Health Status-Based Predictive Maintenance Decision-Making via LSTM and Markov Decision Process

Maintenance decision-making is essential to achieve safe and reliable operation with high performance for equipment. To avoid unexpected shutdown increase machine life as well system efficiency, it fundamental design an effective maintenance scheme In this paper, we propose a novel method equipment based on Long Short-Term Memory (LSTM) Markov decision process, which can provide specific strategies in different degradation stages of the system. Specifically, LSTM model firstly applied predict remaining service distinguish its health state quantitatively. Then, bearing residual prediction curve, process constructed, corresponding parameters are identified. Finally, curve obtained by model, constructed accurate conditions demonstrate effectiveness proposed method, experimental study full cycle data set rolling bearings carried out. The results show that efficient decisions under states, provides feasible solution systems.