摘要
故障样本缺乏是制约智能故障诊断发展的重要原因。支持向量机是近10 a来提出的一种基于小样本的统计学习方法。将支持向量机分类算法用于滚动轴承的多类故障分类并与RBF神经网络进行对比研究。实验表明,在有限样本条件下,支持向量机算法比RBF神经网络具有更好的分类性能。
The Shortage of fault samples is one of the main reasons that restrict the development of intelligent fault diagnosis. Support vector machine （SVM） is a statistic learning method based on less samples proposed in the last decade. In this paper, the classification algorithm of support vector machine is used to deal with the multi - class fault classification problem in intelligent fault diagnosis. The experimental results of trundle bearing fault diagnoses by using SVM is compared with that by using RBF neural network, which shows that the SVM method has higher classification performance than RBF neural network under the condition of restricted samples.
出处
《煤矿机械》
北大核心
2007年第1期182-184,共3页
Coal Mine Machinery
基金
河南省自然科学基金(0611022400)
关键词
支持向量机(SVM)
多类故障分类
人工神经网络
智能故障诊断
support vector machines
multi - class fault classification
RBF neural network
intelligent fault diagnosis
