2020
DOI: 10.1016/j.cej.2019.123340
|View full text |Cite
|
Sign up to set email alerts
|

Automated self-optimisation of multi-step reaction and separation processes using machine learning

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
86
0

Year Published

2020
2020
2022
2022

Publication Types

Select...
5
2
1

Relationship

2
6

Authors

Journals

citations
Cited by 124 publications
(95 citation statements)
references
References 40 publications
0
86
0
Order By: Relevance
“…An example of an algorithm for efficient multi-objective reaction optimization is the open-source Thompson Sampling Efficient Multi-Objective (TS-EMO). [7] Lapkin and co-workers [6,[8][9][10] have demonstrated the quality of the generated Pareto fronts, as well as the algorithm's efficiency at identifying them, when compared with alternative algorithms such as ParEGO. [11] Alternative examples multi-objective algorithms [12] developed for chemical process include Phoenics [13] and Chimera.…”
Section: Introductionmentioning
confidence: 99%
“…An example of an algorithm for efficient multi-objective reaction optimization is the open-source Thompson Sampling Efficient Multi-Objective (TS-EMO). [7] Lapkin and co-workers [6,[8][9][10] have demonstrated the quality of the generated Pareto fronts, as well as the algorithm's efficiency at identifying them, when compared with alternative algorithms such as ParEGO. [11] Alternative examples multi-objective algorithms [12] developed for chemical process include Phoenics [13] and Chimera.…”
Section: Introductionmentioning
confidence: 99%
“…The use of design‐of‐experiment (DoE) methods partially addresses these drawbacks, but the high number of experiments required to locate a satisfactory optimum associated to the absence of feedback are strong handicaps to develop efficient automations. The development and optimization of continuous flow processes can be greatly speeded‐up with the use of autonomous self‐optimizing flow reactors [11–26] . These powerful automated devices combine flow reactors with process control instrumentations, in‐line/online analyses and optimization algorithms to assist the decision‐making process of chemists [27–34] .…”
Section: Resultsmentioning
confidence: 99%
“…Another option is to use an optimization algorithm [ 5 ] in combination with a continuous‐flow platform for the automated optimization of a specific chemical transformation, which can then be expanded to expand the substrate scope. [ 6 ] Machine learning (ML) can also be used here to aid in the synthesis of small organic molecules, [ 7 ] for example, by automating the self‐optimization of chemical reactions, [ 8 ] including those that involve multiple steps, [ 9 ] and searching for new chemical reactivity. [ 10 ]…”
Section: Steps To Materials Discoverymentioning
confidence: 99%