Evaluation of the performance of different feature selection techniques for identification of NPPs transients using deep learning.

• To determine the most important input parameters for NPP transient identification, the present paper has proposed a hybrid feature selection method. • Several filter methods are used to generate appropriate feature subsets by calculating the score of each feature. • A Long Short-Term Memory (LSTM) deep neural network is selected as the classifier to determine the best feature subset. • The Neighbourhood Components Analysis filter method has selected the best subset of features. • The effect of the number of used features on the accuracy of the model was investigated. Accidents that occur at NPPs must be correctly identified so quickly that mitigation actions can be taken in a timely manner. Depending on the type of transient, the operating parameters follow different patterns and it might be possible to identify the transient by monitoring these parameters. Due to the large number of parameters of an NPP, it is necessary to determine the parameters that play a vital role in transient identification. Data-driven methods have shown effective performance for NPP transient identification. To determine the most important input parameters for NPP transient identification, the present paper has utilized a hybrid feature selection method, in which feature subsets are created using several filter methods and then the best feature subset is determined by comparing the training results of a deep Long Short-Term Memory network. According to the results, the Neighbourhood Components Analysis method has selected the best subset of features. [ABSTRACT FROM AUTHOR]