Multi-objective optimization system and method for 3D glass cover plate hot press molding key parameters

Abstract

The invention relates to the technical field of glass processing, in particular to a 3D glass cover plate hot press forming key parameter multi-objective optimization system and method.The method comprises the steps that the glass material, the target shape, the mold design and the heating and cooling process parameter range of a 3D glass cover plate are obtained; modeling the hot press molding process into a multi-physics coupling system, and extracting glass deformation and residual stress distribution characteristics based on finite element simulation; based on a self-adaptive evolutionary algorithm, the heating rate, the maximum pressure, the dwell time and the cooling curve are optimized, and a multi-objective optimal solution set is generated through Pareto leading edge analysis; preparing a porous anti-dazzle coating on the surface of the glass blank by adopting a sol-gel method; and evaluating an optimization scheme, if a simulation result meets a requirement, outputting optimization process parameters, otherwise, continuing optimization. According to the method, the optimal process parameters can be efficiently searched, a plurality of optimization targets are balanced, and the quality and production efficiency of the glass forming part are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of glass processing, and specifically to a multi-objective optimization system and method for key parameters of hot pressing forming of 3D glass cover plates. Background Art

[0002] Hot pressing forming is the most widely used 3D glass forming method at present. Its basic principle is to heat the glass blank to a temperature above the softening point, and make the glass deform under the action of pressure and high temperature in the mold cavity, so as to obtain a curved glass product with the same shape as the mold cavity. The key factors affecting the quality of hot-pressed glass include process parameters such as glass material properties, mold design, heating rate, and forming pressure. In order to obtain high-quality hot-pressed glass, it is necessary to optimize the design and precisely control various process parameters.

[0003] The optimization of traditional hot pressing forming process parameters mainly relies on the experience of engineers and a large number of experiments. Usually, methods such as single-factor experiments or orthogonal experiments are used to investigate the influence of each process parameter on the forming quality one by one, which is costly and inefficient. In recent years, computer simulation technology and optimization algorithms have been increasingly applied in the field of glass forming, providing a new way for the optimization of glass hot pressing forming process.

[0004] In view of this, the present invention proposes a multi-objective optimization system and method for key parameters of hot pressing forming of 3D glass cover plates. Summary of the Invention

[0005] To achieve the above object, the present invention provides a multi-objective optimization system and method for key parameters of hot pressing forming of 3D glass cover plates. The specific technical solutions are as follows:

[0006] The multi-objective optimization method for key parameters of hot pressing forming of 3D glass cover plates includes:

[0007] Obtaining the input parameters of hot pressing forming of 3D glass cover plates, including glass material, target shape, mold design, and heating and cooling process parameter ranges;

[0008] Modeling the hot pressing forming process as a multi-physical field coupling system, taking temperature, stress, and flow characteristics as key variables, and extracting the characteristics of glass deformation and residual stress distribution based on finite element simulation;

[0009] Based on the adaptive evolutionary algorithm, optimizing the heating rate, maximum pressure, holding time, and cooling curve, and generating a multi-objective optimization solution set by Pareto front analysis;

[0010] Using the sol-gel method to prepare a porous anti-glare coating on the surface of the glass blank, optimizing the preparation process parameters, and obtaining a uniform and transparent anti-glare surface;

[0011] Evaluate the optimization plan. If the simulation results meet the requirements of deformation error, residual stress, production efficiency, and anti-glare, output the optimized process parameters; otherwise, continue to optimize.

[0012] Preferably, obtain the physical property parameters of the glass material, including: elastic modulus, Poisson's ratio, dimensionless density, specific heat capacity, linear expansion coefficient, specific heat capacity, thermal conductivity, and glass transition temperature.

[0013] Define the target shape of the 3D glass cover plate, including: external dimensions: length, width, height, radius of curvature, and edge chamfer radius.

[0014] Design the upper and lower die cavities according to the target shape of the 3D glass cover plate, including: cavity dimensions, curved surface cavity, and concave die chamfer.

[0015] Set the heating and cooling process parameter ranges for the 3D glass cover plate, including: glass heating temperature range, glass forming pressure range, holding time range, and cooling rate range.

[0016] Preferably, establish a multi-physics mathematical model for the hot pressing process, including the constitutive equation of glass deformation, the heat conduction equation of the temperature field, and the Navier-Stokes equation of glass melt flow.

[0017] Use the generalized Maxwell viscoelastic constitutive equation to describe the deformation behavior of glass; establish the heat conduction equation to describe the temperature field distribution during the glass forming process; establish the flow control equation and use the Navier-Stokes equation to describe the flow behavior of glass melt.

[0018] Preferably, according to the obtained physical property parameters of the glass material, target shape dimensions, and die cavity design parameters, construct a three-dimensional geometric solid model in the finite element preprocessing software, including glass billet, upper and lower dies, heating device, and cooling channels.

[0019] Adopt the sequential coupling strategy. In each time increment step, first solve the heat conduction equation to obtain the temperature field distribution, then input the temperature field as a load into the stress field solution, and at the same time consider the influence of flow on temperature and stress, and iterate to solve until convergence.

[0020] For the glass forming process, extract the deformation nephogram and stress nephogram of the glass respectively, and pay attention to the maximum deformation amount, stress concentration area, and residual stress distribution of the glass.

[0021] By changing the mesh size and solution parameter settings, evaluate the convergence and stability of the calculation results, and conduct mesh independence verification and solution parameter sensitivity analysis.

[0022] Preferably, an adaptive evolutionary algorithm is used to optimize the hot pressing process parameters, and a balanced solution among multiple optimization objectives is obtained through Pareto front analysis;

[0023] Determine the optimization design variables, including heating rate, maximum pressure, holding time, and cooling rate; given the value ranges of the design variables, use the Latin hypercube sampling method to generate an initial population in the design space;

[0024] Define the optimization objective functions, considering multiple optimization objectives in the glass forming process, including minimizing the maximum deformation of the glass formed part, minimizing the maximum residual stress of the glass formed part; minimizing the production cycle of the glass formed part.

[0025] Preferably, an improved adaptive weight aggregation method is used to transform the multi-objective optimization problem into a single-objective optimization problem, improving the optimization efficiency and convergence speed;

[0026] Introduce an adaptive weight aggregation function, weighted sum multiple optimization objective functions, and transform them into a single-objective optimization problem;

[0027] Adopt an adaptive weight allocation strategy to dynamically adjust the weight coefficients of each optimization objective according to the non-dominated rank and crowding degree of the population individuals.

[0028] Preferably, tetraethyl orthosilicate, absolute ethanol, and deionized water are mixed in proportion, hydrochloric acid is added to adjust the pH value, and hydrolysis is carried out by stirring at room temperature to obtain a silica sol; a quantitative surfactant polyethylene glycol is added to the silica sol and stirred until uniformly dispersed;

[0029] Use the dip coating method and / or spin coating method to coat the prepared silica sol on the surface of the glass blank, control the dip coating speed or spin coating speed, and obtain a uniform coating;

[0030] Dry the coating at a predetermined temperature and calcine it to remove, obtaining a silica anti-glare coating with a porous structure.

[0031] Preferably, taking the porosity and light transmittance of the coating as the optimization objectives, use the orthogonal experimental design method to optimize the level combination of the hydrolysis time of the silica sol, the addition amount of polyethylene glycol, and the coating process parameters;

[0032] Use a scanning electron microscope to characterize the surface morphology and pore structure of the coating, use a spectrophotometer to test the optical properties of the coating, and establish a response surface model of the preparation process parameters and the coating properties; use the particle swarm optimization algorithm to search for the global optimal solution of the model.

[0033] Preferably, the optimized process parameters are input into the finite element model for numerical simulation to obtain the predicted values of the quality indicators of the glass formed part, including the maximum deformation, the maximum residual stress, and the production cycle; the predicted values of the quality indicators are compared with the design requirement limits.

[0034] If the predicted values of the quality indicators meet the design requirements, the optimized process parameters are considered effective and the optimization results are output; if the predicted values of the quality indicators do not meet the design requirements, the parameter settings of the adaptive evolutionary algorithm are adjusted.

[0035] The multi-objective optimization system for the key parameters of the hot pressing forming of the 3D glass cover plate, which is used to implement the multi-objective optimization method for the key parameters of the hot pressing forming of the 3D glass cover plate, includes: a data acquisition module, a feature analysis module, a multi-objective optimization module, an anti-glare coating preparation module, and a process parameter evaluation module.

[0036] The data acquisition module is used to acquire the input parameters for the hot pressing forming of the 3D glass cover plate, including the glass material, the target shape, the mold design, and the heating and cooling process parameter ranges.

[0037] The feature analysis module is used to model the hot pressing forming process as a multi-physical field coupling system, with temperature, stress, and flow characteristics as the key variables, and extract the glass deformation and residual stress distribution characteristics based on finite element simulation.

[0038] The multi-objective optimization module, based on the adaptive evolutionary algorithm, optimizes the heating rate, the maximum pressure, the holding time, and the cooling curve, and generates a multi-objective optimization solution set by using Pareto front analysis.

[0039] The anti-glare coating preparation module uses the sol-gel method to prepare a porous anti-glare coating on the surface of the glass blank, optimizes the preparation process parameters, and obtains a uniform and transparent anti-glare surface.

[0040] The process parameter evaluation module evaluates the optimization scheme. If the simulation results meet the requirements of deformation error, residual stress, production efficiency, and anti-glare, the optimized process parameters are output; otherwise, the optimization continues.

[0041] The beneficial effects of the present invention: This application comprehensively obtains the input parameters, provides the necessary data support for subsequent modeling, simulation, and optimization, and improves the pertinence and effectiveness of the optimization.

[0042] This application uses the adaptive evolutionary algorithm and Pareto front analysis to efficiently search for the optimal process parameter combination and obtain the balanced solution among multiple optimization objectives.

[0043] This application combines the actual production requirements for manufacturability analysis, screens the process parameters that are easy to implement and have stable quality, and improves the practicability of the optimization scheme.

[0044] By preparing a porous anti-glare coating on the surface of the glass blank, the present application can effectively reduce the light reflectivity of the glass surface, reduce glare, and improve the user experience of the glass cover plate.

[0045] The present application evaluates the effectiveness of the optimization scheme, verifies whether it meets the design requirements, provides a quantitative basis for the determination of process parameters, and ensures the quality of the glass formed parts. Description of the Drawings

[0046] Figure 1 It is a flowchart of the multi-objective optimization method for key parameters of the hot embossing forming of 3D glass cover plates provided by the present invention;

[0047] Figure 2 It is a flowchart of the multi-physical field modeling and simulation of the hot embossing forming of the multi-objective optimization method for key parameters of the hot embossing forming of 3D glass cover plates provided by the present invention;

[0048] Figure 3 It is a flowchart of the multi-objective optimization and evaluation of the hot embossing forming process parameters of the multi-objective optimization method for key parameters of the hot embossing forming of 3D glass cover plates provided by the present invention;

[0049] Figure 4 It is a structural diagram of the multi-objective optimization system for key parameters of the hot embossing forming of 3D glass cover plates provided by the present invention. Detailed Description of the Invention

[0050] To make the above objects, features, and advantages of the present invention more apparent and understandable, the following detailed description of the specific embodiments of the present invention will be made in conjunction with the accompanying drawings of the specification.

[0051] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0052] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation manner of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that excludes other embodiments.

[0053] Embodiment 1

[0054] Refer to Figure 1 , which is the first embodiment of the present invention, providing a multi-objective optimization method for key parameters of the hot embossing forming of 3D glass cover plates.

[0055] Step 1: Obtain the input parameters for the hot pressing forming of the 3D glass cover plate, including glass material, target shape, mold design, and the parameter ranges of heating and cooling processes.

[0056] Select a suitable glass material, such as borosilicate glass, soda-lime glass, or aluminosilicate glass, etc.; Obtain the physical property parameters of the glass, including: elastic modulus E, Poisson's ratio v, dimensionless density ρ, specific heat capacity c p , linear expansion coefficient α, specific heat capacity c p , thermal conductivity k, and glass transition temperature T g ; Elastic modulus E: Describes the ability of the material to resist deformation, with the unit of Pascal (Pa); Poisson's ratio v: Describes the ratio of the transverse deformation to the axial deformation of the material; Dimensionless density ρ: The mass of glass per unit volume, with the unit of kilogram per cubic meter (kg / m 3 ); Linear expansion coefficient α: Describes the thermal expansion ability of the material, with the unit of per Kelvin (1 / K); Specific heat capacity c p : The heat required for the glass to absorb heat and increase the temperature by one unit, with the unit of joule per kilogram Kelvin (J / (kg·K)); Thermal conductivity k: Describes the heat transfer ability of the glass, with the unit of watt per meter Kelvin (W / (m·K)); Glass transition temperature T g , that is, the temperature at which the glass changes from a hard and brittle state to a viscoelastic state, with the unit of degree Celsius (°C) or Kelvin (K).

[0057] Define the target shape of the 3D glass cover plate, including: external dimensions: length L, width W, height H, radius of curvature R, and edge chamfer radius r; The radius of curvature is used to describe the degree of curvature of the curved surface, with the unit of millimeter (mm); Edge chamfer radius r: Reduces stress concentration, with the unit of millimeter (mm).

[0058] Design the upper and lower mold cavities according to the target shape of the 3D glass cover plate, including: cavity dimensions, curved surface cavity, and concave die chamfer; The cavity dimensions include: Considering the shrinkage of glass forming, the cavity dimensions are slightly larger than the target dimensions; The curved surface cavity includes: Manufactured by means such as CNC machining or 3D printing, etc.; The concave die chamfer includes: The concave die chamfer matches the chamfer radius r of the glass cover plate to avoid stress concentration. Select the mold material, which requires good high-temperature strength and wear resistance, such as tungsten carbide, cermet, etc.; Coat the mold surface with a high-temperature resistant and easy-to-release coating, such as boron nitride, graphite, etc.; Install heating and cooling channels in the mold to achieve rapid heating and uniform cooling.

[0059] Set the parameter ranges of heating and cooling processes. Exemplarily, set the range of glass heating temperature T: T g +100K ≤ T ≤ T g +250K; The range of glass forming pressure P: 0.1MPa ≤ P ≤ 1.0MPa; Holding pressure time t hRange: 30s ≤ t h ≤ 300s; Cooling rate v c Range: 1K / s ≤ v c ≤ 5K / s.

[0060] Set the initial process parameters based on experience, such as T = T g + 150K, P = 0.5MPa, t h = 120s, v c = 2K / s.

[0061] Step 2: Model the hot pressing process as a multi-physics coupling system, with temperature, stress, and flow characteristics as key variables, and extract the glass deformation and residual stress distribution characteristics based on finite element simulation.

[0062] Use the generalized Maxwell viscoelastic constitutive equation to describe the deformation behavior of glass:

[0063]

[0064] Among them, σ(t) is the stress tensor, e is the strain tensor, θ is the volume strain, G(t) and K(t) are the relaxation functions of the shear and bulk elastic moduli respectively, I is the unit tensor, t is the time, and τ is the time variable;

[0065] Establish the heat conduction equation to describe the temperature field distribution during the glass forming process:

[0066]

[0067] Among them, ρ is the density, c is the specific heat capacity, T is the temperature, t is the time, ξ is the thermal conductivity, is the gradient operator, and Q is the internal heat source;

[0068] Establish the flow control equation and use the Navier-Stokes equation to describe the flow behavior of the glass melt:

[0069]

[0070] Among them, ρ is the density, u i is the velocity component, t is the time, f i is the body force component, p is the pressure, μ is the dynamic viscosity, and x i is the coordinate component.

[0071] Perform numerical solution on the hot pressing process based on the finite element simulation method, and extract the deformation and residual stress distribution characteristics during the glass forming process.

[0072] According to the obtained physical property parameters of the glass material, the target shape and size, and the die cavity design parameters, an accurate three-dimensional geometric solid model is constructed in the finite element preprocessing software, including the glass blank, the upper and lower dies, the heating device, and the cooling channels. Using a sequential coupling strategy, within each time increment step, first solve the heat conduction equation to obtain the temperature field distribution, and then input the temperature field as a load into the stress field solution, while considering the influence of flow on temperature and stress, and perform iterative solution until convergence. For the critical moments in the glass forming process, such as heating, pressing, holding pressure, and cooling, respectively extract the deformation nephogram and stress nephogram of the glass, and focus on the maximum deformation amount of the glass, the stress concentration area, and the residual stress distribution, etc. By changing the mesh size and solution parameter settings, evaluate the convergence and stability of the calculation results, and conduct mesh independence verification and solution parameter sensitivity analysis to ensure the reliability and applicability of the numerical simulation method.

[0073] Step 3: Based on the adaptive evolutionary algorithm, optimize the heating rate, maximum pressure, holding pressure time, and cooling curve, and use Pareto front analysis to generate a multi-objective optimization solution set.

[0074] Determine the optimization design variables, including the heating rate v h , the maximum pressure P max , the holding pressure time t h , and the cooling rate v c .

[0075] Given the value range of the design variables, use the Latin hypercube sampling (LHS) method to generate an initial population in the design space; define the optimization objective function, considering multiple optimization objectives in the glass forming process: minimize the maximum deformation amount of the glass formed part: f1 = min(max(Δd)); minimize the maximum residual stress of the glass formed part: f2 = min(max(σ r )); minimize the production cycle of the glass formed part: f3 = min(t c ); where, Δd is the deformation amount of the glass formed part, σ r is the residual stress of the glass formed part, and t c is the production cycle of the glass formed part.

[0076] Use the finite element simulation method to evaluate the fitness value of each individual in the current population, that is, calculate the values of each optimization objective function.

[0077] Use the Pareto sorting and crowding degree calculation methods to perform non-dominated sorting and diversity preservation on the population individuals; perform genetic operations on the current population, including selection, crossover, and mutation; use the binary tournament selection algorithm to select excellent individuals from the parental population, and use the simulated binary crossover (SBX) and polynomial mutation algorithms to perform crossover and mutation on the selected individuals to generate a new offspring population.

[0078] Merge the parental population and the offspring population, and use the elitist retention strategy to select the next generation population from the merged population; repeat the selection process until the maximum number of evolutionary generations is reached or the convergence criterion is satisfied; perform non-dominated sorting on the final population to obtain the Pareto optimal solution set.

[0079] Use the improved adaptive weight aggregation method to transform the multi-objective optimization problem into a single-objective optimization problem, improving the optimization efficiency and convergence speed.

[0080] Introduce an adaptive weight aggregation function to weight and sum multiple optimization objective functions, transforming it into a single-objective optimization problem: where, F is the aggregated objective function, f i is the i-th optimization objective function, w i is the weight coefficient of the i-th optimization objective function, and n is the number of optimization objectives.

[0081] Adopt an adaptive weight allocation strategy to dynamically adjust the weight coefficients of each optimization objective according to the non-dominated rank and crowding degree of the population individuals:

[0082] where, N i is the number of non-dominated individuals of the i-th optimization objective function, rank j is the non-dominated rank of the j-th non-dominated individual, and density j is the crowding degree of the j-th non-dominated individual.

[0083] During each generation of evolution, update the weight coefficients according to the non-dominated rank and crowding degree information of the current population, so that the optimization algorithm adaptively adjusts the importance of each optimization objective at different evolutionary stages, taking into account both the convergence speed and the diversity of solutions; use the aggregated objective function as the fitness function and use the standard genetic algorithm to solve the single-objective optimization problem; during the evolution process, record the values of each optimization objective function corresponding to each individual at the same time, which is used for the generation and visualization of the Pareto front.

[0084] Step 4: Use the sol-gel method to prepare a porous anti-glare coating on the surface of the glass blank, optimize the preparation process parameters, and obtain a uniform and transparent anti-glare surface.

[0085] Tetraethyl orthosilicate (TEOS), absolute ethanol, and deionized water were mixed in a molar ratio of 1:20:5. Here, TEOS served as the silicon source, ethanol as the co-solvent, and water participated in the hydrolysis reaction of TEOS.

[0086] Hydrochloric acid was added dropwise to the mixed solution to adjust the pH value to 2 - 3, preparing a hydrolysis environment under acidic conditions. The mixed solution was stirred at room temperature for 2 - 4 h to allow TEOS to hydrolyze fully, generating a silicon alcohol sol.

[0087] The surfactant polyethylene glycol PEG - 400 was added to the silicon alcohol sol. PEG - 400 served as a pore - forming agent and a dispersant, which helped to form a uniform porous structure. The mass fraction of PEG - 400 was adjusted to 20% - 30%, and stirring was continued until the sol was uniformly dispersed, obtaining the final SiO2 sol.

[0088] The glass blank was pre - cleaned to remove surface oil and impurities. The prepared SiO2 sol was uniformly coated on the surface of the glass blank by the dip - coating method or the spin - coating method.

[0089] For dip - coating, the glass blank was vertically immersed in the SiO2 sol and then pulled up at a uniform speed of 2 - 5 mm / s, causing the sol to form a uniform liquid film on the glass surface.

[0090] For spin - coating, the glass blank was placed horizontally on a rotating table, an appropriate amount of SiO2 sol was added dropwise, and then it was rotated at a speed of 2000 - 3000 rpm for 1 - 2 min, causing the sol to spread uniformly under the action of centrifugal force.

[0091] The glass blank coated with SiO2 sol was placed in an oven at 60 - 80 °C and dried for 2 - 4 h to volatilize the solvent in the sol, forming a gel - state SiO2 film.

[0092] The dried coating was placed in a muffle furnace and calcined at 500 - 600 °C for 2 - 3 h. High - temperature calcination completely decomposed the residual organic matter in the gel film, and PEG - 400 was burned off, forming uniform nano - pores in the SiO2 matrix.

[0093] After the calcination was completed, it was cooled to room temperature with the furnace, obtaining a porous - structured SiO2 anti - glare coating, and the coating thickness could be controlled within 100 - 200 nm.

[0094] In order to obtain a porous SiO2 anti - glare coating with excellent performance, it is necessary to optimize the porosity and light transmittance of the coating. The porosity determines the anti - reflection ability of the coating, and the light transmittance affects the optical quality of the coating.

[0095] Using the orthogonal experimental design method, factors such as the hydrolysis time of SiO2 sol, the addition amount of PEG-400, the coating method, the pulling speed (or spin coating speed), the drying temperature and time, and the calcination temperature and time are selected as experimental variables, and 3 - 5 levels are set.

[0096] According to the orthogonal table, design the experimental scheme, prepare a series of SiO2 anti-glare coating samples with different combinations of process parameters, and prepare each sample 3 times to reduce random errors.

[0097] Use a scanning electron microscope (SEM) to observe the surface morphology and cross-sectional structure of the coating, measure the thickness and pore size distribution of the coating; use a gas adsorption instrument to test the specific surface area and pore volume of the coating, and calculate the porosity of the coating.

[0098] Use a spectrophotometer to test the transmittance curve of the coating in the visible light band (400 - 800 nm), and calculate the average transmittance; use an ellipsometer to test the reflectivity of the coating surface to evaluate the anti-reflection performance of the coating.

[0099] According to the performance indicators such as the porosity, light transmittance and reflectivity of the coating, conduct statistical analysis on the experimental results, and establish a multiple quadratic response surface model of the preparation process parameters and the coating performance.

[0100] Exemplarily, with the coating porosity greater than 60% and the light transmittance higher than 90% as the optimization goal, and the value ranges of each process parameter as the constraint conditions, use the particle swarm optimization algorithm to search for the global optimal solution of the response surface model.

[0101] Through multiple iterative optimizations, obtain one or more sets of the best process parameter combinations that meet the performance requirements.

[0102] Verify the repeatability and stability of the best process parameter combination, prepare multiple anti-glare coating samples, test the fluctuation range of their performance indicators, and ensure the reliability of the process and the consistency of the products.

[0103] Apply the optimized anti-glare coating preparation process to the production of 3D glass covers, evaluate the batch preparation effect and service performance of the coating, continuously improve and optimize the process parameters, and improve the product yield and quality level.

[0104] Step 5: Evaluate the optimization plan. If the simulation results meet the requirements of deformation error, residual stress, production efficiency, and anti-glare, output the optimized process parameters; otherwise, continue to optimize.

[0105] Input the optimized process parameters into the finite element model, conduct numerical simulations, and obtain the predicted values of the quality indicators of the glass formed parts, including the maximum deformation amount Δd max 、the maximum residual stress σ r,max and the production cycle t c; Compare the predicted value of the quality index with the design requirement limit value to determine whether the following conditions are met: maximum deformation: Δd max ≤ [Δd], maximum residual stress: σ r,max ≤ [σ r , production cycle: t c ≤ [t c , where [Δd], [σ r and [t c are the design requirement limit values of the maximum deformation, maximum residual stress and production cycle respectively;

[0106] If the predicted value of the quality index meets the design requirements, it is considered that the optimized process parameters are feasible and effective, and the optimization results are output, including the optimized values of the heating rate v h 、maximum pressure P max 、holding pressure time t h and cooling rate v c ;

[0107] If the predicted value of the quality index does not meet the design requirements, adjust the parameter settings of the adaptive evolutionary algorithm, such as population size, crossover probability, mutation probability, etc., improve the search ability of the optimization algorithm, regenerate the Pareto optimal solution set, and continue to iteratively optimize the combination of optimized process parameters that meet the design requirements.

[0108] Example 2

[0109] Refer to Figure 2 , for the second embodiment of the present invention, a multi-objective optimization system for the key parameters of 3D glass cover hot pressing forming is provided.

[0110] The system includes: a data acquisition module, a feature analysis module, a multi-objective optimization module, an anti-glare coating preparation module, and a process parameter evaluation module.

[0111] The data acquisition module is used to acquire the input parameters of 3D glass cover hot pressing forming, including glass material, target shape, mold design, and heating and cooling process parameter ranges.

[0112] The feature analysis module is used to model the hot pressing forming process as a multi-physical field coupling system, with temperature, stress and flow characteristics as key variables, and extract the glass deformation and residual stress distribution characteristics based on finite element simulation.

[0113] The multi-objective optimization module, based on the adaptive evolutionary algorithm, optimizes the heating rate, maximum pressure, holding pressure time and cooling curve, and generates a multi-objective optimization solution set by Pareto front analysis.

[0114] The anti-glare coating preparation module prepares a porous anti-glare coating on the surface of the glass blank by the sol-gel method, optimizes the preparation process parameters, and obtains a uniform and transparent anti-glare surface.

[0115] The process parameter evaluation module evaluates the optimization scheme. If the simulation results meet the requirements of deformation error, residual stress, production efficiency, and anti-glare, it outputs the optimized process parameters; otherwise, it continues to optimize.

[0116] Embodiment 3

[0117] This application provides a storage medium with a computer program stored thereon. When the computer program is executed by a processor, it runs the steps in the above method. Through the above technical solution, when the computer program is executed by the processor, it executes the method in any optional implementation manner of the above embodiment to achieve the following functions: obtaining multiple sets of historical electricity consumption data, dividing the historical electricity consumption data, and outputting specific electricity consumption groups; calculating the historical electricity consumption data and outputting the moving average value; analyzing the moving average value and outputting the equipment type and peak time; obtaining the current time and the real-time electricity consumption, analyzing and calculating the real-time electricity consumption based on the current time, peak time, and equipment type, and outputting abnormal electricity consumption information based on the calculation results.

[0118] In the above embodiments of this application, the descriptions of each embodiment have their own focuses. For parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0119] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media that contain computer-usable program code. Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM for short), electrically erasable programmable read-only memory (EEPROM for short), erasable programmable read-only memory (EPROM for short), programmable read-only memory (PROM for short), read-only memory (ROM for short), magnetic memory, flash memory, magnetic disk or optical disk. These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device, and the instruction device implements the process Figure 1 one process or multiple processes and / or Figure 1 functions specified in one block or multiple blocks.

[0120] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some communication interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0121] The embodiments of the present invention have been described above in conjunction with the accompanying drawings, but the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Those of ordinary skill in the art, under the inspiration of the present invention, without departing from the purpose of the present invention and the scope protected by the claims, can also make changes, modifications, substitutions, and deformations to the above embodiments, and these all fall within the protection scope of the present invention.

Claims

1. A multi-objective optimization method for key parameters of 3D glass cover hot pressing molding, characterized in that: include: Obtain input parameters for hot pressing of 3D glass cover sheets, including glass material, target shape, mold design, and heating and cooling process parameter ranges; The hot pressing process is modeled as a multi-physics coupling system. Temperature, stress and flow characteristics are used as key variables. The glass deformation and residual stress distribution characteristics are extracted based on finite element simulation. Based on the adaptive evolutionary algorithm, the heating rate, maximum pressure, holding time and cooling curve are optimized, and the Pareto frontier analysis is used to generate a multi-objective optimization solution set; The porous anti-glare coating was prepared on the surface of glass blank by sol-gel method, and the preparation process parameters were optimized to obtain a uniform and transparent anti-glare surface. Evaluate the optimization scheme. If the simulation results meet the requirements of deformation error, residual stress production efficiency and anti-glare, output the optimized process parameters, otherwise continue to optimize.

2. The multi-objective optimization method for key parameters of 3D glass cover hot pressing molding according to claim 1, characterized in that: Obtain the physical properties of glass materials, including elastic modulus, Poisson's ratio, dimensionless density, specific heat capacity, linear expansion coefficient, specific heat capacity, thermal conductivity and glass transition temperature; Define the target shape of the 3D glass cover, including: dimensions: length, width, height, curvature radius, and edge chamfer radius; Design the upper and lower mold cavities according to the target shape of the 3D glass cover, including: cavity size, curved cavity and concave mold chamfer; The heating and cooling process parameter ranges of the 3D glass cover are set, including: glass heating temperature range, glass forming pressure range, holding time range, and cooling rate range.

3. The multi-objective optimization method for key parameters of 3D glass cover hot pressing molding according to claim 2, characterized in that: Establish a multi-physics mathematical model of the hot pressing process, including the constitutive equation of glass deformation, the heat conduction equation of the temperature field, and the Navier-Stokes equation of glass melt flow; The generalized Maxwell viscoelastic constitutive equation is used to describe the deformation behavior of glass; the heat conduction equation is established to describe the temperature field distribution during the glass forming process; the flow control equation is established and the Navier-Stokes equation is used to describe the flow behavior of the glass melt.

4. The multi-objective optimization method for key parameters of 3D glass cover hot pressing molding according to claim 3, characterized in that: According to the obtained glass material physical properties, target shape and size, and mold cavity design parameters, a three-dimensional geometric solid model is constructed in the finite element pre-processing software, including the glass blank, upper and lower molds, heating device, and cooling channel; A sequential coupling strategy is adopted. In each time increment, the heat conduction equation is first solved to obtain the temperature field distribution. Then the temperature field is input as a load into the stress field solution. The influence of flow on temperature and stress is considered at the same time. The solution is iterated until convergence. In the glass forming process, the deformation cloud map and stress cloud map of the glass are extracted respectively, focusing on the maximum deformation of the glass, the stress concentration area and the residual stress distribution; By changing the grid size and solution parameter settings, the convergence and stability of the calculation results are evaluated, and grid independence verification and solution parameter sensitivity analysis are performed.

5. The multi-objective optimization method for key parameters of 3D glass cover hot pressing molding according to claim 4, characterized in that: The adaptive evolutionary algorithm is used to optimize the hot pressing process parameters, and the equilibrium solution among multiple optimization objectives is obtained through Pareto frontier analysis; Determine the optimal design variables, including heating rate, maximum pressure, holding time, and cooling rate; Given the range of design variables, the Latin hypercube sampling method is used to generate the initial population in the design space; The optimization objective function is defined, taking into account multiple optimization objectives of the glass forming process, including minimizing the maximum deformation of the glass forming parts, minimizing the maximum residual stress of the glass forming parts, and minimizing the production cycle of the glass forming parts.

6. The multi-objective optimization method for key parameters of 3D glass cover hot pressing molding according to claim 5, characterized in that: The improved adaptive weight aggregation method is used to transform the multi-objective optimization problem into a single-objective optimization problem, thus improving the optimization efficiency and convergence speed. An adaptive weight aggregation function is introduced to convert multiple optimization objective functions into a single objective optimization problem by weighted summation. An adaptive weight allocation strategy is adopted to dynamically adjust the weight coefficients of various optimization objectives according to the non-dominated level and crowding degree of individuals in the population.

7. The multi-objective optimization method for key parameters of 3D glass cover hot pressing molding according to claim 6, characterized in that: Mixing tetraethyl orthosilicate, anhydrous ethanol and deionized water in proportion, adding hydrochloric acid to adjust the pH value, stirring and hydrolyzing at room temperature to obtain silica sol; adding a certain amount of surfactant polyethylene glycol to the silica sol, stirring until uniform dispersion; The prepared silica sol is coated on the surface of the glass blank by using a pulling method and / or a spin coating method, and the pulling speed or the spin coating speed is controlled to obtain a uniform coating; The coating is dried at a predetermined temperature and calcined to be removed, thereby obtaining a silicon dioxide anti-glare coating with a porous structure.

8. The multi-objective optimization method for key parameters of 3D glass cover hot pressing molding according to claim 7, characterized in that: Taking the porosity and transmittance of the coating as the optimization targets, the orthogonal experimental design method was used to optimize the hydrolysis time of silica sol, the amount of polyethylene glycol added, and the level combination of coating process parameters. The surface morphology and pore structure of the coating were characterized by scanning electron microscopy, the optical properties of the coating were tested by spectrophotometer, and a response surface model of the preparation process parameters and coating performance was established. The particle swarm optimization algorithm was used to search for the global optimal solution of the model.

9. The multi-objective optimization method for key parameters of 3D glass cover hot pressing molding according to claim 8, characterized in that: Input the optimized process parameters into the finite element model and perform numerical simulation to obtain the predicted values ​​of the quality indicators of the glass molded parts, including the maximum deformation, the maximum residual stress and the production cycle; compare the predicted values ​​of the quality indicators with the design requirement limits; If the predicted value of the quality index meets the design requirements, the optimized process parameters are considered effective and the optimization results are output; If the predicted value of the quality index does not meet the design requirements, the parameter settings of the adaptive evolutionary algorithm are adjusted.

10. A multi-objective optimization system for key parameters of 3D glass cover hot pressing molding, which is used to implement the multi-objective optimization method for key parameters of 3D glass cover hot pressing molding according to any one of claims 1 to 9, characterized in that: include: Data acquisition module, feature analysis module, multi-objective optimization module, anti-glare coating preparation module and process parameter evaluation module; The data acquisition module is used to obtain input parameters for hot pressing of 3D glass cover plates, including glass material, target shape, mold design, and heating and cooling process parameter ranges; The feature analysis module is used to model the hot pressing process as a multi-physics field coupling system, taking temperature, stress and flow characteristics as key variables, and extracting the glass deformation and residual stress distribution characteristics based on finite element simulation; The multi-objective optimization module optimizes the heating rate, maximum pressure, holding time and cooling curve based on an adaptive evolutionary algorithm, and generates a multi-objective optimization solution set using Pareto frontier analysis; The anti-glare coating preparation module adopts a sol-gel method to prepare a porous anti-glare coating on the surface of a glass blank, optimizes the preparation process parameters, and obtains a uniform and transparent anti-glare surface; The process parameter evaluation module evaluates the optimization scheme, and outputs the optimized process parameters if the simulation results meet the requirements of deformation error, residual stress, production efficiency and anti-glare, otherwise the optimization is continued.

Images