当前位置: X-MOL 学术Chem. Eng. Commun. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Using neural network and RSM to evaluate improvement in thermal conductivity of nanodiamond-iron oxide/antifreeze
Chemical Engineering Communications ( IF 1.9 ) Pub Date : 2021-09-27 , DOI: 10.1080/00986445.2021.1974417
Yacine Khetib, Ahmad Alahmadi, Ali Alzaed, S. Mohammad Sajadi, Roozbeh Vaziri, Mohsen Sharifpur

Abstract

This study aimed to investigate the accuracy of the artificial neural network in estimating thermal conductivity (k) of ferrofluid-based nanofluids. The parameters of kND+Fe2O3/EGwater and kEGwater have been measured at 20–60°C, 0.05, 0.1, and 0.2 vol.% and the results showed that kFe2O3/EGwater was greater than kEGwater by 89%, which is obtained at 60°C and 0.2 vol.%. To estimate kND+ Fe3O4/EGwater a three-layer ANN was developed that contained two, three, and one neurons, respectively. This neural network was able to estimate kND+ Fe3O4/EGwater with less than 0.8% error considering of R2=0.996. The response surface methodology was also implemented, and it was observed that cubic polynomials, taking to account of R2=0.994, will figure out the best results so that kND+ Fe3O4/EGwater can be predicted with an error of less than 0.5%.



中文翻译:

使用神经网络和 RSM 评估纳米金刚石-氧化铁/防冻剂导热性的改善

摘要

本研究旨在研究人工神经网络在估算基于铁磁流体的纳米流体的热导率 (k) 时的准确性。的参数k无损检测+2个3个/例如k例如已被测量为 20–60°C,0.05、0.1 和 0.2 vol.%,结果表明k2个3个/例如大于k例如89%,这是在 60 时获得的°C和 0.2 体积%。估计k无损检测+ 3个4个/例如开发了一个三层 ANN,分别包含两个、三个和一个神经元。这个神经网络能够估计k无损检测+ 3个4个/例如考虑到误差小于 0.8%R2个=0.996.还实施了响应面方法,观察到三次多项式,考虑到R2个=0.994,会找出最好的结果,这样k无损检测+ 3个4个/例如可以预测误差小于0.5%。

更新日期:2021-09-27
down
wechat
bug