4.4 Article

Predicting of Covalent Organic Frameworks for Membrane-based Isobutene/1,3-Butadiene Separation: Combining Molecular Simulation and Machine Learning

Journal

CHEMICAL RESEARCH IN CHINESE UNIVERSITIES
Volume 38, Issue 2, Pages 421-427

Publisher

HIGHER EDUCATION PRESS
DOI: 10.1007/s40242-022-1452-z

Keywords

Covalent organic framework; Isobutene/1,3-butadiene separation; Molecular simulation; Machine learning

Funding

  1. National Natural Science Foundation of China [22038010, 21878229, 22108202, 22008179, 21978212, 22078024]
  2. Science and Technology Plans of Tianjin, China [19PTSYJC00020, 20ZYJDJC00110, 21ZYJDJC00040]

Ask authors/readers for more resources

In this study, the application of COF membranes in the separation of i-C4H8 and C4H6 was investigated using molecular simulation and machine learning. Potential COF membranes with high membrane performance score and moderate membrane selectivity were screened out, and the mechanism of membrane separation dominated by adsorption was revealed. A random forest model with high prediction accuracy was established to elucidate the key factors controlling membrane selectivity and i-C4H8 permeability, and the optimal COF features were obtained through a structure-performance relationship study. These findings may accelerate the design of novel COFs with improved separation performance of i-C4H8/C4H6.
Efficient separation of C4 olefins is of critical importance and a challenging task in petrochemical industry. Covalent organic frameworks(COFs) could be used as promising candidates for membrane-based isobutene/1,3-butadiene(i-C4H8/C4H6) separation. Owing to large amounts of COFs appearing, however, the rapid prediction of optimal COFs is imperative before experimental efforts. In this work, we combine molecular simulation and machine learning to study COF membranes for efficient isolation of i-C4H8 over C4H6. Using molecular simulation, four potential COF membranes, which possess both high membrane performance score (MPS) value and moderate membrane selectivity were screened out and the mechanism of membrane separation further revealed is an adsorption dominated process. Further, random forest(RF) model with high prediction accuracy(R-2>0.84) was obtained and used for elucidating key factors in controlling the membrane selectivity and i-C4H8 permeability. Ultimately, the optimal COF features were obtained through structure-performance relationship study. Our results may trigger experimental efforts to accelerate the design of novel COFs with better i-C4H8/C4H6 separation performance.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.4
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available