Probabilistic deep learning methodology for uncertainty quantification of remaining useful lifetime of multi-component systems

For dealing with uncertainty in Remaining Useful Life (RUL) predictions, numerous studies in literature use stochastic models to characterize the degradation process and predict the RUL distribution. However, in practice, it is difficult to derive stochastic models to capture degradation mechanisms of complex physical systems. Besides, the outstanding achievements in sensing technologies have facilitated the development of data-driven methods. Among them, deep learning methods become one of the most popular trends in recent studies; but they usually provide point predictions without quantifying the output uncertainties. In this paper, we present a new probabilistic deep leaning methodology for uncertainty quantification of multi-component systems’ RUL. It is a combination of a probabilistic model and a deep recurrent neural network to predict the components’ RUL distributions. Then, using the information about the system’s architecture, the formulas to quantify system reliability or system-level-RUL uncertainty are derived. The performance of the proposed methodology is investigated through the benchmark data provided by NASA. The obtained results highlight the point prediction accuracy and the uncertainty management capacity of the proposed methodology. In addition, thanks to the explicit RUL distributions of components, the system reliability for different structures is obtained with high accuracy, especially for series structures. •New data-driven methodology for dealing with uncertainties in prognostics.•Handling uncertainty propagation from component’s RUL to system reliability.•New approach based on combination between probabilistic model and neural network.•Discussion of data quantity impact on system prognostics uncertainty management.•Verification of proposed methodology performance through an engineering application.