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.

RPV钢辐照诱导转变温度偏移的预测是核电厂长期运行的重要方法。基于辐照脆化数据，利用机器学习方法XGBoost建立了辐照诱导转变温度偏移预测模型。然后进行残差、标准偏差和预测值与实测值的分析，以分析该模型的准确性。最后，给出了Cu含量阈值和饱和值分析、温度依赖性、Ni/Cu依赖性和通量效应以验证可靠性。这些结果表明，使用 XGBoost 开发的预测模型对于预测 RPV 钢的辐照脆化趋势具有较高的准确性。