Machine learning-assisted discovery of flow reactor designs

Tom Savage, Nausheen Basha, Jonathan McDonough, James Krassowski, Omar Matar, Ehecatl Antonio del Rio Chanona
{"title":"Machine learning-assisted discovery of flow reactor designs","authors":"Tom Savage, Nausheen Basha, Jonathan McDonough, James Krassowski, Omar Matar, Ehecatl Antonio del Rio Chanona","doi":"10.1038/s44286-024-00099-1","DOIUrl":null,"url":null,"abstract":"Additive manufacturing has enabled the fabrication of advanced reactor geometries, permitting larger, more complex design spaces. Identifying promising configurations within such spaces presents a significant challenge for current approaches. Furthermore, existing parameterizations of reactor geometries are low dimensional with expensive optimization, limiting more complex solutions. To address this challenge, we have established a machine learning-assisted approach for the design of new chemical reactors, combining the application of high-dimensional parameterizations, computational fluid dynamics and multi-fidelity Bayesian optimization. We associate the development of mixing-enhancing vortical flow structures in coiled reactors with performance and used our approach to identify the key characteristics of optimal designs. By appealing to the principles of fluid dynamics, we rationalized the selection of design features that lead to experimental plug flow performance improvements of ~60% compared with conventional designs. Our results demonstrate that coupling advanced manufacturing techniques with ‘augmented intelligence’ approaches can give rise to reactor designs with enhanced performance. Identifying the optimal geometry of continuous flow reactors is a major challenge due to the large available parameter design space. Here the authors combine a machine learning-assisted methodology with computational fluid dynamics and additive manufacturing for the design of more efficient, complex coiled-tube reactors.","PeriodicalId":501699,"journal":{"name":"Nature Chemical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44286-024-00099-1.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nature Chemical Engineering","FirstCategoryId":"1085","ListUrlMain":"https://www.nature.com/articles/s44286-024-00099-1","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Additive manufacturing has enabled the fabrication of advanced reactor geometries, permitting larger, more complex design spaces. Identifying promising configurations within such spaces presents a significant challenge for current approaches. Furthermore, existing parameterizations of reactor geometries are low dimensional with expensive optimization, limiting more complex solutions. To address this challenge, we have established a machine learning-assisted approach for the design of new chemical reactors, combining the application of high-dimensional parameterizations, computational fluid dynamics and multi-fidelity Bayesian optimization. We associate the development of mixing-enhancing vortical flow structures in coiled reactors with performance and used our approach to identify the key characteristics of optimal designs. By appealing to the principles of fluid dynamics, we rationalized the selection of design features that lead to experimental plug flow performance improvements of ~60% compared with conventional designs. Our results demonstrate that coupling advanced manufacturing techniques with ‘augmented intelligence’ approaches can give rise to reactor designs with enhanced performance. Identifying the optimal geometry of continuous flow reactors is a major challenge due to the large available parameter design space. Here the authors combine a machine learning-assisted methodology with computational fluid dynamics and additive manufacturing for the design of more efficient, complex coiled-tube reactors.

Abstract Image

机器学习辅助发现流动反应器设计
快速成型制造技术能够制造出先进的反应堆几何形状,允许更大、更复杂的设计空间。要在这些空间内确定有前景的配置,对目前的方法是一个巨大的挑战。此外,现有的反应器几何参数化维度较低,优化成本高昂,限制了更复杂的解决方案。为了应对这一挑战,我们建立了一种机器学习辅助方法,将高维参数化、计算流体动力学和多保真贝叶斯优化的应用结合起来,用于设计新型化学反应器。我们将盘式反应器中混合增强涡流结构的发展与性能联系起来,并利用我们的方法确定了最佳设计的关键特征。通过利用流体动力学原理,我们合理地选择了设计特征,与传统设计相比,这些特征使实验塞流性能提高了约 60%。我们的研究结果表明,将先进制造技术与 "增强智能 "方法相结合,可以产生具有更高性能的反应器设计。由于可用参数设计空间较大,确定连续流反应器的最佳几何形状是一项重大挑战。在这里,作者将机器学习辅助方法与计算流体动力学和增材制造相结合,设计出了更高效、更复杂的盘管反应器。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信