当前位置: X-MOL 学术Int. Commun. Heat Mass Transf. › 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.)
On the evaluation of thermal conductivity of nanofluids using advanced intelligent models
International Communications in Heat and Mass Transfer ( IF 6.4 ) Pub Date : 2020-11-01 , DOI: 10.1016/j.icheatmasstransfer.2020.104825
Abdolhossein Hemmati-Sarapardeh , Amir Varamesh , Menad Nait Amar , Maen M. Husein , Mingzhe Dong

Abstract Accurate knowledge of thermal conductivity (TC) of nanofluids is emphasized in studies related to the thermophysical aspects of nanofluids. In this work, a comprehensive review of the most important theoretical, empirical, and computer-aided predictive models of TC of nanofluids is undertaken. Then, several intelligent models, including multilayer perceptron (MLP), radial basis function neural network (RBFNN) and least square support vector machine (LSSVM) were developed to predict relative TC of nanofluids using 3200 experimental points. The database encompasses 78 different nanofluids, covering extensive-ranged parameters; namely temperature ranging from −30.00 to 149.15 °C, particle volume fraction in the range of 0.01–11.22%, particle size from 5.00 to 150.00 nm, particle TC ranging from 1.20 to 1000.00 W/mK and base fluid TC of 0.11 to 0.69 W/mK. Combining the developed intelligent models into a committee machine intelligence system (CMIS) provided more accurate predictive model. The CMIS model exhibited very low AARE values of 0.843% during the training and 0.954% in the test phase. Moreover, a comparison of performances showed that CMIS largely outperforms the best theoretical and empirical models. Lastly, by performing Leverage approach, the statistical validity of CMIS was confirmed and the quality of the employed data was checked.

中文翻译:

基于先进智能模型的纳米流体导热系数评价研究

摘要 在与纳米流体的热物理方面相关的研究中,强调对纳米流体的热导率 (TC) 的准确了解。在这项工作中,对纳米流体 TC 的最重要的理论、经验和计算机辅助预测模型进行了全面审查。然后,开发了几种智能模型,包括多层感知器(MLP)、径向基函数神经网络(RBFNN)和最小二乘支持向量机(LSSVM),使用 3200 个实验点预测纳米流体的相对 TC。该数据库包含 78 种不同的纳米流体,涵盖范围广泛的参数;即温度范围为 -30.00 至 149.15 °C,颗粒体积分数范围为 0.01-11.22%,粒径为 5.00 至 150.00 nm,颗粒 TC 范围为 1.20 至 1000.00 W/mK,基液 TC 为 0。11 至 0.69 W/mK。将开发的智能模型结合到委员会机器智能系统 (CMIS) 中,提供了更准确的预测模型。CMIS 模型在训练期间表现出非常低的 AARE 值,为 0.843%,在测试阶段为 0.954%。此外,性能比较表明,CMIS 在很大程度上优于最好的理论和经验模型。最后,通过执行 Leverage 方法,确认了 CMIS 的统计有效性并检查了所使用数据的质量。性能比较表明,CMIS 在很大程度上优于最好的理论和经验模型。最后,通过执行 Leverage 方法,确认了 CMIS 的统计有效性并检查了所使用数据的质量。性能比较表明,CMIS 在很大程度上优于最好的理论和经验模型。最后,通过执行 Leverage 方法,确认了 CMIS 的统计有效性并检查了所使用数据的质量。
更新日期:2020-11-01
down
wechat
bug