基于机器学习的燃料棒温度分布代理模型构建方法研究  

Research on Construction Method of a Machine Learning-Based Fuel Rod Temperature Distribution Surrogate Model

作　　者：刘振海[1] 齐飞鹏 周毅[1] 李垣明[1] 李文杰[1] 曾未[1] 辛勇[1] 王浩煜 马超[1] Liu Zhenhai;Qi Feipeng;Zhou Yi;Li Yuanming;Li Wenjie;Zeng Wei;Xin Yong;Wang Haoyu;Ma Chao(Science and Technology on Reactor System Design Technology Laboratory,Nuclear Power Institute of China,Chengdu,610213,China)

机构地区：[1]中国核动力研究设计院核反应堆系统设计技术重点实验室,成都610213

出　　处：《核动力工程》2023年第S02期1-5,共5页Nuclear Power Engineering

摘　　要：为提高大规模燃料棒性能模拟的计算效率,以燃料棒温度预测为例,研究了燃料棒温度分布预测代理模型(简称“代理模型”)的构建方法。以燃料棒性能分析程序COPERNIC的计算结果作为数据源,采用k-means聚类算法筛选代表性的训练数据,训练了4个全连接前馈神经网络,分别能够考虑冷却剂流动传热及氧化膜生长影响的包壳外表面温度预测、包壳径向温度分布预测、燃料芯块和包壳间隙变化影响的燃料芯块外表面温度预测、燃料芯块径向温度分布预测。通过这些神经网络的组合,可以根据输入的燃料棒功率史快速预测出燃料棒不同时刻的温度分布。数值试验表明:构建的代理模型相比COPERNIC程序计算速度提升约204倍,同时具有较高精度。在整个数据集上,包壳温度和燃料芯块温度预测的平均偏差分别为0.07℃、0.44℃。In order to improve the computational efficiency of large-scale fuel rod performance simulation,the construction method of fuel rod temperature distribution surrogate model(referred to as"surrogate model")is studied by taking fuel rod temperature prediction as an example.The calculation results of the fuel rod performance analysis code COPERNIC are used as the data source,and the representative training data are selected by using the k-means clustering algorithm.Four fully connected feedforward neural networks are trained to predict the outer surface temperature of the cladding considering the effects of coolant flow heat transfer and oxide film growth,the radial temperature distribution of the cladding,the outer surface temperature of the fuel pellet considering the effects of the gap variation between the fuel pellet and cladding,and the radial temperature distribution of the fuel pellet.By combining these neural networks,the temperature distribution of the fuel rod at different times can be quickly predicted based on the input fuel rod power history.Numerical experiments show that the calculation speed of the surrogate model is about 204 times faster than that of the COPERNIC code,and it has high accuracy.The mean deviations of fuel cladding and pellet temperature prediction on the whole data set are about 0.07°C and 0.44°C respectively.

关 键 词：神经网络 燃料棒温度 代理模型 燃料行为 

分 类 号：TL333[核科学技术—核技术及应用]