Physics-informed Neural Network With Transfer Learning (tl-pinn) Based On Domain Similarity Measure For Prediction Of Nuclear Reactor Transients

This article discusses the use of Physics Informed Neural Networks (PINNs) to enhance the safety and efficiency of nuclear reactors. It demonstrates that a transfer learning (TL-PINN) approach can significantly reduce the number of iterations needed for model training. Using the Purdue University Reactor One (PUR-1) research reactor as a case study, the article shows that pre-training TL-PINN on one reactor transient (RT) results in up to two orders of magnitude acceleration in prediction of a different RT. The mean error for conventional PINN and TL-PINN models prediction of neutron densities is smaller than 1%. A correlation between TL-PINN performance acceleration and similarity measure of RTs is also developed.