Scholarlink

<p>In the present paper, ANNs with different neurons considering <i>T</i> and SVF of nanoparticle parameters were applied to evaluate the test set for TC of MWCNT-ZnO (15:85)/EG nanofluid. Nanofluid data were evaluated at SVF = 0.055–1.85% and <i>T</i> = 28–55&#xa0;°C. MLP ANN with LM training algorithm was applied. MOD versus all ANN data (TCR) is in the range between ± 0.05. <i>R</i><sup>2</sup> is 0.998677. The MSE in the training is less than the other phases and is 1.29364E-06. Also, in the final part, ANN output is compared with measured values and test results. Comparisons show that ANN modeling is more precise in forecasting increased TCR than other methods.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Prediction of thermal conductivity of MWCNT (85)-ZnO (15)/EG hybrid nano-refrigerant using optimized ANN and comparison of its deviation with experimental data and classical model

  • 期刊论文

  • 发表日期：

    2025年1月21日

查看全文
  • Mohammad Hemmat Esfe,
  • Davood Toghraie,
  • Hossein Hatami

摘要

In the present paper, ANNs with different neurons considering T and SVF of nanoparticle parameters were applied to evaluate the test set for TC of MWCNT-ZnO (15:85)/EG nanofluid. Nanofluid data were evaluated at SVF = 0.055–1.85% and T = 28–55 °C. MLP ANN with LM training algorithm was applied. MOD versus all ANN data (TCR) is in the range between ± 0.05. R2 is 0.998677. The MSE in the training is less than the other phases and is 1.29364E-06. Also, in the final part, ANN output is compared with measured values and test results. Comparisons show that ANN modeling is more precise in forecasting increased TCR than other methods.