摘要
将经验模态分解和自回归(AR)模型应用到滚动轴承的故障诊断中,该方法先把轴承振动信号分解成不同特征时间尺度的固有模态函数,从而把非平稳信号处理转化为平稳信号处理问题,然后选取表征轴承故障的IMF分量,并建立其AR模型,提取模型的参数输入到支持向量机中进行识别。实验结果表明,该方法是有效的。
Empirical mode decomposition (EMD) and AR model are applied to the fault diagnosis of wiling bearing. The methodology developed decomposes the signal in intrinsic oscillation modes first, to translate the non- stationary signals into stationary signals. Then the autoregressive (AR) model of the selected IMF is established, and the parameters were served as input parameter of SVM to identify fault patterns of rolling bearing. The experimental result shows that the proposed approach is effective.
出处
《煤矿机械》
北大核心
2007年第7期183-186,共4页
Coal Mine Machinery
基金
河南省自然科学基金(0611022400)
河南省教育厅自然科学基金(2006460005)
河南省杰出人才创新基金(0621000500)资助项目
关键词
AR模型
经验模态分解
支持向量机
滚动轴承
AR model
empirical mode decomposition (EMD)
support vector machine(SVM)
wiling bearing