Monitoring and learning algorithms for dynamic hybrid Bayesian network in on-line system health management applications

This paper presents a new modeling approach, computational algorithm, and an example application for health monitoring and learning in on-line System Health Management (SHM). A hybrid Dynamic Bayesian Network (DBN) is introduced to represent complex engineering systems with underlying physics of failure by modeling a theoretical or empirical degradation model with continuous variables. The methodology is designed to be flexible and intuitive, and scalable from small, localized functionality to large complex dynamic systems. Markov Chain Monte Carlo (MCMC) inference is optimized using a pre-computation strategy and dynamic programming for on-line monitoring of system health. Proposed Monitoring and Anomaly Detection algorithm uses pattern recognition to improve failure detection and estimation of Remaining Useful Life (RUL). Pre-computation inference database enables efficient on-line learning and maintenance decision-making. The proposed methodology and algorithm are demonstrated with an Unmanned Aerial Vehicle (UAV) application.