Prediction of Automatic Scram during Abnormal Conditions of Nuclear Power Plants Based on Long Short-Term Memory (LSTM) and Dropout

<div>Testing RMSE (with error bar) vs. training RMSE by Elman neural network models. (a) Hidden node number = 10. (b) Hidden node number = 20.</div>

Science and Technology of Nuclear Installations

Figure 7: Prediction of Automatic Scram during Abnormal Conditions of Nuclear Power Plants Based on Long Short-Term Memory (LSTM) and Dropout 