Development of countermeasure proposal system using deep reinforcement learning

吉川 雅紀; 関 暁之; 沖田 将一朗; 高屋 茂; Yan, X.

no journal, , 

Downsizing number of operators for advanced nuclear power plant is required in terms of economic performance. However, there is a lack of experience in operating advanced nuclear power plant. Therefore, it is important to develop a support system to make plant state normal if anomalies occurred. To meet the demand, we develop , which, from measured plant values, proposes implementation plans on control apparatuses to recover state of plant. We adopt reinforcement learning to develop this system. By using reinforcement learning, it is expected that the system can deal with broader scope of anomalies than that of followed by conventional human review. In this presentation, we present basic concept of the system and show the efficiency of it under some assumptions.