High-throughput screening of zeolite materials for CO2/N2 selective adsorption separation by machine learning

被引：0

作者：

Wang L. ^{[1
]}

Zhang L. ^{[1
]}

Du J. ^{[1
]}

机构：

[1] Institute of Chemical Process Systems Engineering, School of Chemical Engineering, Dalian University of Technology, Liaoning, Dalian

来源：

Huagong Jinzhan/Chemical Industry and Engineering Progress | 2023年 / 42卷 / 01期

关键词：

CO[!sub]2[!/sub] capture; grand canonical Monte Carlo; machine learning; neural networks; zeolite;

D O I：

10.16085/j.issn.1000-6613.2022-0539

中图分类号：

学科分类号：

摘要：

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 CO2 and N2, 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 CO2/N2 (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 N2 was much lower than that for CO2, so they had high adsorption selectivity for the two gases and can well separate CO2 from binary mixtures. © 2023 Chemical Industry Press. All rights reserved.

引用

页码：148 / 158

页数：10

共 40 条

[21]

YANN LeCun, YOSHUA Bengio, Convolutional networks for images, speech, and time-series, The Handbook of Brain Theory and Neural Networks, pp. 255-258, (1995)

[22]

HINTON Geoffrey E, OSINDERO Simon, TEH Yee Whye, A fast learning algorithm for deep belief nets, Neural Computation, 18, 7, pp. 1527-1554, (2006)

[23]

IYER Shachit, DEMIREL Salih E, HASAN M M Faruque, Combined natural gas separation and storage based on in silico material screening and process optimization, Industrial & Engineering Chemistry Research, 57, 49, pp. 16727-16750, (2018)

[24]

SIMON Cory M, SMIT Berend, HARANCZYK Maciej, pyIAST: ideal adsorbed solution theory (IAST) Python package, Computer Physics Communications, 200, pp. 364-380, (2016)

[25]

ANUROVA Natalia A, BLATOV Vladislav A, ILYUSHIN Gregory D, Et al., Natural tilings for zeolite-type frameworks, The Journal of Physical Chemistry C, 114, 22, pp. 10160-10170, (2010)

[26]

Database of Zeolite Structures

[27]

GOODFELLOW I, BENGIO Y, COURVILLE A., Deep learning, (2016)

[28]

MCCULLOCH Warren S, PITTS Walter, A logical calculus of the ideas immanent in nervous activity, The Bulletin of Mathematical Biophysics, 5, 4, pp. 115-133, (1943)

[29]

MYERS A L, PRAUSNITZ J M., Thermodynamics of mixed-gas adsorption, AIChE Journal, 11, 1, pp. 121-127, (1965)

[30]

HAND D W, LOPER S, ARI M, Et al., Prediction of multicomponent adsorption equilibria using ideal adsorbed solution theory, Environmental Science & Technology, 19, 11, pp. 1037-1043, (1985)

← 1 2 3 4 →