基于小波包变换和极限学习机的滚动轴承故障诊断

Multifault Dignosis for Rolling Bearings Based on Wavelet Packet Transform and Extreme Learning Machine

采用基于小波包变换(WPT)和极限学习(ELM)的方法对轴承故障进行诊断和分类辨识。该方法首先采用小波包变换对采集到的振动信号进行分解,求得各频带的相对能量,并构建特征向量,接着利用极限学习机进行自动分类识别。经使用实验台实测电机滚动轴承不同状态的信号进行分析,研究结果表明,所建立的自动分类模型可以有效地对轴承的单一故障,以及不同程度故障有很好的辨识能力。

In this paper,a new intelligent fault diagnosis scheme and classification based on wavelet packet transform(WPT)and extreme learning machine(ELM)was proposed.The energy of each band was calculated from decomposed original vibration signals as the feature vector input to classifiers.A novel classifier,ELM,was introduced in this study to diagnose the fault on rolling bearings.Different kinds of motor bearing vibration signals were analyzed.The results show that the bearing's normal state,single fault state and multifault state can be effectively classified.