Stochastic prognostics under multiple time-varying environmental factors

Prediction of the remaining useful life in-field components, traditionally, relies on condition monitoring signals which are correlated with physical degradation system. Many models assume that behave under similar environmental conditions (e.g. pressure, temperature, workload and relative humidity) or these have no effect process. In this paper, we propose a Brownian motion process stress-dependent drift to model multiple time-varying covariates. A semiparametric regression approach utilizing penalized splines is, further, proposed covariates-drift relationship. The unique feature our is it does not functional form for covariates’ Moreover, combined in situ measurements unit its predict unit’s through Bayesian updating scheme. performance framework investigated benchmarked analysis based numerical studies case study using real-world data frying oil collected from connected fryers.