基于支持向量机的不锈钢冷轧薄板力学性能的预测模型  

SVM-Based Mechanical Model Used to Predict Mechanical Properties of Cold Rolled Stainless Steel Sheet

作　　者：张春霞[1] 吴良[1] 

机构地区：[1]东华大学机械工程学院,上海201620

出　　处：《东华大学学报（自然科学版）》2010年第5期559-562,共4页Journal of Donghua University(Natural Science)

摘　　要：介绍了支持向量机(SVM)技术中的支持向量机回归模型原理,建立了不锈钢冷轧薄板力学性能预测模型.结果表明,随着训练样本的增加,模型的预测精度也得到提高.证明应用支持向量机构建不锈钢冷轧薄板力学性能预测的数学模型,能较好地解决小样本和模型预测精度间的矛盾,具有较强的泛化能力.A support vector machine（SVM） regression model based on the SVM theory is introduced, and mathematical model which is used to predict the mechanical properties of cold rolled stainless steel sheet is built by SVM technology.The results show that the predicting precision of the model is improved with the increasing of the training samples.It can be seen that SVM technology is suitable to be used to build mathematical model for predicting the mechanical properties of cold rolled stainless steel sheet. And the model can solve the contradiction between a small quantity samples and predicting precision, also it has strong generalization ability.

关 键 词：支持向量机(SVM) 不锈钢 冷轧薄板 预测模型 

分 类 号：TG335[金属学及工艺—金属压力加工] TP301[自动化与计算机技术—计算机系统结构]