Search

Multi-principal element alloys (MPEAs), inclusive of high entropy alloys (HEAs), continue to attract significant research attention owing to their potentially desirable properties. Although MPEAs remain under extensive research, traditional (i.e. empirical) alloy production and testing is both costly and time-consuming, partly due to the inefficiency of the early discovery process which involves experiments on a large number of alloy compositions. It is intuitive to apply machine learning in the discovery of this novel class of materials, of which only a small number of potential alloys has been probed to date. In this work, a proof-of-concept is proposed, combining generative adversarial networks (GANs) with discriminative neural networks (NNs), to accelerate the exploration of novel MPEAs. By applying the GAN model herein, it was possible to directly generate novel compositions for MPEAs, and to predict their phases. To verify the predictability of the model, alloys designed by the model are presented and a candidate produced; as validation. This suggests that the model herein offers an approach that can significantly enhance the capacity and efficiency of development of novel MPEAs.

Background:The design of new nuclear reactors and transmutation devices requires to reduce the present neutron cross section uncertainties of minor actinides. Purpose: Reduce the $^{243}$Am(n,$\gamma$) cross section uncertainty. Method: The $^{243}$Am(n,$\gamma$) cross section has been measured at the n_TOF facility at CERN with a BaF$_{2}$ Total Absorption Calorimeter, in the energy range between 0.7 eV and 2.5 keV. Results: The $^{243}$Am(n,$\gamma$) cross section has been successfully measured in the mentioned energy range. The resolved resonance region has been extended from 250 eV up to 400 eV. In the unresolved resonance region our results are compatible with one of the two incompatible capture data sets available below 2.5 keV. The data available in EXFOR and in the literature has been used to perform a simple analysis above 2.5 keV. Conclusions: The results of this measurement contribute to reduce the $^{243}$Am(n,$\gamma$) cross section uncertainty and suggest that this cross section is underestimated up to 25% in the neutron energy range between 50 eV and a few keV in the present evaluated data libraries.