A deep reinforcement learning approach for real-time sensor-driven decision making and predictive analytics. (September 2020)

• Record Type: Journal Article
• Authors: Skordilis, Erotokritos; Moghaddass, Ramin
• Is Part Of: Computers & industrial engineering. Volume 147(2020)
• Publication Date: 2020-09
• Subjects: Particle filters -- Deep reinforcement learning -- Real-time control -- Decision-making -- Remaining useful life estimation; Engineering -- Data processing -- Periodicals; Industrial engineering -- Periodicals; 620.00285
• DOI: 10.1016/j.cie.2020.106600
• Languages: English
• ISSNs: 0360-8352

Abstract

Highlights: A real-time control and decision making framework for system maintenance. A Bayesian Reinforcement Learning framework to estimate remaining life. Stochastic system control policies using system's latent states over time. Generalizing sensor observations to previously unseen states and conditions. Abstract: The increased complexity of sensor-intensive systems with expensive subsystems and costly repairs and failures calls for efficient real-time control and decision making policies. Deep reinforcement learning has demonstrated great potential in addressing highly complex and challenging control and decision making problems. Despite its potential to derive real-time policies using real-time data for dynamic systems, it has been rarely used for sensor-driven maintenance related problems. In this paper, we propose two novel decision making methods in which reinforcement learning and particle filtering are utilized for (i) deriving real-time maintenance policies and (ii) estimating remaining useful life for sensor-monitored degrading systems. The proposed framework introduces a new direction with many potential opportunities for system monitoring. To demonstrate the effectiveness of the proposed methods, numerical experiments are provided from a set of simulated data and a turbofan engine dataset provided by NASA.