Kershaw, OJ, Clayton, AD orcid.org/0000-0002-4634-8008, Manson, JA orcid.org/0000-0001-7392-3197 et al. (8 more authors) (2023) Machine learning directed multi-objective optimization of mixed variable chemical systems. Chemical Engineering Journal, 451 (1). 138443. ISSN 1385-8947
Abstract
The consideration of discrete variables (e.g. catalyst, ligand, solvent) in experimental self-optimisation approaches remains a significant challenge. Herein we report the application of a new mixed variable multi-objective optimisation (MVMOO) algorithm for the self-optimisation of chemical reactions. Coupling of the MVMOO algorithm with an automated continuous flow platform enabled identification of the trade-off curves for different performance criteria by optimizing the continuous and discrete variables concurrently. This approach utilizes a Bayesian methodology to provide high optimisation efficiency, enhances process understanding by considering key interactions between the mixed variables, and requires no prior knowledge of the reaction. Nucleophilic aromatic substitution (SNAr) and palladium catalyzed Sonogashira reactions were investigated, where the effect of solvent and ligand selection on the regioselectivity and process efficiency were determined respectively whilst simultaneously determining the optimum continuous parameters in each case.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2022 The Author(s). Published by Elsevier B.V. This is an open access article under the terms of the Creative Commons Attribution License (CC-BY 4.0), which permits unrestricted use, distribution and reproduction in any medium, provided the original work is properly cited. |
Keywords: | Automated flow reactor; Machine learning; Mixed variable optimization; Multi-objective; Reaction engineering |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Chemical & Process Engineering (Leeds) The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Chemistry (Leeds) > Inorganic Chemistry (Leeds) |
Funding Information: | Funder Grant number EPSRC (Engineering and Physical Sciences Research Council) EP/V055089/1 EPSRC (Engineering and Physical Sciences Research Council) EP/S000380/1 |
Depositing User: | Symplectic Publications |
Date Deposited: | 09 Aug 2022 15:11 |
Last Modified: | 02 Aug 2023 00:13 |
Status: | Published |
Publisher: | Elsevier |
Identification Number: | 10.1016/j.cej.2022.138443 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:189712 |
Downloads
Filename: Mixed Variable Optimization (manuscript - revised).pdf
Licence: CC-BY-NC-ND 4.0
Filename: 1-s2.0-S1385894722039250-main.pdf
Licence: CC-BY 4.0