Multi-objective optimization method of injection molding process parameters based on hierarchical sampling and comprehensive entropy weights

Abstract

The key of the multi-objective optimization of injection molding processes lies in achieving a balance between the accuracy of the surrogate model and the multiple objectives while taking the diversity and interdependence of process parameters into consideration. However, the sampling process for building high-precision surrogate models requires a large number of sample points, resulting in high modeling costs for other regions. Moreover, the selection of Pareto fronts often relies solely on the magnitudes of objective values, without considering the uncertainties associated with the information. To address these issues, this research proposes a novel multi-objective optimization method for injection molding process parameters, using hierarchical sampling and integrated entropy weighting. The method introduces a unique hierarchical sampling approach to enhance the accuracy of the surrogate model in injection molding, with a specific focus on critical components. Additionally, our method incorporates entropy calculations for multiple objective defect value parameters during the multi-objective optimization process, enhancing the rationality of the optimization process. The proposed method is utilized to optimize the injection molding parameters of a thin-walled propeller blade. The result shows that our surrogate model fits well and exhibits superior performance compared to the response surface method in optimizing multiple objectives.