Automated self-optimisation of multi-step reaction and separation processes using machine learning
Adam D. Clayton,Artur M. Schweidtmann,Graeme Clemens,Jamie A. Manson,Connor J. Taylor,Carlos González Niño,Thomas W. Chamberlain,Nikil Kapur,A. John Blacker,Alexei A. Lapkin,Richard A. Bourne +10 more
Reads0
Chats0
TLDR
The combination of multi-objective optimisation based on machine learning methods (TSEMO algorithm) with self-optimising platforms for the optimisation of multi -step continuous reaction processes with respect to multiple objectives has the potential to make substantial savings in time and resources.About:
This article is published in Chemical Engineering Journal.The article was published on 2020-03-15 and is currently open access. It has received 78 citations till now. The article focuses on the topics: Active learning (machine learning).read more
Citations
More filters
DatasetDOI
Research data supporting "A novel internet-based reaction monitoring, control and autonomous self-optimization platform for chemical synthesis"
TL;DR: In this article, the authors present raw data files from analytical equipment for each example experiment described in the paper, as well as a detailed description of the experiments performed by the analytical equipment.
Journal ArticleDOI
Machine Learning in Chemical Engineering: Strengths, Weaknesses, Opportunities, and Threats
Maarten R. Dobbelaere,Pieter Plehiers,Ruben Van de Vijver,Christian V. Stevens,Kevin Van Geem +4 more
TL;DR: The greatest opportunities involve using machine learning in time-limited applications such as real-time optimization and planning that require high accuracy and that can build on models with a self-learning ability to recognize patterns, learn from data, and become more intelligent over time.
Journal ArticleDOI
Intelligent Microfluidics: The Convergence of Machine Learning and Microfluidics in Materials Science and Biomedicine
TL;DR: The potential of operating microfluidic platforms via closed-loop data-driven models by leveraging multimodal monitoring and data-acquisition instrumentation is elaborated on, believing this approach will provide a robust framework for fundamental explorations in materials science and biomedicine.
Journal ArticleDOI
Toward Machine Learning-Enhanced High-Throughput Experimentation
TL;DR: This analysis highlights the complementarity of the two fields, while exposing a number of obstacles that can and should be overcome to take full advantage of this merger and thereby accelerate chemical research.
Journal ArticleDOI
Summit: Benchmarking Machine Learning Methods for Reaction Optimisation
TL;DR: In this paper, the authors developed chemically-motivated virtual benchmarks for reaction optimisation and compared several strategies on these benchmarks, which are encompassed in an open source framework named Summit.
References
More filters
Journal ArticleDOI
A fast and elitist multiobjective genetic algorithm: NSGA-II
TL;DR: This paper suggests a non-dominated sorting-based MOEA, called NSGA-II (Non-dominated Sorting Genetic Algorithm II), which alleviates all of the above three difficulties, and modify the definition of dominance in order to solve constrained multi-objective problems efficiently.
Journal ArticleDOI
ParEGO: a hybrid algorithm with on-line landscape approximation for expensive multiobjective optimization problems
TL;DR: Results show that NSGA-II, a popular multiobjective evolutionary algorithm, performs well compared with random search, even within the restricted number of evaluations used.
Journal ArticleDOI
On-demand continuous-flow production of pharmaceuticals in a compact, reconfigurable system
Andrea Adamo,Rachel L. Beingessner,Mohsen Behnam,Jie Chen,Timothy F. Jamison,Klavs F. Jensen,Jean-Christophe Monbaliu,Allan S. Myerson,Eve Revalor,David R. Snead,Torsten Stelzer,Nopphon Weeranoppanant,Shin Yee Wong,Ping Zhang +13 more
TL;DR: An apparatus roughly the size of a household refrigerator is presented that can synthesize and purify pharmaceuticals under continuous-flow conditions, and the synthesis and formulation of active pharmaceutical ingredients in a compact, reconfigurable manufacturing platform is reported.
Journal ArticleDOI
Single- and multiobjective evolutionary optimization assisted by Gaussian random field metamodels
TL;DR: The extensive use of the uncertainty information of predictions for screening the candidate solutions makes it possible to significantly reduce the computational cost of singleand multiobjective EA.
Journal ArticleDOI
Flow Chemistry: Recent Developments in the Synthesis of Pharmaceutical Products
TL;DR: In this article, it has been demonstrated that a safer manufacturing of organic intermediates and APIs could be obtained under continuous flow conditions, where some s... can also be easily combined to other enabling technologies, such as microwave irradiation, supported reagents or catalysts, photochemistry, inductive heating, electrochemistry, new solvent systems, 3D printing, or microreactor technology.