Yubin Ryu , Sunkyu Shin , Won Bo Lee , Jonggeol Na
{"title":"利用物理信息神经网络实现聚合反应器中的多物理场泛化","authors":"Yubin Ryu , Sunkyu Shin , Won Bo Lee , Jonggeol Na","doi":"10.1016/j.ces.2024.120385","DOIUrl":null,"url":null,"abstract":"<div><p>Multiphysics engineering has been a crucial task in a chemical reactor because complicated interactions among fluid mechanics, chemical reactions, and transport phenomena greatly affect the performance of a chemical reactor. Recently, physics-informed neural networks (PINN) have been successfully applied to various engineering problems thanks to their domain generalization ability. Herein, we introduce a novel application of PINN to multiphysics in a chemical reactor. Specifically, we examined the effectiveness of PINN to reconstruct and extrapolate ethylene conversion in a polymerization reactor. We ran CFD for the polymerization reactor to use in the training process; thereafter, we constructed the PINN by combining the loss of conventional neural networks (NN) with the residuals of the continuity, Navier-Stokes, and species transport physics equations. Our results showed that the PINN more accurately predicted the overall ethylene concentration profile, which is the primary result of multiphysics in the reactor; PINN showed 18 % lower mean absolute error (0.1028 mol/L) than NN (0.1267 mol/L). Furthermore, the PINN satisfactorily predicted the conversion concaveness effect, which is a unique multiphysical effect in a radical polymerization reactor, while NN couldn’t. These results highlight that multiphysics in a chemical reactor may be efficiently predicted and even extrapolated by harnessing physics in neural networks.</p></div>","PeriodicalId":271,"journal":{"name":"Chemical Engineering Science","volume":null,"pages":null},"PeriodicalIF":4.1000,"publicationDate":"2024-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Multiphysics generalization in a polymerization reactor using physics-informed neural networks\",\"authors\":\"Yubin Ryu , Sunkyu Shin , Won Bo Lee , Jonggeol Na\",\"doi\":\"10.1016/j.ces.2024.120385\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Multiphysics engineering has been a crucial task in a chemical reactor because complicated interactions among fluid mechanics, chemical reactions, and transport phenomena greatly affect the performance of a chemical reactor. Recently, physics-informed neural networks (PINN) have been successfully applied to various engineering problems thanks to their domain generalization ability. Herein, we introduce a novel application of PINN to multiphysics in a chemical reactor. Specifically, we examined the effectiveness of PINN to reconstruct and extrapolate ethylene conversion in a polymerization reactor. We ran CFD for the polymerization reactor to use in the training process; thereafter, we constructed the PINN by combining the loss of conventional neural networks (NN) with the residuals of the continuity, Navier-Stokes, and species transport physics equations. Our results showed that the PINN more accurately predicted the overall ethylene concentration profile, which is the primary result of multiphysics in the reactor; PINN showed 18 % lower mean absolute error (0.1028 mol/L) than NN (0.1267 mol/L). Furthermore, the PINN satisfactorily predicted the conversion concaveness effect, which is a unique multiphysical effect in a radical polymerization reactor, while NN couldn’t. These results highlight that multiphysics in a chemical reactor may be efficiently predicted and even extrapolated by harnessing physics in neural networks.</p></div>\",\"PeriodicalId\":271,\"journal\":{\"name\":\"Chemical Engineering Science\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.1000,\"publicationDate\":\"2024-06-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Chemical Engineering Science\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0009250924006857\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, CHEMICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Chemical Engineering Science","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0009250924006857","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, CHEMICAL","Score":null,"Total":0}
Multiphysics generalization in a polymerization reactor using physics-informed neural networks
Multiphysics engineering has been a crucial task in a chemical reactor because complicated interactions among fluid mechanics, chemical reactions, and transport phenomena greatly affect the performance of a chemical reactor. Recently, physics-informed neural networks (PINN) have been successfully applied to various engineering problems thanks to their domain generalization ability. Herein, we introduce a novel application of PINN to multiphysics in a chemical reactor. Specifically, we examined the effectiveness of PINN to reconstruct and extrapolate ethylene conversion in a polymerization reactor. We ran CFD for the polymerization reactor to use in the training process; thereafter, we constructed the PINN by combining the loss of conventional neural networks (NN) with the residuals of the continuity, Navier-Stokes, and species transport physics equations. Our results showed that the PINN more accurately predicted the overall ethylene concentration profile, which is the primary result of multiphysics in the reactor; PINN showed 18 % lower mean absolute error (0.1028 mol/L) than NN (0.1267 mol/L). Furthermore, the PINN satisfactorily predicted the conversion concaveness effect, which is a unique multiphysical effect in a radical polymerization reactor, while NN couldn’t. These results highlight that multiphysics in a chemical reactor may be efficiently predicted and even extrapolated by harnessing physics in neural networks.
期刊介绍:
Chemical engineering enables the transformation of natural resources and energy into useful products for society. It draws on and applies natural sciences, mathematics and economics, and has developed fundamental engineering science that underpins the discipline.
Chemical Engineering Science (CES) has been publishing papers on the fundamentals of chemical engineering since 1951. CES is the platform where the most significant advances in the discipline have ever since been published. Chemical Engineering Science has accompanied and sustained chemical engineering through its development into the vibrant and broad scientific discipline it is today.