled to contain the photovoltaic panel; the robot is controlled to move according to the advancing route, a photovoltaic panel surface image shot by the robot is obtained in real time, and the photovoltaic panel surface image is recognized; and according to the identification result, marking the corresponding to-be-processed position in the first area, and pushing the to-be-processed position to the matched user, thereby effectively solving the problems of time and labor consumption and easy missing detection due to manual one-by-one detection of the surface of the photovoltaic panel.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent inspection collaborative operation management of new energy photovoltaic power stations, and in particular relates to a method and system for intelligent inspection collaborative operation management of new energy photovoltaic power stations. Background Art

[0002] New energy photovoltaic power stations are power generation facilities that use the photovoltaic effect to directly convert solar energy into electrical energy. According to the installation method, photovoltaic power stations can be divided into centralized photovoltaic power stations and distributed photovoltaic power stations. Centralized photovoltaic power stations are usually built on large open spaces such as deserts and Gobi, and are large in scale; distributed photovoltaic power stations are mainly installed on the roofs and walls of buildings, and are small in scale.

[0003] It is usually necessary to conduct regular inspections on the surface cleanliness of photovoltaic panels. Centralized photovoltaic power stations have a large number of photovoltaic panels. The traditional inspection method relies on manual inspection one by one, which is time-consuming and labor-intensive, and is prone to missed inspections. Summary of the invention

[0004] Based on this, an embodiment of the present invention provides a new energy photovoltaic power station intelligent inspection collaborative operation management method and system, which aims to solve the problem in the prior art that it relies on manual inspection of the surface of photovoltaic panels one by one, which is time-consuming, labor-intensive, and prone to missed inspections.

[0005] A first aspect of an embodiment of the present invention provides a collaborative operation management method for intelligent inspection of a new energy photovoltaic power station, which is applied to a scene with a robot, wherein the robot is equipped with a 360° rotating camera, and an image is captured by the camera, and the method includes:

[0006] Obtaining a bird's-eye view image including all photovoltaic panels, and determining an outer boundary of the bird's-eye view image;

[0007] Acquire pixel values ​​representing photovoltaic panels in a target image surrounded by an outer boundary of the bird's-eye view, and divide the target image into a first area representing a plurality of photovoltaic panels and a second area representing a corridor according to the pixel values;

[0008] Planning a travel route of the robot in the second area, controlling the robot to move to a starting position of the travel route, and controlling a camera of the robot to move to a preset height above the photovoltaic panel, and controlling the camera to rotate to an angle perpendicular to a surface of a standard photovoltaic panel;

[0009] Controlling the robot to move along the travel route, acquiring in real time the surface image of the photovoltaic panel taken by the robot, and identifying the surface image of the photovoltaic panel, which at least includes identifying the cleanliness of the surface of the photovoltaic panel and the skewness of the photovoltaic panel;

[0010] According to the recognition result, the corresponding position to be processed is marked in the first area, and the position to be processed is pushed to the matching user.

[0011] Furthermore, the step of acquiring the photovoltaic panel surface image taken by the robot in real time and identifying the photovoltaic panel surface image includes:

[0012] Identify the photovoltaic panel surface image, determine the long side and wide side of the photovoltaic panel in the current photovoltaic panel surface image, and compare the long side and wide side of the photovoltaic panel in the current photovoltaic panel surface image with the standard long side and standard wide side respectively;

[0013] According to the comparison results, determine whether the current photovoltaic panel is skewed;

[0014] If it is determined that the current photovoltaic panel is skewed, the step of marking the corresponding position to be processed in the first area according to the recognition result and pushing the position to be processed to the matching user is executed;

[0015] If it is determined that the current photovoltaic panel is not skewed, the surface image of the photovoltaic panel is identified to determine whether there is an obstruction on the surface of the current photovoltaic panel;

[0016] If it is determined that there is an obstruction on the current photovoltaic panel surface, the step of marking the corresponding position to be processed in the first area according to the recognition result and pushing the position to be processed to the matching user is executed;

[0017] If it is determined that there is no obstruction on the current photovoltaic panel surface, the photovoltaic panel surface image is identified to determine whether there is dust accumulation on the current photovoltaic panel surface;

[0018] If it is determined that dust is accumulated on the surface of the current photovoltaic panel, the steps of marking the corresponding position to be processed in the first area according to the recognition result and pushing the position to be processed to the matching user are performed.

[0019] Furthermore, the steps of identifying the photovoltaic panel surface image, determining the long side and the wide side of the photovoltaic panel in the current photovoltaic panel surface image, and comparing the long side and the wide side of the photovoltaic panel in the current photovoltaic panel surface image with the standard long side and the standard wide side respectively include:

[0020] Determine whether the long side and the wide side of the photovoltaic panel in the current photovoltaic panel surface image are parallel to the standard long side and the standard wide side respectively;

[0021] If it is determined that the long side and the wide side of the photovoltaic panel in the current photovoltaic panel surface image are not parallel to the standard long side and the standard wide side, it means that the current photovoltaic panel is skewed;

[0022] If it is determined that the long side and the wide side of the photovoltaic panel in the current photovoltaic panel surface image are parallel to the standard long side and the standard wide side respectively, then the long side length and the wide side length of the photovoltaic panel in the current photovoltaic panel surface image are obtained respectively, and it is determined whether the long side length and the wide side length are consistent with the standard long side length and the standard wide side length respectively;

[0023] If the long side length and the wide side length are respectively consistent with the standard long side length and the standard wide side length, it means that the current photovoltaic panel is not skewed;

[0024] If the long side length and the wide side length are judged to be inconsistent with the corresponding standard long side length and the standard wide side length, it means that the current photovoltaic panel is skewed.

[0025] Furthermore, the step of identifying the surface image of the photovoltaic panel and determining whether there is an obstruction on the current photovoltaic panel surface includes:

[0026] Identify the surface image of the photovoltaic panel and obtain the pixel value of each pixel in the surface image of the photovoltaic panel;

[0027] Randomly select a pixel point as an initial pixel point, and search outward from the initial pixel point, specifically, compare the pixel values ​​of adjacent pixel points, wherein it is determined whether the pixel value difference of the adjacent pixel points is within a preset range;

[0028] If it is determined that the pixel value difference between adjacent pixel points is within a preset range, the adjacent pixel points are determined as one category;

[0029] If it is determined that the pixel value difference of adjacent pixel points is not within the preset range, the adjacent pixel points whose pixel value difference is not within the preset range are determined as another initial pixel point, and the search is conducted outwards based on the other initial pixel point until all categories of the pixel points in the photovoltaic panel surface image are determined;

[0030] Determine whether the number of categories is unique;

[0031] If the number of categories is not unique, it means that there are obstructions on the surface of the current photovoltaic panel.

[0032] Furthermore, the step of identifying the surface image of the photovoltaic panel and determining whether there is dust accumulation on the current surface of the photovoltaic panel includes:

[0033] Obtaining target pixel values ​​of pixels in a surface image of a photovoltaic panel without dust accumulation and pixel values ​​of each pixel in a current surface image of the photovoltaic panel, and calculating the difference between the pixel value of each pixel in the current surface image of the photovoltaic panel and the target pixel value;

[0034] Determine whether the difference between the pixel value of each pixel point in the current photovoltaic panel surface image and the target pixel value is greater than a first threshold;

[0035] If it is determined that the difference between the pixel value of each pixel point in the current photovoltaic panel surface image and the target pixel value is greater than a first threshold, the corresponding pixel point is determined to be a target pixel point, the number of the target pixel points is counted, and the ratio of the number of the target pixel points to all the pixel points is calculated;

[0036] Determining whether the ratio is greater than a second threshold;

[0037] If it is determined that the ratio is greater than the second threshold, it indicates that dust is currently accumulated on the surface of the photovoltaic panel.

[0038] Furthermore, the step of marking a corresponding position to be processed in the first area according to the recognition result, and pushing the position to be processed to a matching user includes:

[0039] When the recognition result shows that there are obstructions or dust accumulation on the surface of the current photovoltaic panel, the corresponding photovoltaic panel is marked in the first area, and at the same time, the geographical location of the robot is recorded, and a target area is generated according to the geographical location of the robot;

[0040] Obtain user information and the highest height of the photovoltaic panel surface where the obstruction is located, and assign the cleaning task to the user based on the user information, the highest height of the photovoltaic panel surface where the obstruction is located, and the geographic location of the robot, wherein the user information includes the user's geographic location and height.

[0041] Furthermore, the step of obtaining user information and the highest height of the photovoltaic panel surface where the obstruction is located, and assigning the cleaning task to the user according to the user information, the highest height of the photovoltaic panel surface where the obstruction is located, and the geographical location of the robot includes:

[0042] Obtain the number of geographical locations of the robots recorded in the same aisle, and determine whether the number of geographical locations of the robots recorded is unique;

[0043] If it is determined that the number of recorded geographical locations of the robot is not unique, calculating the distance between adjacent geographical locations based on the recorded geographical locations of the robot, and determining whether the distance between adjacent geographical locations is greater than a third threshold;

[0044] If it is determined that the distance between the adjacent geographical locations is greater than the third threshold, the corresponding aisle is determined to be the target aisle, and at the same time, the distance required to walk after entering the aisle is marked at the beginning and end of the corresponding aisle, and the target aisle requires the user to enter from the beginning and end of the aisle respectively;

[0045] Obtain the first highest height of the same photovoltaic panel surface where the obstruction is located, then determine the second highest height of the obstruction in the same aisle, and mark the second highest height at the beginning and end of the aisle of the corresponding aisle. At the same time, mark the distance required to walk after entering the aisle at the beginning and end of the aisle of the corresponding aisle;

[0046] The height of the user is obtained, the height of the user is matched with the second highest height, and then the optimal route is determined based on the distance required to walk after entering the aisle marked at the beginning and end of the aisle of the corresponding aisle, and pushed to the user.

[0047] A second aspect of an embodiment of the present invention provides a new energy photovoltaic power station intelligent inspection collaborative operation management system, which is used to implement the new energy photovoltaic power station intelligent inspection collaborative operation management method provided in the first aspect, and the system includes:

[0048] An acquisition module, used for acquiring a bird's-eye view including all photovoltaic panels and determining an outer boundary of the bird's-eye view;

[0049] a division module, used for obtaining pixel values ​​representing photovoltaic panels in a target image surrounded by an outer boundary of the bird's-eye view, and dividing the target image into a first area representing a plurality of photovoltaic panels and a second area representing an aisle according to the pixel values;

[0050] A control module, used for planning a travel route of the robot in the second area, controlling the robot to move to a starting position of the travel route, and controlling a camera of the robot to move to a preset height above the photovoltaic panel, and controlling the camera to rotate to an angle perpendicular to a surface of a standard photovoltaic panel;

[0051] an identification module, used to control the robot to move along the travel route, obtain in real time the surface image of the photovoltaic panel taken by the robot, and identify the surface image of the photovoltaic panel, which at least includes the identification of the cleanliness of the surface of the photovoltaic panel and the skewness of the photovoltaic panel;

[0052] The push module is used to mark the corresponding to-be-processed position in the first area according to the recognition result, and push the to-be-processed position to the matched user.

[0053] A third aspect of an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the intelligent inspection collaborative operation management method for a new energy photovoltaic power station provided in the first aspect.

[0054] The fourth aspect of an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the new energy photovoltaic power station intelligent inspection collaborative operation management method provided in the first aspect is implemented.

[0055] A method and system for managing intelligent inspection and collaborative operation of a new energy photovoltaic power station provided in an embodiment of the present invention, the method obtains a bird's-eye view including all photovoltaic panels and determines the outer boundary of the bird's-eye view; obtains pixel values ​​representing photovoltaic panels in a target image surrounded by the outer boundary of the bird's-eye view, and divides the target image into a first area representing a number of photovoltaic panels and a second area representing an aisle according to the pixel values; plans a robot's travel route in the second area, controls the robot to move to the starting position of the travel route, controls the robot's camera to move to a preset height above the photovoltaic panel, and controls the camera to rotate to an angle perpendicular to the surface of a standard photovoltaic panel; controls the robot to move according to the travel route, obtains the surface image of the photovoltaic panel taken by the robot in real time, and recognizes the surface image of the photovoltaic panel, which at least includes the recognition of the cleanliness of the surface of the photovoltaic panel and the skewness of the photovoltaic panel; marks the corresponding position to be processed in the first area according to the recognition result, and pushes the position to be processed to a matching user, effectively solving the problem of relying on manual inspection of the surface of the photovoltaic panel one by one, which is time-consuming and labor-intensive, and easy to miss. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 A flowchart of a method for implementing a collaborative operation management method for intelligent inspection of a new energy photovoltaic power station provided in the first embodiment of the present invention;

[0057] Figure 2 A flowchart of a new energy photovoltaic power station intelligent inspection collaborative operation management method provided in the second embodiment of the present invention;

[0058] Figure 3 This is a structural block diagram of an electronic device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0059] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0060] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0062] Embodiment 1

[0063] According to an embodiment of the present invention, a method for collaborative operation management of intelligent inspection of a new energy photovoltaic power station is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and, although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0064] In the first embodiment of the present invention, a collaborative operation management method for intelligent inspection of a new energy photovoltaic power station is provided, which can be used in electronic devices, such as computers. It should be noted that the method is applied to a scene with a robot, and the robot is equipped with a 360° rotating camera to capture images, wherein the robot can also be a drone.

[0065] See also Figure 1 , Figure 1 A flowchart of an implementation method of a new energy photovoltaic power station intelligent inspection collaborative operation management method provided by the first embodiment of the present invention is shown, which specifically includes steps S01 to S05.

[0066] Step S01, obtaining a bird's-eye view including all photovoltaic panels, and determining the outer boundary of the bird's-eye view.

[0067] Specifically, the bird's-eye view can be collected by using a drone. The drone can be controlled to move directly above the photovoltaic panels. It can be manually moved to a height where the image taken by the drone includes all photovoltaic panels. After obtaining the bird's-eye view, the outer boundary of the bird's-eye view can be circled, which can also be done through manual marking.

[0068] Step S02, obtaining pixel values ​​representing photovoltaic panels in a target image surrounded by an outer boundary of the bird's-eye view, and dividing the target image into a first area representing a plurality of photovoltaic panels and a second area representing an aisle according to the pixel values.

[0069] It should be noted that photovoltaic panels occupy a larger area in the target image surrounded by the outer boundary of the bird's-eye view, and a range of pixel values ​​that occupies a larger area is obtained to divide the target image into a first area representing a number of photovoltaic panels and a second area representing an aisle.

[0070] Step S03, planning the robot's travel route in the second area, controlling the robot to move to the starting position of the travel route, and controlling the robot's camera to move to a preset height above the photovoltaic panel, and controlling the camera to rotate to an angle perpendicular to the surface of the standard photovoltaic panel.

[0071] In this embodiment, since the arrangement of photovoltaic panels is relatively regular and neat, the robot's route can be manually planned, and the route is basically S-shaped. The camera of the robot is controlled to move to a preset height above the photovoltaic panel, and the camera is controlled to rotate to an angle perpendicular to the surface of the standard photovoltaic panel, so that the photovoltaic panel accounts for a larger proportion of the captured image, which is convenient for image recognition. At the same time, the camera of the robot is controlled to obtain images under standard parameters, and the skewness of the photovoltaic panel can be found by comparing the images.

[0072] Among them, standard photovoltaic panels refer to photovoltaic panels that are placed and installed according to standard specifications. The orientation of the photovoltaic panels and the angle with the ground are fixed.

[0073] Step S04, controlling the robot to move according to the travel route, acquiring in real time the surface image of the photovoltaic panel taken by the robot, and identifying the surface image of the photovoltaic panel, which at least includes identifying the cleanliness of the surface of the photovoltaic panel and the skewness of the photovoltaic panel.

[0074] It should be noted that the photovoltaic panel surface image is identified, the long side and the wide side of the photovoltaic panel in the current photovoltaic panel surface image are determined, and the long side and the wide side of the photovoltaic panel in the current photovoltaic panel surface image are compared with the standard long side and the standard wide side respectively. Specifically, it is determined whether the long side and the wide side of the photovoltaic panel in the current photovoltaic panel surface image are parallel to the standard long side and the standard wide side respectively;

[0075] If it is determined that the long side and the wide side of the photovoltaic panel in the current photovoltaic panel surface image are not parallel to the standard long side and the standard wide side, it means that the current photovoltaic panel is skewed;

[0076] If it is determined that the long side and the wide side of the photovoltaic panel in the current photovoltaic panel surface image are parallel to the standard long side and the standard wide side respectively, then the long side length and the wide side length of the photovoltaic panel in the current photovoltaic panel surface image are obtained respectively, and it is determined whether the long side length and the wide side length are consistent with the standard long side length and the standard wide side length respectively;

[0077] If the long side length and the wide side length are respectively consistent with the standard long side length and the standard wide side length, it means that the current photovoltaic panel is not skewed;

[0078] If the long side length and the wide side length are inconsistent with the corresponding standard long side length and standard wide side length, it means that the current photovoltaic panel is skewed. It is understandable that when the long side length is less than the standard long side length, the current photovoltaic panel may be tilted left and right, and when the wide side length is less than the standard wide side length, the current photovoltaic panel may be tilted up and down;

[0079] According to the comparison results, determine whether the current photovoltaic panel is skewed;

[0080] If it is determined that the current photovoltaic panel is skewed, the steps of marking the corresponding position to be processed in the first area according to the recognition result and pushing the position to be processed to the matching user are executed;

[0081] If it is determined that the current photovoltaic panel is not skewed, the surface image of the photovoltaic panel is identified to determine whether there is an obstruction on the surface of the current photovoltaic panel. Specifically, the surface image of the photovoltaic panel is identified to obtain the pixel value of each pixel in the surface image of the photovoltaic panel;

[0082] Randomly select a pixel point as the initial pixel point, and search outward from the initial pixel point, specifically, compare the pixel values ​​of adjacent pixel points, wherein it is determined whether the pixel value difference of the adjacent pixel points is within a preset range;

[0083] If it is determined that the pixel value difference between adjacent pixel points is within a preset range, the adjacent pixel points are determined as one category;

[0084] If it is determined that the pixel value difference of adjacent pixel points is not within the preset range, the adjacent pixel points whose pixel value difference is not within the preset range are determined as another initial pixel point, and the search is conducted outwards based on the other initial pixel points until all categories of the pixel points in the photovoltaic panel surface image are determined. It can be understood that the pixel points that have completed the comparison are not compared repeatedly;

[0085] Determine whether the number of categories is unique;

[0086] If the number of categories is not unique, it means that there are obstacles on the surface of the photovoltaic panel. This method can be used to quickly determine whether there are obstacles.

[0087] If it is determined that there is an obstruction on the current photovoltaic panel surface, the steps of marking the corresponding position to be processed in the first area according to the recognition result and pushing the position to be processed to the matching user are executed;

[0088] If it is determined that there is no obstruction on the current photovoltaic panel surface, the photovoltaic panel surface image is identified to determine whether there is dust accumulation on the current photovoltaic panel surface. Specifically, the target pixel value of the pixel point in the photovoltaic panel surface image without dust accumulation and the pixel value of each pixel point in the current photovoltaic panel surface image are obtained, and the difference between the pixel value of each pixel point in the current photovoltaic panel surface image and the target pixel value is calculated;

[0089] Determine whether the difference between the pixel value of each pixel point in the current photovoltaic panel surface image and the target pixel value is greater than a first threshold;

[0090] If it is determined that the difference between the pixel value of each pixel point in the current photovoltaic panel surface image and the target pixel value is greater than a first threshold, the corresponding pixel point is determined to be a target pixel point, the number of target pixel points is counted, and the ratio of the number of target pixel points to all pixel points is calculated;

[0091] Determine whether the ratio is greater than a second threshold;

[0092] If the judgment ratio is greater than the second threshold, it means that dust has accumulated on the surface of the photovoltaic panel, which has affected the performance;

[0093] If it is determined that dust is accumulated on the current photovoltaic panel surface, the steps of marking the corresponding position to be processed in the first area according to the recognition result and pushing the position to be processed to the matching user are executed.

[0094] In some other embodiments of the present invention, a number of jet devices are mounted on the robot, and the jet devices of the robot are controlled to move to a certain distance from the surface of the photovoltaic panel. Then, the number of jet devices are controlled to spray jets toward the surface of the photovoltaic panel, and the changes in pixel values ​​of the pixel points at corresponding positions before and after the jetting are compared to determine whether there is dust accumulation on the surface of the photovoltaic panel. It can be understood that if there is a change in the pixel values ​​of the pixel points at corresponding positions before and after the jetting, it means that part of the dust on the surface of the photovoltaic panel has been blown away, and there is dust accumulation on the surface of the photovoltaic panel.

[0095] Step S05: According to the recognition result, a corresponding position to be processed is marked in the first area, and the position to be processed is pushed to a matching user.

[0096] Specifically, when the recognition result shows that there are obstructions or dust accumulation on the surface of the current photovoltaic panel, the corresponding photovoltaic panel is marked in the first area, and at the same time, the geographical location of the robot is recorded, and a target area is generated according to the geographical location of the robot, wherein the target area is used to feed back the previously collected photovoltaic panel image when the user enters the area, and annotate the recognition result. It can be understood that the user needs to be equipped with a mobile terminal that can display images, such as a mobile phone or a watch, to collect the user's geographical location and receive the annotated photovoltaic panel image;

[0097] Obtain user information and the highest height of the photovoltaic panel surface where the obstruction is located, and assign the cleaning task to the user according to the user information, the highest height of the photovoltaic panel surface where the obstruction is located, and the geographical location of the robot, wherein the user information includes the geographical location and height of the user. Specifically, obtain the number of geographical locations of the robots recorded in the same aisle, and determine whether the number of geographical locations of the robots recorded is unique, that is, whether the number of photovoltaic panels to be processed is unique;

[0098] If it is determined that the number of recorded geographical locations of the robot is not unique, calculating the distance between adjacent geographical locations based on the recorded geographical locations of the robot, and determining whether the distance between adjacent geographical locations is greater than a third threshold;

[0099] If it is determined that the distance between adjacent geographical locations is greater than the third threshold, the corresponding aisle is determined to be the target aisle. At the same time, the distance required to walk after entering the aisle is marked at the beginning and end of the corresponding aisle. The target aisle requires users to enter from the beginning and end of the aisle respectively. It can be understood that in the same aisle, if the distance between the photovoltaic panels to be processed is far, the user can be arranged to enter from the aisle entrance closer to the photovoltaic panels to be processed. In general, photovoltaic panels are arranged in rows, and one aisle has two entrances;

[0100] Obtain the first highest height of the same photovoltaic panel surface where the obstruction is located, then determine the second highest height of the obstruction in the same aisle, and mark the second highest height at the beginning and end of the corresponding aisle. At the same time, mark the distance required to walk after entering the aisle at the beginning and end of the corresponding aisle, so that users can view it intuitively;

[0101] Get the user's height, match the user's height with the second highest height, let the taller user deal with the taller obstacles, and then determine the optimal route based on the distance required to walk after entering the aisle marked at the beginning and end of the corresponding aisle, based on the principle of proximity, and push it to the user to ensure that the number of abnormal photovoltaic panels handled by the user and the walking distance are not much different.

[0102] In summary, the intelligent inspection collaborative operation management method for new energy photovoltaic power stations in the above-mentioned embodiments of the present invention obtains a bird's-eye view including all photovoltaic panels and determines the outer boundary of the bird's-eye view; obtains pixel values ​​representing photovoltaic panels in a target image surrounded by the outer boundary of the bird's-eye view, and divides the target image into a first area representing a number of photovoltaic panels and a second area representing an aisle according to the pixel values; plans the robot's travel route in the second area, controls the robot to move to the starting position of the travel route, controls the robot's camera to move to a preset height above the photovoltaic panel, and controls the camera to rotate to an angle perpendicular to the surface of the standard photovoltaic panel; controls the robot to move according to the travel route, obtains the surface image of the photovoltaic panel taken by the robot in real time, and recognizes the surface image of the photovoltaic panel, which at least includes the recognition of the cleanliness of the surface of the photovoltaic panel and the skewness of the photovoltaic panel; marks the corresponding position to be processed in the first area according to the recognition result, and pushes the position to be processed to the matching user, which effectively solves the problem of relying on manual inspection of the surface of the photovoltaic panel one by one, which is time-consuming and labor-intensive, and easy to miss.

[0103] Embodiment 2

[0104] See also Figure 2 , Figure 2 It is a structural block diagram of a new energy photovoltaic power station intelligent inspection collaborative operation management system provided in Example 2 of the present invention. The new energy photovoltaic power station intelligent inspection collaborative operation management system 200 is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0105] Specifically, it is applied to a scene with a robot, the robot is equipped with a 360° rotating camera, and images are captured by the camera. The new energy photovoltaic power station intelligent inspection collaborative operation management system 200 includes: an acquisition module 21, a division module 22, a control module 23, an identification module 24 and a push module 25, wherein:

[0106] An acquisition module 21 is used to acquire a bird's-eye view including all photovoltaic panels and determine an outer boundary of the bird's-eye view;

[0107] A division module 22 is used to obtain pixel values ​​representing photovoltaic panels in a target image surrounded by an outer boundary of the bird's-eye view, and divide the target image into a first area representing a plurality of photovoltaic panels and a second area representing a corridor according to the pixel values;

[0108] The control module 23 is used to plan the robot's travel route in the second area, control the robot to move to the starting position of the travel route, and control the robot's camera to move to a preset height above the photovoltaic panel, and control the camera to rotate to an angle perpendicular to the surface of the standard photovoltaic panel;

[0109] The recognition module 24 is used to control the robot to move along the travel route, obtain the surface image of the photovoltaic panel taken by the robot in real time, and recognize the surface image of the photovoltaic panel, which at least includes the recognition of the cleanliness of the surface of the photovoltaic panel and the skewness of the photovoltaic panel;

[0110] The push module 25 is used to mark the corresponding position to be processed in the first area according to the recognition result, and push the position to be processed to the matching user.

[0111] Further, in some optional embodiments of the present invention, the identification module 24 includes:

[0112] A comparison unit is used to identify the photovoltaic panel surface image, determine the long side and wide side of the photovoltaic panel in the current photovoltaic panel surface image, and compare the long side and wide side of the photovoltaic panel in the current photovoltaic panel surface image with the standard long side and standard wide side respectively;

[0113] A first judgment unit is used to judge whether the current photovoltaic panel is skewed according to the comparison result;

[0114] A first execution unit, configured to execute the step of marking a corresponding position to be processed in the first area according to the recognition result and pushing the position to be processed to a matching user if it is determined that the current photovoltaic panel is skewed;

[0115] The second judgment unit is used to identify the surface image of the photovoltaic panel and judge whether there is an obstruction on the surface of the photovoltaic panel if it is judged that the current photovoltaic panel is not skewed;

[0116] A second execution unit is used for executing the step of marking the corresponding position to be processed in the first area according to the recognition result and pushing the position to be processed to a matching user if it is determined that there is an obstruction on the current photovoltaic panel surface;

[0117] The third judgment unit is used to identify the surface image of the photovoltaic panel and judge whether there is dust accumulation on the surface of the photovoltaic panel if it is judged that there is no obstruction on the surface of the photovoltaic panel;

[0118] The third execution unit is used to execute the step of marking the corresponding position to be processed in the first area according to the recognition result and pushing the position to be processed to a matching user if it is determined that dust is accumulated on the surface of the current photovoltaic panel.

[0119] Further, in some optional embodiments of the present invention, the comparison unit includes:

[0120] The first judgment subunit is used to judge whether the long side and the wide side of the photovoltaic panel in the current photovoltaic panel surface image are parallel to the standard long side and the standard wide side respectively;

[0121] If it is determined that the long side and the wide side of the photovoltaic panel in the current photovoltaic panel surface image are not parallel to the standard long side and the standard wide side, it means that the current photovoltaic panel is skewed;

[0122] The second judgment subunit is used to obtain the length of the long side and the length of the wide side of the photovoltaic panel in the current photovoltaic panel surface image respectively, and judge whether the length of the long side and the length of the wide side are respectively consistent with the standard long side and the standard wide side if it is judged that the long side and the wide side of the photovoltaic panel in the current photovoltaic panel surface image are parallel to the standard long side and the standard wide side respectively;

[0123] If the long side length and the wide side length are respectively consistent with the standard long side length and the standard wide side length, it means that the current photovoltaic panel is not skewed;

[0124] If the long side length and the wide side length are judged to be inconsistent with the corresponding standard long side length and the standard wide side length, it means that the current photovoltaic panel is skewed.

[0125] Further, in some optional embodiments of the present invention, the second judgment unit includes:

[0126] An acquisition subunit is used to identify the surface image of the photovoltaic panel and acquire the pixel value of each pixel in the surface image of the photovoltaic panel;

[0127] The third judgment subunit is used to randomly select a pixel point as an initial pixel point, and search outward according to the initial pixel point, specifically, compare the pixel values ​​of adjacent pixel points, wherein it is judged whether the pixel value difference of the adjacent pixel points is within a preset range;

[0128] A first determination subunit is used to determine adjacent pixel points as one category if it is determined that the pixel value difference between adjacent pixel points is within a preset range;

[0129] The second determination subunit is used for determining the adjacent pixel points whose pixel value difference is not within the preset range as another initial pixel point if it is determined that the pixel value difference of the adjacent pixel points is not within the preset range, and searching outwards based on the other initial pixel points until all categories of the pixel points in the photovoltaic panel surface image are determined;

[0130] The fourth judgment subunit is used to judge whether the number of categories is unique;

[0131] If the number of categories is not unique, it means that there are obstructions on the surface of the current photovoltaic panel.

[0132] Further, in some optional embodiments of the present invention, the third judgment unit includes:

[0133] The first calculation subunit is used to obtain the target pixel value of the pixel point in the photovoltaic panel surface image without dust accumulation and the pixel value of each pixel point in the current photovoltaic panel surface image, and calculate the difference between the pixel value of each pixel point in the current photovoltaic panel surface image and the target pixel value;

[0134] A fifth judgment subunit, used to judge whether the difference between the pixel value of each pixel point in the current photovoltaic panel surface image and the target pixel value is greater than a first threshold;

[0135] A second calculation subunit is used for determining that the corresponding pixel point is a target pixel point if the difference between the pixel value of each pixel point in the current photovoltaic panel surface image and the target pixel value is greater than a first threshold value, counting the number of the target pixel points, and calculating the ratio of the number of the target pixel points to all the pixel points;

[0136] a sixth judging subunit, configured to judge whether the ratio is greater than a second threshold;

[0137] If it is determined that the ratio is greater than the second threshold, it indicates that dust is currently accumulated on the surface of the photovoltaic panel.

[0138] Further, in some optional embodiments of the present invention, the push module 25 includes:

[0139] a target area generating unit, for marking the corresponding photovoltaic panel in the first area when the recognition result shows that there are obstructions or dust accumulation on the surface of the current photovoltaic panel, and at the same time, recording the geographical location of the robot, and generating a target area according to the geographical location of the robot;

[0140] The allocation unit is used to obtain user information and the highest height of the photovoltaic panel surface where the obstruction is located, and allocate the cleaning task to the user based on the user information, the highest height of the photovoltaic panel surface where the obstruction is located, and the geographical location of the robot, wherein the user information includes the user's geographical location and height.

[0141] Further, in some optional embodiments of the present invention, the allocation unit includes:

[0142] a seventh judgment subunit, configured to obtain the number of geographical locations of the robots recorded in the same aisle, and to judge whether the number of geographical locations of the robots recorded is unique;

[0143] an eighth judgment subunit, configured to calculate the distance between adjacent geographical locations according to the recorded geographical locations of the robot if it is determined that the number of geographical locations of the robot recorded is not unique, and to judge whether the distance between adjacent geographical locations is greater than a third threshold;

[0144] A third determination subunit is used to determine that the corresponding aisle is a target aisle if it is determined that the distance between the adjacent geographical locations is greater than a third threshold value, and at the same time, mark the distance required to walk after entering the aisle at the beginning and end of the corresponding aisle, and the target aisle requires the user to enter from the beginning and end of the aisle respectively;

[0145] The fourth determination subunit is used to obtain the first highest height of the same photovoltaic panel surface where the shielding object is located, and then determine the second highest height of the shielding object in the same aisle, and mark the second highest height at the beginning and end of the aisle of the corresponding aisle, and at the same time, mark the distance required to walk after entering the aisle at the beginning and end of the aisle of the corresponding aisle;

[0146] The fifth determination subunit is used to obtain the user's height, match the user's height with the second maximum height, and then determine the optimal route based on the distance required to walk after entering the aisle marked at the beginning and end of the corresponding aisle, and push it to the user.

[0147] Embodiment 3

[0148] Another aspect of the present invention provides an electronic device, see Figure 3 , shown is an electronic device in Embodiment 3 of the present invention, including a memory 20, a processor 10, and a computer program 30 stored in the memory and executable on the processor. When the processor 10 executes the computer program 30, the above-mentioned intelligent inspection collaborative operation management method for new energy photovoltaic power stations is implemented.

[0149] In some embodiments, the processor 10 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 20, such as executing access restriction programs.

[0150] Among them, the memory 20 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. The memory 20 may be an internal storage unit of an electronic device in some embodiments, such as a hard disk of the electronic device. The memory 20 may also be an external storage device of an electronic device in other embodiments, such as a plug-in hard disk equipped on the electronic device, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Further, the memory 20 may also include both an internal storage unit and an external storage device of the electronic device. The memory 20 may be used not only to store application software and various types of data of the electronic device, but also to temporarily store data that has been output or is to be output.

[0151] It should be pointed out that Figure 3 The structure shown does not constitute a limitation on the electronic device. In other embodiments, the electronic device may include fewer or more components than those shown in the figure, or combine certain components, or arrange the components differently.

[0152] The embodiment of the present invention further proposes a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method for managing the intelligent inspection and collaborative operation of a new energy photovoltaic power station as described above is implemented.

[0153] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, a "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0154] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0155] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0156] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0157] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the attached claims.

Claims

1. A new energy photovoltaic power station intelligent inspection collaborative operation management method, characterized in that: Applied to a scene with a robot, the robot is equipped with a 360° rotating camera, and an image is captured by the camera. The method includes: Obtaining a bird's-eye view image including all photovoltaic panels, and determining an outer boundary of the bird's-eye view image; Acquire pixel values ​​representing photovoltaic panels in a target image surrounded by an outer boundary of the bird's-eye view, and divide the target image into a first area representing a plurality of photovoltaic panels and a second area representing a corridor according to the pixel values; Planning a travel route of the robot in the second area, controlling the robot to move to a starting position of the travel route, and controlling a camera of the robot to move to a preset height above the photovoltaic panel, and controlling the camera to rotate to an angle perpendicular to a surface of a standard photovoltaic panel; Controlling the robot to move along the travel route, acquiring in real time the surface image of the photovoltaic panel taken by the robot, and identifying the surface image of the photovoltaic panel, which at least includes identifying the cleanliness of the surface of the photovoltaic panel and the skewness of the photovoltaic panel; According to the recognition result, the corresponding position to be processed is marked in the first area, and the position to be processed is pushed to the matching user.

2. The intelligent inspection and collaborative operation management method for new energy photovoltaic power stations according to claim 1 is characterized in that: The step of acquiring the photovoltaic panel surface image taken by the robot in real time and identifying the photovoltaic panel surface image comprises: Identify the photovoltaic panel surface image, determine the long side and wide side of the photovoltaic panel in the current photovoltaic panel surface image, and compare the long side and wide side of the photovoltaic panel in the current photovoltaic panel surface image with the standard long side and standard wide side respectively; According to the comparison results, determine whether the current photovoltaic panel is skewed; If it is determined that the current photovoltaic panel is skewed, the step of marking the corresponding position to be processed in the first area according to the recognition result and pushing the position to be processed to the matching user is executed; If it is determined that the current photovoltaic panel is not skewed, the surface image of the photovoltaic panel is identified to determine whether there is an obstruction on the surface of the current photovoltaic panel; If it is determined that there is an obstruction on the current photovoltaic panel surface, the step of marking the corresponding position to be processed in the first area according to the recognition result and pushing the position to be processed to the matching user is executed; If it is determined that there is no obstruction on the current photovoltaic panel surface, the photovoltaic panel surface image is identified to determine whether there is dust accumulation on the current photovoltaic panel surface; If it is determined that dust is accumulated on the surface of the current photovoltaic panel, the steps of marking the corresponding position to be processed in the first area according to the recognition result and pushing the position to be processed to the matching user are performed.

3. The intelligent inspection and collaborative operation management method for new energy photovoltaic power stations according to claim 2 is characterized in that: The steps of identifying the photovoltaic panel surface image, determining the long side and the wide side of the photovoltaic panel in the current photovoltaic panel surface image, and comparing the long side and the wide side of the photovoltaic panel in the current photovoltaic panel surface image with the standard long side and the standard wide side respectively include: Determine whether the long side and the wide side of the photovoltaic panel in the current photovoltaic panel surface image are parallel to the standard long side and the standard wide side respectively; If it is determined that the long side and the wide side of the photovoltaic panel in the current photovoltaic panel surface image are not parallel to the standard long side and the standard wide side, it means that the current photovoltaic panel is skewed; If it is determined that the long side and the wide side of the photovoltaic panel in the current photovoltaic panel surface image are parallel to the standard long side and the standard wide side respectively, then the long side length and the wide side length of the photovoltaic panel in the current photovoltaic panel surface image are obtained respectively, and it is determined whether the long side length and the wide side length are consistent with the standard long side length and the standard wide side length respectively; If the long side length and the wide side length are respectively consistent with the standard long side length and the standard wide side length, it means that the current photovoltaic panel is not skewed; If the long side length and the wide side length are judged to be inconsistent with the corresponding standard long side length and the standard wide side length, it means that the current photovoltaic panel is skewed.

4. The intelligent inspection collaborative operation management method for a new energy photovoltaic power station according to claim 3 is characterized in that: The step of identifying the surface image of the photovoltaic panel and determining whether there is an obstruction on the current photovoltaic panel surface comprises: Identify the surface image of the photovoltaic panel and obtain the pixel value of each pixel in the surface image of the photovoltaic panel; Randomly select a pixel point as an initial pixel point, and search outward from the initial pixel point, specifically, compare the pixel values ​​of adjacent pixel points, wherein it is determined whether the pixel value difference of the adjacent pixel points is within a preset range; If it is determined that the pixel value difference between adjacent pixel points is within a preset range, the adjacent pixel points are determined as one category; If it is determined that the pixel value difference of adjacent pixel points is not within the preset range, the adjacent pixel points whose pixel value difference is not within the preset range are determined as another initial pixel point, and the search is conducted outwards based on the other initial pixel point until all categories of the pixel points in the photovoltaic panel surface image are determined; Determine whether the number of categories is unique; If the number of categories is not unique, it means that there are obstructions on the surface of the current photovoltaic panel.

5. The intelligent inspection and collaborative operation management method for new energy photovoltaic power stations according to claim 4 is characterized in that: The step of identifying the surface image of the photovoltaic panel and determining whether dust is currently accumulated on the surface of the photovoltaic panel comprises: Obtaining target pixel values ​​of pixels in a surface image of a photovoltaic panel without dust accumulation and pixel values ​​of each pixel in a current surface image of the photovoltaic panel, and calculating the difference between the pixel value of each pixel in the current surface image of the photovoltaic panel and the target pixel value; Determine whether the difference between the pixel value of each pixel point in the current photovoltaic panel surface image and the target pixel value is greater than a first threshold; If it is determined that the difference between the pixel value of each pixel point in the current photovoltaic panel surface image and the target pixel value is greater than a first threshold, the corresponding pixel point is determined to be a target pixel point, the number of the target pixel points is counted, and the ratio of the number of the target pixel points to all the pixel points is calculated; Determining whether the ratio is greater than a second threshold; If it is determined that the ratio is greater than the second threshold, it indicates that dust is currently accumulated on the surface of the photovoltaic panel.

6. The intelligent inspection and collaborative operation management method for a new energy photovoltaic power station according to claim 5 is characterized in that: The step of marking a corresponding position to be processed in the first area according to the recognition result and pushing the position to be processed to a matching user comprises: When the recognition result shows that there are obstructions or dust accumulation on the surface of the current photovoltaic panel, the corresponding photovoltaic panel is marked in the first area, and at the same time, the geographical location of the robot is recorded, and a target area is generated according to the geographical location of the robot; Obtain user information and the highest height of the photovoltaic panel surface where the obstruction is located, and assign the cleaning task to the user based on the user information, the highest height of the photovoltaic panel surface where the obstruction is located, and the geographic location of the robot, wherein the user information includes the user's geographic location and height.

7. The intelligent inspection collaborative operation management method for a new energy photovoltaic power station according to claim 6 is characterized in that: The step of obtaining user information and the highest height of the photovoltaic panel surface where the obstruction is located, and assigning the cleaning task to the user according to the user information, the highest height of the photovoltaic panel surface where the obstruction is located, and the geographical location of the robot comprises: Obtain the number of geographical locations of the robots recorded in the same aisle, and determine whether the number of geographical locations of the robots recorded is unique; If it is determined that the number of recorded geographical locations of the robot is not unique, calculating the distance between adjacent geographical locations based on the recorded geographical locations of the robot, and determining whether the distance between adjacent geographical locations is greater than a third threshold; If it is determined that the distance between the adjacent geographical locations is greater than the third threshold, the corresponding aisle is determined to be the target aisle, and at the same time, the distance required to walk after entering the aisle is marked at the beginning and end of the corresponding aisle, and the target aisle requires the user to enter from the beginning and end of the aisle respectively; Obtain the first highest height of the same photovoltaic panel surface where the obstruction is located, then determine the second highest height of the obstruction in the same aisle, and mark the second highest height at the beginning and end of the aisle of the corresponding aisle. At the same time, mark the distance required to walk after entering the aisle at the beginning and end of the aisle of the corresponding aisle; The height of the user is obtained, the height of the user is matched with the second highest height, and then the optimal route is determined based on the distance required to walk after entering the aisle marked at the beginning and end of the aisle of the corresponding aisle, and pushed to the user.

8. A new energy photovoltaic power station intelligent inspection collaborative operation management system, characterized in that: The system is used to implement the intelligent inspection collaborative operation management method of the new energy photovoltaic power station according to any one of claims 1 to 7, and the system comprises: An acquisition module, used for acquiring a bird's-eye view including all photovoltaic panels and determining an outer boundary of the bird's-eye view; a division module, used for obtaining pixel values ​​representing photovoltaic panels in a target image surrounded by an outer boundary of the bird's-eye view, and dividing the target image into a first area representing a plurality of photovoltaic panels and a second area representing an aisle according to the pixel values; A control module, used for planning a travel route of the robot in the second area, controlling the robot to move to a starting position of the travel route, and controlling a camera of the robot to move to a preset height above the photovoltaic panel, and controlling the camera to rotate to an angle perpendicular to a surface of a standard photovoltaic panel; an identification module, used to control the robot to move along the travel route, obtain in real time the surface image of the photovoltaic panel taken by the robot, and identify the surface image of the photovoltaic panel, which at least includes the identification of the cleanliness of the surface of the photovoltaic panel and the skewness of the photovoltaic panel; The push module is used to mark the corresponding to-be-processed position in the first area according to the recognition result, and push the to-be-processed position to the matched user.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the new energy photovoltaic power station intelligent inspection collaborative operation management method as described in any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the intelligent inspection collaborative operation management method for a new energy photovoltaic power station as described in any one of claims 1 to 7 is implemented.

Images