Answers are grounded in this paper and cite their sources.
This paper presents an investigation into the possible influence of pre-irradiation hardening of RPV steel on the transition temperature shift, ΔT 41J . Using the ASTM PLOTTER-22 database supplemented with unirradiated yield stress, YS(u), data the study uses machine learning regression algorithms to construct a predictive model that accounts for YS(u) alongside more well-established predictor variables (e.g., copper, fluence, …). The Gradient Boosting algorithm emerged as the most efficient, with performance metrics R 2 = 0.89 ± 0.02 and root-mean square error (RMSE) = 11.2 ± 0.7 °C. Comparative analyses via bootstrapping underscore the beneficial effect of incorporating YS(u) as a regressor, resulting in a RMSE reduction by 7 % and R 2 improvement of 15 %. Feature interpretation techniques demonstrate that the significance of YS(u) is comparable to elements like nickel and irradiation temperature and above others such as manganese, phosphorus, or the product form of the steel. The revealed trend — higher YS(u) corresponding to lower ΔT 41J — and the lack of significant interactions between YS(u) and the chemical composition, supports the roughly independent role of YS(u). These results underscore the value of incorporating YS(u) as a predictor variable for irradiation embrittlement. • ML algorithms were developed to predict ΔT41J using YS(u) as a predictor. • This extended model led to a 7 % reduction in RMSE and a 15 % boost in R 2 . • SHAP importance showed that YS(u) is on par with features such as Ni or temperature. • Steels with a higher YS(u) exhibit a lower ΔT 41J , the rest of things being equal.
No takes yet. Share an insight, caveat, or question.
Ferreño et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: