基于支持向量机地旋转机械多类故障识别研究.pdfVIP

Proceedings of the 26th Chinese Control Conference July 26-31, 2007, Zhangji aj ie, Hunan, China 于支持向量机的旋转机械多类故障识别研究* 1,2 1 2 顾小军 ，杨世锡，钱苏翔 1. 江大学机械与能源工程学院，杭州 310027 E-mail: guxiaoj un@zj u.edu.cn 2. 嘉兴学院机电工程学院，嘉兴 314001 要：本文针对在旋转机械故障诊断中样本缺乏的现状，利用支持向量机在小样本分类中的优势，对三种基于二 值支持向量机的多类支持向量机分类方法在旋转机械多类故障识别的应用进行了对比研究，实验证明，支持向量机适 合于小样本状态下的旋转机械故障诊断。 关键词：支持向量机，旋转机械，故障诊断，模式识别 On Rotary Machine s Multi-Class Fault Recognition Based on SVM 1,2 1 2 Gu Xiaojun , Yang Shixi , Qian Suxiang 1. College of Mechanical and Energy Engineering, Zhej iang University, Hangzhou, 310027, P. R. China E-mail: guxiaoj un@zj u.edu.cn 2. College of Mechanical Engineering, Jiaxing University, Jiaxing, China, 314001, P. R. China Abstract: In response to the lack of rotary mechanical diagnostic samples, this paper takes the advantages of support vector machine (SVM) in small sample classification for rotary machine multi-class fault pattern recognition, and introduces three methods based on binary classifications: one-against-all”, one-against-one”, and directed acyclic graph” SVM (DAGSVM) and then compare their performance. The experiments indicate that the SVM has high adaptability for rotary machine fault diagnosis in the case of small number of samples. Key Words: Support Vector Machine (SVM), Rotary Machine, Fault Diagnosis, Pattern Recognition 1 引言(Introduction ) 2 支持向量机分类原理(Classification P