{"title":"Deep-learning-based acceleration of critical point calculations","authors":"Vishnu Jayaprakash, Huazhou Li","doi":"10.1016/j.ces.2024.120371","DOIUrl":null,"url":null,"abstract":"<div><p>Computation of the critical point of complex fluid mixtures is an important part of understanding their thermodynamic phase behaviour. While algorithms for these calculations are well established, they are often slow when the number of constituting components is large. In this work, we propose a new procedure to significantly accelerate critical point calculations by leveraging deep neural network (DNN) models. A DNN model for critical point predictions of a given mixture is first trained based on the critical points of such a mixture with various compositions. The predictions of the DNN model are then used to initialize both of the commonly used algorithms for mixture critical point calculations: root finding and global minimization. We demonstrate that when using the DNN-based predictions to initialize the root-finding-based and optimization-based algorithms, we can achieve 50-90% and 80-90% reductions in the number of required iterations, respectively.</p></div>","PeriodicalId":271,"journal":{"name":"Chemical Engineering Science","volume":null,"pages":null},"PeriodicalIF":4.1000,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0009250924006717/pdfft?md5=ae64546b84ca23c68621fd530a3323a2&pid=1-s2.0-S0009250924006717-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Chemical Engineering Science","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0009250924006717","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}
引用次数: 0
Abstract
Computation of the critical point of complex fluid mixtures is an important part of understanding their thermodynamic phase behaviour. While algorithms for these calculations are well established, they are often slow when the number of constituting components is large. In this work, we propose a new procedure to significantly accelerate critical point calculations by leveraging deep neural network (DNN) models. A DNN model for critical point predictions of a given mixture is first trained based on the critical points of such a mixture with various compositions. The predictions of the DNN model are then used to initialize both of the commonly used algorithms for mixture critical point calculations: root finding and global minimization. We demonstrate that when using the DNN-based predictions to initialize the root-finding-based and optimization-based algorithms, we can achieve 50-90% and 80-90% reductions in the number of required iterations, respectively.
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.