Multi-Point Stretch Forming Springback Prediction and Parameter Sensitivity Analysis Based on GWO-CatBoost

Springback control in Multi-Point Stretch Forming (MPSF) is significantly hindered by the computational intensity of Finite Element Analysis (FEA) and the limited predictive robustness of traditional regression methods. This study develops a hybrid GWO-CatBoost model acting as a data-driven surrogate for MPSF simulations by integrating the Grey Wolf Optimizer (GWO) with the CatBoost algorithm for high-precision springback forecasting. An FEA model of the MPSF process was initially validated through experimental comparison under a representative working condition to assess modeling accuracy. A comprehensive dataset comprising 1200 scenarios was generated via a full factorial design, incorporating key variables: curvature radius, sheet thickness, cushion thickness, and pre-stretching rate. In this study, the GWO was employed to perform automated hyperparameter tuning for CatBoost by optimizing the learning rate, tree depth, and number of iterations, thereby enabling accurate modeling of the complex nonlinear relationship between process inputs and numerical springback values. Numerical evaluations demonstrate that the GWO-CatBoost model outperforms GWO-XGBoost and GWO-Random Forest benchmarks, achieving a Coefficient of Determination (R2) of 0.9293, a root mean square error (RMSE) of 0.0274 mm and mean absolute error (MAE) of 0.0189 mm. Sensitivity analysis identifies sheet thickness as the dominant factor (46% contribution), with cushion thickness as the secondary driver (23%). This predictive framework serves as a computationally efficient auxiliary surrogate, designed to assist iterative finite element analyses and support process optimization in the manufacture of complex-curved panels.