基于小波及AR模型的机车滚动轴承故障特征提取

滚动轴承失效是机车牵引传动系统的主要故障源之一。为了有效诊断滚动轴承故障,提出了基于小波变换及AR模型参数的机车滚动轴承特征提取方法,以提取能准确反映滚动轴承运行状态的特征信息。首先,通过小波变换对滚动轴承运行时产生的非平稳振动信号进行分解重构,得到不同尺度下的重构信号;然后对重构信号建立AR模型,提取AR模型的自回归参数作为表征滚动轴承运行状态的特征;最后采用支持向量机分类器对提取的特征进行故障分类与识别。仿真结果表明机车滚动轴承故障得到了有效诊断。

Fault Feature Extraction of Locomotive Rolling Bearing Based on Wavelet Transformation and AR Model

Rolling element bearing failures account for a large majority of mechanical faults in a locomotive traction system. A novel feature extraction approach based on wavelet transformation and AR（auto-regressive） model is proposed to detect locomotive rolling bearing faults. so as to that the feature vectors are extracted to reflect accurately the running state of rolling bearing. First of all, the non-stationary signals generated by rolling bearing vibration are decomposed into some coefficients by wavelet transformation. Then the signals of single reconstruction are modeled as auto-regressive models and the parameters are extracted. Finally, fault patterns are recognized by the feature vectors using support vector machine（SVM） classifier. Simulation results show that the locomotive rolling bearings is diagnosed effectively.