|
Evaluating the effectiveness of artificial neural network models for estimating and calculating the conductive heat transfer coefficient in nanofluids
|
Hasan Amirahmadi *1   , Mohammadhasan Nobakhti2 , GholamReza Salehi3 |
1- Department of Mechanical Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran , hasan.amirahmadi@srbiau.ac.ir
2- Department of Mechanical Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
3- Department of Mechanical Engineering, Centeral Tehran Branch, Islamic Azad University, Tehran, Iran |
|
|
Abstract: (22 Views) |
In this article, it has been tried to develop the data related to nanofluids using artificial intelligence models and introduce an optimal model to estimate and calculate the coefficient of thermal conductivity for nanofluids. Therefore, the experimental data of experiments based on Al2O3, CuO, TiO2, Fe2O3 nanoparticles in the base fluid of distilled water for volume percentages of 0.2 to 2 were measured at different temperatures and were used as input to the models along with library data. The type of nanoparticle, temperature, density and viscosity were the input data to the models, and the thermal conductivity parameter of the nanofluid is the output of the models. A total of 268 data series were defined as input to the models, 70% of which were used for training and 30% for testing. It was investigated with five different modes including artificial neural network with activation function ANN-Trainlm, ANN-Trainbr, ANN-Trainscg, long short term memory network (LSTM) and support vector regression (RVS) for modeling. The results showed that LSTM has a much better match with the experimental data, because the values of regression coefficient (R2), root mean square error (RSME) and mean absolute percentage error (MAPE) values are 0.9764, 0.0313 and 0.0819, respectively. |
|
| Keywords: Nanofluid, artificial neural network, thermal conductivity coefficient, modeling |
|
|
Full-Text [PDF 2356 kb]
(12 Downloads)
|
Type of Study: Research |
Subject:
Heat and Mass Transfer
Received: 2025/05/18 | Accepted: 2025/08/23 | Published: 2025/09/1
|
|
|
|
|
|
|
| Send email to the article author |
|
|
|
| Add your comments about this article |
|
|
|
