A reliability assessment method based on support vector machines for CNC equipment

作     者：WU Jun DENG Chao SHAO XinYu XIE S Q 

作者机构：School of Naval Architecture and Ocean EngineeringHuazhong University of Science and TechnologyWuhan 430074China State Key Laboratory of Digital Manufacturing Equipment&TechnologyHuazhong University of Science and TechnologyWuhan 430074China Department of Mechanical EngineeringUniversity of AucklandAucklandNew Zealand 

出 版 物：《Science China(Technological Sciences)》 (中国科学（技术科学英文版）)

年 卷 期：2009年第52卷第7期

页      面：1849-1857页

核心收录：

学科分类：08[工学] 0802[工学-机械工程] 080201[工学-机械制造及其自动化] 

基　　金：National High Technology Research and Development Program of China (“863” Program), (2006AA04Z407) National Natural Science Foundation of China, NSFC, (50675082) 

主　　题：reliability assessment least squares support vector machines performance degradation radial basis function parameter optimization 

摘      要：With the applications of high technology,a catastrophic failure of CNC equipment rarely occurs at normal operation *** it is difficult for traditional reliability assessment methods based on time-to-failure distributions to deduce the reliability *** paper presents a novel reliability assessment methodology to estimate the reliability level of equipment with machining performance degradation data when only a few samples are *** least squares support vector machines(LS-SVM) are introduced to analyze the performance degradation process on the equipment.A two-stage parameter optimization and searching method is proposed to improve the LS-SVM regression performance and a reliability assessment model based on the LS-SVM is built.A machining performance degradation experiment has been carried out on an OTM650 machine tool to validate the effectiveness of the proposed reliability assessment methodology.