Semi-supervised constrained hidden markov model using multiple sensors for remaining useful life prediction and optimal predictive maintenance

Abstract

Remaining Useful Life (RUL) estimation is critical in many engineering systems where proper predictive maintenance is needed to increase a unit's effectiveness and reduce time and cost of repairing. Typically for such systems, multiple sensors are normally used to monitor performance, which create difficulties for system state identification. In this paper, we propose a semi-supervised left-to-right constrained Hidden Markov Model (HMM) model, which is the first in the literature to simultaneously address the challenges of semisupervised setting, left-to-right constraint, and monotonicity constraint in a multiple-sensor setting. This proposed method is also effective in estimating the RUL while capturing the jumps among states in condition dynamics. In addition, based on the HMM model learned from multiple sensors, we build a Partial Observable Markov Decision Process (POMDP) to demonstrate how such RUL estimation can be effectively used for optimal preventative maintenance decision making. We apply this technique to the NASA Engine degradation data and demonstrate the effectiveness of the proposed method.