基于小波分析的机械故障特征提取研究_陈长征.pdfVIP

Journal of Mechanical Strength 机械强度 2001, 23(2) : 161~ 164 X FAULT FEATURE EXTRATION OF MACHINERY BASED ON WAVELET ANALYSIS XX ( 沈阳工业大学 建筑工程系, 沈阳 110023) ( 东北大学 设备诊断工程中心, 沈阳 110006) CHEN Changzheng LUO Yuegang ( Dep artment of Architecture Engineering , Shenyang University of Technology , Shenyang 110023, China) Z HANG Sheng YU Heji ( Center fo Equipment Diagnosis , Northeastern University , Shenyang 110006, China) , ; , , , , , , , TP206. 3 TH165. 3 Abstract The research of diagnosing common mechanical fault usually ut more em hasize on their recognition and classification. Thus the method of fault diagnosis is designed to increase diagnosis rate, while according to ractical a lication, the method is not er- fect. It is ut forward, in this a er, that the reflection factors of mechanical failure are not only fault category, but also its osition and intensity. Shock, oil whi , friction and rotating s eed mutation roduce singular signal, the singular oint of signal contains enormous fault information. The wavelet analysis is a goodway to describe singular signal, for it ossesses a fine local time-frequency characteris- tics. The feature of fault signal, which is obtained by singular signal ins ection, signal-noise se aration and signal frequency range anal- ysis by means of wavelet analysis, can be used to identify the osition and intensity of the fault. The extracted fault information can be a lied with other fault diagnosis methods, such as neural networks and fuzzy diagnosi