Abstract
A neural network was designed to model the elongation of neutron-irradiated steels. Predictions were compared to experimental values and were in agreement. The model was extrapolated to predict the elongation at high irradiation doses (200 dpa) and high temperatures (750°C). Because of the lack of experimental values at such doses and temperatures, predictions were accompanied with very large modelling uncertainties. The role of chromium was evaluated; although important in determining the resistance to irradiation-induced hardening, it was not found to have a major influence on elongation.
ACKNOWLEDGMENT
We are grateful to the Engineering and Physical Sciences Research Council for supporting this work.