Photovoltaic assembly glass plate crack early warning method, device, electronic device and medium

Abstract

The present application provides a method, device, electronic device, and medium for early warning of cracks in a glass plate of a photovoltaic assembly, which relates to the field of photovoltaic assembly technology. The method includes the steps of: acquiring target point cloud data obtained by scanning a target glass plate with a target scanner, the target glass plate being a glass plate located on the surface of the photovoltaic assembly, the target point cloud data including color point cloud data composed of color data of all pixel points corresponding to the target glass plate and temperature point cloud data composed of temperature data and position data of all pixel points corresponding to the target glass plate; determining an area value of a crack center of the target glass plate based on the color point cloud data, determining shape information of the crack in the target glass plate based on the temperature point cloud data, determining a target early warning level based on the area value of the crack center and / or the crack shape information, and issuing an early warning according to an early warning scheme corresponding to the target early warning level. The scheme improves the safety of the photovoltaic assembly.

Description

[Technical Field]

[0001] This application relates to the field of photovoltaic assembly technology, and more particularly to glass sheet crack early warning methods, devices, electronic devices and media for photovoltaic assemblies. [Background technology]

[0002] Due to the convenience, efficiency, and land resource saving characteristics of photovoltaic power generation, photovoltaic stations have been constructed over large areas in the deserts and other regions of the northwest. The photovoltaic assemblies in the photovoltaic stations are subject to adverse weather conditions such as dry climates, high temperatures, little rain, and sandstorms. In particular, the glass panes of the photovoltaic assemblies are prone to cracking and localized hot spots due to adverse weather conditions and glass materials, which can cause the photovoltaic panels to burn and even cause fires. In this context, the impact of adverse weather conditions and glass materials on the normal operation of the photovoltaic assemblies is obvious.

[0003] Most conventional glass plate crack early warning methods use manual methods, specifically, on-site personnel inspect, record, and report whether there are cracks in the glass plate of each photovoltaic assembly. This method takes into account personnel subjectivity and the fact that different personnel may describe and classify the same crack, which may result in various discrepancies. Furthermore, when cracks occur simultaneously in the glass plate of different photovoltaic assemblies, some of the cracks may not be detected in a timely manner.

[0004] Due to the poor promptness of early warning in the prior art, if the photovoltaic assembly continues to operate when the glass plate crack is serious, there is a technical problem that it is prone to fire and is unsafe. Summary of the Invention [Problem to be solved by the invention]

[0005] The present application provides a method, device, electronic device and medium for early warning of glass plate cracks in a photovoltaic assembly, in order to solve the technical problem that in the prior art, photovoltaic assemblies continue to operate when the glass plate crack is serious, resulting in poor safety. [Means for solving the problem]

[0006] According to a first aspect of the present application, there is provided an early warning method for a crack in a glass plate of a photovoltaic assembly, the early warning method for a crack in a glass plate of a photovoltaic assembly comprising: acquiring target point cloud data obtained by scanning a target glass sheet with a target scanner, the target glass sheet being a glass sheet located on a surface of a photovoltaic assembly, the target point cloud data including: color point cloud data consisting of color data of all pixel points corresponding to the target glass sheet; and temperature point cloud data consisting of temperature data and position data of all pixel points corresponding to the target glass sheet; determining an area value of the crack center of the target glass plate based on the color point cloud data, and determining shape information of the crack of the target glass plate based on the temperature point cloud data; determining a target early warning level based on the area value of the crack center and / or the shape information of the crack, and issuing an early warning according to an early warning method corresponding to the target early warning level.

[0007] Optionally, the step of determining an area value of a crack center of the target glass sheet based on the color point cloud data includes: determining the number of designated color data, which are preset RGB color values, in the color point cloud data; and determining the number of the designated color data as an area value of the crack center.

[0008] Optionally, the step of determining shape information of cracks in the target glass sheet based on the temperature point cloud data includes: determining the number and position data of designated temperature data in the temperature point cloud data; The method includes a step of determining an area value of the crack based on the number of the designated temperature data, and determining shape type information of the crack and position information of the crack based on the position data of the designated temperature data.

[0009] Optionally, the step of determining a target early warning level based on the area value of the crack center and / or the shape information of the crack includes: generating a first early warning level when the area value of the crack reaches a first preset area threshold or the area value of the crack center reaches a second preset area threshold; generating a second early warning level when the area value of the crack is between a first preset area threshold and a third preset area threshold, or the area value of the crack center is between a second preset area threshold and a fourth preset area threshold, wherein the third preset area threshold is greater than the first preset area threshold, the fourth preset area threshold is greater than the second preset area threshold, and the second early warning level is greater than the first early warning level; generating a third early warning level when the area value of the crack reaches a third preset area threshold or the area value of the crack center reaches a fourth preset area threshold, the third early warning level being higher than the second early warning level, and the first preset area threshold, the second preset area threshold, the third preset area threshold and the fourth preset area threshold are all determined based on shape type information of the crack.

[0010] Optionally, the early warning manner corresponding to the first early warning level includes a first display manner, the early warning manner corresponding to the second early warning level includes a second display manner, and the early warning manner corresponding to the third early warning level includes a third display manner and a message sending manner; In this case, the step of issuing an early warning according to an early warning method corresponding to the target early warning level includes: displaying the crack position information according to the first display method; displaying the crack position information according to the second display method; and a step of displaying the crack position information according to the third display method and transmitting the crack position information to a terminal, wherein an output font color provided in the first display method, an output font color provided in the second display method, and an output font color provided in the third display method are different from each other.

[0011] Optionally, after determining an area value of the crack center of the target glass sheet based on the color point cloud data and determining shape information of the crack of the target glass sheet based on the temperature point cloud data, the method further comprises: Comparing the area values ​​of the crack center at different time nodes to obtain a first comparison result, and comparing the shape information of the crack at different time nodes to obtain a second comparison result; The method further includes a step of obtaining crack movement information based on the first comparison result and / or the second comparison result.

[0012] Optionally, the photovoltaic assembly includes a photovoltaic panel that is a double-glazed double-faced assembly, the double-glazed double-faced assembly including, in order from top to bottom, a first glass sheet, a first adhesive layer, a silicon crystal plate, a second adhesive layer, and a second glass sheet; The target glass sheet is the first glass sheet and / or the second glass sheet.

[0013] According to a second aspect of the present application, there is provided an early warning device for a glass plate crack in a photovoltaic assembly, the early warning device for a glass plate crack in a photovoltaic assembly comprising: an acquisition module for acquiring target point cloud data obtained by a target scanner scanning a target glass sheet, the target glass sheet being a glass sheet located on a surface of a photovoltaic assembly, the target point cloud data including: color point cloud data consisting of color data of all pixel points corresponding to the target glass sheet; and temperature point cloud data consisting of temperature data and position data of all pixel points corresponding to the target glass sheet; a determination module for determining an area value of the crack center of the target glass sheet based on the color point cloud data, and determining shape information of the crack of the target glass sheet based on the temperature point cloud data; and an early warning module for determining a target early warning level based on the area value of the crack center and / or the shape information of the crack, and issuing an early warning according to an early warning method corresponding to the target early warning level.

[0014] According to a third aspect of the present application, there is provided an electronic device, the electronic device including at least one processor and a memory; the memory stores computer-executable instructions; The at least one processor executes computer executable instructions stored in the memory, causing the at least one processor to perform the glass sheet crack early warning method for a photovoltaic assembly described in the first aspect above.

[0015] According to a fourth aspect of the present application, there is provided a computer-readable storage medium having computer-executable instructions stored thereon, the computer-executable instructions being used to implement the glass sheet crack early warning method for a photovoltaic assembly according to the first aspect above, when executed by a processor.

[0016] According to a fifth aspect of the present application, there is provided a computer program product, the computer program product including a computer program that, when executed by a processor, realizes the glass plate crack early warning method for a photovoltaic assembly according to the first aspect.

[0017] Method, device, electronic device and medium for early warning of glass plate cracks in photovoltaic assemblies according to the present application According to the method for early warning of cracks in glass sheets of a photovoltaic assembly, the method includes the steps of: acquiring target point cloud data obtained by a target scanner scanning a target glass plate, the target glass plate being a glass plate located on the surface of a photovoltaic assembly, the target point cloud data including color point cloud data composed of color data of all pixel points corresponding to the target glass plate; and temperature point cloud data composed of temperature data and position data of all pixel points corresponding to the target glass plate; determining an area value of a crack center of the target glass plate based on the color point cloud data, and determining shape information of the crack of the target glass plate based on the temperature point cloud data; and determining a target early warning level based on the area value of the crack center and / or the crack shape information, and issuing an early warning according to an early warning method corresponding to the target early warning level.

[0018] The color point cloud data and temperature point cloud data in the above method are both highly accurate and high resolution, and can completely restore and reproduce the size, shape type, and shape size of cracks in glass sheets of photovoltaic assemblies in real scenes. Based on this, the present application determines the area value of the crack center of the target glass sheet using color point cloud data and determines the shape information of the crack in the target glass sheet using temperature point cloud data, thereby realizing the extraction of various information about the crack, accurately and quickly realizing early warning level classification of the crack, and further ensuring the safety of the photovoltaic assembly.

[0019] It should be understood that the contents described in this section are not intended to identify key or important features of the embodiments of the present application, and are not intended to limit the scope of the present application. Other features of the present application will be readily apparent from the following description. [Brief explanation of the drawings]

[0020] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the specification, serve to explain the principles of the present application. [Figure 1] 1 is a flowchart of a glass plate crack early warning method for a photovoltaic assembly provided in an embodiment of the present application. [Figure 2] 1 is a schematic diagram illustrating the operation of a target scanner provided in an embodiment of the present application. [Figure 3] 1 is a flowchart of another glass sheet crack early warning method for a photovoltaic assembly provided in an embodiment of the present application. [Figure 4] 1 is a structural schematic diagram of a glass plate crack early warning device of a photovoltaic assembly provided in an embodiment of the present application; FIG. [Figure 5]

[0023] Figure 1 is a structural schematic diagram of an electronic device provided in an embodiment of the present application. The above attached drawings illustrate clear embodiments of the present application, which will be described in more detail below. These attached drawings and written descriptions are not intended to limit the scope of the concept of the present application in any manner, but to explain the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION OF THE INVENTION

[0021] Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different accompanying drawings refer to the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application.

[0022] Most conventional glass plate crack early warning methods use manual methods, specifically, on-site personnel inspect, record, and report whether there are cracks in the glass plate of each photovoltaic assembly. This method takes into account personnel subjectivity and the fact that different personnel may describe and classify the same crack, which may result in various discrepancies. Furthermore, when cracks occur simultaneously in the glass plate of different photovoltaic assemblies, some of the cracks may not be detected in a timely manner.

[0023] Due to the poor promptness of early warning in the prior art, if the photovoltaic assembly continues to operate when the glass plate crack is serious, there is a technical problem that it is prone to fire and is unsafe.

[0024] To solve the above technical problems, the overall inventive concept of the present application is to provide a method for use in the photovoltaic assembly field to improve the safety of the photovoltaic assembly.

[0025] The following specific embodiments will be used to describe in detail the technical solution of the present application and how the technical solution of the present application solves the above technical problems. Some specific embodiments below may be combined with each other, and the same or similar concepts or processes may not be further described in some embodiments. The following describes the embodiments of the present application in conjunction with the accompanying drawings.

[0026] Example 1: 1 is a flow chart of a method for early warning of cracks in a glass plate of a photovoltaic assembly provided in an embodiment of the present application. As shown in FIG. 1, the method of this embodiment includes the following steps S10 to S30.

[0027] In S10, a target scanner scans a target glass sheet to obtain target point cloud data, where the target glass sheet is a glass sheet located on the surface of the photovoltaic assembly, and the target point cloud data includes color point cloud data composed of color data of all pixel points corresponding to the target glass sheet, and temperature point cloud data composed of temperature data and position data of all pixel points corresponding to the target glass sheet. The temperature point cloud data is also called position point cloud data.

[0028] It should be understood that the target point cloud data may be understood as crack feature point cloud data, and the photovoltaic assembly may be a photovoltaic assembly located at a target observation point within an area where the photovoltaic station is located. Since the photovoltaic assembly may be composed of a helical pile, a photovoltaic panel, and a photovoltaic bracket, the surface of the photovoltaic assembly may be a device on the surface of the photovoltaic panel. The area where the photovoltaic station is located is also called a photovoltaic area.

[0029] 2, the target scanner 100 is a three-dimensional laser scanner, also called a monitor. The terminal device 200 connected to the target scanner 100 may be a device such as a computer for acquiring target point cloud data and storing and analyzing the data. A power source 300 is used to supply power to the terminal device 200, and the terminal device 200 functions as a power source to supply power to the target scanner 100.

[0030] Optionally, the target scanner 100 includes at least one of an RGB device (also called an RGB camera, color camera), an infrared transmitter, and a 3D depth sensor, wherein the 3D depth sensor is composed of three lenses (i.e., infrared lenses) of an infrared camera.

[0031] For example, in a photovoltaic panel, crystalline silicon cells in a silicon layer are attached to a glass plate, the thickness of the glass plate is generally a value between 3.2 mm and 8 mm, the thickness of the crystalline silicon cells may be a value between 1.5 μm and 2.0 μm, the glass plate may be a transparent material, an infrared camera can illuminate the silicon layer through the glass plate, and a monitor modulates the RGB pixels of the monitor to A×B and the infrared pixels to C×D, with a detectable range of 0.5 to 5 m, although the specific values ​​of A, B, C, and D are not specifically limited in the embodiment of the present application. In this embodiment, the side of the monitor illuminates the photovoltaic panel, so that not only can the lateral development (e.g., width, length, etc.) of a crack on the surface of the glass plate (i.e., the cross section) be measured, but also the vertical development (e.g., depth, etc.) of the crack on the side of the glass plate can be measured.

[0032] In this method, the hardware design of this embodiment mainly includes devices such as a photovoltaic assembly, a 3D laser scanner, and a computer, among which computer processing software is executed on the computer, which may be open source software (such as Visual Studio software), which calls the OpenCV library (or other libraries, the embodiment of this application is not specifically limited thereto) to set scanning parameters and collect crack feature point cloud data at designated observation points, and then sends the collected crack feature point cloud data to third-party software for analysis to analyze various crack feature data (such as crack size, crack shape type, length of each texture in the crack, depth of each texture in the crack, length of each texture in the crack at a certain time in the future, depth of each texture in the crack at a certain time in the future, etc.), the corresponding early warning level of the crack, and the corresponding processing method, thereby improving the accuracy and comprehensiveness of the analysis.

[0033] Furthermore, the present application further improves the accuracy of early crack warnings by configuring computer visualization software to display only point cloud data with crack shape characteristics and white point cloud data, and further improves the accuracy of early crack warnings by using third-party software to classify risk levels and quickly observe point cloud data.

[0034] In S20, the area value of the crack center of the target plate glass is determined based on the color point cloud data, and the shape information of the crack of the target plate glass is determined based on the temperature point cloud data.

[0035] It should be understood that both the area value of the crack center and the shape information of the crack can indicate the crack characteristics.

[0036] In S30, a target early warning level is determined based on the area value of the crack center and / or the shape information of the crack, and an early warning is issued according to an early warning method corresponding to the target early warning level.

[0037] The number of target early warning levels is not specifically limited in the embodiment of the present application, and may be two, three, four, etc.

[0038] The color point cloud data and temperature point cloud data in the above method are both highly accurate and high resolution, which can completely restore and reproduce the size, shape type, and shape size of cracks in glass sheets of photovoltaic assemblies in real scenes. Based on this, the embodiment of the present application determines the area value of the crack center of the target glass sheet using color point cloud data and determines the shape information of the crack in the target glass sheet using temperature point cloud data, thereby realizing the extraction of various information about the crack, accurately and quickly realizing early warning level classification of the crack, and further ensuring the safety of the photovoltaic assembly.

[0039] In a possible implementation, in step S20, determining the area value of the crack center of the target glass sheet based on the color point cloud data includes the following steps S201 to S202.

[0040] In S201, the number of designated color data, which are preset RGB color values, in the color point cloud data is determined.

[0041] In the present embodiment, the specified color data is white, and may refer to the RGB color value (255, 225, 255), or may refer to other color values ​​close to this color value, and the present embodiment does not specifically limit the range of values ​​that this color value can take or the magnitude of the color value.

[0042] In S202, the number of designated color data is determined as the area value of the crack center.

[0043] It should be understood that the number of designated color data refers to the number of pixels having the designated color data. The present application does not specifically limit the conversion method for converting the number of pixels into an area value. When a crack occurs due to a collision of a glass plate, the center of the crack is called the collision center.

[0044] The embodiment of the present application can provide data support for accurately recognizing the area value of the crack center through the number of specified color data, and then accurately determining the early warning level corresponding to the crack.

[0045] In a possible implementation, in step S20, determining the shape information of the crack in the target glass plate based on the temperature point cloud data includes the following steps S203 and S204.

[0046] In S203, the number of designated temperature data and position data in the temperature point cloud data are determined.

[0047] In S204, the area value of the crack is determined based on the number of designated temperature data, and the shape type information of the crack and the position information of the crack are determined based on the position data of the designated temperature data.

[0048] In the embodiment of the present application, the crack shape information includes a crack area value, crack shape type information, crack position information, etc. The crack shape type information includes bull's-eye type, star-shaped type, long crack type, comprehensive type, etc. Here, a bull's-eye type crack is mainly caused by a pebble hitting the glass plate, a star-shaped crack is mainly caused by a collision with an external object, a long crack type crack is mainly caused by spontaneous occurrence due to the influence of the material and environment, and a comprehensive type crack is mainly formed by the crack continuing to develop in a later stage after the glass plate is hit.

[0049] The point cloud data collected by third-party software was analyzed, and an infrared camera and a color camera were combined to set all of the above four types of shapes as point cloud recognition targets. The color value of the color was white (255, 225, 255). When the infrared camera illuminated the crack in the plate glass, the light was refracted, resulting in a large amount of point cloud data on the cross section. Therefore, the crack was recognized by the infrared camera, and the impact center was recognized by the color camera.

[0050] The embodiments of the present application can obtain information such as crack area value, crack shape type information, and crack location information by analyzing temperature point cloud data, and can provide data support for later accurately determining the early warning level corresponding to the crack.

[0051] In a possible implementation, in step S30, determining a target early warning level based on the area value of the crack center and / or the shape information of the crack includes at least one of the following:

[0052] In the first term, when the area value of the crack reaches a first preset area threshold or the area value of the crack center reaches a second preset area threshold, a first early warning level is generated.

[0053] In the present embodiment, the area value of the crack may be understood as the crack point cloud data, and the area value of the crack center may be understood as the white point cloud data. The first preset area threshold is the N value, and the second preset area threshold is the Q value. The first early warning level is also called the Level 1 early warning level.

[0054] In the second term, if the area value of the crack is between the first and third preset area thresholds, or if the area value of the crack center is between the second and fourth preset area thresholds, a second early warning level is generated. Here, the third preset area threshold is greater than the first preset area threshold, the fourth preset area threshold is greater than the second preset area threshold, and the second early warning level is higher than the first early warning level. The third preset area threshold is the M value, and the fourth preset area threshold is the K value. The second early warning level is also referred to as a Level 2 early warning level. Here, the N / M value is not related to the Q / K value.

[0055] In the third term, when the area value of the crack reaches a third preset area threshold or the area value of the crack center reaches a fourth preset area threshold, a third early warning level is generated, where the third early warning level is higher than the second early warning level, and the third early warning level is also referred to as a level 3 early warning level.

[0056] For example, when the total number of crack point cloud data reaches the N value or the white color value reaches the Q value (Q value is 1cm), 2When the total number of crack point cloud data reaches a range consisting of N to M values ​​and the white color value reaches a range consisting of Q to K values, it indicates that the glass plate is broken and the adhesive layer (also called adhesive sheet) connecting the glass plate is also broken, and a blue early warning is sent, and this embodiment may promptly replace damaged devices in the photovoltaic panel in the photovoltaic assembly in a later stage. When the total number of crack point cloud data reaches the M value and the area consisting of the white color value reaches the K value (this K value > 1 cm 2 ), it indicates that the glass plate of the photovoltaic assembly is severely damaged and the silicon layer is damaged, which means that a fire is likely to occur, and a red early warning is sent. For safety reasons, this embodiment can turn off the power, perform fire extinguishing procedures, and use the smart device to promptly replace the photovoltaic panel.

[0057] In this embodiment, the visualization software is preset to display only crack point cloud data and white point cloud data, and four types of crack development shapes can be preset in the third-party software, which can effectively recognize actual plate glass cracks in the photovoltaic assembly, compare the real-time observed data with the preset threshold values ​​for generating early warning signals (e.g., N, M, Q, K values, etc.), obtain the comparison results, and then determine the specific level of the early warning level based on the comparison results.

[0058] The first preset area threshold, the second preset area threshold, the third preset area threshold and the fourth preset area threshold are all determined based on the shape type information of the crack.

[0059] For example, the predetermined area thresholds corresponding to the bull's eye type are N1 value, Q1 value, M1 value, and K1 value, respectively; the predetermined area thresholds corresponding to the star type are N2 value, Q2 value, M2 value, and K2 value, respectively; the predetermined area thresholds corresponding to the long crack type are N3 value, Q3 value, M3 value, and K3 value, respectively; and the predetermined area thresholds corresponding to the comprehensive type are N4 value, Q4 value, M4 value, and K4 value, respectively.

[0060] In the present embodiment, the first early warning level is used to indicate that the glass pane is broken but the adhesive layer is not broken, the second early warning level is used to indicate that the adhesive layer is broken, and the third early warning level is used to indicate that the silicon layer is broken.

[0061] In the embodiment of the present application, by setting different early warning levels, it is possible to quickly recognize the destruction situation caused by the glass plate crack, and further provide a tailored processing method, which ultimately improves the safety of the safety assembly.

[0062] In a possible implementation, the early warning method corresponding to the first early warning level includes a first display method, the early warning method corresponding to the second early warning level includes a second display method, and the early warning method corresponding to the third early warning level includes a third display method and a message sending method; In this case, in step S30, the step of issuing an early warning according to an early warning method corresponding to the target early warning level includes: In the first paragraph, a step of displaying crack position information according to a first display method; In the second paragraph, a step of displaying crack position information according to a second display method; In the third paragraph, the method includes at least one of the steps of: displaying crack location information according to a third display method and transmitting the crack location information to a terminal, wherein the output font color provided in the first display method, the output font color provided in the second display method, and the output font color provided in the third display method are different from each other.

[0063] Specifically, in this embodiment, the early warning levels are preset to include a level 1 early warning level, a level 2 early warning level, and a level 3 early warning level. The level 1 early warning level corresponds to a yellow early warning, the level 2 early warning level corresponds to a blue early warning, and the level 3 early warning level corresponds to a red early warning. The different color early warning methods may include setting a font color for the crack location information, setting a background color for an icon corresponding to the photovoltaic assembly, or setting a light color for an indicator lamp corresponding to the photovoltaic assembly.

[0064] For example, if the number of crack point cloud data reaches the value N or the number of white point cloud data reaches the value Q, a yellow early warning signal is issued; if the number of crack point cloud data is between the values ​​N and M or the number of white point cloud data is between the values ​​Q and K, a blue early warning signal is issued; and if the number of crack point cloud data reaches the value M and the number of white point cloud data reaches the value K, a red early warning signal is issued.

[0065] For example, if the number of crack point cloud data is within the N value, it indicates that the plate glass is damaged, and the early warning level corresponding to the plate glass is level 1 early warning; if the number of crack point cloud data is between N and M, it indicates that the plate glass and adhesive sheet are damaged, and the early warning level corresponding to the plate glass is level 2 early warning; if the number of crack point cloud data reaches the M value, it indicates that the silicone sheet is destroyed, and the early warning level corresponding to the plate glass is level 3 early warning.

[0066] In the process of a computer monitoring glass plate cracks of multiple photovoltaic assemblies and providing early warnings for different cracks, this embodiment can display all early warnings for all cracks using a scroll bar, and can simultaneously display multiple cracks by strobe-illuminating icons corresponding to each photovoltaic assembly on one interface. The embodiment of the present application can be customized according to actual situations, and the embodiment of the present application is not specifically limited thereto.

[0067] Before transmitting the crack location information to the terminal, the embodiment of the present application can bind information such as the name and location of the photovoltaic assembly with the corresponding mobile phone number of the maintenance personnel to obtain a correspondence table, and the mobile phone number of the maintenance personnel can be queried through the correspondence table. Furthermore, when the glass plate crack of the photovoltaic assembly reaches level 3 early warning, the computer can automatically send a short message to the corresponding mobile phone number through software. The content of the short message may include the location information of the photovoltaic assembly, various information and images of the glass plate crack of the photovoltaic assembly, etc. The embodiment of the present application does not specifically limit the content of the short message.

[0068] The embodiments of the present application can quickly and accurately determine the early warning level corresponding to the crack according to different early warning signals, and further provide corresponding solutions, thereby ensuring the safety of the photovoltaic assembly, avoiding the security risk caused by the photovoltaic assembly continuing to operate when the safety is very poor, and effectively maintaining the photovoltaic power plant in a long-term stable operating state after the maintenance personnel resolve the security risk.

[0069] In a possible implementation, after determining the area value of the crack center of the target glass sheet based on the color point cloud data and determining the shape information of the crack of the target glass sheet based on the temperature point cloud data, the method further includes the following steps S40 and S50.

[0070] In S40, the area values ​​of the crack centers at different time nodes are compared to obtain a first comparison result, and the shape information of the cracks at different time nodes is compared to obtain a second comparison result.

[0071] In S50, based on the first comparison result and / or the second comparison result, crack movement information is obtained.

[0072] In the present embodiment, the crack movement information may refer to a change in crack length, a change in crack depth, etc. Since the crack includes multiple textures, the change in crack length may include a change in texture length, and the change in crack depth may refer to a change in texture depth. This crack movement information is used to predict a future time when the glass sheet of the photovoltaic assembly will burst, and to replace the glass sheet of the photovoltaic assembly by a further future time.

[0073] The present application provides an early warning method for cracks in glass sheets of photovoltaic assemblies, which studies a method for quantifying whether early warnings for cracks occur when glass sheets of photovoltaic assemblies are affected by bad weather and glass materials. This method is economical, convenient, and efficient, and can greatly improve the measurement efficiency and accuracy of predicting the cracking of glass sheets of photovoltaic assemblies, effectively avoiding the occurrence of fire accidents in photovoltaic fields, and providing technical support for future early warning methods for further monitoring the cracking of glass sheets of photovoltaic assemblies.

[0074] In a possible implementation, the photovoltaic assembly includes a photovoltaic panel, which is a double-glazed double-sided assembly, which includes, in order from top to bottom, a first glass sheet, a first adhesive layer, a silicon crystal plate, a second adhesive layer, and a second glass sheet, and the target glass sheet is the first glass sheet and / or the second glass sheet.

[0075] It is to be understood that the double-pane double-faced assembly is a monocrystalline silicon P-type double-pane double-pane, which includes a first glass sheet, the bottom of which is fixedly connected to the top of a first adhesive layer, the bottom of which is fixedly connected to the top of a silicon crystal plate, the bottom of which is fixedly connected to the top of a second adhesive layer, and the bottom of which is fixedly connected to the top of a second glass sheet.

[0076] The photovoltaic area may be made of monocrystalline silicon P-type double-sided double-pane glass. The assembly has a five-layer structure, with the two outer layers being glass sheets, the two inner layers being adhesive sheets, and the middle layer being a silicon sheet. Since breakage of the glass sheets can easily cause cross-sectional breakage and lead to breakage in depth, the thickness of the glass sheets is set to 3mm to 8mm. If the monitor detects that there is a crack point cloud data in the adhesive sheet area, it will immediately issue a red early warning. As can be seen from the above, the embodiment of the present application can effectively recognize cracks in depth.

[0077] The embodiment of the present application provides a method for early warning of cracks in a glass plate of a photovoltaic assembly, which uses a 3D laser scanner to set the shape parameters of the cracks in the glass plate of the photovoltaic assembly through a computer program, collects point cloud data of cracks on the surface of the glass plate of the photovoltaic assembly and point cloud data of cracks in the thickness of the glass plate of the photovoltaic assembly, transmits the data to third-party software, and classifies the cracks into danger levels based on the point cloud data reflected in the crack size set in the program. If a crack develops and causes a local hot spot in the photovoltaic assembly, the third-party software immediately issues a red early warning signal on the page, and also sets a message sending mechanism in the third-party software to send an early warning short message to the mobile phone number of a shift staff member. This method requires simple hardware structure and is easy to use. It can accurately measure the development and change trends of cracks in the glass plate of the photovoltaic assembly, predict the time of a fire, and even allow the photovoltaic assembly to be replaced before the time comes, effectively avoiding the outbreak of a fire and improving the safety of the photovoltaic assembly.

[0078] Based on the above embodiments, the technical solution of the present application will be described in more detail below in conjunction with some specific embodiments.

[0079] 3 is a flowchart of another glass plate crack early warning method for a photovoltaic assembly provided in an embodiment of the present application. As shown in FIG. 3, the method of this embodiment includes the following steps S31 to S36.

[0080] In S31, the device is debugged.

[0081] In S32, the photovoltaic assembly is monitored.

[0082] In S33, the monitoring data is saved.

[0083] At S34, the monitoring data is analyzed by the third party client / mobile phone side.

[0084] In S35, a risk coefficient level classification process is executed.

[0085] At S36, an early warning signal is sent.

[0086] As can be seen from the description of steps S31 to S36, the operating process of this embodiment is as follows: first, the scanner and the computer are debugged; when powered on, the program is executed by calling the OpenCV library in open source software (e.g., Visual Studio software); based on the size of the photovoltaic panel in the photovoltaic assembly, the scanning range (x, y, z) is set by the computer program; the scanner is started, and the point cloud data collection and storage operations are controlled; after the data is acquired, a risk level classification analysis is performed using third-party software, and the data is displayed in real time on the third-party software; that is, when the crack area value reaches a certain early warning level threshold and / or the crack center area value reaches a certain early warning level threshold, the software automatically issues an early warning signal corresponding to this early warning level.

[0087] In order to improve the validity of the data, in the embodiment of the present application, the point cloud data obtained by the monitor can be pre-processed by third-party software (this pre-processing includes filtering noise reduction processing to remove irrelevant noise from the point cloud data). After the pre-processing is completed, the surface and depth of the glass plate are observed, and the early warning level corresponding to the crack is determined from the surface observation of the glass plate, and the crack depth development status and specific damage device are determined from the depth observation.

[0088] The embodiment of the present application provides the following two extensions. First, this method has the advantage of providing early warning to prevent fires caused by cracks in the plate glass of the photovoltaic assembly. The imaging data is more accurate, and in order to expand the scanning range, this embodiment can set multiple observation points, and use multiple scanners to observe a specified location at multiple observation points, achieving the effect of constructing a surface from points, and further enabling real-time monitoring of the photovoltaic area, which can achieve early detection of cracks, focused observation, and the effect of fire prevention.

[0089] Second, this embodiment further uses a drone control method to realize 3D laser scanning with a wider scanning range. The scanning method controls low-altitude flight of the drone to store the point cloud data of the cracks in the glass plate of the photovoltaic assembly, and the collected data can be collectively processed and controlled by a single computer, achieving economical, convenient, and efficient results.

[0090] In the above method flow, a monitor that integrates infrared, color, and depth cameras is used to obtain three-dimensional point cloud data of the crack shape using the infrared and depth cameras, and color attributes are added to the point cloud data using a color lens. Therefore, in this embodiment, a group of spatial three-dimensional color point cloud data that is the same as the actual crack can be obtained on the monitor.

[0091] Example 3: 4 is a structural schematic diagram of a glass plate crack early warning device for a photovoltaic assembly provided in an embodiment of the present application. The device in this embodiment may be in the form of software and / or hardware. As shown in FIG. 4, the glass plate crack early warning device for a photovoltaic assembly provided in this embodiment includes an acquisition module 41, a determination module 42, and an early warning module 43, among which: The acquisition module 41 is used to acquire target point cloud data obtained by the target scanner scanning the target glass sheet, where the target glass sheet is a glass sheet located on the surface of the photovoltaic assembly, and the target point cloud data includes color point cloud data composed of color data of all pixel points corresponding to the target glass sheet, and temperature point cloud data composed of temperature data and position data of all pixel points corresponding to the target glass sheet.

[0092] The determination module 42 is used to determine the area value of the crack center of the target glass sheet based on the color point cloud data, and to determine the shape information of the crack of the target glass sheet based on the temperature point cloud data.

[0093] The early warning module 43 is used to determine a target early warning level based on the area value of the crack center and / or the shape information of the crack, and issue an early warning according to an early warning method corresponding to the target early warning level.

[0094] In a possible implementation, the decision module 42 further comprises: determining the number of designated color data, which are preset RGB color values, in the color point cloud data; The number of designated color data is used to determine the area value of the crack center.

[0095] In a possible implementation, the decision module 42 further comprises: Determine the number of designated temperature data and position data in the temperature point cloud data; It is used to determine the area value of the crack based on the number of specified temperature data, and to determine the shape type information of the crack and the position information of the crack based on the position data of the specified temperature data.

[0096] In a possible implementation, the early warning module 43 further comprises: generating a first early warning level when the area value of the crack reaches a first preset area threshold or the area value of the crack center reaches a second preset area threshold; generating a second early warning level when the area value of the crack is between the first preset area threshold and the third preset area threshold, or the area value of the crack center is between the second preset area threshold and the fourth preset area threshold, where the third preset area threshold is greater than the first preset area threshold, the fourth preset area threshold is greater than the second preset area threshold, and the second early warning level is higher than the first early warning level; When the area value of the crack reaches a third preset area threshold, or the area value of the crack center reaches a fourth preset area threshold, a third early warning level is generated, where the third early warning level is higher than the second early warning level, and the first preset area threshold, the second preset area threshold, the third preset area threshold and the fourth preset area threshold are all determined based on the shape type information of the crack.

[0097] In a possible implementation, the early warning manner corresponding to the first early warning level includes a first display manner, the early warning manner corresponding to the second early warning level includes a second display manner, and the early warning manner corresponding to the third early warning level includes a third display manner and a message sending manner. Displaying crack location information according to the first display method; Display crack location information according to the second display method, It is used to display crack location information according to a third display method and transmit the crack location information to a terminal, where the output font color provided in the first display method, the output font color provided in the second display method, and the output font color provided in the third display method are different from each other.

[0098] In a possible implementation, after determining the area value of the crack center of the target glass sheet based on the color point cloud data and determining the shape information of the crack of the target glass sheet based on the temperature point cloud data, the glass sheet crack early warning device of the photovoltaic assembly further comprises: Compare the area values ​​of the crack center at different time nodes to obtain a first comparison result; compare the shape information of the crack at different time nodes to obtain a second comparison result; The first comparison result and / or the second comparison result are used to obtain crack movement information.

[0099] In a possible implementation, the photovoltaic assembly includes a photovoltaic panel, which is a double-glazed double-sided assembly, which includes, in order from top to bottom, a first glass sheet, a first adhesive layer, a silicon crystal plate, a second adhesive layer, and a second glass sheet, and the target glass sheet is the first glass sheet and / or the second glass sheet.

[0100] The photovoltaic assembly glass plate crack early warning device provided in this embodiment can be used to implement the photovoltaic assembly glass plate crack early warning method provided in any of the above method embodiments, and the realization principles and technical effects are similar, so they will not be further described here.

[0101] Furthermore, all user information and data related to this application (including, but not limited to, data for analysis, data for storage, data for display, etc.) are information and data authorized by the user or fully authorized by each party, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and a corresponding operating interface will be provided for the user to select whether to allow or deny.

[0102] In other words, in the technical solution of this application, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved all comply with the provisions of relevant laws and regulations and do not violate public order and morals.

[0103] According to an embodiment of the present application, the present application further provides an electronic device and a readable storage medium.

[0104] 5 is a structural schematic diagram of an electronic device provided in an embodiment of the present application, which includes a receiver 50, a transmitter 51, at least one processor 52, and a memory 53. The electronic device configured by the above components is used to implement the above several specific embodiments of the present application, and will not be further described here.

[0105] An embodiment of the present application further provides a computer-readable storage medium, which stores computer-executable instructions, and when a processor executes the computer-executable instructions, realizes each step of the method of the above embodiment.

[0106] An embodiment of the present application further provides a computer program product including a computer program, which, when executed by a processor, implements each step in the method of the above embodiment.

[0107] Various embodiments of the systems and techniques described herein may be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard parts (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include being embodied in one or more computer programs that can be executed and / or interpreted by a programmable system including at least one programmable processor, which may be a special purpose or general purpose programmable processor, and that can receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0108] The program code for implementing the methods of the present application may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, so that when the program code is executed by the processor or controller, the functions / operations defined in the flowcharts and / or block diagrams are performed. The program code may be executed entirely on the device, partially on the device, partially on the device as a separate software package and partially on a remote device, or entirely on a remote or electronic device.

[0109] In the context of this application, a computer-readable storage medium may be a tangible medium that may be used by or contain or store a program for use in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may be a machine-readable signal medium or a machine-readable storage medium. A computer-readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a suitable combination of any of the above. More specific examples of computer-readable storage media include one or more cable-based electrical connections, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or a suitable combination of any of the above.

[0110] To provide for interaction with a user, the systems and techniques described herein can be implemented on a computer having a display device (e.g., a cathode ray tube (CRT) or liquid crystal display (LCD) monitor) for displaying information to a user, and a keyboard and pointing device (e.g., a mouse or trackball) through which a user can provide input to the computer. Other types of devices can also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback) and can receive input from the user in any form (including voice input, audio input, or tactile input).

[0111] The systems and techniques described herein may be implemented in a computing system that includes background components (e.g., as data electronics), or middleware components (e.g., application electronics), or front-end components (e.g., a user computer having a graphical user interface or network browser through which a user can interact with embodiments of the systems and techniques described herein), or any combination of such background, middleware, or front-end components. The components of the system may be connected to one another by any form or medium of digital data communication (e.g., a communications network). Examples of communications networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0112] It should be understood that various types of flows shown above can be rearranged, and steps can be added or deleted. For example, the steps described in the present disclosure can be performed in parallel, sequentially, or in different orders, as long as the desired results of the technical solution disclosed in the present disclosure can be achieved, and this specification does not limit this.

[0113] The above specific embodiments do not constitute limitations on the scope of protection of the present application. Those skilled in the art will understand that various modifications, combinations, sub-combinations, and substitutions can be made based on design requirements and other factors. Any modifications, equivalent substitutions, improvements, etc. made based on the principles of the present application should all be included in the scope of protection of the present application.

[0114] This application claims priority to a Chinese patent application filed with the China Patent Office on September 19, 2023, bearing application number 202311212913.5 and entitled "Method, device, electronic device and medium for early warning of glass plate cracks in photovoltaic assemblies," the entire contents of which are incorporated herein by reference.

Claims

1. 1. A glass plate crack early warning method for a photovoltaic assembly, comprising: acquiring target point cloud data obtained by scanning a target glass sheet with a target scanner, the target glass sheet being a glass sheet located on a surface of a photovoltaic assembly, the target point cloud data including: color point cloud data consisting of color data of all pixel points corresponding to the target glass sheet; and temperature point cloud data consisting of temperature data and position data of all pixel points corresponding to the target glass sheet; determining an area value of the crack center of the target glass plate based on the color point cloud data, and determining shape information of the crack of the target glass plate based on the temperature point cloud data; determining a target early warning level based on the area value of the crack center and / or the shape information of the crack, and issuing an early warning according to an early warning method corresponding to the target early warning level; 10. An early warning method for glass plate cracks in a photovoltaic assembly, comprising:

2. The step of determining an area value of the crack center of the target glass plate based on the color point cloud data includes: determining the number of designated color data, which are preset RGB color values, in the color point cloud data; determining the number of the designated color data as an area value of the crack center, 2. The glass plate crack early warning method for a photovoltaic assembly according to claim 1.

3. The step of determining shape information of a crack in the target glass plate based on the temperature point cloud data includes: determining the number and position data of designated temperature data in the temperature point cloud data; determining an area value of the crack based on the number of the designated temperature data, and determining shape type information of the crack and position information of the crack based on position data of the designated temperature data; 2. The glass plate crack early warning method for a photovoltaic assembly according to claim 1.

4. The step of determining a target early warning level based on the area value of the crack center and / or the shape information of the crack includes: generating a first early warning level when the area value of a crack reaches a first preset area threshold or the area value of the crack center reaches a second preset area threshold; generating a second early warning level when the area value of a crack is between a first predetermined area threshold and a third predetermined area threshold, or the area value of the crack center is between a second predetermined area threshold and a fourth predetermined area threshold, wherein the third predetermined area threshold is greater than the first predetermined area threshold, the fourth predetermined area threshold is greater than the second predetermined area threshold, and the second early warning level is greater than the first early warning level; generating a third early warning level when the area value of a crack reaches a third preset area threshold or the area value of the crack center reaches a fourth preset area threshold, the third early warning level being higher than the second early warning level, and the first preset area threshold, the second preset area threshold, the third preset area threshold and the fourth preset area threshold are all determined based on shape type information of the crack.

2. The glass plate crack early warning method for a photovoltaic assembly according to claim 1.

5. The early warning manner corresponding to the first early warning level includes a first display manner, the early warning manner corresponding to the second early warning level includes a second display manner, and the early warning manner corresponding to the third early warning level includes a third display manner and a message sending manner; In this case, the step of issuing an early warning according to an early warning method corresponding to the target early warning level includes: displaying the crack position information according to the first display method; displaying the crack position information according to the second display method; a step of displaying the crack position information according to the third display method and transmitting the crack position information to a terminal, wherein an output font color provided in the first display method, an output font color provided in the second display method, and an output font color provided in the third display method are different from each other; 2. The glass plate crack early warning method for a photovoltaic assembly according to claim 1.

6. After determining the area value of the crack center of the target glass sheet based on the color point cloud data and determining the shape information of the crack of the target glass sheet based on the temperature point cloud data, the glass sheet crack early warning method for the photovoltaic assembly includes: Comparing the area values ​​of the crack center at different time nodes to obtain a first comparison result, and comparing the shape information of the crack at different time nodes to obtain a second comparison result; and obtaining crack movement information based on the first comparison result and / or the second comparison result.

2. The glass plate crack early warning method for a photovoltaic assembly according to claim 1.

7. The photovoltaic assembly includes a photovoltaic panel that is a double-glazed, double-faced assembly, the double-glazed, double-faced assembly including, in order from top to bottom, a first glass sheet, a first adhesive layer, a silicon crystal plate, a second adhesive layer, and a second glass sheet; The target glass sheet is the first glass sheet and / or the second glass sheet.

2. The glass plate crack early warning method for a photovoltaic assembly according to claim 1.

8. 1. A glass plate crack early warning device for a photovoltaic assembly, comprising: an acquisition module for acquiring target point cloud data obtained by a target scanner scanning a target glass sheet, the target glass sheet being a glass sheet located on a surface of a photovoltaic assembly, the target point cloud data including: color point cloud data consisting of color data of all pixel points corresponding to the target glass sheet; and temperature point cloud data consisting of temperature data and position data of all pixel points corresponding to the target glass sheet; a determination module for determining an area value of a crack center of the target glass sheet based on the color point cloud data, and determining shape information of the crack of the target glass sheet based on the temperature point cloud data; an early warning module for determining a target early warning level according to the area value of the crack center and / or the shape information of the crack, and issuing an early warning according to an early warning method corresponding to the target early warning level; 1. A glass plate crack early warning device for a photovoltaic assembly, comprising:

9. at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes computer executable instructions stored in the memory, causing the at least one processor to perform the glass sheet crack early warning method for a photovoltaic assembly according to any one of claims 1 to 7. An electronic device characterized by:

10. 8. A computer-readable storage medium having stored thereon computer-executable instructions, the computer-executable instructions being used to implement the glass sheet crack early warning method for photovoltaic assemblies according to any one of claims 1 to 7, when executed by a processor.

Images