Nicolas Hayer, Thorsten Wendel, Stephan Mandt, Hans Hasse, Fabian Jirasek
{"title":"Advancing thermodynamic group-contribution methods by machine learning: UNIFAC 2.0","authors":"Nicolas Hayer, Thorsten Wendel, Stephan Mandt, Hans Hasse, Fabian Jirasek","doi":"10.1016/j.cej.2024.158667","DOIUrl":null,"url":null,"abstract":"Accurate prediction of thermodynamic properties is pivotal in chemical engineering for optimizing process efficiency and sustainability. Physical group-contribution (GC) methods are widely employed for this purpose but suffer from historically grown, incomplete parameterizations, limiting their applicability and accuracy. In this work, we overcome these limitations by combining GC with matrix completion methods (MCM) from machine learning. We use the novel approach to predict a complete set of pair-interaction parameters for the most successful GC method: UNIFAC, the workhorse for predicting activity coefficients in liquid mixtures. The resulting new method, UNIFAC 2.0, is trained and validated on more than 224,000 experimental data points, showcasing significantly enhanced prediction accuracy (e.g., nearly halving the mean squared error) and increased scope by eliminating gaps in the original model’s parameter table. Moreover, the generic nature of the approach facilitates updating the method with new data or tailoring it to specific applications.","PeriodicalId":270,"journal":{"name":"Chemical Engineering Journal","volume":"24 1","pages":""},"PeriodicalIF":13.3000,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Chemical Engineering Journal","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1016/j.cej.2024.158667","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, CHEMICAL","Score":null,"Total":0}
引用次数: 0
Abstract
Accurate prediction of thermodynamic properties is pivotal in chemical engineering for optimizing process efficiency and sustainability. Physical group-contribution (GC) methods are widely employed for this purpose but suffer from historically grown, incomplete parameterizations, limiting their applicability and accuracy. In this work, we overcome these limitations by combining GC with matrix completion methods (MCM) from machine learning. We use the novel approach to predict a complete set of pair-interaction parameters for the most successful GC method: UNIFAC, the workhorse for predicting activity coefficients in liquid mixtures. The resulting new method, UNIFAC 2.0, is trained and validated on more than 224,000 experimental data points, showcasing significantly enhanced prediction accuracy (e.g., nearly halving the mean squared error) and increased scope by eliminating gaps in the original model’s parameter table. Moreover, the generic nature of the approach facilitates updating the method with new data or tailoring it to specific applications.
期刊介绍:
The Chemical Engineering Journal is an international research journal that invites contributions of original and novel fundamental research. It aims to provide an international platform for presenting original fundamental research, interpretative reviews, and discussions on new developments in chemical engineering. The journal welcomes papers that describe novel theory and its practical application, as well as those that demonstrate the transfer of techniques from other disciplines. It also welcomes reports on carefully conducted experimental work that is soundly interpreted. The main focus of the journal is on original and rigorous research results that have broad significance. The Catalysis section within the Chemical Engineering Journal focuses specifically on Experimental and Theoretical studies in the fields of heterogeneous catalysis, molecular catalysis, and biocatalysis. These studies have industrial impact on various sectors such as chemicals, energy, materials, foods, healthcare, and environmental protection.