摘要
目前,针对气体吸附性能的测定及材料设计筛选,传统的实验法耗时耗力,因此分子力学方法中的巨正则蒙特卡洛(GCMC)方法已被广泛应用于该领域中,但日益增长的材料数目使得GCMC方法的计算量越来越高。为解决这一问题,本文提出了一种基于机器学习(ML)方法的吸附材料的筛选框架,包含ML模型的建立、理想化PSA工艺模型筛选材料及GCMC方法的验证三个阶段。首先,建立人工神经网络模型,提出了沸石材料的结构描述符“天然构造单元(NBU)”对特定条件下的气体吸附量进行预测。对于CO_(2)和N_(2)气体,分别构建了两个拓扑结构不同的多层前馈神经网络。其次,通过理想吸附溶液理论(IAST)将纯组分的吸附等温线转化为摩尔分数为0.14/0.86的CO_(2)/N_(2)二元混合物吸附等温线,并根据一系列吸附材料评估指标筛选出11种最佳沸石材料,并从中选出4种沸石(MON、ABW、NAB和VSV)计算其GCMC的吸附数据。结果表明,它们对N_(2)的吸附能力远低于CO_(2),因此对两种气体的吸附选择性较高,能够很好地从二元混合物中分离CO_(2)。
At present,in the determination of gas adsorption performance and material design screening,the traditional experiments consume time and effort,so Grand Canonical Monte Carlo(GCMC)method in molecular mechanics has been widely used.However,the growing number of materials makes the GCMC method more and more computationally intensive,and a framework for screening adsorption materials based on machine learning(ML)method was proposed to solve this problem.The framework included three stages:the building of ML model,material selection of idealized PSA process model and validation using GCMC method.Firstly,artificial neural network models were established,and the structure descriptors“natural building unit(NBU)”of zeolite materials was proposed to predict the adsorption capacity under certain conditions.For CO_(2)and N_(2),two multi-layer feed-forward neural networks with different topological structures were built.Secondly,the ideal adsorbed solution theory(IAST)can predict the mixture adsorption isotherms of CO_(2)/N_(2)(mole fractions is 0.14/0.86)from pure-component adsorption isotherms,and then 11“best”zeolite materials were selected by some adsorbent evaluation metrics.Four zeolite materials(MON,ABW,NAB and VSV)were selected and calculate their adsorption data using GCMC method.The results proved that their adsorption capacity for N_(2)was much lower than that for CO_(2),so they had high adsorption selectivity for the two gases and can well separate CO_(2)from binary mixtures.
作者
王璐
张磊
都健
WANG Lu;ZHANG Lei;DU Jian(Institute of Chemical Process Systems Engineering,School of Chemical Engineering,Dalian University of Technology,Dalian 116024,Liaoning,China)
出处
《化工进展》
EI
CAS
CSCD
北大核心
2023年第1期148-158,共11页
Chemical Industry and Engineering Progress
基金
国家自然科学基金(22078041,21808025)
中央高校基本科研业务费(DUT20JC41)。
关键词
机器学习
神经网络
二氧化碳捕集
沸石
巨正则蒙特卡洛
machine learning
neural networks
CO_(2) capture
zeolite
grand canonical Monte Carlo
