机器学习辅助高通量筛选金属有机骨架用于富碳天然气中分离CO_(2)  

Machine learning-assisted high-throughput screening approach for CO_(2)separation from CO_(2)-rich natural gas using metal-organic frameworks

作　　者：周印洁 吉思蓓 何松阳 吉旭[1] 贺革[1] ZHOU Yinjie;JI Sibei;HE Songyang;JI Xu;HE Ge(School of Chemical Engineering,Sichuan University,Chengdu 610065,Sichuan,China)

机构地区：[1]四川大学化学工程学院,四川成都610065

出　　处：《化工学报》2025年第3期1093-1101,共9页CIESC Journal

基　　金：国家重点研发计划项目(2021YFB40005)。

摘　　要：在碳达峰和碳中和目标的推动下,开发绿色化学技术,如利用海上风电电解水生产的绿色氢气和从富碳天然气中分离出来的CO_(2)合成绿甲醇具有重要的社会经济意义。但如何高效分离海洋富碳天然气中的二氧化碳成为其中的关键技术难点,常规的高通量筛选方法用于金属有机骨架(MOFs)分离实际天然气组分CO_(2)面临着模型复杂性高、求解时间长的问题。提出了一种机器学习辅助的高通量筛选策略,其在训练集和测试集上的R^(2)值分别超过了0.98和0.92,可用于快速从富碳天然气六元混合物(N_(2)、CO_(2)、CH_(4)、C_(2)H_(6)、C_(3)H_(8)、H_(2)S)中分离出CO_(2)。Driven by the goal of carbon dioxide peaking and carbon neutrality,it is of great social and economic significance to develop green chemical technologies,such as the substantial use of H_(2)generated by water electrolysis with offshore wind power and CO_(2)separated from CO_(2)-rich natural gas to produce green methanol is gaining significant socioeconomic and environmental relevance.However,how to efficiently separate carbon dioxide from marine carbon-rich natural gas has become a key technical difficulty.Conventional high-throughput screening methods for metal organic frameworks(MOFs)to separate actual natural gas component CO_(2)face the problems of high model complexity and long solution time.Therefore,a machine learning-assisted high-throughput screening strategy is proposed.The R^(2)values on the training set and the test set are more than 0.98 and 0.92,respectively,which can be used to quickly and efficiently separate CO_(2)from the actual natural gas of six components(N_(2),CO_(2),CH_(4),C_(2)H_(6),C_(3)H_(8),H_(2)S).

关 键 词：金属有机骨架 高通量筛选 CO_(2)分离 机器学习 分子模拟 富碳天然气 

分 类 号：O604[理学—化学]