Multi-Objective Optimization of Injection Molding Process Parameters for Thin-Walled Shell Parts Based on a RIME–RF– MOGWO Framework

Thin-walled components are widely used in automotive interior parts. However, during injection molding, thin-walled shell structures are highly sensitive to process parameters, which often leads to warpage and volumetric shrinkage, thereby significantly reducing their service life. To address this issue, a multi-objective optimization method for injection molding process parameters of thin-walled plastic parts is proposed based on an integrated RIME–RF–MOGWO framework. Simulation-generated samples are employed as the research data, with volumetric shrinkage and warpage deformation selected as the optimization objectives. First, the synthetic minority oversampling technique (SMOTE) is adopted to alleviate data imbalance and enhance the representativeness of minority samples. Subsequently, a random forest (RF) regression model is constructed to capture the nonlinear relationship between process parameters and quality responses. To further improve predictive accuracy, the frost-inspired RIME optimization algorithm is introduced to optimize the hyperparameters of the RF model, thereby strengthening its global search capability. Furthermore, the optimized RF surrogate model is coupled with the multi-objective grey wolf optimizer (MOGWO) to achieve multi-objective optimization of injection molding process parameters. A Pareto-optimal solution set is obtained through non-dominated sorting and crowding-distance-based diversity control. Multi-round optimization and simulation-based validation demonstrate that the proposed method effectively identifies optimal process parameter combinations, resulting in a 19.02% reduction in volumetric shrinkage and a 50.63% reduction in warpage deformation. These results indicate that the proposed approach can significantly improve the molding quality of thin-walled plastic parts used in automotive interior applications.