基于Online LS-SVM的钢铁件淬火硬度在线检测  

Online ENDT for hardness of iron and steel parts based on online LS-SVM

作　　者：贾健明[1] 颜鹏[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：《电子测量技术》2009年第3期68-71,共4页Electronic Measurement Technology

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(CE2008070)

摘　　要：为了实现钢铁件淬火硬度的在线电磁无损检测,提出了在线最小二乘支持向量机(online least square support vector machine)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不仅能实现钢铁件淬火硬度的在线电磁无损检测,而且具有学习速度快,泛化性能好,对样本依赖程度低的优点。On the purpose of realizing the online electromagnetic nondestructive testing （ENDT） for hardness of iron and steel parts, a novel method of Online LS-SVM（Online Least Square Support Vector Machine）was proposed. Online LS-SVM means that LS-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 hardness 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 硬度 

分 类 号：TG156.81[金属学及工艺—热处理]