A bending process for curved glass

Abstract

The application belongs to the technical field of curved glass manufacturing, and proposes a bending forming process of curved glass. The first extrusion die correction feature is obtained by performing feature processing on the first liquid viscosity of the first bending forming glass after high-temperature processing, the first thermal expansion coefficient of the glass liquid, and the first aging parameter of the extrusion die. A curved glass bending forming hot-pressing control model is constructed according to the first extrusion die correction feature and the first extrusion die control method set by the corresponding staff at this time. The second extrusion die correction feature calculated by inputting the second bending forming glass to be hot-pressed and the related features of the die is input into the curved glass bending forming hot-pressing control model to obtain the second extrusion die control method of the second bending forming glass. The working parameters of the extrusion die are controlled according to the second extrusion die control method to realize the adjustment of the glass shape, so that the curved glass with higher shape complexity and more accurate forming is obtained.

Description

Technical Field

[0001] This invention belongs to the field of curved glass manufacturing technology, and particularly relates to a bending and forming process for curved glass. Background Technology

[0002] With the development of glass technology and the improvement of aesthetics, the demand for various irregularly shaped glass in automobiles, home appliances and building facades is increasing day by day. In addition to conventional single-curved and double-curved glass, the need for more complex 3D composite curvature glass is also increasing.

[0003] Currently, in the hot bending industry, domestic and foreign manufacturers feed molds containing raw glass sheets into a hot bending furnace. The furnace heats the glass until it softens, and the glass's own weight causes it to conform to the mold, completing the forming process. After cooling to ambient temperature according to a cooling curve, the hot-bent glass is removed. This method is energy-intensive, results in high product costs, and cannot guarantee the repeatability of finished products. In the tempering industry, a common method for processing curved glass is to use a combination of lower air grid curvature and upper air grid light pressure to assist in forming. After the glass is formed, it undergoes rapid cooling and blowing to become tempered glass.

[0004] Another common method is to extrude the glass using upper and lower molds, then quickly transport the formed glass to the blowing area for tempering. However, the parameter design in traditional upper and lower mold extrusion molding usually uses fixed parameters or is manually designed and adjusted according to product needs, consuming a lot of expert verification time, and the accuracy of parameter design is relatively low. Therefore, it is particularly important to provide a bending forming process and system for curved glass to improve the variability of the obtained glass shape, thereby improving the accuracy of the formed glass and the precision of the finished curved glass.

[0005] Therefore, the existing technology has the following problems:

[0006] First, how to determine the upper and lower mold parameters for the hot bending process based on the state of the glass and the actual state of the mold to adjust the glass shape, thereby increasing the complexity of the obtained glass shape and improving the accuracy of the formed glass. Second, how to adopt methods that assist or even reduce labor costs, and how to improve the stability of the formed glass by using a large-scale glass hot bending forming control model that is adapted to control the changes in mold parameters, thereby improving the accuracy and reliability of the formed glass, increasing the product precision of the formed glass, and realizing the high-quality production of curved glass products. Summary of the Invention

[0007] To address the aforementioned technical problems, this invention proposes a bending and forming process for curved glass.

[0008] In a first aspect of the invention, a bending forming process for curved glass is provided, characterized in that the method comprises:

[0009] By performing feature processing on the first liquid viscosity, the first coefficient of thermal expansion, and the first aging parameters of the extrusion die obtained after the first curved glass is processed at high temperature, the first extrusion die correction feature is obtained.

[0010] Obtain a first extrusion die control method set for the first bending glass employee;

[0011] A hot pressing control model for curved glass bending forming is constructed based on the correction features of the first extrusion die and the corresponding control method of the first extrusion die.

[0012] By performing feature processing on the second liquid viscosity, second thermal expansion coefficient, and second aging parameters of the extrusion die obtained after the second curved glass is processed at high temperature, the modified features of the second extrusion die are obtained.

[0013] The second extrusion die correction feature is input into the curved glass bending forming hot pressing control model to obtain the second extrusion die control method for the second curved glass. The working parameters of the extrusion die are controlled according to the second extrusion die control method to achieve the adjustment of the glass shape.

[0014] Furthermore, the first liquid viscosity or the second liquid viscosity is calculated from the internal resistance of the glass after it is heated to form a molten glass, the contact area between parallel liquids, and the velocity gradient of the horizontal flow perpendicular to the liquid surface.

[0015] Furthermore, the first or second coefficient of thermal expansion is obtained by processing with a transition temperature and an expansion softening temperature.

[0016] Furthermore, the extrusion die is a graphite die.

[0017] Furthermore, the first aging parameter or the second aging parameter is obtained by processing the hardness, density, and number of uses of the graphite mold.

[0018] Furthermore, the feature processing of the first liquid viscosity, first coefficient of thermal expansion, and first aging parameters of the extrusion die calculated after the first curved glass is performed by laterally splicing the first liquid viscosity, the first coefficient of thermal expansion, and the first aging parameters of the extrusion die; the feature processing of the second liquid viscosity, second coefficient of thermal expansion, and second aging parameters of the extrusion die calculated after the second curved glass is performed by laterally splicing the second liquid viscosity, the second coefficient of thermal expansion, and the second aging parameters of the extrusion die.

[0019] Furthermore, the hot-pressing control model for curved glass bending is based on an improved neural network model using liquid viscosity and thermal expansion coefficient.

[0020] A curved glass bending forming system is also provided, including a curved glass high-temperature heating parameter processing module, an extrusion die parameter acquisition and processing module, a curved glass control feature processing module, a curved glass bending forming hot pressing control model construction module, and an extrusion module control module, characterized in that:

[0021] The curved glass high-temperature heating parameter processing module is used to collect the internal resistance of the glass melt after high temperature, the contact area between parallel liquids, and the velocity gradient of the horizontal flow along the direction perpendicular to the liquid surface, and to process and obtain the first liquid viscosity of the first curved glass, and also to process and obtain the second liquid viscosity of the second curved glass.

[0022] Furthermore, the first or second coefficient of thermal expansion is obtained by collecting the transition temperature and expansion softening temperature of the glass to be hot-pressed and processed.

[0023] The extrusion die parameter acquisition and processing module acquires the hardness, density, and number of uses of the graphite die, and processes them to obtain the first aging parameter or the second aging parameter.

[0024] The curved glass control feature processing module: by performing feature processing on the first liquid viscosity, the first thermal expansion coefficient, and the first aging parameter obtained from the extrusion die parameter acquisition processing module of the curved glass high-temperature heating parameter processing module, the first extrusion die correction feature is obtained;

[0025] Furthermore, by performing feature processing on the second liquid viscosity, the second thermal expansion coefficient, and the second aging parameters of the extrusion die parameter acquisition and processing module, a second extrusion die correction feature is obtained.

[0026] The curved glass bending and hot pressing control model construction module: stores the first extrusion mold control method set by the employee, receives the first extrusion mold correction feature from the curved glass control feature processing module, and constructs the curved glass bending and hot pressing control model through the first extrusion mold correction feature and the first extrusion mold control method;

[0027] The extrusion module control module stores the first extrusion mold control method and also processes the second extrusion mold correction features obtained from the curved glass control feature processing module by calling the curved glass bending and hot pressing control model construction module to obtain the second extrusion mold control method, and controls the working parameters of the extrusion mold according to the second extrusion mold control method.

[0028] Furthermore, the hot-pressing control model for curved glass bending is based on an improved neural network model using liquid viscosity and thermal expansion coefficient.

[0029] This invention determines the adjustment of upper and lower mold parameters for the hot bending process based on the liquid state parameters of the glass after high-temperature curing and the aging state of the mold. This increases the complexity of the obtained glass shape and improves the accuracy of the formed glass. Secondly, it assists in or even reduces labor costs by using a glass hot bending forming control parameter correction neural network model adapted to control mold parameter changes. This allows for adaptive adjustment of the extrusion mold's working parameters, thereby improving the stability of the formed glass. This, in turn, helps improve the accuracy and reliability of the formed glass, increases the product precision of the formed glass, and enables the production of high-quality curved glass products.

[0030] Further embodiments and improvements of the present invention will be described in conjunction with the accompanying drawings and specific examples. Attached Figure Description

[0031] Figure 1 This is a flow chart of a bending and forming process for curved glass according to the present invention;

[0032] Figure 2 This is a schematic diagram of a curved glass bending and forming system according to the present invention;

[0033] Figure 3 This is a schematic diagram of hot pressing forming in this invention;

[0034] Figure 4 This is a schematic diagram of the neural network model in this invention;

[0035] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0036] The invention will now be further described in conjunction with the accompanying drawings and specific embodiments.

[0037] In a first aspect, the invention provides a bending process for curved glass. The curved glass in this invention generally refers to automotive curved glass.

[0038] In a first aspect of the invention, a bending forming process for curved glass is provided, characterized in that the method comprises:

[0039] By performing feature processing on the first liquid viscosity, the first coefficient of thermal expansion, and the first aging parameters of the extrusion die obtained after the first curved glass is processed at high temperature, the first extrusion die correction feature is obtained.

[0040] Obtain a first extrusion die control method set for the first bending glass employee;

[0041] A hot pressing control model for curved glass bending forming is constructed based on the correction features of the first extrusion die and the corresponding control method of the first extrusion die.

[0042] By performing feature processing on the second liquid viscosity, second thermal expansion coefficient, and second aging parameters of the extrusion die obtained after the second curved glass is processed at high temperature, the modified features of the second extrusion die are obtained.

[0043] The second extrusion die correction feature is input into the curved glass bending forming hot pressing control model to obtain the second extrusion die control method for the second curved glass. The working parameters of the extrusion die are controlled according to the second extrusion die control method to achieve the adjustment of the glass shape.

[0044] Furthermore, the first liquid viscosity or the second liquid viscosity is calculated from the internal resistance of the glass after it has been heated to form molten glass, the contact area between parallel liquids, and the velocity gradient along the direction perpendicular to the liquid surface. The calculation formula is as follows:

[0045]

[0046] In the formula, σ is the viscosity of the first liquid or the viscosity of the second liquid, F is the internal resistance, and S... p This represents the contact area between parallel liquids. It represents the reciprocal of the velocity gradient of horizontal flow along the direction perpendicular to the liquid surface.

[0047] Furthermore, the first coefficient of thermal expansion or the second coefficient of thermal expansion is calculated using the transition temperature and the expansion softening temperature:

[0048]

[0049] In the formula, α is the first or second coefficient of thermal expansion, V is the volume of glass, and T is the volumetric thermal expansion coefficient. c To change the temperature, T p This is the expansion and softening temperature. This indicates that the temperature is below the transition temperature T. c The value at time Greater than or equal to the transition temperature T c The value at time

[0050] Furthermore, the extrusion die is a graphite die.

[0051] Furthermore, the first aging parameter or the second aging parameter is obtained by processing the hardness, density, and number of uses of the graphite mold;

[0052]

[0053] In the formula, L G Here, ρ is the density of the graphite mold, H is the hardness of the graphite mold, and n is the aging parameter. u n represents the number of times the graphite mold has been used in glass bending and pressing. t This indicates the maximum number of times a graphite mold can be used.

[0054] Furthermore, the feature processing of the first liquid viscosity, first coefficient of thermal expansion, and first aging parameters of the extrusion die calculated after the first curved glass is performed by laterally splicing the first liquid viscosity, the first coefficient of thermal expansion, and the first aging parameters of the extrusion die; the feature processing of the second liquid viscosity, second coefficient of thermal expansion, and second aging parameters of the extrusion die calculated after the second curved glass is performed by laterally splicing the second liquid viscosity, the second coefficient of thermal expansion, and the second aging parameters of the extrusion die.

[0055] Furthermore, the hot-pressing control model for curved glass bending is based on an improved neural network model using liquid viscosity and thermal expansion coefficient.

[0056] Furthermore, the activation function calculation formula for the improved neural network model based on liquid viscosity and thermal expansion coefficient is as follows:

[0057]

[0058] Where F(X) is the activation function value, σ is the first liquid viscosity or the second liquid viscosity, α is the first thermal expansion coefficient or the second thermal expansion coefficient, and X is the first extrusion die correction feature or the second extrusion die correction feature obtained by weighting and biasing the neurons.

[0059] Those skilled in the art, when utilizing neural network models, know that the selection of activation functions can delinearize the corresponding input feature vectors. Therefore, choosing an appropriate activation function has a significant impact on the classification ability of the neural network model, which will not be elaborated further here. In this embodiment, a neural network model improved based on liquid viscosity and thermal expansion coefficient is used to optimize the input feature vectors for either the first extrusion die correction feature or the second extrusion die correction feature in the production scenario of curved glass, thereby obtaining superior processing performance in the model scenario.

[0060] A curved glass bending forming system is also provided, including a curved glass high-temperature heating parameter processing module, an extrusion die parameter acquisition and processing module, a curved glass control feature processing module, a curved glass bending forming hot pressing control model construction module, and an extrusion module control module, characterized in that:

[0061] The curved glass high-temperature heating parameter processing module is used to collect the internal resistance of the glass melt after high temperature, the contact area between parallel liquids, and the velocity gradient of the horizontal flow along the direction perpendicular to the liquid surface, and to process and obtain the first liquid viscosity of the first curved glass, and also to process and obtain the second liquid viscosity of the second curved glass.

[0062] Furthermore, the first or second coefficient of thermal expansion is obtained by collecting the transition temperature and expansion softening temperature of the glass to be hot-pressed and processed.

[0063] The extrusion die parameter acquisition and processing module acquires the hardness, density, and number of uses of the graphite die, and processes them to obtain the first aging parameter or the second aging parameter.

[0064] The curved glass control feature processing module: by performing feature processing on the first liquid viscosity, the first thermal expansion coefficient, and the first aging parameter obtained from the extrusion die parameter acquisition processing module of the curved glass high-temperature heating parameter processing module, the first extrusion die correction feature is obtained;

[0065] Furthermore, by performing feature processing on the second liquid viscosity, the second thermal expansion coefficient, and the second aging parameters of the extrusion die parameter acquisition and processing module, a second extrusion die correction feature is obtained.

[0066] The curved glass bending and hot pressing control model construction module: stores the first extrusion mold control method set by the employee, receives the first extrusion mold correction feature from the curved glass control feature processing module, and constructs the curved glass bending and hot pressing control model through the first extrusion mold correction feature and the first extrusion mold control method;

[0067] The extrusion module control module stores the first extrusion mold control method and also processes the second extrusion mold correction features obtained from the curved glass control feature processing module by calling the curved glass bending and hot pressing control model construction module to obtain the second extrusion mold control method, and controls the working parameters of the extrusion mold according to the second extrusion mold control method.

[0068] In this example, the first or second extrusion die control method includes the control of the temperature and pressure of the extrusion die. For example, the pressure controlled by the extrusion die is 40 MPa and the temperature is 550°C. Experienced employees set the type of extrusion die control method based on the pressure and temperature. This setting is based on the experience of those skilled in the art and will not be elaborated here. That is, the neural network model improved based on liquid viscosity and thermal expansion coefficient in this invention outputs a first or second extrusion die control method mapped to two extrusion die operating parameters: pressure and temperature. In this invention, pressure refers to the pressure of the upper die.

[0069] Furthermore, the hot-pressing control model for curved glass bending is based on an improved neural network model using liquid viscosity and thermal expansion coefficient.

[0070] The activation function calculation formula for the improved neural network model based on liquid viscosity and thermal expansion coefficient is shown below:

[0071]

[0072] Where F(X) is the activation function value, σ is the liquid viscosity, α is the coefficient of thermal expansion, and X is the first extrusion die correction feature or the second extrusion die correction feature obtained by weighting and biasing the neurons.

[0073] This invention determines the adjustment of upper and lower mold parameters for the hot bending process based on the liquid state parameters of the glass after high-temperature curing and the aging state of the mold. This increases the complexity of the obtained glass shape and improves the accuracy of the formed glass. Secondly, it assists in or even reduces labor costs by using a glass hot bending forming control parameter correction neural network model adapted to control mold parameter changes. This allows for adaptive adjustment of the extrusion mold's working parameters, thereby improving the stability of the formed glass. This, in turn, helps improve the accuracy and reliability of the formed glass, increases the product precision of the formed glass, and enables the production of high-quality curved glass products.

[0074] Of course, it is understood that each embodiment of the present invention can achieve one of the effects on its own, and the combination of multiple embodiments of the present invention can achieve all the above effects. However, it is not required that each embodiment of the present invention achieve all the above advantages and effects, because each embodiment of the present invention can constitute a separate technical solution and make one or more contributions to the prior art.

[0075] For any module structures not specifically defined in this invention, the existing technical specifications shall prevail. The existing technical specifications mentioned in the foregoing background and specific embodiments sections are considered part of this invention and are used to understand the meaning of certain technical features or parameters. The scope of protection of this invention is determined by the actual contents of the claims.

Claims

1. A process for bending forming a curved glass, characterized in that, The process comprises: characteristic processing of the first liquid viscosity, the first thermal expansion coefficient and the first aging parameter of the extrusion die calculated after high-temperature processing of the first curved glass forming glass to obtain a first extrusion die correction feature; obtaining a first extrusion die control method set by the employee for the first curved glass forming glass; constructing a curved glass bending forming hot-pressing control model according to the first extrusion die correction feature and the first extrusion die control method; characteristic processing of the second liquid viscosity, the second thermal expansion coefficient and the second aging parameter of the extrusion die calculated after high-temperature processing of the second curved glass forming glass to obtain a second extrusion die correction feature; inputting the second extrusion die correction feature into the curved glass bending forming hot-pressing control model to obtain a second extrusion die control method for the second curved glass forming glass, and controlling the working parameters of the extrusion die according to the second extrusion die control method to realize adjustment of the glass shape.

2. The curved glass bending forming process of claim 1, wherein: the first liquid viscosity or the second liquid viscosity is calculated from the internal resistance of the glass after high-temperature processing, the contact area between the parallel liquids, and the velocity gradient of the horizontal flow perpendicular to the liquid surface.

3. The curved glass bending forming process of claim 2, wherein: the first thermal expansion coefficient or the second thermal expansion coefficient is obtained by processing the transformation temperature and the expansion softening temperature.

4. The curved glass bending forming process of claim 1, wherein: the extrusion die is a graphite die.

5. The curved glass bending forming process of claim 4, wherein: the first aging parameter or the second aging parameter is obtained by processing the hardness, density and number of uses of the graphite die.

6. The curved glass bending forming process of claim 3, wherein: the characteristic processing of the first liquid viscosity, the first thermal expansion coefficient and the first aging parameter of the extrusion die calculated after high-temperature processing of the first curved glass forming glass is performed by transverse feature vector splicing of the first liquid viscosity, the first thermal expansion coefficient and the first aging parameter of the extrusion die; and the characteristic processing of the second liquid viscosity, the second thermal expansion coefficient and the second aging parameter of the extrusion die calculated after high-temperature processing of the second curved glass forming glass is performed by transverse feature vector splicing of the second liquid viscosity, the second thermal expansion coefficient and the second aging parameter of the extrusion die.

7. The curved glass bending forming process of claim 6, wherein: the curved glass bending forming hot-pressing control model adopts a neural network model improved based on liquid viscosity and thermal expansion coefficient.

8. The curved glass bending forming process of claim 7, wherein: The activation function calculation formula of the improved neural network model based on liquid viscosity and thermal expansion coefficient is as follows: wherein is the activation function value, is the first liquid viscosity or the second liquid viscosity, is the first thermal expansion coefficient or the second thermal expansion coefficient, is the first extrusion die correction feature or the second extrusion die correction feature passing through the weighted neuron plus the bias calculation.

Images