Estimation of radiation damage at the structural materials of a hybrid reactor by probabilistic neural networks

This paper presents a new approach based on probabilistic neural networks (PNNs) for the radiation damage parameters at the structural material of a nuclear fusion–fission (hybrid) reactor. Artificial neural networks (ANNs) have recently been introduced to the nuclear engineering applications as a fast and flexible vehicle to modeling, simulation and optimization. The results of the PNNs implemented for the atomic displacement and the helium generation at the structural material of the reactor and the results available in the literature obtained by using the code (Scale 4.3) were compared. The drawn conclusions confirmed that the proposed PNNs could provide an accurate computation of the radiation damage parameters.