Imperial College London
Alternate

DrRonnyPini

Faculty of Engineering, Department of Chemical Engineering

Reader in Chemical Engineering
 
 
 
//

Contact

 

+44 (0)20 7594 7518r.pini Website

 
 
//

Location

 

415ACE ExtensionSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Ward:2022:10.1021/acs.iecr.2c02313,
author = {Ward, A and Pini, R},
doi = {10.1021/acs.iecr.2c02313},
journal = {Industrial and Engineering Chemistry Research},
pages = {13650--13668},
title = {Efficient Bayesian optimisation of industrial-scale pressure-vacuum swing adsorption processes for CO2 capture},
url = {http://dx.doi.org/10.1021/acs.iecr.2c02313},
volume = {61},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - The design of adsorption systems for separation of CO2/N2 in carbon capture applications is notoriously challenging because it requires constrained multiobjective optimization to determine appropriate combinations of a moderately large number of system operating parameters. The status quo in the literature is to use the nondominated sorting genetic algorithm II (NSGA-II) to solve the design problem. This approach requires 1000s of time-consuming process simulations to find the Pareto front of the problem, meaning it can take days of computational time to obtain a solution. As an alternative approach, we have employed a Bayesian optimization algorithm, the Thompson sampling efficient multiobjective optimization (TSEMO). For constrained productivity/energy usage optimization, we find that the TSEMO algorithm is able to find an essentially identical solution to the design problem as that found using NSGA-II, while requiring 14 times less computational time. We have used the TSEMO algorithm to design a postcombustion carbon capture system for a 1000 MW coal fired power plant using two adsorbent materials, zeolite 13X and ZIF-36-FRL. Although ZIF-36-FRL showed promising process-scale performance in previous studies, we find that the industrial-scale performance is inferior to the benchmark zeolite 13X, requiring a 21% greater cost per tonne of CO2 captured. Finally, we have also tested the performance of the Bayesian design framework when coupled with a data-driven machine learning process modeling framework. In this instance, we find that the incumbent NSGA-II offers better computational performance than the Bayesian approach by a factor of 3.
AU  - Ward,A
AU  - Pini,R
DO  - 10.1021/acs.iecr.2c02313
EP  - 13668
PY  - 2022///
SN  - 0888-5885
SP  - 13650
TI  - Efficient Bayesian optimisation of industrial-scale pressure-vacuum swing adsorption processes for CO2 capture
T2  - Industrial and Engineering Chemistry Research
UR  - http://dx.doi.org/10.1021/acs.iecr.2c02313
UR  - http://hdl.handle.net/10044/1/98982
VL  - 61
ER  -
Download