Optimal Prescriptive Maintenance of Nuclear Power Plants by Deep Reinforcement Learning

The Operation & Maintenance (O&M) of complex energy systems, such as Nuclear Power Plants (NPPs), is driven by productivity and safety goals, but it is also challenged by the need of flexibility of production to respond to uncertain demand in an economically sustainable manner. Most O&M strategies for NPPs do not directly address the flexible requirement. In this paper, we develop a Deep Reinforcement Learning (DRL)-based prescriptive maintenance approach to search for the best O&M strategy, considering the actual system health conditions (e.g., the Remaining Useful Life (RUL), and satisfying the need of flexible operation to accommodate load-following while keeping reliability and profitability high. The approach integrates Proximal Policy Optimization (PPO) and Imitation Learning (IL) for training the RL agent of prescriptive maintenance. The Advanced Lead-cooled Fast Reactor European Demonstrator (ALFRED) is considered to show the applicability of the approach proposed.