四川大学学报（自然科学版）2025，Vol.62Issue(2)：297-308,12.DOI:10.19907/j.0490-6756.240291
机器学习在PUREX工艺中的应用综述
A review on the application of machine learning in PUREX
摘要
Abstract
With the development of nuclear power industry and the widespread applications of nuclear fuel in energy sector,the amount of nuclear waste generated increases rapidly.Due to the necessity of resource re-covery and management of the radioactive materials to control hazards,nuclear fuel reprocessing is consid-ered an indispensable process.Plutonium uranium refining by extraction(PUREX),owing to its high effi-ciency,strong scalability and wide applicability,has been extensively employed in nuclear fuel reprocessing.In PUREX,it is necessary to comprehensively measure and analyze the properties of extractants and solution systems and to ensure the safeguarding of PUREX reprocessing.Previous studies mainly focused on obtaining relevant data by traditional batch experiments involving multiple experimental iterations and manual opera-tions,which results in long research cycle,increased resource consumption and low extraction efficiency.Ma-chine learning(ML)is extensively expected to play a vital role in the prediction and decision-making of PUREX since ML can avoid the problem inherent in the repeated experiments by learning and analysis of vast amounts of data.In this paper,we focus on the application of ML in PUREX and provide a review on the ap-plication of ML in the internal reaction and reprocessing of PUREX process.On the one hand,the applica-tions of ML in the selection of extractants,the prediction of extractants properties and the selection of solu-tion systems are elucidated.On the other hand,the applications of ML for safeguarding the reprocessing pro-cess are introduced.It is positive that the applications of ML in PUREX can provide more accurate predictions and improve the extraction efficiency.We also delve into the applications of ML in other relevant fields of PUREX,such as the liquid-liquid extraction domain and nuclear engineering field,which lays the ground-work for the integrations of PUREX with other ML models.Specifically,we introduce a novel approach com-bining molecular dynamics with ML which allows for model training and prediction at molecular level,thereby improving the accuracy of model predictions significantly.Besides the selection of suitable ML algo-rithms for PUREX,we also provide an overview on how ML algorithms can be employed to expand and en-hance the datasets to overcome the challenge of small data set required to establish the mathematical models of PUREX process and to reduce the cost of batch experiments.Finally,as for further studies in the future,we recommend the use of ML to predict the distribution ratios which reflects the extraction efficiency of metal ions,and the algorithms combining ML with molecular dynamics.关键词
PUREX/机器学习/核燃料后处理/萃取剂/溶液体系Key words
PUREX/Machine learning/Nuclear fuel reprocessing/Extractant/Solution system分类
数理科学引用本文复制引用
于婷,张音音,金文蕾,张睿志,罗应婷,朱升峰,何辉,龚禾林,叶国安..机器学习在PUREX工艺中的应用综述[J].四川大学学报（自然科学版）,2025,62(2):297-308,12.基金项目
国家自然科学基金(U2241289) （U2241289）
中核集团青年英才基金(FY222506000503) （FY222506000503）
