A mixture of Gaussians Hidden Markov Model for failure diagnostic and prognostic

This paper deals with a data-driven diagnostic and prognostic method based on a Mixture of Gaussians Hidden Markov Model. The prognostic process of the proposed method is made in two steps. In the first step, which is performed off-line, the monitoring data provided by sensors are processed to extract features, which are then used to learn different models that capture the time evolution of the degradation and therefore of the system's health state. In the second step, performed on-line, the learned models are exploited to do failure diagnostic and prognostic by estimating the asset's current health state, its remaining useful life and the associated confidence degree. The proposed method is tested on a benchmark data related to several bearings and simulation results are given at the end of the paper.