Numerical multi-objective optimization of segmented and variable blank holder force trajectories in deep drawing based on DNN-GA-MCS strategy

Abstract

This research introduces a novel methodology for mitigating defects in sheet metal forming processes. The proposed approach employs a segmented and variable blank holder force (S-VBHF) trajectory, adjusting the blank holder force (BHF) during the forming cycle, enhancing formability, and reducing failure, wrinkling and springback defects. Optimal process parameters, including the S-VBHF, friction coefficient and drawbead restraining force (DBRF), were determined through a systematic methodology integrating deep neural network, genetic algorithm and Monte Carlo simulation (DNN-GA-MCS) techniques. The design constraint, defined as sheet failure during the forming process, was quantitatively evaluated using the forming limit diagram (FLD) to ensure rigorous assessment. The proposed methodology was validated through numerical simulations using a cylindrical cup provided by NUMISHEET 2011 (BM1) as test samples. The simulation results demonstrated a significant improvement in the formed sheet quality, characterized by reductions of 8.33%, 10.81% and 5.88% in failure, wrinkling and springback defects, respectively. These findings underscore the potential of the proposed approach in enhancing the quality of sheet metal forming processes and mitigating defects.