摘要
针对齿轮工作状态的识别与智能故障诊断问题,提出了应用小波与支持向量机相结合进行齿轮智能故障诊断的方法。将齿轮不同工作状态下的振动信号经小波包分解后的频带能量作为特征向量,并以此作为训练样本对多个支持向量机构成的齿轮多故障分类器进行训练,进而实现对齿轮的智能诊断。通过对提升机齿轮的故障诊断研究表明,小波包与支持向量机相融合的故障诊断与识别技术发挥了两者的优点,是提取机械故障特征进行设备状态自动识别的有效方法。
Aiming at the problem of gear working state on identification and intelligent fault diagnosis,a method of gear intelligent fault diagnosis is proposed by means of the wavelet-support vector machine. According to the method,the energy of frequency bands after wavelet packet decomposition of the vibration signals in different working states is taken as the eigenvectors and also as training samples of SVM multi-fault classifier. The result of research on elevator gear shows that the fault diagnosis and identification technology, based on synthesizing the wavelet packet and support vector machine, shows their strong points. And it is an effective method of extracting mechanical fault characteristics and auto-identifying working states of equipment.
出处
《山东科技大学学报（自然科学版）》
CAS
2008年第4期31-36,共6页
Journal of Shandong University of Science and Technology(Natural Science)
关键词
小波包
支持向量机
齿轮
故障诊断
wavelet packet
support vector machine
gear
fauh diagnosis
