Journal of South China University of Technology (Natural Science Edition) ›› 2007, Vol. 35 ›› Issue (12): 23-27,33.

• Mechanical Engineering • Previous Articles     Next Articles

Modeling and Prediction of Water-Assisted Injection Molding Based on GA-LMßP Inverse Neural Network

Huαng Han-xiong  He Jian-min  Liu Xu-hui  Deng Zhi-wu   

  1. School of lndustrial Equipment and Control Engineering , South China Univ. of Tech. , Guangzhou 510640 , Guangdong , China
  • Received:2006-10-16 Online:2007-12-25 Published:2007-12-25
  • Contact: 黄汉雄(1963-) ，男，教授，博士生导师，主要从事聚合物加工装备及工程研究. E-mail:mmhuang@ scut.edu. cn
  • About author:黄汉雄(1963-) ，男，教授，博士生导师，主要从事聚合物加工装备及工程研究.
  • Supported by:

    广东省自然科学基金资助项目( 06025643 ) ;教育部留学回国人员科研启动基金资助项目

PDF

774

Abstract:

Water-assisted injection molding (W AIM) is a new injection molding technique whose mathematical model is difficult to establish by mathematical method due to the process complexity. In this work , an inverse neural network named GA-LMBP is proposed by combining the genetic algorithm (GA) with the Levenberg-Marquardt back-propagation (LMBP) neural network. Based on the proposed GA-LMBP , a model to predict the W AIM process is developed according to a series of experimental results. It is found from the cross-validation that there is a good agreement between the predicted results by the model and the experimental ones , and that , with the thickness at different locations of molded parts as the system input , the model can quickly and accurately predict such processing parameters as short-shot size , water pressure , water injection delay time , and melt temperature.

Key words: water-assisted injection molding, Levenberg-Marquardt back-propagation neural network, genetic algorithm, inverse process, modeling