An automatic glass sheet arranging system and sheet matching method applicable to laminated glass

Abstract

The present invention relates to the technical field of glass production, and discloses a glass matching method applicable to an automatic glass laminating system. The system detects multiple parameters of glass, such as thickness, size, flatness, surface quality, and optical properties, through sensors and an image processing unit connected to a control processing unit. During the detection process, the system automatically enters the acquired data into a database and classifies the glass according to preset standards. The classification results are managed through an MES system, and finally, the qualified products and unqualified products are automatically sorted. Through the method of the present invention, comprehensive detection and efficient classification of laminated glass can be achieved, ensuring product quality while improving production efficiency and avoiding errors and omissions that may occur in traditional manual detection.

Description

Technical Field

[0001] The present invention belongs to the technical field of glass production, and particularly relates to a method for matching glass sheets in an automatic glass sheet sorting system applicable to laminated glass. Background Art

[0002] In modern architecture and the photovoltaic industry, laminated glass has become one of the widely used materials due to its excellent safety, sound insulation, and ultraviolet resistance. Laminated glass is composed of two or more glass sheets bonded together by one or more layers of interlayer films (such as PVB films), which can effectively prevent glass fragments from flying when broken, greatly improving safety performance. Therefore, in the fields of building curtain walls, automotive windshields, and high-standard photovoltaic glass, the demand for laminated glass has been increasing year by year, and the requirements for its production process have also been rising.

[0003] In the production process of laminated glass, the cutting and laying of the interlayer film are key steps to ensure the quality of the finished product. Traditional production methods of laminated glass often rely on manual operation or semi-automatic equipment for the cutting and laying of the interlayer film. However, with the diversification of order requirements and the increasing complexity of glass specifications, traditional operation methods are difficult to meet the requirements of high-efficiency and high-precision production. Especially in the case of a large number of orders or more personalized customization requirements, manual operation has obvious problems of low efficiency and high error rate. This not only affects the production efficiency of laminated glass but also easily leads to unstable quality of the finished product, thereby increasing the production cost of enterprises.

[0004] To solve this problem, an automatic glass sheet sorting system has emerged and gradually become an important device in the production of laminated glass. The automatic glass sheet sorting system uniformly manages and schedules the glass specifications and order requirements through MES (Manufacturing Execution System), making the cutting and laying of the interlayer film more accurate and efficient. In this system, the cutting process of the interlayer film can be dynamically adjusted according to the glass specifications and order requirements entered in the MES system to ensure that the cutting result precisely matches the shape and size of the glass sheet. In this way, the automatic glass sheet sorting system can significantly improve the quality of the finished product and production efficiency and reduce the error rate during the production process.

[0005] In the production process of laminated glass, the automatic glass sheet sorting system is a key link to ensure product quality and production efficiency. Currently, the automatic glass sheet sorting system usually includes multiple sensors, such as thickness detectors, edge detectors, etc. These sensors can monitor various parameters of the glass sheet in real time and automatically complete the task of matching glass sheets according to the set standards. The system uses a high-precision positioning device to ensure that each glass sheet is accurately aligned before entering the next process, avoiding misalignment problems during subsequent processing.

[0006] In order to better meet the requirements of modern production, improve the production efficiency and product quality of laminated glass, it is particularly necessary to develop an intelligent method for sorting laminated glass based on the MES system. By dynamically adjusting the cutting process of the interlayer film, it can effectively solve the deficiencies in traditional processes, achieve the production goals of automation and refinement, and create greater market competitiveness for enterprises. The sorting system includes an automatic sorting device: an automatic sorting device is set at key nodes of the production line. When the detector finds unqualified glass, the system can be automatically started to separate the unqualified products and ensure that the glass on the production line meets the quality requirements.

[0007] Therefore, in view of the above problems, a more intelligent automatic sorting system for laminated glass is needed, which can automatically adjust the film matching method according to the specific parameters of the glass and production requirements, improve production efficiency, and ensure product quality. Summary of the Invention

[0008] The present invention provides a method for matching the film of an automatic sorting system applicable to laminated glass, using a new system for sorting the film to solve the technical problems of the existing identification method relying on manual discrimination, depending on the level of personnel, or discriminating by making a large number of products, resulting in waste of materials and labor.

[0009] To solve the above technical problems, the present invention provides the following technical solutions:

[0010] The present invention provides a method for matching the film of an automatic sorting system applicable to laminated glass, including:

[0011] S1: Use X-ray scanning to detect the glass raw material, and input the specifications of the glass (such as thickness and size) into the MES (Manufacturing Execution System).

[0012] S2: Order input and matching, and the system retrieves data according to the order requirements.

[0013] S3: Interlayer film cutting, start cutting the interlayer film according to the glass and order requirements.

[0014] S4: Edge grinding treatment, grind the edges of the cut glass to remove burrs.

[0015] S5: Cleaning and drying, remove surface dirt and dust and ensure that the surface is free of water stains and impurities.

[0016] S6: Interlayer film laying, lay a layer of cut interlayer film (PVB film) between two pieces of glass.

[0017] S7: Initial lamination, preliminarily laminate the glass and the interlayer film together through hot pressing and vacuum degassing.

[0018] S8: Autoclave, completely bond the interlayer film and the glass through high temperature and high pressure.

[0019] S9: Inspection and trimming, conduct appearance and quality inspections to ensure that the dimensions meet the requirements.

[0020] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0021] 1. The laminated glass automatic sheet sorting system designed by the present invention uses advanced high-resolution image acquisition technology and intelligent algorithms to comprehensively detect laminated glass. Specifically, it includes the following steps: First, use X-ray scanning technology to collect images of glass raw materials and input them into the MES system to accurately record the specifications of the glass; Second, according to the order requirements, the system automatically retrieves and displays eligible glass models; Subsequently, transmit the selected results to the laminated film cutting process to accurately cut the laminated film; Then, perform edge grinding, cleaning, and drying on the glass to ensure that the surface has no burrs, dirt, and water stains; Then, evenly lay the laminated film between the glass sheets and perform lamination treatment through an initial laminator and an autoclave to ensure that the laminated film is thoroughly bonded to the glass sheets; Finally, through inspection and trimming, ensure that the glass dimensions and quality meet the requirements.

[0022] 2. The present invention uses high-precision detection methods such as the Canny edge detection algorithm, laser interferometry, Fourier transform analysis, edge detection and morphological analysis, photoelastic effect detection, and spectrophotometer measurement to comprehensively analyze the edge state, flatness, surface cleanliness, internal stress distribution, optical properties, etc. of the glass, significantly improving the detection accuracy and quality control level. At the same time, use machine learning algorithms (such as support vector machine SVM) to intelligently classify the detection data, and classify the glass into qualified products, slightly defective products, or unqualified products, further improving the automation and intelligence level of the production process.

[0023] 3. The method of the present invention can efficiently and accurately complete the automatic sheet sorting of laminated glass, reduce manual operation errors, improve production efficiency and product quality, and meet the requirements of modern industrial production for high precision and high quality. Brief Description of the Drawings

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other relevant drawings can also be obtained based on these drawings.

[0025] Figure 1 is the method flow chart of the present invention;

[0026] Figure 2 is the edge contour diagram extracted by the Canny algorithm of the present invention;

[0027] Figure 3 is the Fourier transform analysis feature map of the present invention;

[0028] Figure 4 is the infrared spectrum diagram of the glass of the present invention;

[0029] Figure 5 is the stress-strain curve diagram of the glass of the present invention;

[0030] Figure 6 is the image analysis process diagram of the present invention. Detailed implementation manners

[0031] To make the objectives, technical solutions and advantages of the present invention clearer, the following will further describe the implementation manners of the present invention in detail with reference to the accompanying drawings.

[0032] Embodiment

[0033] A method for allocating sheets in an automatic sheet sorting system applicable to laminated glass.

[0034] Please refer to Figure 1 is the flowchart of a method for allocating sheets in an automatic sheet sorting system applicable to laminated glass provided by an embodiment of the present invention.

[0035] The present invention provides a method for allocating sheets in an automatic sheet sorting system applicable to laminated glass. Through multi-step precise detection and dynamic adjustment, the quality and processing efficiency of laminated glass are ensured. First is the glass preparation stage S1: The glass raw materials are detected by X-ray scanning, and the specifications of the glass (such as thickness and size) are entered into the MES (Manufacturing Execution System). This system is used for data calling and process control in subsequent steps to ensure that each piece of glass can be accurately identified and processed during the processing.

[0036] After the glass enters the processing line, S101: Preliminary scanning and classification. The thickness and size of the glass are determined by scanning, and the data is entered into the database for subsequent processing. The system uses the Canny edge detection algorithm to identify the edges of the glass in the X-ray scanning image, specifically as shown in Equation (1) - Equation (2);

[0037] Equation (1)

[0038] Equation (2)

[0039] wherein, is the image pixel value, is the gradient image, is the area of the region, is the edge length;

[0040] Next, the flatness, edge integrity, and surface cleanliness of the glass are detected. S102: Flatness and surface detection. The flatness of the glass is detected, and the edge integrity and surface cleanliness are inspected, mainly detecting oil stains, dirt, or other surface contaminants. The flatness, edge integrity, and surface cleanliness of the glass are detected using laser interferometry and smoothing algorithms, as shown in Equations (3)-(5);

[0041] Equation (3)

[0042] Equation (4)

[0043] Equation (5)

[0044] where, is the laser measurement image, is the surface image, and Threshold is the threshold for detecting stains;

[0045] S103: Optical quality detection. The optical quality of the glass is detected, with a focus on detecting defects that affect aesthetics, such as bubbles, ripples, and impurities. In the optical quality detection step, a professional detection device is used to scan the glass surface to find defects that affect aesthetics, such as bubbles, ripples, impurities, etc. This step ensures that the appearance quality of the glass meets the requirements, especially for the high standards required in applications such as building facades and photovoltaic glass. Fourier transform is used to analyze the optical image to detect bubbles, ripples, and impurities in the glass, as shown in Equation (6);

[0046] Equation (6)

[0047] where, through Fourier transform the optical image is converted to the frequency domain, and the defects will exhibit characteristic patterns in the frequency domain; the formula is used to detect these characteristic patterns to identify defects;

[0048] S104: Surface defect detection. Scratches and stains on the glass surface are inspected, which directly affect the appearance quality of the glass. Through surface defect detection, the scratches and stains on the glass are mainly inspected, and these defects will directly affect the appearance quality of the glass. This detection uses edge detection and morphological analysis algorithms to detect scratches and stains on the glass surface, as shown in Equations (7)-(8);

[0049] Equation (7)

[0050] Equation (8)

[0051] is the gradient of the surface image, used to identify the intensity changes in the image that may represent scratches; in the formula, represents morphological opening or closing operations, and Structuring Element is the structural element for morphological operations;

[0052] Uneven internal stress distribution may cause the glass to spontaneously break during processing or use. Therefore, this step ensures that the internal stress of the glass is within a reasonable range to prevent future safety hazards. S105: Internal stress detection, using equipment such as polarizing microscopes to detect the internal stress distribution of the glass, preventing the glass from spontaneously breaking due to uneven stress during processing or use. Utilize the photoelastic effect and polarizing microscope images to detect the internal stress distribution of the glass, specifically as shown in Equation (9);

[0053] Equation (9)

[0054] wherein, the formula calculates the light intensity under the polarizing microscope and the angle with the optical axis relationship, thereby inferring the internal stress distribution of the glass;

[0055] To ensure that the light transmittance and optical properties of the glass meet the standards, use optical instruments to conduct detailed measurements on the glass. These properties are difficult to judge by visual inspection, especially in applications with extremely high requirements, such as building facades and photovoltaic glass. S106: Detection of light transmittance and optical properties of the glass, using optical instruments to measure the light transmittance and optical properties of the glass to ensure compliance with the requirements of high-standard applications (such as building facades or photovoltaic glass). Use a spectrophotometer to measure the light transmittance and other optical properties of the glass, specifically as shown in Equation (10) - Equation (11);

[0056] Equation (10)

[0057] Equation (11)

[0058] wherein, the light transmittance is calculated by the ratio of the incident light intensity and the transmitted light intensity , is the wavelength of light; the formula combines the light transmittance at different wavelengths and weights to evaluate the overall optical properties of the glass;

[0059] After completing all detections, the system classifies the glass into qualified products and unqualified products according to the obtained data. Qualified products are further divided into perfect products and slightly defective products. Slightly defective products can be used for applications with lower appearance requirements, while perfect products are used for high-standard applications. S107: Classification and grading, according to the above detection results, classify the glass into qualified products and unqualified products, and further classify the qualified products into slightly defective products and perfect products.

[0060] Using machine learning algorithms such as support vector machines (SVM) or decision trees based on the detected data, classify the glass into qualified products, slightly defective products, or unqualified products, as shown in Equation (12);

[0061] Equation (12)

[0062] Among them, use the support vector machine (SVM) algorithm to classify the glass. The input feature vector f includes thickness, flatness, optical quality, surface scratch stress, light transmittance, etc. The SVM model is used to determine the category of the glass. The algorithms and formulas for each step are specifically designed to optimize the detection process of the automatic glass sorting system, ensuring the accuracy and efficiency of each detection process.

[0063] According to the specific requirements of the customer order, input the order information into the MES system. The system automatically retrieves the glass models that match the order requirements in the database and displays them on the operator's screen for selection. S2: Order input and matching, input the order requirements into the system, and the system retrieves data according to the order requirements and displays the glass models that meet the requirements.

[0064] After the selection is completed, the system transfers the glass model and order requirements to the laminated film cutting unit. The laminated film cutting process is dynamically adjusted according to the glass specifications and order requirements entered into the MES system to ensure that the cut laminated film precisely matches the glass sheet in shape and size. Before cutting, the system also performs a secondary scan of the glass sheet's shape and size to further optimize the cutting accuracy of the laminated film. S3: Laminated film cutting, after selecting the glass that meets the order requirements, transfer the result to the laminated film cutting process and start cutting the laminated film according to the glass and order requirements.

[0065] The cut glass will enter the edge grinding process to remove the burrs on the glass edge and perform grinding treatment on the edge. This step ensures that the glass edge is smooth and burr-free, improving the safety and processing quality of the glass. S4: Edge grinding treatment, perform edge grinding on the cut glass to remove burrs.

[0066] The edge-ground glass sheet will enter the cleaning machine for cleaning, using deionized water and special cleaning agents to remove surface dirt and dust. After cleaning, the glass sheet undergoes a drying process to ensure that the surface is free of water stains and impurities, reaching the best clean state and preparing for the subsequent laying of the laminated film. S5: Cleaning and drying, send the edge-ground glass into the cleaning machine, use deionized water and cleaning agents to remove surface dirt and dust; after cleaning, the glass sheet passes through the drying section to ensure that the surface is free of water stains and impurities.

[0067] Place two cleaned and dried glass sheets on the workbench, and lay a layer of cut interlayer film (PVB film) between the two glasses. This step ensures that the interlayer film is evenly laid without wrinkles and bubbles. S6: Laying the interlayer film, place the two cleaned and dried glasses on the workbench, and lay a layer of cut interlayer film (PVB film) between the two glasses, ensuring that the film is evenly covered without wrinkles and bubbles.

[0068] In the initial lamination step, place the glass sheets with the interlayer film laid on them into the initial laminator, and preliminarily laminate the glass and the interlayer film together through hot pressing and vacuum degassing. The initial lamination ensures that the interlayer film is tightly attached to the glass sheets, removes the bubbles in the interlayer, and lays the foundation for the subsequent autoclave treatment. S7: Initial lamination, place the glass sheets with the interlayer film laid on them into the initial laminator, and preliminarily laminate the glass and the interlayer film together through hot pressing and vacuum degassing, ensuring that the film is tightly attached to the glass and removing the bubbles in the interlayer.

[0069] Send the glass sheets after initial lamination into the autoclave, and through high temperature and high pressure treatment, make the interlayer film and the glass sheets completely bonded. The autoclave treatment is usually carried out in an environment of 130 - 145 °C and 10 - 15 atmospheres for 1 - 2 hours to ensure that the final laminated glass has high strength and high quality. S8: Autoclave, send the glass sheets after initial lamination into the autoclave, and completely bond the interlayer film and the glass through high temperature and high pressure; the autoclave treatment is usually carried out at 130 - 145 °C and 10 - 15 atmospheres for 1 - 2 hours.

[0070] After the laminated glass after autoclave treatment is cooled, conduct the final appearance and quality inspection to ensure that there are no defects such as bubbles, impurities, and cracks. Trim the edges of the glass to ensure that the glass size meets the requirements and reaches the quality standards of the customers. S9: Inspection and trimming, after the glass after autoclave treatment is cooled, conduct the appearance and quality inspection to ensure that there are no defects such as bubbles, impurities, and cracks, and trim the edges to ensure that the size meets the requirements.

[0071] The above description is only the preferred embodiment of the present invention and is not used to limit the present invention. For those skilled in the art, there are various changes and modifications to the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for allocating glass sheets in an automatic glass laminating system applicable to laminated glass, characterized in that, It includes the following steps: S1: Use X-ray scanning to detect the glass raw material, and input the thickness and size of the glass into the manufacturing execution system; S2: Order input and matching, and the system retrieves data according to the order requirements; S3: Laminating film cutting, start cutting the laminating film according to the glass and order requirements; S4: Edge grinding treatment, grind the edges of the cut glass to remove burrs; S5: Cleaning and drying, remove surface dirt and dust and ensure that the surface is free of water stains and impurities; S6: Laminating film laying, lay a layer of cut PVB film between two pieces of glass; S7: Initial lamination, preliminarily laminate the glass and the laminating film together through hot pressing and vacuum degassing; S8: Autoclave, make the laminating film and the glass bond completely through high temperature and high pressure; S9: Inspection and trimming, conduct appearance and quality inspections to ensure that the dimensions meet the requirements; In the said S1, the processing method of the assembled glass is as follows: S101: Preliminary scanning and classification, determine the thickness and size of the glass by scanning, and input the data into the database for subsequent processing; S102: Flatness and surface inspection, conduct flatness inspection on the glass, check the edge integrity and surface cleanliness, mainly detect oil stains, dirt or other surface contaminants; S103: Optical quality inspection, detect the optical quality of the glass, and focus on detecting defects that affect the appearance; S104: Surface defect inspection, check the scratches and stains on the glass surface, which directly affect the appearance quality of the glass; S105: Internal stress inspection, use a polarizing microscope to detect the internal stress distribution of the glass, and prevent the glass from spontaneously cracking due to uneven stress during processing or use; S106: Transmittance and optical performance inspection of the glass, use optical instruments to measure the transmittance and optical performance of the glass to ensure that it meets the requirements of high-standard applications; S107: Classification and grading, according to the above inspection results, classify the glass into qualified products and unqualified products, and further classify the qualified products into slightly defective products and perfect products; In step S1, the size analysis of the glass is specifically carried out according to the following steps: S101: Use the Canny edge detection algorithm to identify the edges of the glass in the X-ray scanning image, specifically as shown in formula (1) - formula (2); Formula (1); Formula (2); Among them, is the image pixel value, is the gradient image, is the area of the region, is the edge length; In step S1, the size analysis of the glass is specifically carried out according to the following steps: S107: Use machine learning algorithms according to the detected data, use support vector machines or decision trees to classify the glass into qualified products, slightly defective products or unqualified products, specifically as shown in formula (12); Formula (12); Among them, when using the support vector machine algorithm to classify the glass, the input feature vector f includes thickness, flatness, optical quality, surface scratch stress, transmittance, and determine the category of the glass through the SVM model. The algorithms and formulas for each step are specifically designed to optimize the detection process of the glass automatic sheet sorting system to ensure the accuracy and efficiency of each detection process; In the said S3 step, the cutting process of the laminating film is dynamically adjusted according to the glass specifications and order requirements entered into the MES system to ensure that the cut laminating film precisely matches the glass sheet in shape and size.

2. The method for allocating glass sheets in an automatic glass laminating system for laminated glass according to claim 1, wherein :In step S1, the size analysis of the glass is specifically carried out according to the following steps: S102: Detect the flatness, edge integrity, and surface cleanliness of the glass using laser interferometry and smoothing algorithms, as shown in Equations (3)-(5); Formula (3); Formula (4); Formula (5); Among them, is the laser measurement image, is the surface image, and Threshold is the threshold for detecting stains.

3. A method for allocating glass sheets in an automatic glass laminating system for laminated glass according to claim 1, characterized in that : In step S1, the dimensional analysis of the glass is performed specifically according to the following steps: S103: Analyze the optical image using Fourier transform to detect bubbles, ripples, and impurities in the glass, as shown in Equation (6); Formula (6); Among them, through Fourier transform the optical image is transformed into the frequency domain, and defects will present characteristic patterns in the frequency domain; formulas are used to detect these characteristic patterns to identify defects.

4. A method for matching glass in an automatic glass laminating system according to claim 1, characterized in that : In step S1, the dimensional analysis of the glass is performed specifically according to the following steps: S104: Detect scratches and stains on the glass surface using edge detection and morphological analysis algorithms, as shown in Equations (7)-(8); Formula (7); Formula (8); is the gradient of the surface image, used to identify the intensity changes in the image that may represent scratches; in the formula, represents morphological opening or closing operations, and Structuring Element is the structural element of the morphological operation.

5. A method for allocating glass for an automatic glass laminating system according to claim 1, characterized in that : In step S1, the dimensional analysis of the glass is performed specifically according to the following steps: S106: Measure the light transmittance and other optical properties of the glass using a spectrophotometer, as shown in Equations (10)-(11); Formula (10); Formula (11); wherein, the light transmittance is calculated by the ratio of the incident light intensity and the transmitted light intensity ; is the wavelength of light; the formula combines the light transmittance at different wavelengths and weights to evaluate the overall optical performance of the glass.

Images