Preparation method of super-strong durable energy-saving glass

Abstract

The invention relates to the technical field of building glass, and particularly discloses a preparation method of super-strong durable energy-saving glass, which comprises the following specific steps: carrying out film removal treatment on the edge part of LOW-E glass; the LOW-E glass obtained after film removal treatment is cleaned, and dust, greasy dirt and other impurities left on the edges are removed; a PVB film is used as a substrate, and a bonding material is spliced to the periphery of the PVB film; feeding the spliced LOW-E glass, the film and the bonding material into a sheet combining machine for interlayer sheet combining; after the glass interlayer is laminated, the exhaust process is optimized, and residues of bubbles and water vapor in the glass interlayer are reduced; after the glass and the film are subjected to vacuum exhausting and preliminary bonding, the glass and the film enter a high-pressure kettle to be treated; and after the autoclave treatment is completed, cooling the glass interlayer. According to the preparation method, the sealing performance and durability of the glass are improved, and the long-term maintenance cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of architectural glass, and more specifically, to a preparation method of super-strong durable energy-saving glass. Background Art

[0002] In the prior art, LOW-E (low-emissivity) glass has been widely used in fields such as architecture, automobiles, and aviation because a metal or metal oxide film is coated on the glass surface. Its main advantages lie in low infrared transmittance, low emissivity, and relatively low heat transfer coefficient, effectively reducing heat exchange and energy loss. Therefore, it is widely used in energy-saving buildings and environmental protection fields, especially in building windows and curtain walls. However, with the increasingly wide application of the technology, some problems have emerged during the actual use of LOW-E laminated glass. Especially during long-term use, water vapor penetrates the edge of the glass, resulting in poor sealing between the glass and the interlayer material, thus causing phenomena such as delamination and long bubbles, affecting the aesthetics and service life of the glass. Currently, to address these problems, the prior art uses edge sealants or sealants to seal the glass and the interlayer material. These methods can improve the sealing to a certain extent and reduce water vapor penetration. However, these solutions are still difficult to maintain the sealing effect during long-term use, especially in a high-humidity environment, the durability of the sealing effect is poor, and the cost of sealants and edge sealants is relatively high. Therefore, the prior art has not effectively solved the problem of water vapor penetration at the edge of LOW-E laminated glass, resulting in a shortened glass life, and the existing sealing technology fails to meet the requirements of low cost and super-strong durability. Therefore, a new manufacturing technology is urgently needed to effectively solve these problems. Summary of the Invention

[0003] To overcome the above-mentioned defects of the prior art, the present invention provides a preparation method of super-strong durable energy-saving glass. By establishing a film layer removal control model to remove the film at the edge of LOW-E glass, controlling the film layer removal amount, using an automatic cleaning machine to remove impurities at the edge of the glass, splicing PVB films, optimizing the exhaust process of the glass interlayer to reduce the residual bubbles and water vapor, and performing autoclave treatment in stages to prevent water vapor penetration and delamination phenomena, so as to solve the problems proposed in the above background art.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] Step S1, perform film removal treatment on the edge of LOW-E glass.

[0006] Step S2, clean the LOW-E glass after film removal treatment to remove residual dust, oil stains, and other impurities at the edge.

[0007] Step S3, use PVB film as the base and splice the bonding material around the PVB film.

[0008] Step S4: Feed the assembled LOW-E glass, film, and bonding material into a laminator for laminating.

[0009] Step S5: After the glass laminating, optimize the exhaust process to reduce the residual air bubbles and water vapor inside the glass laminate.

[0010] Step S6: After the glass and film have undergone vacuum exhaust and completed preliminary bonding, they enter an autoclave for treatment.

[0011] Step S7: After completing the autoclave treatment, cool the glass laminate.

[0012] A method for preparing a super-strong durable energy-saving glass, comprising the following steps:

[0013] In the said Step S5, in order to achieve the optimal exhaust process, the final control target is expressed as an optimization problem: where t f is the end time of vacuum exhaust, P bubble (t) is the generation probability of air bubbles inside the glass laminate, w1 is the pressure deviation weight coefficient, P(t) is the instantaneous gas pressure inside the glass laminate at time t, P target is the target vacuum degree, w2 is the temperature deviation weight coefficient, T(t) is the temperature of the glass laminate at time t, T opt is the preset optimal temperature of the glass laminate, w3 is the weight coefficient of the water vapor removal efficiency, J w is the water vapor diffusion flux per unit time and per unit area.

[0014] As a further solution of the present invention, the gradient descent algorithm is adopted to optimize the exhaust process, reduce the residual air bubbles and water vapor inside the glass laminate, and adjust the pumping rate Q(t) and T(t) at each time step to minimize the loss function. The specific steps are as follows:

[0015] Step P1: Set the initial pumping rate Q(0) = Q max , set the initial temperature T(0) = T opt , and set the learning rate to η;

[0016] Step P2: Calculate the gradient of the loss function with respect to Q(t): Calculate the gradient of the loss function with respect to T(t): where L represents the loss function;

[0017] Step P3: Parameter update: where Q new represents the updated pumping rate, Q old represents the pumping rate before update, T newDenote the updated temperature as T old Denote the temperature before update;

[0018] Step P4: Update Q(t) and T(t) within each time step dt, and keep iterating in a loop. If the difference in the values of the loss function L between two consecutive iterations is less than the preset threshold ∈, it is considered that convergence has been achieved and the iteration stops.

[0019] As a further solution of the present invention, in step S5, during the vacuum exhaust process, the goal is to make the pressure drop to the target vacuum degree over time and reduce the generation of residual bubbles. The pressure change in the glass interlayer is described as: where V is the volume of the glass interlayer, Q(t) is the instantaneous pumping rate of the vacuum pump at time t, and it satisfies where Q max is the maximum pumping rate, ξ is the sensitivity coefficient of the pumping rate to the pressure change, is the sensitivity coefficient of the pumping rate to the temperature change. Define the generation probability P bubble (t) of the bubbles in the glass interlayer as a function of the residual gas concentration and the pressure change rate: C(t) is the residual gas concentration in the glass interlayer, k1 is the influence coefficient of the residual gas on bubble formation, k2 is the influence coefficient of the pressure change rate on bubble formation, is the instantaneous change rate of the internal pressure of the glass interlayer; Introduce Fick's diffusion law to calculate the water vapor diffusion rate inside the glass interlayer: where J w is the water vapor diffusion flux per unit time and per unit area, D w is the water vapor diffusion coefficient, C w is the water vapor concentration, and x is the water vapor diffusion path.

[0020] As a further solution of the present invention, in step S1, the edge of the LOW-E glass is subjected to film removal treatment, including the following specific contents: The LOW-E glass is made by a technology of coating a thin film on a glass substrate. The function of this thin film is to reduce the transfer of thermal energy and improve the energy-saving performance of the glass. However, the coating layer on the edge of the glass needs to be removed during the manufacturing process because the edge is a key area for bonding laminated glass. If these areas are not subjected to film removal treatment, the bonding effect between the glass and other materials will be greatly affected, and ultimately, the sealing performance between the glass and the film and the adhesive resin composition may be poor, resulting in water vapor penetration and the generation of bubbles, thereby reducing the service life and performance of the glass.

[0021] Debonding is carried out using a debonder. Removing too much film layer may cause damage to the glass surface or expose too much glass substrate, which will reduce the bonding effect at the glass edge and may affect the strength and durability of the glass in subsequent steps. Insufficient removal may result in the film layer remaining on the glass surface, affecting the bonding force between the bonding material and the glass, and thus affecting the sealing performance of the glass. A film layer removal control model is established to control the removal amount of the film layer. The calculation formula of the film layer removal control model is as follows: where d is the removal thickness of the film layer, is the instantaneous rate of film layer removal, v is the removal speed of the debonder, β is the exponential coefficient of the removal rate with respect to the removal speed, P′ is the pressure applied during the debonding process, θ is the angle of the debonder tool head, γ is the exponent of the removal rate with respect to the pressure, θ is the angle of the debonder tool head; f(θ) is the influence function of the debonder tool head angle, satisfying λ is the temperature influence coefficient; T′ is the ambient temperature; k is the material constant, representing the correction coefficient under the working conditions of the debonder; H is the film layer hardness; η is the exponent of the hardness, E is the elastic modulus of the glass substrate, μ is the friction coefficient between the film layer and the tool, and α is the exponent of the film layer removal.

[0022] As a further solution of the present invention, in step S2, the LOW-E glass after debonding treatment is cleaned to remove dust, oil and other impurities remaining at the edge, including the following specific contents: The LOW-E glass is cleaned using an automated glass cleaning machine. The glass cleaning machine uses multiple processes of high-pressure water flow, brushing and air drying, and can effectively remove dust, oil and other impurities on the glass surface. When using the glass cleaning machine, the water pressure should be moderate to avoid the impact of too high water pressure on the glass. Especially when the film layer of the LOW-E glass is thin, too high water pressure may damage the film layer.

[0023] During the cleaning process, a non-corrosive and low-temperature cleaning liquid is selected to ensure the cleaning effect while not having any negative impact on the glass surface. For some difficult-to-clean oil stains or organic matter residues, a small amount of surfactant can be used for auxiliary cleaning, but avoid using cleaning liquids with too strong acidity or alkalinity to avoid chemical corrosion of the surface coating layer of the glass, resulting in film layer degradation or reduced adhesion.

[0024] During the cleaning process, a soft cloth or cleaning brush can be used to gently brush the glass edge to remove impurities in cooperation with the cleaning liquid and water flow. The glass surface after cleaning is thoroughly dried to ensure that there are no water marks, residual cleaning liquid or impurities. The drying methods include air drying and heating drying. After cleaning, a warm air blower is used to heat and dry the glass. When heating and drying, the temperature is controlled at about 40°C, and the moisture evaporates rapidly with the blowing of the warm air.

[0025] As a further solution of the present invention, in step S3, using a PVB film as the substrate and splicing hot melt adhesive around the PVB film, the following specific steps are included: placing the cleaned and dried LOW-E glass on the operation platform, cutting the PVB film into an appropriate size, and aligning it with the glass surface for splicing. Refer to Figure 3 the schematic diagram shown. During the splicing process, within a range of 5 - 30 mm around the PVB film, a layer of adhesive material is evenly coated. The adhesive material is hot melt adhesive or an adhesive resin composition. The function of this layer of adhesive material is to firmly bond the PVB film to the surface of the LOW-E glass and provide additional sealing performance. The water vapor transmission rate of the used hot melt adhesive or adhesive resin composition is less than 0.8 g / m 2 ·d, and its softening temperature is between 100°C and 130°C. Such requirements ensure that the adhesive material can maintain its stability in high humidity or high temperature environments, avoiding bonding failure due to temperature changes or humidity fluctuations.

[0026] The accuracy and position of the PVB film splicing are inspected using a computer vision algorithm, and the splicing method is adjusted to ensure accurate alignment. The computer vision algorithm is YOLOv5, and the specific steps are as follows:

[0027] Step Y1, input the image of the film splicing into the YOLOv5 model, and the image undergoes preprocessing operations such as scaling, normalization, and color standardization.

[0028] Step Y2, YOLOv5 predicts the bounding box of each target through a regression problem, outputs the position and size of each film bounding box, and gives the confidence level and class probability of the target contained in the bounding box.

[0029] Step Y3, if Δx and Δy exceed the preset threshold, where Δx represents the horizontal deviation between the actual position and the target position of the film center point, and Δy represents the vertical deviation between the actual position and the target position of the film center point, that is, splicing deviation is detected, then calculate the new placement position. The calculation formula is: x1 = x0 + Δx, y1 = y0 + Δy, where x0 is the x-direction position of the current film center point, y0 is the y-direction position of the current film center point, x1 is the new x-direction position of the film center point, and y1 is the new y-direction position of the film center point.

[0030] As a further aspect of the present invention, in step S4, the assembled LOW-E glass, film, and adhesive material are fed into a laminator for laminating, which includes the following specific details: The laminating process is carried out in an environment with a temperature of 25 ± 5°C and a relative humidity of 25 ± 5%. This environmental condition ensures that the hot melt adhesive or adhesive resin composition works under the optimal curing conditions, effectively avoiding the instability of material properties caused by too low or too high temperatures. During the laminating process, the laminator applies pressure to ensure sufficient contact between the glass and the PVB film or adhesive resin composition, avoiding the inclusion of air bubbles. The pressure applied by the laminator is between 0.1 - 0.5 MPa, and the laminating time is about 30 minutes.

[0031] As a further aspect of the present invention, in step S6, after the glass and the film have undergone vacuum evacuation and completed preliminary bonding, they enter an autoclave for treatment, which includes the following specific details: By heating and pressurizing the glass and the film in a high-temperature and high-pressure environment, not only can the bonding strength between the film and the glass be further improved, but also the occurrence of water vapor penetration and delamination phenomena during the long-term use of the laminated glass can be effectively prevented. The autoclave treatment is divided into three stages. In the first stage, the temperature is controlled at 85°C, the pressure is set at 0.60 MPA, and the stabilization time is 15 - 20 minutes; in the second stage, the temperature is set at 100°C, the pressure is increased to 1.05 MPA, and the stabilization time is 2 minutes. At this time, the high-temperature and high-pressure environment of the autoclave promotes the cross-linking reaction between the glass and the film materials, making the contact between the film and the glass more uniform and stable, and further enhancing the bonding strength; in the third stage, the temperature is set at 135°C, the pressure is 1.30 MPA, and the stabilization time is 30 - 50 minutes. In this stage, the bonding between the glass and the film reaches the best state, and the overall performance of the laminated glass is also improved to the greatest extent.

[0032] As a further aspect of the present invention, in step S7, after the autoclave treatment is completed, the glass laminate is cooled, which includes the following specific details: The glass laminate is cooled in an environment with a temperature below 40°C. A gradual cooling method is adopted, and the environmental temperature is continuously adjusted during the temperature drop process, controlling the temperature difference not to exceed 5°C / minute to ensure uniform cooling of the glass and prevent the generation of thermal stress.

[0033] Technical effects and advantages of a preparation method for a super-strong durable energy-saving glass of the present invention: The present invention solves the problems of poor sealing performance, short lifespan, and high sealing cost existing in existing LOW-E laminated glass. During the preparation process, by establishing a film layer removal control model to remove the film at the edge of the LOW-E glass, the film layer removal amount is accurately controlled, which not only avoids damage to the glass surface but also ensures the subsequent bonding effect; an automatic cleaning machine is used in combination with a suitable cleaning liquid and drying method to remove impurities at the edge of the glass while protecting the coating layer on the glass surface. A bonding material with specific properties is selected and the PVB film is spliced with the aid of a computer vision algorithm, ensuring the accurate splicing and firm bonding of the film and the glass, and the additional sealing performance also helps to reduce water vapor penetration. During lamination, the temperature, humidity environment, and pressure are controlled, the exhaust process is optimized, and the residual bubbles and water vapor are reduced, improving the sealing performance of the glass. The autoclave treatment is carried out in stages, enhancing the bonding strength between the film and the glass, effectively preventing water vapor penetration and delamination, and improving the overall performance of the glass. When cooling, the temperature difference is controlled by the step-by-step cooling method to avoid the generation of thermal stress. Compared with the prior art, the preparation method of the present invention significantly improves the sealing performance and durability of the glass, reduces the long-term maintenance cost, overcomes the defect of poor effect of traditional sealing technology in high-humidity environments, ensures the energy-saving performance of the glass, and extends the service life of the glass. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a flowchart of a preparation method for a super-strong durable energy-saving glass of the present invention.

[0035] Figure 2 It is a schematic structural diagram of a curve graph showing the relationship between the film layer thickness and the removal rate in the film layer removal control model of the present invention.

[0036] Figure 3 It is a schematic diagram of the bonding material spliced around the PVB film of the present invention.

[0037] Figure 4 It is a schematic diagram of a confusion matrix generated during the detection of the YOLOv5 model of the present invention.

[0038] In the figure: True Negative represents the number of samples correctly predicted as negative classes by the YOLOv5 model, False Positive represents the number of samples where the YOLOv5 model wrongly predicts negative classes as positive classes, False Negative represents the number of samples where the YOLOv5 model wrongly predicts positive classes as negative classes, and True Positive represents the number of samples correctly predicted as positive classes by the YOLOv5 model. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0039] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0040] Embodiment 1

[0041] Referring to Figure 1 the flowchart shown, an embodiment of the present invention provides a method for preparing a super durable and energy-saving glass, which includes the following steps:

[0042] Step S1, perform defilming treatment on the edge of the LOW-E glass.

[0043] Step S2, clean the defilmed LOW-E glass to remove residual dust, oil stains and other impurities on the edge.

[0044] Step S3, use a PVB film as the base and splice the bonding material around the PVB film.

[0045] Step S4, send the spliced LOW-E glass, film and bonding material into a laminator for interlayer laminating.

[0046] Step S5, after the glass interlayer is laminated, optimize the exhaust process to reduce the residual bubbles and water vapor inside the glass interlayer.

[0047] Step S6, after the glass and the film undergo vacuum exhaust and complete preliminary bonding, enter an autoclave for treatment.

[0048] Step S7, after completing the autoclave treatment, perform a cooling treatment on the glass interlayer.

[0049] Further, performing defilming treatment on the edge of the LOW-E glass includes: The LOW-E glass is made by a technology of coating a thin film on a glass substrate, and the function of this thin film is to reduce the transfer of heat energy and improve the energy-saving performance of the glass. However, the edge coating layer of the glass needs to be removed during the manufacturing process because the edge is a key area for bonding laminated glass. If these areas are not subjected to defilming treatment, the bonding effect between the glass and other materials will be greatly affected, and ultimately it may lead to poor sealing between the glass and the film and the adhesive resin composition, resulting in water vapor penetration and the generation of bubbles, thereby reducing the service life and performance of the glass.

[0050] The film is removed by a film removal machine. Removing too much film layer may cause damage to the glass surface or expose too much glass substrate, which will reduce the bonding effect at the glass edge and may affect the strength and durability of the glass in subsequent steps. Insufficient removal may result in the film layer remaining on the glass surface, affecting the bonding force between the bonding material and the glass, and thus affecting the sealing performance of the glass. A film layer removal control model is established to control the removal amount of the film layer. The calculation formula of the film layer removal control model is: where d is the removal thickness of the film layer, is the instantaneous rate of film layer removal, v is the removal speed of the film removal machine, β is the exponential coefficient of the removal rate with respect to the removal speed, P′ is the pressure applied during the film removal process, θ is the angle of the cutter head of the film removal machine, γ is the exponent of the removal rate with respect to the pressure, θ is the angle of the cutter head of the film removal machine; f(θ) is the influence function of the cutter head angle of the film removal machine, satisfying λ is the temperature influence coefficient; T′ is the ambient temperature; k is the material constant, representing the correction coefficient under the working conditions of the film removal machine; H is the film layer hardness; η is the exponent of the hardness, E is the elastic modulus of the glass substrate, μ is the friction coefficient between the film layer and the tool, and α is the exponent of the film layer removal.

[0051] In this embodiment, referring to Figure 2 the shown curve graph, it shows the change trend of the removal rate with the change of the film layer thickness: when the film layer thickness is relatively thin, the removal rate is low; as the film layer thickness increases, the removal rate gradually increases and reaches a peak; after that, as the film layer thickness further increases, the removal rate begins to decline.

[0052] In this embodiment, by adjusting the working parameters such as the removal speed, the applied pressure, the cutter head angle, the ambient temperature, the removal exponent, and the film layer removal rate, the thickness of the film layer can be controlled between 5 and 30 millimeters. The following table shows the film layer removal experimental data under different parameter settings:

[0053] Table 1 Film Layer Removal Experimental Data Table

[0054]

[0055] Furthermore, in step S2, the LOW-E glass after the film removal treatment is cleaned to remove the dust, oil stains, and other impurities remaining on the edge, including: using an automated glass cleaning machine to clean the LOW-E glass. The glass cleaning machine uses multiple processes of high-pressure water flow, brushing, and air drying, and can effectively remove the dust, oil stains, and other impurities on the glass surface. When using the glass cleaning machine, the water pressure should be moderate to avoid the impact of too high water pressure on the glass. Especially when the film layer of the LOW-E glass is relatively thin, too high water pressure may damage the film layer.

[0056] During the cleaning process, a non-corrosive and low-temperature cleaning solution is selected to ensure the cleaning effect while not having any negative impact on the glass surface. For some stubborn oil stains or organic residues that are difficult to clean, a small amount of surfactant can be used for auxiliary cleaning, but avoid using cleaning solutions with too strong acidity or alkalinity to prevent chemical corrosion of the surface coating layer of the glass, which may lead to film layer degradation or reduced adhesion.

[0057] During the cleaning process, a soft cloth or cleaning brush can be used to gently brush the edges of the glass, and cooperate with the cleaning solution and water flow to remove impurities. After cleaning, the glass surface is thoroughly dried to ensure that there are no water marks, residual cleaning solution or impurities. Drying methods include air drying and heating drying. After cleaning, a warm air blower is used to heat-dry the glass. When heating and drying, the temperature is controlled at about 40°C, and the moisture evaporates rapidly with the blowing of the warm air.

[0058] Furthermore, in step S3, using a PVB film as the substrate and splicing hot melt adhesive around the PVB film includes the following specific steps: Place the cleaned and dried LOW-E glass on the operating platform, cut the PVB film into an appropriate size, and align it with the glass surface for splicing. Refer to Figure 3 the schematic diagram shown. During the splicing process, within a range of 5 - 30 mm around the PVB film, a layer of adhesive material is evenly coated. The adhesive material is hot melt adhesive or an adhesive resin composition. The function of this layer of adhesive material is to firmly bond the PVB film to the LOW-E glass surface and provide additional sealing performance. The water vapor transmission rate of the used hot melt adhesive or adhesive resin composition is less than 0.8 g / m 2 ·d, and its softening temperature is between 100°C and 130°C. Such requirements ensure that the adhesive material can maintain its stability in high humidity or high temperature environments, avoiding adhesive failure due to temperature changes or humidity fluctuations.

[0059] The accuracy and position of the PVB film splicing are inspected using a computer vision algorithm, and the splicing method is adjusted to ensure accurate alignment. The computer vision algorithm is YOLOv5, and the specific steps are as follows:

[0060] Step Y1, input the image of the film splicing into the YOLOv5 model, and the image undergoes preprocessing operations such as scaling, normalization, and color standardization.

[0061] Step Y2, YOLOv5 predicts the bounding box of each target through a regression problem, outputs the position and size of each film bounding box, and gives the confidence level and class probability of the target included in the bounding box.

[0062] Step Y3, if Δx and Δy exceed a preset threshold, where Δx represents the horizontal deviation between the actual position and the target position of the center point of the film, and Δy represents the vertical deviation between the actual position and the target position of the center point of the film, that is, a splicing deviation is detected, then calculate a new placement position. The calculation formula is: x1 = x0 + Δx, y1 = y0 + Δy, where x0 is the x-direction position of the current center point of the film, y0 is the y-direction position of the current center point of the film, x1 is the new x-direction position of the center point of the film, and y1 is the new y-direction position of the center point of the film.

[0063] In this embodiment, referring Figure 4 to the schematic diagram shown, the data in the figure shows the classification effect of the YOLOv5 model on the target during the detection process. The number of samples correctly predicted as negative classes by the model (8), the number of samples where the model wrongly predicts negative classes as positive classes (1), the number of samples where the model wrongly predicts positive classes as negative classes (3), and the number of samples correctly predicted as positive classes by the model (8).

[0064] Further, in step S4, the spliced LOW-E glass, film, and adhesive material are sent to a laminator for interlayer lamination, including: The lamination process is carried out in an environment with a temperature of 25 ± 5°C and a relative humidity of 25 ± 5%. This environmental condition ensures that the hot melt adhesive or adhesive resin composition works under optimal curing conditions, effectively avoiding the instability of material properties caused by too low or too high temperatures. During the lamination process, the laminator applies pressure to ensure full contact between the glass and the PVB film or adhesive resin composition, avoiding the inclusion of air bubbles. The pressure applied by the laminator is between 0.1 - 0.5 MPa, and the lamination time is about 30 minutes.

[0065] Further, in step S5, after the glass interlayer lamination, optimize the exhaust process to reduce the residual bubbles and water vapor inside the glass interlayer, including: After the interlayer lamination, the water vapor and air between the glass and the film need to be completely removed. Use a vacuum pump to evacuate at a pressure of -0.1 MPA for 30 minutes. During the vacuum evacuation process, the goal is to make the pressure drop to the target vacuum degree over time and reduce the generation of residual bubbles. The pressure change inside the glass interlayer is described as: where P(t) is the instantaneous gas pressure inside the glass interlayer at time t, V is the volume of the glass interlayer, Q(t) is the instantaneous pumping rate of the vacuum pump at time t, satisfying where Q max is the maximum pumping rate, ξ is the sensitivity coefficient of the pumping rate to the pressure change, P target is the target vacuum degree, is the sensitivity coefficient of the pumping rate to the temperature change, T(t) is the temperature of the glass interlayer at time t, T optis the preset optimal temperature of the glass interlayer.

[0066] Define the generation probability P bubble (t) of the bubbles in the glass interlayer as a function of the residual gas concentration and the rate of change of pressure: C(t) is the residual gas concentration in the glass interlayer, k1 is the influence coefficient of the residual gas on bubble formation, and k2 is the influence coefficient of the rate of change of pressure on bubble formation. is the instantaneous rate of change of the internal pressure of the glass interlayer.

[0067] Introduce Fick's diffusion law to calculate the water vapor diffusion rate inside the glass interlayer: where J w is the water vapor diffusion flux per unit time and per unit area, D w is the water vapor diffusion coefficient, C w is the water vapor concentration, and x is the water vapor diffusion path.

[0068] To achieve the optimal exhaust process, the final control objective is expressed as an optimization problem:

[0069]

[0070] where t f is the end time of vacuum exhaust, w1 is the weight coefficient of pressure deviation, w2 is the weight coefficient of temperature deviation, and w3 is the weight coefficient of water vapor removal efficiency. The gradient descent algorithm is used to optimize the exhaust process, reduce the residual bubbles and water vapor inside the glass interlayer, and adjust the pumping rate Q(t) and T(t) at each time step to minimize the loss function. The specific steps are as follows:

[0071] Step P1, set the initial pumping rate Q(0) = Q max , set the initial temperature T(0) = T opt , and set the learning rate to η.

[0072] Step P2, calculate the gradient of the loss function with respect to Q(t): Calculate the gradient of the loss function with respect to T(t): where L represents the loss function.

[0073] Step P3, parameter update: where Q new represents the updated pumping rate, Q old represents the pumping rate before update, T new represents the updated temperature, and T old represents the temperature before update.

[0074] Step P4: Update Q(t) and T(t) within each time step dt and keep iterating in a loop. If the difference in the values of the loss function L between two consecutive iterations is less than the preset threshold ∈, it is considered to have converged and the iteration is stopped.

[0075] Further, in step S6, after the glass and the film have undergone vacuum exhaust and completed preliminary bonding, they enter an autoclave for treatment, including: heating and pressurizing the glass and the film in a high-temperature and high-pressure environment can not only further improve the bonding strength between the film and the glass, but also ensure that the laminated glass can effectively prevent water vapor penetration and delamination during long-term use. The autoclave treatment is divided into three stages. In the first stage, the temperature is controlled at 85°C, the pressure is set at 0.60 MPA, and the stabilization time is 15 - 20 minutes; in the second stage, the temperature is set at 100°C, the pressure is increased to 1.05 MPA, and the stabilization time is 2 minutes. At this time, the high-temperature and high-pressure environment in the autoclave promotes the cross-linking reaction between the molecules of the glass and the film materials, making the contact between the film and the glass more uniform and stable, and further enhancing the bonding strength; in the third stage, the temperature is set at 135°C, the pressure is 1.30 MPA, and the stabilization time is 30 - 50 minutes. In this stage, the bonding between the glass and the film reaches the best state, and at the same time, the overall performance of the laminated glass is also maximally improved.

[0076] Further, in step S7, after the autoclave treatment is completed, the glass laminate is cooled, including: the glass laminate is cooled in an environment where the temperature is lower than 40°C. The method of gradually decreasing the temperature is adopted, and the ambient temperature is continuously adjusted during the temperature drop process to control the temperature difference not to exceed 5°C per minute to ensure uniform cooling of the glass and prevent the generation of thermal stress.

[0077] The present invention solves the problems of poor sealing performance, short lifespan, and high sealing cost existing in the existing LOW-E laminated glass. During the preparation process, by establishing a film layer removal control model to remove the film at the edge of the LOW-E glass, the amount of film layer removal is accurately controlled, which not only avoids damage to the glass surface but also ensures the subsequent bonding effect; an automatic cleaning machine is used in combination with a suitable cleaning liquid and drying method to remove impurities at the edge of the glass while protecting the coating on the glass surface. A bonding material with specific properties is selected and the PVB film is spliced with the aid of a computer vision algorithm, ensuring the accurate splicing and firm bonding of the film and the glass, and the additional sealing performance also helps to reduce water vapor penetration. During lamination, the temperature, humidity environment, and pressure are controlled, the exhaust process is optimized, and the residual bubbles and water vapor are reduced, improving the sealing performance of the glass. The autoclave treatment is carried out in stages, enhancing the bonding strength between the film and the glass, effectively preventing water vapor penetration and delamination, and improving the overall performance of the glass. During cooling, the temperature difference is controlled by the step-by-step cooling method to avoid the generation of thermal stress. Compared with the prior art, the preparation method of the present invention significantly improves the sealing performance and durability of the glass, reduces the long-term maintenance cost, overcomes the defect that the traditional sealing technology has poor effect in a high-humidity environment, ensures the energy-saving performance of the glass, and extends the service life of the glass.

[0078] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily think of changes or substitutions, which should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claimed rights.

[0079] Finally: The above is only the preferred embodiment of the present invention and is not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A preparation method of a super-strong durable and energy-saving glass, characterized in that, It includes the following steps: Step S1, perform defilming treatment on the edge of the LOW-E glass; Step S2, clean the defilmed LOW-E glass to remove residual dust, oil stains and other impurities on the edge; Step S3, use PVB film as the base and splice the bonding material around the PVB film; Step S4, send the spliced LOW-E glass, film and bonding material into a laminator for laminating; Step S5, after the glass is laminated, optimize the exhaust process to reduce the residual bubbles and water vapor inside the glass laminate; Step S6, after the glass and the film go through vacuum exhaust and complete preliminary bonding, enter an autoclave for treatment; Step S7, after the autoclave treatment is completed, cool the glass laminate; In the step S5, in order to achieve the optimal exhaust process, the final control objective is expressed as an optimization problem: where t f is the end time of vacuum exhaust, P bubble (t) is the generation probability of bubbles in the glass interlayer, w1 is the pressure deviation weight coefficient, P(t) is the instantaneous gas pressure inside the glass interlayer at time t, P target is the target vacuum degree, w2 is the temperature deviation weight coefficient, T(t) is the temperature of the glass interlayer at time t, T opt is the preset optimal temperature of the glass interlayer, w3 is the weight coefficient of the water vapor removal efficiency, J w is the water vapor diffusion flux per unit time and per unit area.

2. The preparation method of a super-strong durable energy-saving glass according to claim 1, characterized in that , in the said Step S5, adopt the gradient descent algorithm to optimize the exhaust process, reduce the residual bubbles and water vapor inside the glass laminate, and adjust the pumping rate Q(t) and T(t) at each time step to minimize the loss function. The specific steps are as follows: Step P1, set the initial pumping rate Q(0) = Q max , set the initial temperature T(0) = T opt , set the learning rate to η; Step P2, calculate the gradient of the loss function with respect to Q(t): Calculate the gradient of the loss function with respect to T(t): where L represents the loss function; Step P3, parameter update: where Q new represents the updated pumping rate, and Q old represents the pumping rate before update, T new represents the updated temperature, and T old represents the temperature before update; Step P4, update Q(t) and T(t) at each time step dt, and keep looping and iterating. If the difference in the numerical values of the loss function L between two consecutive iterations is less than the preset threshold ∈, it is considered that convergence has been achieved and the iteration stops.

3. The preparation method of a super durable and energy-saving glass according to claim 1, characterized in that , in step S5, during the vacuum evacuation process, the goal is to reduce the pressure to the target vacuum degree over time and minimize the generation of residual bubbles. The pressure change within the glass interlayer is described as: where V is the volume of the glass interlayer, and Q(t) is the instantaneous pumping rate of the vacuum pump at time t, satisfying where Q max is the maximum pumping rate, ξ is the sensitivity coefficient of the pumping rate to pressure change, and ζ is the sensitivity coefficient of the pumping rate to temperature change.

4. The preparation method of a super-strong durable and energy-saving glass according to claim 1, characterized in that, In the step S5, the generation probability P of bubbles in the glass interlayer is defined. bubble as a function of the residual gas concentration and the pressure change rate: C(t) is the residual gas concentration in the glass interlayer, k1 is the influence coefficient of the residual gas on bubble formation, k2 is the influence coefficient of the pressure change rate on bubble formation, is the instantaneous change rate of the internal pressure of the glass interlayer; Fick's diffusion law is introduced to calculate the water vapor diffusion rate inside the glass interlayer: where J w is the water vapor diffusion flux per unit time and per unit area, D w is the water vapor diffusion coefficient, C w is the water vapor concentration, and x is the water vapor diffusion path.

5. The preparation method of a super-strong durable energy-saving glass according to claim 1, characterized in that, In the step S1, a film layer removal control model is established to control the removal amount of the film layer. The calculation formula of the film layer removal control model is as follows: where d is the removal thickness of the film layer, is the instantaneous rate of film layer removal, v is the removal speed of the film removal machine, β is the exponential coefficient of the removal rate with respect to the removal speed, P′ is the pressure applied during the film removal process, θ is the angle of the cutter head of the film removal machine, γ is the exponent of the removal rate with respect to the pressure, and θ is the angle of the cutter head of the film removal machine; f(θ) is the influence function of the cutter head angle of the film removal machine, satisfying λ is the temperature influence coefficient; T′ is the ambient temperature; k is the material constant, representing the correction coefficient under the working conditions of the film removal machine; H is the film layer hardness; η is the exponent of the hardness, E is the elastic modulus of the glass substrate, μ is the friction coefficient between the film layer and the tool, and α is the exponent of film layer removal.

6. The preparation method of a super-strong durable energy-saving glass according to claim 1, characterized in that In the said Step S3, adopt a computer vision algorithm to check the accuracy and position of the PVB film splicing, and adjust the splicing method to ensure accurate alignment. The computer vision algorithm is YOLOv5. The specific steps are as follows: Step Y1, input the image of the film splicing into the YOLOv5 model, and the image undergoes preprocessing operations such as scaling, normalization and color standardization; Step Y2, YOLOv5 predicts the bounding box of each target through a regression problem, outputs the position and size of each film bounding box, and gives the confidence level and class probability of the target included in the bounding box; Step Y3, if Δx and Δy exceed the preset threshold, where Δx represents the horizontal deviation between the actual position and the target position of the film center point, and Δy represents the vertical deviation between the actual position and the target position of the film center point, that is, splicing deviation is detected, then calculate the new placement position. The calculation formula is: x1 = x0 + Δx, y1 = y0 + Δy, where x0 is the x-direction position of the current film center point, y0 is the y-direction position of the current film center point, x1 is the new x-direction position of the film center point, and y1 is the new y-direction position of the film center point.

7. The preparation method of a super-strong durable energy-saving glass according to claim 1, characterized in that, In the said Step S1, by adjusting the working parameters such as the removal speed, applied pressure, cutter head angle, ambient temperature, removal index and film layer removal rate, control the thickness of the film layer between 5 and 30 millimeters.

8. The preparation method of a super-strong durable energy-saving glass according to claim 1, characterized in that, In the said Step S2, an automatic glass cleaning machine is used to clean the LOW-E glass. The cleaning machine uses the processes of high-pressure water flow, brushing and air drying, selects a non-corrosive and low-temperature cleaning liquid, and uses a surfactant to assist in cleaning for difficult-to-clean oil stains or organic matter residues. After cleaning, air drying or heating drying with the temperature controlled at about 40°C is adopted.

9. The preparation method of a super-strong durable energy-saving glass according to claim 1, characterized in that, In step S3, an adhesive material is uniformly coated within a range of 5-30 mm around the PVB film. The adhesive material is a hot melt adhesive or an adhesive resin composition, and its water vapor transmission rate is less than 0.8 g / m 2 ·d, and the softening temperature is between 100 °C and 130 °C.

10. The preparation method of a super-strong durable energy-saving glass according to claim 1, characterized in that, In the step S4, the lamination process is carried out in an environment with a temperature of 25 ± 5 °C and a relative humidity of 25 ± 5%. The pressure applied by the laminator is between 0.1 - 0.5 MPa, and the lamination time is 30 minutes.

Images