Summary Based on the failure of critical parameter sensors at nuclear power plants (NPPs) during accidents, a prediction model for critical parameter prediction during accidents was developed utilizing a long short‐term memory (LSTM) neural network and historical‐critical parameter operation sequences. The validation results show that the critical parameters model built with the LSTM neural network accurately predicts nuclear power, pressurizer pressure, pressurizer water level, coolant flow rate, coolant average temperature, and steam generator water level under loss of coolant accident and steam generator tube rupture conditions, and can help in the event of a sensor failure of critical operating parameters. This means that NPP operators will be able to better control the unit's status and improve safety in the event of a major operating parameter sensor failure.

Summary To address the issue of large inaccuracies in the low‐burnup region of aditonal machine learning algorithms for predicting nuclide density, the DRAGON code is used to produce 9600 samples using the nuclide densities of 235U, 239Pu, 241Pu, 137Cs, and 154Nd as prediction parameters. The mean square error (MSE) was used as the loss function for the deep neural network‐based nuclide density prediction model. The trained model is used to predict the target nuclides in the test set, and the relative error with the multilayer perceptron model are compared. The prediction results demonstrate that the deep neural network‐based prediction model not only overcomes the issue of excessive prediction errors in the low‐burnup region of the traditional machine learning algorithm model, but also has lower prediction errors in the medium‐burnup and high‐burnup regions, demonstrating the feasibility of artificial intelligence in nuclide density prediction.

No abstract