Data driven and model based fault prognosis applied to a mechatronic system

This paper deals with fault prognosis method based on fault reconstruction. The presented method aims to estimate the RUL by the reconstruction of the fault trend after detecting the degradation beginning. The fault diagnosis part is realized using a Principal Component Analysis (PCA), and the fault reconstruction is done using the fault direction matrix. The RUL is estimated using a qualitative model when a data on faulty operation are available, and multi-physical model when a data on faulty operation are not available. The developed method is applied on a mechatronic system.