A prognostic driven predictive maintenance framework based on Bayesian deep learning

Recent years have witnessed prominent advances in predictive maintenance (PdM) for complex industrial sys-tems. However, the existing PdM literature predominately separates two inter-related stages-prognostics and maintenance decision making-and either studies remaining useful life (RUL) prognostics without considering maintenance issues or optimizes maintenance plans based on given/assumed prognostic information. In this paper, we propose a prognostic driven dynamic PdM framework by integrating the two stages. In the prognostic stage, we characterize the latent structure between degradation features and RULs through a Bayesian deep learning model. By doing so, the framework is capable of generating a predictive RUL distribution that can well describe prognostic uncertainties. In the maintenance decision-making stage, we dynamically update maintenance and spare-part ordering decisions with the latest predictive RUL information, while satisfying operational constraints. The advantage of the proposed PdM framework is validated by comparison with several benchmark polices, based on the famous C-MAPSS turbofan engine data set.

Automated summary

Recent years have seen significant advances in predictive maintenance (PdM) for complex industrial systems. However, existing literature primarily focuses on either prognostics or maintenance decision making, without integrating the two stages. In this paper, we propose a dynamic PdM framework that integrates prognostics and maintenance decision making, using a Bayesian deep learning model to characterize the relationship between degradation features and remaining useful life (RUL). The framework can generate a predictive RUL distribution that effectively represents prognostic uncertainties, and update maintenance decisions based on the latest predictive RUL information.