基于小波包分解和支持向量数据描述的故障诊断方法

METHOD OF FAULT DIAGNOSIS BASED ON WAVELET PACKET DECOMPOSITION AND SUPPORT VECTOR DATA DESCRIPTION

支持向量数据描述(support vector data description,SVDD)是一种单值分类方法,该方法能够在只有一类学习样本的情况下建立分类器,其在机械故障诊断中的应用有望解决制约智能故障诊断技术发展的故障数据缺乏问题。文中提出一种基于小波包分解特征提取和SVDD的故障诊断方法,用小波包分解技术提取信号各频带的能量作为信号特征,用SVDD方法进行分类。对滚动轴承故障诊断的仿真实验结果显示,该方法可有效处理复杂机械振动信号,提高故障诊断的准确性。

Support vector data description（SVDD） is a one class classification method. It can build a classifier with only one class data, So the applying of SVDD to the machine fault diagnosis is expected to solve the problem of shortage of fault data in machine diagnosis. A machine diagnose method which use wavelet packet technology to feature extraction and use support vector data description （SVDD） to classification was presented and then the method was applied to rolling bearing fault diagnosis, The result shows that the method is efficient to the complex machine vibration signals and can improve the veracity of diagnosis significantly.