机器学习辅助U-Mo合金等温分解参数设计  

Machine Learning Assisted Design of Isothermal Decomposition Parameters of U-Mo Alloy

作　　者：张雪伟 康世栋 王兆松[1] 董青 刘伟[1] 董秋实 乔帅 杨志远 刘志华 陈连重 Zhang Xuewei;Kang Shidong;Wang Zhaosong;Dong Qing;Liu Wei;Dong Qiushi;Qiao Shuai;Yang Zhiyuan;Liu Zhihua;Chen Lianzhong(China North Nuclear Fuel Co.,Ltd,Baotou 014035,China)

机构地区：[1]中核北方核燃料元件有限公司,内蒙古包头014035

出　　处：《稀有金属材料与工程》2020年第11期3835-3840,共6页Rare Metal Materials and Engineering

基　　金：国家科技重大专项(2015ZX06004-001)。

摘　　要：将机器学习方法应用于U-Mo合金等温分解参数的快速设计,以合金硬度为设计指标,基于少量数据建立了合金硬度与上述参数之间的机器学习支持向量机模型。在对硬度预测的基础上,比较了基于预测值和基于预期提高的2类实验设计算法在优化效率方面的差异。结果表明,基于预期提高的实验设计算法通过少量迭代试验能够明显提高合金硬度,而基于预测值的设计算法对硬度提高不明显。应用上述机器学习辅助设计方法,通过4次实验成功地确定了该合金等温分解最佳参数组合为时效温度565℃,时效时间20 h以上,均匀化处理温度为900~950℃,Mo含量为6%(质量分数),在该工艺窗口下处理的合金硬度最高,制粉率最高。本研究对利用机器学习方法快速优化U基合金工艺参数进行了初步尝试,这类基于数据的方法能够有效提高材料研发效率。A machine learning method was applied to the rapid design of isothermal decomposition parameters of U-Mo alloys.With the hardness of the alloy as a design index,a machine learning support vector machine(SVM)model between the alloy hardness and the above parameters was established based on a small amount of data.Based on the prediction of hardness,the differences in optimization efficiency between the two types of experimental design algorithms based on predicted values and based on expected improvement were compared.The results show that the experimental design algorithm based on the expected improvement can significantly improve the hardness through a small number of iterative experiments,while the design algorithm based on the predicted value does not significantly improve the hardness.Using the above-mentioned machine learning aided design method,the optimal parameter combination for isothermal decomposition of the alloy was successfully determined through four experiments.When the aging temperature is 565℃,the aging time is more than 20 h,the homogenization temperature is 900~950℃,and the Mo content is 6 wt%,the hardness of the alloy processed is the highest,and the powder rate is the highest.This study makes a preliminary attempt to use machine learning methods to quickly optimize U-based alloy process parameters.Such data-based methods can effectively improve the efficiency of material development.

关 键 词：贫铀合金 U-MO合金 机器学习 氢化-脱氢 等温分解 

分 类 号：TG146.8[一般工业技术—材料科学与工程]