Forming Parameter Optimization based on Kriging Model and Genetic Algorithm

When optimizing the processing parameters for hydraulic forming of sheet metal, improving the process parameters based on actual experiments will increase costs, while finite element simulation will lengthen the design cycle. This study proposes a feasible solution by using a Kriging predictive surrogate model to replace the time-consuming finite element model and combining it with multi-objective genetic algorithm for parameter optimization. The optimal process parameters obtained from the simulation validation of finite element analysis prove the feasibility of this solution. This integrated approach of using machine learning and optimization algorithms is practical and promising for improving efficiency and reducing costs in the manufacturing industry.