Fault Diagnosis Capability of Shallow vs Deep Neural Networks for Small Modular Reactor

NPPs warrant a reliable and effective fault diagnosis system. Data driven approaches especially neural networks have gained popularity in the past few years in the field of fault diagnosis. However, most of the researches in this field for NPP apply shallow neural networks which do not amply cater the requirements of this application. This paper is an attempt to show advantages of deep network i.e. LSTM over commonly used feed forward network. Moreover, commonly applied network architecture is 1-D which is not in sync with the requirement of NPP 2-D dataset. In manuscript, IP-200 which is a Small Modular Reactor was simulated in RELAP-5 thermal hydraulic code in different conditions. The results show obvious superiority of deep network over shallow networks.