A Reinforcement Learning Approach to Health Aware Control Strategy
This addresses the challenge of health-aware control for systems with component degradation, such as industrial machinery, but is incremental as it builds on existing reinforcement learning and prognostics methods.
The paper tackles the problem of incorporating Remaining Useful Life (RUL) predictions into control strategies for health-aware systems, where mathematical models are often unavailable, by proposing a reinforcement learning framework that integrates global system transition data and RUL tracking to learn optimal control policies, achieving results demonstrated through simulation of a DC motor and shaft wear.
Health-aware control (HAC) has emerged as one of the domains where control synthesis is sought based upon the failure prognostics of system/component or the Remaining Useful Life (RUL) predictions of critical components. The fact that mathematical dynamic (transition) models of RUL are rarely available, makes it difficult for RUL information to be incorporated into the control paradigm. A novel framework for health aware control is presented in this paper where reinforcement learning based approach is used to learn an optimal control policy in face of component degradation by integrating global system transition data (generated by an analytical model that mimics the real system) and RUL predictions. The RUL predictions generated at each step, is tracked to a desired value of RUL. The latter is integrated within a cost function which is maximized to learn the optimal control. The proposed method is studied using simulation of a DC motor and shaft wear.