使用机器学习理解中子辐照α-U中的Fission气泡分布、镧系元素输运和热导率退化
Understanding Fission Gas Bubble Distribution, Lanthanide Transportation, and Thermal Conductivity Degradation in Neutron-irradiated α-U Using Machine Learning
摘要：
铀锆基金属核燃料是美国下一代钠冷快堆的主要候选燃料。美国研究堆自20世纪60年代以来一直在使用和试验这种燃料类型，并积累了相当多的经验和有关燃料性能的知识。然而，大多数知识仍然是经验性的。对燃料性能的机械理解的缺乏阻碍了UZr燃料用于商业用途的资格。本文提出了一种数据驱动的方法，再加上先进的辐照后检查，由机器学习算法提供动力，通过提供前所未有的量化裂变气泡的新见解来促进这种理解的发展。具体来说，基于先进的后辐射检查数据收集的中子辐照的U-10 Zr环形燃料，我们开发了一种方法来自动检测，分类~19,000裂变气泡到不同的类别，并定量链接的数据，镧系元素蒸腾沿径向温度梯度。该方法是通用的，可以修改，以研究不同的耦合辐照效应，如二次相的再分布和热导率的退化，在辐照核燃料。
英文摘要：
UZr based metallic nuclear fuel is the leading candidate for next-generation sodium-cooled fast reactors in the United States. US research reactors have been using and testing this fuel type since the 1960s and accumulated considerable experience and knowledge about the fuel performance. However, most of knowledge remains empirical. The lack of mechanistic understanding of fuel performance is preventing the qualification of UZr fuel for commercial use. This paper proposes a data-driven approach, coupled with advanced post irradiation examination, powered by machine learning algorithms, to facilitate the development of such understandings by providing unpreceded quantified new insights into fission gas bubbles. Specifically, based on the advanced postirradiation examination data collected on a neutron-irradiated U-10Zr annular fuel, we developed a method to automatically detect, classify ~19,000 fission gas bubbles into different categories, and quantitatively link the data to lanthanide transpiration along the radial temperature gradient. The approach is versatile and can be modified to study different coupled irradiation effects, such as secondary phase redistribution and degradation of thermal conductivity, in irradiated nuclear fuel.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
