基于支持向量机的复合材料力学性能预测(终稿).doc

基于支持向量机的复合材料力学性能预测蔡秋茹,汤嘉立,柳益君( 江苏技术师范学院计算机工程学院,江苏常州 213001 ) 摘要: 通过建立材料力学性能与工艺参数相关的预测模型,可以减少试验次数、实现工艺优化, 提高产品质量。该文提出利用支持向量机建立材料性能影响因素到力学性能的非线性映射。以麦杆增强复合材料为例, 建立其力学性能预测的支持向量机模型, 对材料的注塑工艺参数进行分析, 得出其注塑成型的最佳工艺参数。结果表明所建模型具有较好的学****和泛化能力, 对于优化成型工艺参数具有可行性, 在材料性能研究领域有着较好的应用和推广价值。关键词: 支持向量机;预测模型;力学性能中图分类号: TP183 文献标识码: A Prediction posite material mechanical properties with s upport v ector m achine CAI Qiu-ru, TANG Jia-li, LIU Y i-ju n (College puter Engineering , Jiangsu Teachers University of Technology, Changzhou Jiangsu 213001 , China) A BSTRACT : Predicting model which refers to mechanical properties with technique parameters can be founded to reduce test times, realize the optimization of process and promote product quality . This paper proposes to apply the s upport v ector m achine to set up the nonlinear mapping from influence factors of material mechanical properties to mechanical properties. Taking the wheat straw-posite for instance, the prediction model based ons upport v ector m achine has been built. Besides, the model is used to optimize process parameters of injection molding and find the range of best parameters . The results show the founded model has preferable learning and generalization capabilities , which performs effective ly in predicting mechanical properties . Therefore it is feasible to optimize process parameters and the technology is worthy to be applied and