首页    期刊浏览 2024年12月01日 星期日
登录注册

文章基本信息

  • 标题:Cascade forward Artificial Neural Network to estimate thermal conductivity of functionalized graphene-water nanofluids
  • 本地全文:下载
  • 作者:Mohammad Hemmat Esfe ; Davood Toghraie
  • 期刊名称:Case Studies in Thermal Engineering
  • 印刷版ISSN:2214-157X
  • 电子版ISSN:2214-157X
  • 出版年度:2021
  • 卷号:26
  • 页码:101194
  • DOI:10.1016/j.csite.2021.101194
  • 出版社:Elsevier B.V.
  • 摘要:In the present study, estimation and prediction of thermal conductivity (k nf ) of functionalized Graphene were prepared by the alkaline method in water has been conducted using experimental data using Artificial Neural Network (ANN). k nf of four types of functionalized Graphene-water nanofluid has been modeled in 5 different temperatures ranging from 10 to 50 °C as the input of ANN. The finding shows that the Relative Thermal Conductivity (RTC) of nanofluids in sample 1 has a little decrease with a reduction in temperature, while the other samples had an increase in RTC with an increase in temperature. Also, after training the network and testing the data associated with network testing, the difference between experimental data and the values obtained from modeling (outputs) is obtained. The results show the acceptable precision of modeling and confirm its results.
  • 关键词:Nanofluid ; Thermal conductivity ; ANN ; Functionalized graphene
国家哲学社会科学文献中心版权所有