基于SVM热轧板形识别

The Shape Recognition in Hot Strip Rolling Based on SVM

本文提出了一种热轧板形缺陷分类识别方法,利用支持向量机(SVM)多分类方法中的一对一策略实现了对常见几种板形缺陷的识别,并使用网格搜索法对参数进行了优化。仿真实验证明,该方法行之有效。

This paper presents a kind of hot rolled sheet shape defect classification method, using one- versus-one strategy which is one of the support vector machine （ SVM ） multiple classification methods to achieve the common shape defect recognition. And use the grid search method to optimize parameters, the simulation results verify the method is effective.