作者: Xuejuan Li , Jie Ouyang , Binxin Yang , Tao Jiang
DOI: 10.1080/03602559.2010.496419
关键词:
摘要: In this paper, a Hybrid Neural Network trained by Modified Particle Swarm Optimization (MPSO-HNN) is first proposed for predicting warpage. Then the minimum warpage problem solved MPSO-HNN coupled with MPSO algorithm based on process parameters in injection molding. A model Taguchi experiment designed to find parameters' optimum levels Signal-to-Noise (SN) ratio. All results show that needs less calculating amounts and spends time has better generalization ability than those related literature. Meanwhile, method of combining suitable optimization compared method.