Quality optimization of liquid silicon lenses based on sequential approximation optimization and radial basis function networks

This study introduces an innovative multi-objective optimization method based on sequential approximation optimization (SAO) and radial basis function (RBF) networks to enhance the injection molding process for liquid silicone optical lenses. The method successfully minimizes residual stress and volume shrinkage, thereby improving product quality and manufacturing efficiency. By replacing finite element reanalysis with the RBF network, it constructs an approximate functional relationship between process conditions and quality. The novelty lies in simplifying multi-objective optimization into a single-objective problem and utilizing Pareto boundary analysis for precise parameter tuning. This approach not only reduces trial-and-error costs and material waste but also significantly decreases carbon emissions, showcasing extensive potential for application in various manufacturing processes. Simulations varying key parameters-filling time, melt temperature, mold temperature, curing pressure, and curing time-revealed optimal conditions: filling time of 1.57s, melt temperature of 27.18 degrees C, mold temperature of 150 degrees C, curing time of 20.02s, and curing pressure of 28.79 MPa. Experiments were conducted to validate the numerical results, employing nondestructive testing methods to assess residual stress and volume shrinkage. The results demonstrated significant reductions in these values, affirming the method's reliability and practicality. This innovative and efficient optimization approach provides a robust solution for enhancing injection molding processes while contributing to sustainability and cost efficiency.