Multi-Objective Optimization of Liquid Silica Array Lenses Based on Latin Hypercube Sampling and Constrained Generative Inverse Design Networks

HIGHLIGHTS: In this study, we apply the Latin hypercube sampling method for sampling and combine the CGIDN and response surface modeling methods, which can effectively optimize the injection process. The CGIDN method allows a small number of initial data points to be considered and uses a method of continuously updating the sampling points to guide the search for the optimal process parameters that minimize the residual stress values and volume shrinkage. The Latin hypercube sampling method allows uniform, random and orthogonal sampling within the planned spatial area of the experimental factor design and allows artificial control of the number of trials. The method yields sample data with high spatial coverage of the ex-perimental design can improve the accuracy of modeling. The method proposed in this study can effectively optimize the process parameters in the injection molding process, thus improving the reliability and quality output of the injection molded products and providing guidance to the plant engineers in adjusting the machines. ABSTRACT: Injection molding process parameters have a great impact on plastic production quality, manufacturing cost, and molding efficiency. This study proposes to apply the method of Latin hypercube sampling, and to combine the response surface model and “Constraint Generation Inverse Design Network (CGIDN)” to achieve multi-objective optimization of the injection process, shorten the time to find the optimal process parameters, and improve the production efficiency of plastic parts. Taking the LSR lens array of automotive LED lights as the research object, the residual stress and volume shrinkage were taken as the optimization objectives, and the filling time, melt temperature, maturation time, and maturation pressure were taken as the influencing factors to obtain the optimization target values, and the response surface models between the volume shrinkage rate and the influencing factors were established. Based on the “Constraint-Generated Inverse Design Network”, the optimization was independently sought within the set parameters to obtain the optimal combination of process parameters to meet the injection molding quality of plastic parts. The results showed that the optimal residual stress value and volume shrinkage rate were 11.96 MPa and 4.88%, respectively, in the data set of 20 Latin test samples obtained based on Latin hypercube sampling, and the optimal residual stress value and volume shrinkage rate were 8.47 MPa and 2.83%, respectively, after optimization by the CGIDN method. The optimal process parameters obtained by CGIDN optimization were a melt temperature of 30 °C, filling time of 2.5 s, maturation pressure of 40 MPa, and maturation time of 15 s. The optimization results were obvious and showed the feasibility of the data-driven injection molding process optimization method based on the combination of Latin hypercube sampling and CGIDN.