Proposal of a novel AI-based plant operator support system for the safety of nuclear power plants

Takaya, Shigeru  ; Seki, Akiyuki   ; Yoshikawa, Masanori ; Sasaki, Naoto*; Yan, X. 

Enhancing the ability to manage abnormal situations is important for improvement of the safety of nuclear power plants. It is necessary to investigate potential risks thoroughly in advance, and prepare countermeasures against the identified risks. In case of an occurrence of an abnormal situation, plant operators are required to recognize the plant situation promptly and select a suitable countermeasure. This study develops a novel plant operator support system designed not only to estimate details of anomalies in a plant but also propose countermeasures adaptively by employing several AI technologies of deep neural network and reinforcement learning. The design and performance of the proposed system is illustrated using High Temperature engineering Test Reactor operated in Japan Atomic Energy Agency.