Application of Improved Back-propagation Neural Network and Genetic Algorithm to the Preparation Processing of the Mg,Al-hyd rotalcite/polymer Nanocomposite

摘要：

　　The three-layer structure back-propagation network model based on the non-linear relationship between the break percentage elongation of the Mg,Ai-hydrotalcite/PE nanocomposites and the technological factors was established.And in order to accelerate the converging rate and avoid the local minimum,dimensionality reduction and pre-whitening methods were used.Moreover,the optimum technological process parameters were optimized with genetic algorithm.And the results show that using both the back propagation neural networks and genetic algorithm is very efficient for the prediction of the break percentage elongation of the Mg,Al-hydrotalcite/PE nanocomposite.

关键词： Neural network Genetic algorithm Dimensionality reduction and pre-whitening

作者: Qiang Luo Qingli Ren

作者单位: The Second Artillery Engineering College,Xian 710025,P.R.China School of Technical Physics,Xidian University,Xian 710071,P.R.China

会议类型: 国际会议

会议名称: The Fifth China International Conference on High-Performance Ceramics (第五届先进陶瓷国际研讨会(CICC-5))

会议地点: 长沙

会议语种:英文

页码: 1680-1682

在线出版日期: 2007-05-10（万方平台首次上网日期，不代表论文的发表时间）