摘要
提出了一种基于小波包分解的频带局部能量特征提取方法。在小波包分解的理论基础上 ,引入了频带局部能量的概念 ,用以表征信号在某个频带的某个时间段的能量大小 ,反映了信号频率的时变性。并以仿真信号为例 ,说明基于小波包分解的频带局部能量特征提取方法的有效性。
Vibration signals of a machine are proved to be non stationary ones. They usually carry important dynamic information of a machine and are very useful for fault diagnosis. Wavelet packet decomposition is a tool for signal identification. In this paper, a new feature extraction method based on wavelet packet decomposition was presented. The concept of local power of frequency bands used for measurement of signal power in selected frequency bands and certain periods was defined. The proposed feature extraction method was tested by the simulated signals and the results showed that the method was effective.
出处
《农业机械学报》
EI
CAS
CSCD
北大核心
2004年第5期177-180,共4页
Transactions of the Chinese Society for Agricultural Machinery
关键词
小波包分解
频带局部
能量特征
提取方法
机械
故障诊断
Fault diagnosis, Feature extraction, Wavelet packet, Local power of frequency bands