Non-stationary signal analysis and transient machining process condition monitoring

Non-stationary machine condition monitoring is very important in modem auto mated manufacturing processes. In this research, an innovative non-stationa ry (transient) signal analysis approach has been developed for non-stationa ry machine condition monitoring. It is based on time-frequency distribution analysis and a singular value decomposition approach. The singular value d ecomposition method is used to extract features from the time-frequency dis tribution data. These features will serve as machine condition indices and can be easily incorporated for on-line machine condition monitoring and dia gnosis. Satisfactory results have been obtained through simulation and expe rimental data. Experimental studies have demonstrated the effectiveness of the proposed method for transient machine and process condition monitoring. (C) 2001 Elsevier Science Ltd. All rights reserved.