Elman's recurrent neural network applications to condition monitoring in nuclear power plant and rotating machinery

The purpose of this study is to show the capability of recurrent neural nets (RNN) for condition monitoring and diagnosis in nuclear power plant systems and rotating machinery. In the first application, the study addresses the use of RNN for detecting anomalies introduced from the simulated power operation of a high-temperature gas cooled nuclear reactor. In the second, it is used to detect the motor bearing damage using a coherence function approach, which is defined between the motor current and vibration signals, for induction motors. Hence, the high performance of Elman's RNN was shown by means of two different applications.