摘要
提出了基于奇异值分解和支持向量机进行滚动轴承故障诊断的新方法。对故障轴承的状态特征提取和故障特征准确分类是解决该问题的两个关键。奇异值分解可以将高维相关变量压缩为低维独立的主特征矢量,而支持向量机可以完成模式识别和非线性回归。利用上述原理根据轴承振动信号的变化特征,采用奇异值分解对其提取状态主特征矢量,然后利用建立的支持向量机多故障分类器完成滚动轴承故障模式的识别。试验结果表明,奇异值分解后的主特征矢量与支持向量机相结合可以很好的分辨出轴承的正常和故障状态,并且对未知故障有良好的识别能力。与常用的人工神经网络方法相比,该诊断方法具有更好的有效性、鲁棒性和精确性。
A novel fault diagnosis approach for rolling bearings based on singularity value decomposition（SVD） and support vector machine （SVM） was proposed. The key to the fault bearings diagnosis is condition feature extracting and fault feature classifying. Multidimensional correlated variables were converted into low dimension- al independent main-eigenvector by means of singularity value decomposition. The pattern recognition and the nonlinear regression were achieved by the me^hod of support vector machine. In the light of the feature of bear- ings vibration signals, main-eigenvector was obtained using singularity value decomposition, fault diagnosis of rolling bearing was recognized correspondingly using support vector machine multiple fault classifier. The experi- mental results show that the combination of main-eigenvector and support vector machine distinguish the normal and fault condition finely, and it also has good recognition ability to unknown fault samples. Comparing with the traditional artificial neural networks, theapproach is more efficient, robust and precise.
出处
《农业工程学报》
EI
CAS
CSCD
北大核心
2007年第4期115-119,共5页
Transactions of the Chinese Society of Agricultural Engineering
基金
吉林省教育厅科研基金项目(吉教科合字[2005]第88号)
关键词
滚动轴承
故障诊断
奇异值分解
主特征矢量
支持向量机
模式识别
rolling bearing
fault diagnosis
singularity value decomposition
main-eigenvector
support vector machine
pattern recognition
