{"title":"基于机器学习的纳米流体热特性预测","authors":"Youngsuk Oh, Zhixiong Guo","doi":"10.1615/heattransres.2024054096","DOIUrl":null,"url":null,"abstract":"In this study, machine learning-based predictions of thermal conductivity, dynamic viscosity, and specific heat of nanofluids are explored. Various types of nanofluids and parametric conditions are considered to broaden and evaluate the effectiveness of popular machine learning models, including multilayer perceptron, random forest, light gradient boosting machine, extreme gradient boosting and stacking algorithms. The performance of these prediction models is assessed using mean squared error and coefficient of determination. The influence of each input variable on model development was examined to identify key features. Information gain is introduced and calculated for determining the importance of parameters in prediction. External validation is performed with an additional unseen dataset to further assess the applicability of the selected models across different experimental data points. It was found that the stacking technique is the most accurate machine learning algorithm among those investigated. The results demonstrate that machine learning methods can provide excellent predictions of the thermophysical properties of complex nanofluids.","PeriodicalId":50408,"journal":{"name":"Heat Transfer Research","volume":null,"pages":null},"PeriodicalIF":1.7000,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Machine learning-based predictions of nanofluid thermal properties\",\"authors\":\"Youngsuk Oh, Zhixiong Guo\",\"doi\":\"10.1615/heattransres.2024054096\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this study, machine learning-based predictions of thermal conductivity, dynamic viscosity, and specific heat of nanofluids are explored. Various types of nanofluids and parametric conditions are considered to broaden and evaluate the effectiveness of popular machine learning models, including multilayer perceptron, random forest, light gradient boosting machine, extreme gradient boosting and stacking algorithms. The performance of these prediction models is assessed using mean squared error and coefficient of determination. The influence of each input variable on model development was examined to identify key features. Information gain is introduced and calculated for determining the importance of parameters in prediction. External validation is performed with an additional unseen dataset to further assess the applicability of the selected models across different experimental data points. It was found that the stacking technique is the most accurate machine learning algorithm among those investigated. The results demonstrate that machine learning methods can provide excellent predictions of the thermophysical properties of complex nanofluids.\",\"PeriodicalId\":50408,\"journal\":{\"name\":\"Heat Transfer Research\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.7000,\"publicationDate\":\"2024-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Heat Transfer Research\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1615/heattransres.2024054096\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"THERMODYNAMICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Heat Transfer Research","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1615/heattransres.2024054096","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"THERMODYNAMICS","Score":null,"Total":0}
Machine learning-based predictions of nanofluid thermal properties
In this study, machine learning-based predictions of thermal conductivity, dynamic viscosity, and specific heat of nanofluids are explored. Various types of nanofluids and parametric conditions are considered to broaden and evaluate the effectiveness of popular machine learning models, including multilayer perceptron, random forest, light gradient boosting machine, extreme gradient boosting and stacking algorithms. The performance of these prediction models is assessed using mean squared error and coefficient of determination. The influence of each input variable on model development was examined to identify key features. Information gain is introduced and calculated for determining the importance of parameters in prediction. External validation is performed with an additional unseen dataset to further assess the applicability of the selected models across different experimental data points. It was found that the stacking technique is the most accurate machine learning algorithm among those investigated. The results demonstrate that machine learning methods can provide excellent predictions of the thermophysical properties of complex nanofluids.
期刊介绍:
Heat Transfer Research (ISSN1064-2285) presents archived theoretical, applied, and experimental papers selected globally. Selected papers from technical conference proceedings and academic laboratory reports are also published. Papers are selected and reviewed by a group of expert associate editors, guided by a distinguished advisory board, and represent the best of current work in the field. Heat Transfer Research is published under an exclusive license to Begell House, Inc., in full compliance with the International Copyright Convention. Subjects covered in Heat Transfer Research encompass the entire field of heat transfer and relevant areas of fluid dynamics, including conduction, convection and radiation, phase change phenomena including boiling and solidification, heat exchanger design and testing, heat transfer in nuclear reactors, mass transfer, geothermal heat recovery, multi-scale heat transfer, heat and mass transfer in alternative energy systems, and thermophysical properties of materials.