Optimization of Injection Molding by Combining Numerical Simulation with Surrogate Modeling Approach
The objective of this study is to develop an integrated, simulation-based optimization system that can quickly and intelligently determine the optimal process conditions for injection molding without user intervention. The idea is to use a spe cific non-linear statistical regression technique,Gaussian process (GP) approach, and design of computer experiments to establish an adaptive surrogate model with short turn-around time and adequate accuracy for substituting iterative, time-consuming computer simulations during system-level optimization. While the surrogate model is being established, a hybrid genetic algorithm (GA) is employed to evaluate the model to search for the global optimal solutions in a concurrent fashion. The performance and capabilities of other surrogate modeling approaches, such as polynomial regression (PR), artificial neural network (ANN), and support vector regression (SVR), are also investigated in terms of accuracy, robustness, efficiency, and requirements for training samples. The examples presented in this paper show that the proposed adaptive optimization procedure helps engineers determine the optimal process conditions more efficiently and effectively.
Injection molding optimization surrogate model Gaussian process
Jian Zhou Lihsheng Turng
Polymer Engineering Center Department of Mechanical Engineering University of Wisconsin-Madison, USA
国际会议
郑州
英文
31-54
2006-10-18（万方平台首次上网日期，不代表论文的发表时间）