Machine Learning-Assisted High-Throughput Screening of Metal–Organic Frameworks for CO2 Separation from CO2-Rich Natural Gas,Industrial & Engineering Chemistry Research

当前位置： X-MOL 学术 › Ind. Eng. Chem. Res. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Machine Learning-Assisted High-Throughput Screening of Metal–Organic Frameworks for CO2 Separation from CO2-Rich Natural Gas
Industrial & Engineering Chemistry Research ( IF 3.8 ) Pub Date : 2024-09-13 , DOI: 10.1021/acs.iecr.4c02357
Yinjie Zhou ₁ , Sibei Ji ₁ , Songyang He ₁ , Wei Fan ₁ , Liang Zan ₁ , Li Zhou ₁ , Xu Ji ₁ , Ge He ₁

Affiliation

Under the appeal of carbon peaking and carbon neutrality goals, it is highly advisable to develop green chemical technologies. Based on this, it is even more attractive to synthesize methanol with the H₂ generated from water electrolysis by offshore wind power and the CO₂ separated from offshore CO₂-rich natural gas. Therefore, the separation and adsorption of CO₂-rich natural gas in this context is of great socioeconomic significance. However, the conventional high-throughput screening methods for metal–organic frameworks (MOFs) in separating natural gas components and CO₂ suffer from great challenges such as high model complexity and long computation time. To address the aforementioned problems, a machine learning-assisted modeling and screening strategy is proposed herein for the rapid and efficient separation of CO₂ from the actual natural gas of six components (N₂, CO₂, CH₄, C₂H₆, C₃H₈, and H₂S). First, structural analysis is used to eliminate the MOFs that cannot adsorb CO₂ from the Computation-Ready Experimental Metal–Organic Frameworks (CoRE-MOFs) database. Six structural and 17 chemical descriptors of the remaining MOFs were calculated. Grand Canonical Monte Carlo (GCMC) simulations were applied to evaluate the separation performance metrics of the randomly selected training and testing MOF samples. By combining 23 descriptors and separation performance metrics, a Random Forest (RF) regression model was obtained with R² exceeding 0.92 on the test samples, which was employed to predict the separation performance of the remaining MOFs. As a result, 10 MOF candidates with the best CO₂ separation performance were obtained. Furthermore, a structure–property relationship of MOFs with satisfactory regenerability was conducted. Three design strategies were proposed to guide the development of high-performance novel MOFs for CO₂ separation. This study offers a high-throughput screening framework for MOFs to facilitate the separation of CO₂ from a CO₂-rich natural gas.

中文翻译：

机器学习辅助金属有机框架的高通量筛选，用于从富含二氧化碳的天然气中分离二氧化碳

在碳达峰和碳中和目标的号召下，发展绿色化工技术势在必行。基于此，利用海上风电电解水产生的H ₂和海上富含CO ₂的天然气分离出的CO ₂合成甲醇就更具有吸引力。因此，在此背景下对富CO ₂天然气进行分离和吸附具有重要的社会经济意义。然而，分离天然气组分和CO ₂的金属有机框架（MOF）的传统高通量筛选方法面临着模型复杂度高和计算时间长等巨大挑战。为了解决上述问题，本文提出了一种机器学习辅助建模和筛选策略，用于从实际天然气中快速有效地分离六种_组分（N ₂ 、CO ₂ 、CH ₄ 、C ₂ H ₆ 、 C ₃ H ₈和H ₂ S)。首先，使用结构分析从可计算实验金属有机框架（CoRE-MOF）数据库中消除不能吸附CO _{2 的}MOF。计算了剩余 MOF 的 6 个结构描述符和 17 个化学描述符。应用大正则蒙特卡罗 (GCMC) 模拟来评估随机选择的训练和测试 MOF 样本的分离性能指标。通过结合23个描述符和分离性能指标，获得R ²超过0的随机森林（RF）回归模型。92 在测试样品上，用于预测剩余 MOF 的分离性能。结果，获得了具有最佳CO ₂分离性能的10个候选MOF。此外，还建立了具有令人满意的再生能力的 MOF 的结构-性能关系。提出了三种设计策略来指导用于CO ₂分离的高性能新型MOF的开发。这项研究为 MOF 提供了一个高通量筛选框架，以促进 CO ₂从富含 CO _{2 的}天然气中分离。

更新日期：2024-09-13

点击分享查看原文

点击收藏

阅读更多本刊新发论文本刊介绍/投稿指南