A method for detecting coating defects of BIPV photovoltaic glass

By dividing BIPV photovoltaic glass into multiple glass grids and performing transmittance and weatherability tests, a transmittance and weatherability array is constructed, and combined with matching analysis, the low accuracy problem caused by local detection in the prior art is solved. , realizes global coating defect detection and performance matching correction, and improves the comprehensiveness and accuracy of the detection results.

CN118425190BActive Publication Date: 2024-11-29JIANGSU ZHIJIN INNOVATIVE ENERGY TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202410730607.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-06-06
Publication Date
2024-11-29
Estimated Expiration
2044-06-06

AI Technical Summary

Technical Problem

In the prior art, the coating defect detection of photovoltaic glass is mostly carried out locally, resulting in low accuracy of the detection results.

Method used

By dividing BIPV photovoltaic glass into multiple glass grids, transmittance test and weather resistance test respectively, a transmittance array and weather resistance array are constructed, transmittance performance analysis and weather resistance analysis are performed, and combined with transmittance weather resistance matching Analyze and calculate, correct the coating defect level to obtain.

Benefits of technology

Global coating defect detection is realized, improving the comprehensiveness and accuracy of the detection results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118425190B_ABST
    Figure CN118425190B_ABST
Patent Text Reader

Abstract

The present invention discloses a coating defect detection method for BIPV photovoltaic glass, which relates to the field of data processing technology. The method includes: grid-dividing the BIPV photovoltaic glass to obtain a plurality of glass grids; performing a transmittance test and a weather resistance test to construct a transmittance array and a weather resistance array; performing a transmittance performance analysis and a weather resistance performance analysis to obtain a first transmittance performance parameter, a second transmittance performance parameter, a first weather resistance performance parameter, and a second weather resistance performance parameter; performing a transmittance and weather resistance matching analysis and calculation to obtain a third transmittance performance parameter and a third weather resistance performance parameter, and classifying and obtaining a coating defect grade as a defect detection result. The present invention solves the technical problem that the coating defect detection of photovoltaic glass is mainly carried out locally in the prior art, and the accuracy of the detection result is low, and achieves the technical effect of performing global coating defect detection and performance matching correction through grid division to improve the comprehensiveness and accuracy of the detection result.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method for detecting coating defects of BIPV photovoltaic glass. Background Art

[0002] BIPV photovoltaic glass is a glass material that integrates photovoltaic power generation functions into buildings. It has various forms such as transparent, translucent, and opaque. The transmittance of photovoltaic glass will directly affect the photoelectric conversion efficiency of photovoltaic modules. Coating on photovoltaic glass using the principle of light interference can effectively improve the transmittance and enhance the weather resistance and corrosion resistance of photovoltaic glass. Therefore, coating defect detection of BIPV photovoltaic glass is a key link to ensure product quality and performance. However, the current coating defect detection is mostly carried out on local defects, and the accuracy of the detection results is low. Summary of the invention

[0003] The present application provides a method for detecting coating defects of BIPV photovoltaic glass, which is used to solve the technical problem that the coating defect detection of photovoltaic glass is mostly carried out locally in the prior art, and the accuracy of the detection results is low.

[0004] In a first aspect of the present application, a coating defect detection method for BIPV photovoltaic glass is provided, the method comprising: dividing the BIPV photovoltaic glass to be subjected to coating defect detection into grids to obtain a plurality of glass grids; performing a transmittance test on the plurality of glass grids to obtain a plurality of transmittance information, and constructing a transmittance array; performing a weather resistance test on the plurality of glass grids, and after the test is completed, collecting and obtaining a plurality of grid surface morphology images, and analyzing and obtaining a plurality of weather resistance information, and constructing a weather resistance array; performing a transmittance performance analysis based on the transmittance array to obtain a first transmittance performance parameter, and analyzing and obtaining a transmittance uniformity coefficient, and performing a weather resistance test on the plurality of glass grids; The first light transmittance performance parameter is corrected to obtain the second light transmittance performance parameter; based on the weather resistance array, a weather resistance performance analysis is performed to obtain the first weather resistance performance parameter, and the weather resistance balance coefficient is obtained by analysis, and the first weather resistance performance parameter is corrected to obtain the second weather resistance performance parameter; according to the transmittance array and the weather resistance array, the light transmittance and weather resistance matching analysis and calculation are performed on the multiple glass grids to obtain the matching coefficient, the second light transmittance performance parameter and the second weather resistance performance parameter are corrected to obtain the third light transmittance performance parameter and the third weather resistance performance parameter, and the coating defect level of the BIPV photovoltaic glass is classified as the defect detection result.

[0005] In a second aspect of the present application, a coating defect detection system for BIPV photovoltaic glass is provided, the system comprising: a plurality of glass grid acquisition modules, the plurality of glass grid acquisition modules are used to perform grid division on the BIPV photovoltaic glass to be subjected to coating defect detection, and obtain a plurality of glass grids; a transmittance array construction module, the transmittance array construction module is used to perform transmittance tests on the plurality of glass grids, obtain a plurality of transmittance information, and construct a transmittance array; a weather resistance array construction module, the weather resistance array construction module is used to perform weather resistance tests on the plurality of glass grids, and after the test is completed, collect and obtain a plurality of grid surface morphology images, analyze and obtain a plurality of weather resistance information, and construct a weather resistance array; a transmittance performance parameter acquisition module, the transmittance performance parameter acquisition module is used to perform transmittance performance analysis based on the transmittance array, and obtain a first transmittance Light performance parameter, and analyze to obtain the transmittance balance coefficient, correct the first light transmittance performance parameter, and obtain the second light transmittance performance parameter; a weather resistance performance parameter acquisition module, the weather resistance performance parameter acquisition module is used to perform weather resistance performance analysis based on the weather resistance array, obtain the first weather resistance performance parameter, and analyze to obtain the weather resistance balance coefficient, correct the first weather resistance performance parameter, and obtain the second weather resistance performance parameter; a defect detection result acquisition module, the defect detection result acquisition module is used to perform light transmittance and weather resistance matching analysis and calculation on the multiple glass grids according to the transmittance array and the weather resistance array, obtain the matching coefficient, correct the second light transmittance performance parameter and the second weather resistance performance parameter, obtain the third light transmittance performance parameter and the third weather resistance performance parameter, and classify and obtain the coating defect level of the BIPV photovoltaic glass as the defect detection result.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The present application provides a method for detecting coating defects of BIPV photovoltaic glass, which relates to the field of data processing technology. The method divides the BIPV photovoltaic glass into multiple glass grids, performs transmittance tests and weather resistance tests respectively, constructs a transmittance array and a weather resistance array, performs transmittance performance analysis and weather resistance performance analysis, obtains first and second transmittance performance parameters and first and second weather resistance performance parameters, calculates and corrects the third transmittance performance parameter and the third weather resistance performance parameter through transmittance and weather resistance matching analysis, and obtains the coating defect grade by classification as the defect detection result, thereby solving the technical problem that the coating defect detection of photovoltaic glass in the prior art is mostly carried out locally and the accuracy of the detection result is low, and realizes the technical effect of performing global coating defect detection and performance matching correction through grid division to improve the comprehensiveness and accuracy of the detection result. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A schematic flow chart of a method for detecting coating defects of BIPV photovoltaic glass provided in an embodiment of the present application.

[0010] Figure 2 A schematic diagram of the process of constructing a weather-resistant array in a method for detecting coating defects of a BIPV photovoltaic glass provided in an embodiment of the present application.

[0011] Figure 3 A schematic diagram of a process for obtaining a second light transmission performance parameter in a coating defect detection method for BIPV photovoltaic glass provided in an embodiment of the present application.

[0012] Figure 4 A schematic structural diagram of a coating defect detection system for BIPV photovoltaic glass provided in an embodiment of the present application.

[0013] Explanation of the reference numerals: multiple glass grid acquisition modules 11, light transmittance array construction module 12, weather resistance array construction module 13, light transmittance performance parameter acquisition module 14, weather resistance performance parameter acquisition module 15, defect detection result acquisition module 16. DETAILED DESCRIPTION

[0014] The present application provides a method for detecting coating defects of BIPV photovoltaic glass, which is used to solve the technical problem that the coating defect detection of photovoltaic glass is mostly carried out locally in the prior art, and the accuracy of the detection results is low.

[0015] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0016] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices.

[0017] Embodiment 1

[0018] like Figure 1 As shown, the present application provides a method for detecting coating defects of BIPV photovoltaic glass, the method comprising:

[0019] P10: Grid-dividing the BIPV photovoltaic glass to be inspected for coating defects to obtain multiple glass grids;

[0020] It should be understood that the BIPV photovoltaic glass to be tested for coating defects is divided into grids according to certain division rules. For example, the size of a single grid is first determined, which can be selected based on actual needs and detection accuracy requirements. Generally speaking, the size of the grid should be small enough to detect tiny coating defects. Furthermore, the BIPV photovoltaic glass is divided into multiple glass grids according to rectangular division, grid division, irregular shape division, etc. Each divided glass grid is marked and recorded, including information such as the grid number, position, size, etc., to facilitate subsequent defect location.

[0021] P20: performing a transmittance test on the plurality of glass grids to obtain a plurality of transmittance information, and constructing a transmittance array;

[0022] Optionally, the transmittance of the multiple glass grids is tested separately. Transmittance is one of the important parameters for evaluating the quality of photovoltaic glass, which determines the efficiency of sunlight passing through polycrystalline silicon photovoltaic modules. It can be tested by using a spectrometer, a transmittance meter, etc., including measuring the transmittance of light of different wavelengths, etc., to obtain multiple transmittance information of the multiple glass grids, and perform data cleaning, missing value processing, outlier detection and processing on the multiple transmittance information to improve the quality and reliability of the data, and then use the processed multiple transmittance information to construct a transmittance array.

[0023] P30: Performing a weather resistance test on the plurality of glass grids, acquiring a plurality of grid surface topography images after the test, and analyzing and obtaining a plurality of weather resistance information to construct a weather resistance array;

[0024] Further, such as Figure 2 As shown, step P30 of the embodiment of the present application also includes:

[0025] P31: performing a weather resistance test on the plurality of glass grids, wherein the weather resistance test includes preset weather resistance test conditions;

[0026] P32: After the weather resistance test is completed, multiple grid surface morphology images of multiple glass grid coating surfaces are collected;

[0027] P33: Performing weather resistance analysis on the plurality of grid surface topography images to obtain the plurality of weather resistance information;

[0028] P34: Acquire multiple grid domain coordinate information of the multiple glass grids;

[0029] P35: Constructing a weather resistance array based on the multiple grid domain coordinate information and multiple weather resistance information.

[0030] In a possible embodiment of the present application, the plurality of glass grids are subjected to weather resistance tests respectively, and the weather resistance tests include test items such as light aging, thermal cycling, moisture, salt spray, and hail impact. Weather resistance test conditions are required to be preset before the test. Through these tests, the influence of various environmental factors on photovoltaic glass can be simulated. After the weather resistance test is completed, multiple grid surface morphology images of the coated surfaces of the plurality of glass grids are collected. By detecting the changes in the appearance, physical and electrical properties of the photovoltaic glass, the plurality of grid surface morphology images are subjected to weather resistance analysis to evaluate its weather resistance and long-term stability, and the plurality of weather resistance information of the plurality of glass grids is obtained. Furthermore, the plurality of grid domain coordinate information of the plurality of glass grids, that is, the grid position information, is obtained, and the plurality of weather resistance information is matched one by one with the plurality of grid domain coordinate information to construct a weather resistance array, which can reflect the weather resistance of each part of the BIPV photovoltaic glass to be tested.

[0031] Furthermore, step P33 of the embodiment of the present application also includes:

[0032] P33-1: Obtain a set of sample grid surface topography images, identify the weather resistance grade, and obtain a set of sample weather resistance information;

[0033] P33-2: Using the sample grid surface morphology image set and the sample weather resistance information set, a weather resistance identifier is constructed based on a convolutional neural network;

[0034] P33-3: Based on the weather resistance identifier, the multiple grid surface morphology images are identified to obtain multiple weather resistance information.

[0035] Exemplarily, based on historical defect detection records, multiple sample grid surface morphology images are collected to form a sample grid surface morphology image set, and weather resistance grades are identified for each of the multiple sample grid surface morphology images, including identifying and grading the degree of influence of various environmental factors, to obtain a sample weather resistance information set. Furthermore, the sample grid surface morphology image set and the sample weather resistance information set are used as training data, and based on the architecture of a convolutional neural network, a weather resistance identifier is constructed and supervised training is performed on it until the output converges. The weather resistance identifier is used to perform weather resistance identification on the multiple grid surface morphology images to obtain multiple weather resistance information.

[0036] P40: Based on the transmittance array, perform a transmittance performance analysis to obtain a first transmittance performance parameter, and analyze to obtain a transmittance balance coefficient, and correct the first transmittance performance parameter to obtain a second transmittance performance parameter;

[0037] Further, such as Figure 3 As shown, step P40 of the embodiment of the present application also includes:

[0038] P41: Obtain a set of sample transmittances and a set of sample transmittance performance parameters, and construct a transmittance performance classifier;

[0039] P42: Based on the light transmittance classifier, classify the light transmittance in the light transmittance array to obtain a light transmittance parameter array;

[0040] P43: Obtain the first light transmission performance parameter by weighted calculation according to the light transmission performance parameter array;

[0041] P44: According to the light transmittance performance parameter array, the light transmittance balance coefficient is calculated, and the first light transmittance performance parameter is corrected to obtain a second light transmittance performance parameter.

[0042] Specifically, based on the transmittance array, a transmittance performance analysis is performed. First, based on historical transmittance performance analysis records, a sample transmittance set and a sample transmittance performance parameter set are collected as training data, and in combination with machine learning principles, a transmittance performance classifier is constructed and trained to obtain the transmittance in the transmittance array. The transmittance performance classifier is used to classify the transmittance in the transmittance array to obtain the transmittance performance parameters of multiple glass grids, thereby constructing a transmittance performance parameter array. Furthermore, all parameters in the transmittance performance parameter array are weightedly calculated to obtain the first transmittance performance parameter, that is, the transmittance performance level.

[0043] Furthermore, calculations are performed based on the light transmittance performance parameter array to obtain the transmittance balance coefficient. For example, the inverse of the ratio of the variance of multiple light transmittance performance parameters to the historical average variance is calculated to obtain the transmittance balance coefficient. The first light transmittance performance parameter is corrected using the transmittance balance coefficient to obtain a second light transmittance performance parameter. The larger the transmittance balance coefficient, the more balanced the light transmittance performance of the glass, and the larger the corrected light transmittance performance parameter.

[0044] Furthermore, step P44 of the embodiment of the present application also includes:

[0045] P44-1: Calculate the mean square error of light transmittance performance according to the light transmittance performance parameter array;

[0046] P44-2: Calculate the transmittance uniformity coefficient based on the mean square deviation of the light transmittance performance and the mean square deviation of the historical average light transmittance performance during the light transmittance performance test;

[0047] P44-3: Use the transmittance balance coefficient to correct and calculate the first light transmittance performance parameter to obtain the second light transmittance performance parameter.

[0048] It should be understood that the variance of the multiple light transmittance performance parameters in the light transmittance performance parameter array is calculated to obtain the mean square error of the light transmittance performance, and multiple historical light transmittance performance test data are collected to calculate the historical average light transmittance performance mean square error. Further, the inverse of the ratio of the light transmittance performance mean square error to the historical average light transmittance performance mean square error is calculated to obtain the transmittance balance coefficient. The transmittance balance coefficient is used and multiplied by the first light transmittance performance parameter for correction calculation to obtain the second light transmittance performance parameter.

[0049] P50: Based on the weather resistance array, perform weather resistance performance analysis to obtain a first weather resistance performance parameter, and analyze to obtain a weather resistance balance coefficient, correct the first weather resistance performance parameter, and obtain a second weather resistance performance parameter;

[0050] Exemplarily, referring to the above-mentioned transmittance analysis method, a weather resistance performance analysis is performed based on the weather resistance array to obtain the weather resistance performance of multiple glass grids, and a first weather resistance performance parameter is obtained by weighted calculation, and a weather resistance balance coefficient is obtained by analysis. After correcting the first weather resistance performance parameter using the weather resistance balance coefficient, a second weather resistance performance parameter is obtained.

[0051] P60: Based on the transmittance array and weather resistance array, the transmittance and weather resistance matching of the multiple glass grids are analyzed and calculated to obtain a matching coefficient, the second transmittance performance parameter and the second weather resistance performance parameter are corrected to obtain a third transmittance performance parameter and a third weather resistance performance parameter, and the coating defect level of the BIPV photovoltaic glass is classified as a defect detection result.

[0052] Furthermore, step P60 of the embodiment of the present application also includes:

[0053] P61: Matching the transmittance information and the weather resistance information in the transmittance array and the weather resistance array to obtain a plurality of coating parameter pairs;

[0054] P62: Obtain a set of sample coating parameter pairs and a set of sample matching parameters, wherein each sample coating parameter pair includes sample transmittance information and sample weather resistance information;

[0055] P63: According to the sample coating parameter pair set and the sample matching parameter set, a light transmission and weather resistance matching analyzer is constructed to identify the multiple coating parameter pairs, obtain multiple grid matching coefficients, and obtain the matching coefficients by weighted calculation;

[0056] P64: Using the matching coefficient, the second light transmittance performance parameter and the second weather resistance performance parameter are corrected to obtain the third light transmittance performance parameter and the third weather resistance performance parameter.

[0057] Optionally, the greater the transmittance, the more light the glass receives, and the stronger the corresponding weather resistance needs to be to ensure the service life. Therefore, according to the transmittance array and the weather resistance array, the transmittance and weather resistance matching analysis and calculation are performed on the multiple glass grids, and the matching coefficient is obtained by analyzing the matching of the transmittance and weather resistance in each glass grid. Specifically, according to the multiple grid domain coordinate information, the transmittance information and weather resistance information in the transmittance array and the weather resistance array are matched to obtain multiple coating parameter pairs. Furthermore, based on the historical coating matching records, a set of sample coating parameter pairs and a corresponding set of sample matching parameters are collected and obtained, and each sample coating parameter pair contains corresponding sample transmittance information and sample weather resistance information.

[0058] Furthermore, the sample coating parameter pair set and the sample matching parameter set are used as training data, and training is performed in combination with the principle of machine learning to construct a light transmittance and weather resistance matching analyzer. The light transmittance and weather resistance matching analyzer is used to identify the multiple coating parameter pairs, and multiple grid matching coefficients are obtained. The multiple grid matching coefficients are weighted and calculated to obtain the overall matching coefficient of the BIPV photovoltaic glass to be tested. The matching coefficient is used to correct the second light transmittance performance parameter and the second weather resistance performance parameter to obtain the third light transmittance performance parameter and the third weather resistance performance parameter.

[0059] Furthermore, step P60 of the embodiment of the present application also includes:

[0060] P65: Obtain a set of sample light transmittance performance parameters and a set of sample weather resistance performance parameters, and obtain a set of sample coating defect levels;

[0061] P66: Based on the decision tree, a defect grade classifier is constructed using the sample light transmittance performance parameter set, the sample weather resistance performance parameter set and the sample coating defect grade set;

[0062] P67: Using the defect grade classifier, classify and identify the third light transmittance performance parameter and the third weather resistance performance parameter to obtain the coating defect grade.

[0063] Specifically, based on historical defect classification data, a sample light transmittance performance parameter set and a sample weather resistance performance parameter set, as well as a corresponding sample coating defect level set are collected; further, based on the decision tree principle, the sample light transmittance performance parameter set, the sample weather resistance performance parameter set and the sample coating defect level set are used as training data to train and construct a defect level classifier; the defect level classifier is used to classify and identify the third light transmittance performance parameter and the third weather resistance performance parameter, and the coating defect level of the BIPV photovoltaic glass is obtained as a defect detection result.

[0064] In summary, the embodiments of the present application have at least the following technical effects:

[0065] The present application divides the BIPV photovoltaic glass into multiple glass grids, performs transmittance tests and weather resistance tests respectively, constructs a transmittance array and a weather resistance array, performs transmittance performance analysis and weather resistance performance analysis, obtains the first and second transmittance performance parameters and the first and second weather resistance performance parameters, corrects and obtains the third transmittance performance parameter and the third weather resistance performance parameter through transmittance and weather resistance matching analysis and calculation, and classifies the coating defect level as the defect detection result.

[0066] The technical effect of performing global coating defect detection and performance matching correction through grid division to improve the comprehensiveness and accuracy of the detection results is achieved.

[0067] Embodiment 2

[0068] Based on the same inventive concept as the coating defect detection method of a BIPV photovoltaic glass in the aforementioned embodiment, Figure 4 As shown, the present application provides a coating defect detection system for BIPV photovoltaic glass, and the system and method embodiments in the present application are based on the same inventive concept. The system includes:

[0069] A plurality of glass grid acquisition modules 11, wherein the plurality of glass grid acquisition modules 11 are used to perform grid division on the BIPV photovoltaic glass to be inspected for coating defects to obtain a plurality of glass grids;

[0070] A transmittance array construction module 12, the transmittance array construction module 12 is used to perform transmittance tests on the plurality of glass grids, obtain a plurality of transmittance information, and construct a transmittance array;

[0071] A weather resistance array construction module 13, the weather resistance array construction module 13 is used to perform a weather resistance test on the plurality of glass grids, and after the test is completed, collect and obtain a plurality of grid surface topography images, and analyze and obtain a plurality of weather resistance information to construct a weather resistance array;

[0072] A light transmittance performance parameter acquisition module 14, the light transmittance performance parameter acquisition module 14 is used to perform light transmittance performance analysis based on the transmittance array to obtain a first light transmittance performance parameter, and to obtain a transmittance uniformity coefficient by analysis, and to correct the first light transmittance performance parameter to obtain a second light transmittance performance parameter;

[0073] A weather resistance performance parameter acquisition module 15, the weather resistance performance parameter acquisition module 15 is used to perform weather resistance performance analysis based on the weather resistance array to obtain a first weather resistance performance parameter, and to obtain a weather resistance equilibrium coefficient by analysis, and to correct the first weather resistance performance parameter to obtain a second weather resistance performance parameter;

[0074] The defect detection result acquisition module 16 is used to perform light transmittance and weather resistance matching analysis and calculation on the multiple glass grids according to the transmittance array and the weather resistance array, obtain a matching coefficient, correct the second light transmittance performance parameter and the second weather resistance performance parameter, obtain a third light transmittance performance parameter and a third weather resistance performance parameter, and classify and obtain the coating defect level of the BIPV photovoltaic glass as a defect detection result.

[0075] Furthermore, the weather resistance array construction module 13 is also used to perform the following steps:

[0076] Performing a weather resistance test on the plurality of glass grids, wherein the weather resistance test includes preset weather resistance test conditions;

[0077] After the weather resistance test is completed, multiple grid surface morphology images of multiple glass grid coating surfaces are collected;

[0078] Performing weather resistance analysis on the plurality of grid surface topography images to obtain the plurality of weather resistance information;

[0079] Acquire multiple grid domain coordinate information of the multiple glass grids;

[0080] A weather resistance array is constructed based on the plurality of grid domain coordinate information and the plurality of weather resistance information.

[0081] Furthermore, the weather resistance array construction module 13 is also used to perform the following steps:

[0082] Obtain a set of sample grid surface topography images, identify the weather resistance grade, and obtain a set of sample weather resistance information;

[0083] Using the sample grid surface morphology image set and the sample weather resistance information set, a weather resistance identifier is constructed based on a convolutional neural network;

[0084] Based on the weather resistance identifier, the plurality of grid surface topography images are identified to obtain a plurality of weather resistance information.

[0085] Furthermore, the light transmission performance parameter acquisition module 14 is also used to perform the following steps:

[0086] Obtain a sample light transmittance set and a sample light transmittance performance parameter set, and construct a light transmittance performance classifier;

[0087] Based on the light transmittance classifier, classify the light transmittance in the light transmittance array to obtain a light transmittance parameter array;

[0088] Obtaining the first light transmission performance parameter by weighted calculation according to the light transmission performance parameter array;

[0089] The transmittance uniformity coefficient is calculated based on the transmittance performance parameter array, and the first transmittance performance parameter is corrected to obtain a second transmittance performance parameter.

[0090] Furthermore, the light transmission performance parameter acquisition module 14 is also used to perform the following steps:

[0091] Calculating the light transmittance performance mean square error according to the light transmittance performance parameter array;

[0092] The transmittance uniformity coefficient is calculated based on the mean square deviation of the light transmittance performance and the mean square deviation of the historical average light transmittance performance during the light transmittance performance test;

[0093] The first light transmittance performance parameter is corrected and calculated using the transmittance uniformity coefficient to obtain the second light transmittance performance parameter.

[0094] Furthermore, the defect detection result acquisition module 16 is further configured to perform the following steps:

[0095] Matching the transmittance information and the weather resistance information in the transmittance array and the weather resistance array to obtain a plurality of coating parameter pairs;

[0096] Obtain a set of sample coating parameter pairs and a set of sample matching parameters, wherein each sample coating parameter pair includes sample transmittance information and sample weather resistance information;

[0097] According to the sample coating parameter pair set and the sample matching parameter set, a light transmission and weather resistance matching analyzer is constructed to identify the multiple coating parameter pairs, obtain multiple grid matching coefficients, and obtain the matching coefficients by weighted calculation;

[0098] The second light transmission performance parameter and the second weather resistance performance parameter are corrected by using the matching coefficient to obtain the third light transmission performance parameter and the third weather resistance performance parameter.

[0099] Furthermore, the defect detection result acquisition module 16 is further configured to perform the following steps:

[0100] Obtain a set of sample light transmittance performance parameters and a set of sample weather resistance performance parameters, and obtain a set of sample coating defect levels;

[0101] Based on the decision tree, a defect grade classifier is constructed using the sample light transmittance performance parameter set, the sample weather resistance performance parameter set and the sample coating defect grade set;

[0102] The defect level classifier is used to classify and identify the third light transmittance performance parameter and the third weather resistance performance parameter to obtain the coating defect level.

[0103] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0104] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0105] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for detecting coating defects of BIPV photovoltaic glass, characterized in that: The method comprises: Divide the BIPV photovoltaic glass to be inspected for coating defects into grids to obtain multiple glass grids; Performing light transmittance tests on the plurality of glass grids to obtain a plurality of light transmittance information and constructing a light transmittance array; Performing a weather resistance test on the plurality of glass grids, and acquiring a plurality of grid surface topography images after the test is completed, and analyzing and acquiring a plurality of weather resistance information to construct a weather resistance array; Based on the transmittance array, a transmittance performance analysis is performed to obtain a first transmittance performance parameter, and a transmittance balance coefficient is obtained by analysis, and the first transmittance performance parameter is corrected to obtain a second transmittance performance parameter; Based on the weather resistance array, a weather resistance performance analysis is performed to obtain a first weather resistance performance parameter, and a weather resistance equilibrium coefficient is obtained by analysis, and the first weather resistance performance parameter is corrected to obtain a second weather resistance performance parameter; According to the transmittance array and the weather resistance array, the transmittance and weather resistance matching of the multiple glass grids are analyzed and calculated to obtain a matching coefficient, the second transmittance performance parameter and the second weather resistance performance parameter are corrected to obtain a third transmittance performance parameter and a third weather resistance performance parameter, and the coating defect level of the BIPV photovoltaic glass is obtained by classification as a defect detection result; Based on the transmittance array, a transmittance performance analysis is performed to obtain a first transmittance performance parameter, and a transmittance uniformity coefficient is obtained by analysis, and the first transmittance performance parameter is corrected to obtain a second transmittance performance parameter, including: Obtain a sample light transmittance set and a sample light transmittance performance parameter set, and construct a light transmittance performance classifier; Based on the light transmittance classifier, classify the light transmittance in the light transmittance array to obtain a light transmittance parameter array; Obtaining the first light transmission performance parameter by weighted calculation according to the light transmission performance parameter array; According to the light transmittance performance parameter array, the light transmittance uniformity coefficient is calculated, and the first light transmittance performance parameter is corrected to obtain a second light transmittance performance parameter; The method comprises: calculating the transmittance uniformity coefficient according to the transmittance performance parameter array, and correcting the first transmittance performance parameter to obtain a second transmittance performance parameter. Calculating the light transmittance performance mean square error according to the light transmittance performance parameter array; The transmittance uniformity coefficient is calculated based on the mean square deviation of the light transmittance performance and the mean square deviation of the historical average light transmittance performance during the light transmittance performance test; The first light transmittance performance parameter is corrected and calculated using the transmittance uniformity coefficient to obtain the second light transmittance performance parameter.

2. The method according to claim 1, characterized in that The plurality of glass grids are subjected to a weather resistance test, and after the test is completed, a plurality of grid surface topography images are acquired, and a plurality of weather resistance information is obtained by analysis to construct a weather resistance array, including: Performing a weather resistance test on the plurality of glass grids, wherein the weather resistance test includes preset weather resistance test conditions; After the weather resistance test is completed, multiple grid surface morphology images of multiple glass grid coating surfaces are collected; Performing weather resistance analysis on the plurality of grid surface topography images to obtain the plurality of weather resistance information; Acquire multiple grid domain coordinate information of the multiple glass grids; A weather resistance array is constructed based on the plurality of grid domain coordinate information and the plurality of weather resistance information.

3. The method according to claim 2, characterized in that Performing weather resistance analysis on the plurality of grid surface topography images to obtain the plurality of weather resistance information includes: Obtain a set of sample grid surface topography images, identify the weather resistance grade, and obtain a set of sample weather resistance information; Using the sample grid surface morphology image set and the sample weather resistance information set, a weather resistance identifier is constructed based on a convolutional neural network; Based on the weather resistance identifier, the plurality of grid surface topography images are identified to obtain a plurality of weather resistance information.

4. The method according to claim 1, characterized in that: According to the transmittance array and the weather resistance array, the transmittance and weather resistance matching of the plurality of glass grids are analyzed and calculated to obtain a matching coefficient, and the second transmittance performance parameter and the second weather resistance performance parameter are corrected, including: Matching the transmittance information and the weather resistance information in the transmittance array and the weather resistance array to obtain a plurality of coating parameter pairs; Obtain a set of sample coating parameter pairs and a set of sample matching parameters, wherein each sample coating parameter pair includes sample transmittance information and sample weather resistance information; According to the sample coating parameter pair set and the sample matching parameter set, a light transmission and weather resistance matching analyzer is constructed to identify the multiple coating parameter pairs, obtain multiple grid matching coefficients, and obtain the matching coefficients by weighted calculation; The second light transmission performance parameter and the second weather resistance performance parameter are corrected by using the matching coefficient to obtain the third light transmission performance parameter and the third weather resistance performance parameter.

5. The method according to claim 1, characterized in that The coating defect level of the BIPV photovoltaic glass is obtained by classification, including: Obtain a set of sample light transmittance performance parameters and a set of sample weather resistance performance parameters, and obtain a set of sample coating defect levels; Based on the decision tree, a defect grade classifier is constructed using the sample light transmittance performance parameter set, the sample weather resistance performance parameter set and the sample coating defect grade set; The defect level classifier is used to classify and identify the third light transmittance performance parameter and the third weather resistance performance parameter to obtain the coating defect level.

6. A coating defect detection system for BIPV photovoltaic glass, characterized in that: The system is used to execute the method according to any one of claims 1 to 5, and the system comprises: A plurality of glass grid acquisition modules, wherein the plurality of glass grid acquisition modules are used to perform grid division on the BIPV photovoltaic glass to be inspected for coating defects to obtain a plurality of glass grids; A transmittance array construction module, the transmittance array construction module is used to perform transmittance tests on the plurality of glass grids, obtain a plurality of transmittance information, and construct a transmittance array; A weather resistance array construction module, wherein the weather resistance array construction module is used to perform a weather resistance test on the plurality of glass grids, and after the test is completed, collect and obtain a plurality of grid surface topography images, and analyze and obtain a plurality of weather resistance information to construct a weather resistance array; A light transmittance performance parameter acquisition module, the light transmittance performance parameter acquisition module is used to perform light transmittance performance analysis based on the light transmittance array to obtain a first light transmittance performance parameter, and to obtain a transmittance uniformity coefficient by analysis, and to correct the first light transmittance performance parameter to obtain a second light transmittance performance parameter; A weather resistance performance parameter acquisition module, the weather resistance performance parameter acquisition module is used to perform weather resistance performance analysis based on the weather resistance array to obtain a first weather resistance performance parameter, and to obtain a weather resistance equilibrium coefficient by analysis, and to correct the first weather resistance performance parameter to obtain a second weather resistance performance parameter; A defect detection result acquisition module is used to perform transmittance and weather resistance matching analysis and calculation on the multiple glass grids according to the transmittance array and the weather resistance array, obtain a matching coefficient, correct the second transmittance performance parameter and the second weather resistance performance parameter, obtain a third transmittance performance parameter and a third weather resistance performance parameter, and classify and obtain the coating defect level of the BIPV photovoltaic glass as a defect detection result.

Citation Information

Patent Citations

  • Standard sample for calibrating defect inspection apparatus for flat panel display, and calibration method of defective inspection apparatus

    JP2004028706A

  • Cover glass for solid imaging devices

    JP2004221541A