Stochastic Identification and Analysis of Long-Term Degradation Through Health Index Data

The timely diagnosis and prognosis based on degradation symptoms are essential steps for condition-based maintenance (CBM) to guarantee industrial safety and productivity. Most industrial machines operate under variable operating conditions. This time-varying operating condition can accelerate the machinery’s degradation process. It may have a massive influence on data and impede the process of diagnosis and prognosis of the machinery. So, in this paper, to address the mentioned problems, we introduced an approach for modelling non-stationary long-term condition monitoring data. This procedure includes separating random and deterministic parts and identifying possible autodependence hidden in the random sequence, as well as potential a time-dependent variance. We employ an approach by using a time-varying coefficient autoregressive (TVC-AR) model and Bayesian theory to achieve these purposes. Furthermore, we applied the proposed procedure to an artificial simulated degradation model and real data sets known in the community as benchmark (reference) data sets (namely FEMTO and data from wind turbine drive). Finally, the results obtained for the simulated and real data sets approved the efficiency of the proposed approach.