A study of predicting irradiation-induced transition temperature shift for RPV steels with XGBoost modeling
Chaoliang Xu, Xiangbing Liu, Hongke Wang, Yuanfei Li, Wenqing Jia, Wangjie Qian, Qiwei Quan, Huajian Zhang, Fei Xue
Abstract
The prediction of irradiation-induced transition temperature shift for RPV steels is an important method for long term operation of nuclear power plant. Based on the irradiation embrittlement data, an irradiation-induced transition temperature shift prediction model is developed with machine learning method XGBoost. Then the residual, standard deviation and predicted value vs. measured value analysis are conducted to analyze the accuracy of this model. At last, Cu content threshold and saturation values analysis, temperature dependence, Ni/Cu dependence and flux effect are given to verify the reliability. Those results show that the prediction model developed with XGBoost has high accuracy for predicting the irradiation embrittlement trend of RPV steel. The prediction results are consistent with the current understanding of RPV embrittlement mechanism.