Springback control of sheet metal forming based on high dimension model representation and genetic algorithm

Springback is related to multi-factors in the process of metal forming. In order to construct an accurate metamodel between technical parameters and springback, a general set of quantitative model assessment and analysis tool, termed high dimension model representations (HDMR), is applied to building metamodel. Genetic algorithm is also integrated for optimization based on metamodel. Compared with widely used metamodeling techniques, the most remarkable advantage of this method is its capacity to dramatically reduce sampling effort for learning the input-output behavior from exponential growth to polynomial level. In this work, the blank holding forces (BHFs) and corresponding key time are design variables. The final springback is well controlled by the HDMR-based metamodeling technique.