Towards a Deep Reinforcement Learning based approach for real time decision making and resource allocation for Prognostics and Health Management applications

Abstract

Industrial operational environments are stochastic and can have complex system dynamics which introduce multiple levels of uncertainty. This uncertainty can lead to sub-optimal decision making and resource allocation. Digitalization and automation of production equipment and the maintenance environment enable predictive maintenance, which means that equipment can be stopped for maintenance at the optimal time instant. Resource constraints in maintenance capacity could however result in further undesired downtime if maintenance cannot be performed when scheduled. In this paper the use of a multi-agent deep reinforcement learning based approach for decision making is investigated to determine the optimal maintenance scheduling policy for a fleet of assets where there are maintenance resource constraints. By considering the underlying system dynamics of maintenance capacity, as well as the health state of individual assets, a near-optimal decision making policy is found that increases equipment availability while also maximizing maintenance capacity. The proposed solution is compared to a run-to-failure corrective maintenance strategy, a constant interval preventive maintenance strategy and a condition based predictive maintenance strategy. The proposed approach outperformed traditional maintenance strategies across several asset and operational maintenance performance metrics. It is concluded that deep reinforcement learning based decision making for asset health management and resource allocation is more effective than human based decision making.