基于Online LS-SVM的钢铁件渗碳层深度在线检测  

Online detecting for carburizing depth of iron and steel parts based on Online LS-SVM

作　　者：贾健明[1] 颜鹏[1] 陈黎敏[1] 

机构地区：[1]常州信息职业技术学院机电工程系,常州213164

出　　处：《现代制造工程》2009年第12期121-124,共4页Modern Manufacturing Engineering

基　　金：江苏省高校自然科学研究指导性计划项目(04KJD470014);江苏省高校高新技术产业发展指导性计划项目(JHZD04-046);江苏省常州市工业科技攻关计划项目(CE2008070)

摘　　要：为实现钢铁件渗碳层深度的在线电磁无损检测,提出在线最小二乘支持向量机(Online Least Square Support Vector Machine,Online LS-SVM)的建模方法。Online LS-SVM是以增量学习训练SVM,以减量学习减少样本数,实现小样本估计的训练方法。实验结果表明,Online LS-SVM不仅能实现钢铁件渗碳层深度的在线电磁无损检测,而且具有学习速度快、泛化性能好和对样本依赖程度低的优点。On the purpose of realizing the Online ENDT for carburizing depth of iron and steel parts, a novel method of Online LSSVM（ Online Least Square Support Vector Machine）was proposed. Online LS-SVM means that SVM can be trained in an incremental way, and can be pruned to get sparse approximating in a decremental way. The experiments show that this method not only achieves the Online ENDT for carburizing depth of iron and steel parts, but also have many advantages such as high learning speed,well generalization ability and little dependence on the sample set.

关 键 词：最小二乘支持向量机 人工神经网络 在线检测 电磁无损检测 渗碳 

分 类 号：TG156.81[金属学及工艺—热处理]