Abstract
With the rapid development of computer technology, artificial intelligence and big data technology have undergone a qualitative leap, permeating into various industries. In order to fully harness the role of artificial intelligence in the field of nuclear engineering, we propose to use the LSTM algorithm in deep learning to model the BEAVRS (Benchmark for Evaluation And Validation of Reactor Simulations) core first cycle loading. The BEAVRS core is simulated by DRAGON and DONJON, the training set and the test set are arranged in a sequential fashion according to the evolution of time, and the LSTM model is constructed by changing a number of hyperparameters. In addition to this, the training set and the test set are retained in a chronological order that is different from one another throughout the whole process. Additionally, there is a significant pattern that is followed when subsetting both the training set and the test set. This pattern applies to both sets. The steps in this design are very carefully arranged. The findings of the experiments suggest that the model can be altered by making use of the appropriate hyperparameters in such a way as to bring the maximum error of the effective multiplication factor keff prediction of the core within 2.5 pcm (10(-5)), and the average error within 0.5266 pcm, which validated the successful application of machine learning to transport equations.