Development of AI system to support safety operation of nuclear power plants

Seki, Akiyuki   ; Yoshikawa, Masanori ; Okita, Shoichiro  ; Takaya, Shigeru  ; Yan, X. 

Using AI technology, we have developed a surrogate system to estimate various physical quantities in nuclear plants and a system to estimate the state of disturbances that cause anomalies. Both systems use deep learning technology based on a model that connects multiple layers of neurons. In this study, the estimation was performed on data from an analysis code (ACCORD) that can reproduce the behavior of the High Temperature Engineering Test Reactor (HTTR) under various scenarios. The accuracy of the estimation and the range of application of the developed system are presented.