Health monitoring and fault detection using wavelet packet technique and multivariate process control method

Generally, machines will undergo two stages: normal working stage and irreversible degradation stage, before they fail. The division of two these stages are helpful for remaining useful life (RUL) estimation. With the help of health monitoring technique, the start point of the degradation stage can be detected successfully, which facilitates the prognostic activities. This paper reports the work on the detection of start point of the degradation stage in machines. An approach, which combines the wavelet packet technique and multivariate statistical process control method, for fault detection was developed. Motor bearings and fans data are employed to illustrate the effectiveness of the proposed method. Results show that it is feasible for fault detection.