Modeling heat transfer of non-Newtonian nanofluids using hybrid ANN-Metaheuristic optimization algorithm
An optimal artificial neural network (ANN) has been developed to predict the Nusselt number of non-Newtonian nanofluids. The resulting ANN is a multi-layer perceptron with two hidden layers consisting of six and nine neurons, respectively. The tangent sigmoid transfer function is the best for both h...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Iranian Research Organization for Science and Technology (IROST)
2017-12-01
|
| Series: | Journal of Particle Science and Technology |
| Subjects: | |
| Online Access: | http://jpst.irost.ir/article_646_2d7f512d4bea2469940147e65ebd323a.pdf |
| _version_ | 1819040354464169984 |
|---|---|
| author | Mohammad Hojjat |
| author_facet | Mohammad Hojjat |
| author_sort | Mohammad Hojjat |
| collection | DOAJ |
| description | An optimal artificial neural network (ANN) has been developed to predict the Nusselt number of non-Newtonian nanofluids. The resulting ANN is a multi-layer perceptron with two hidden layers consisting of six and nine neurons, respectively. The tangent sigmoid transfer function is the best for both hidden layers and the linear transfer function is the best transfer function for the output layer. The network was trained by a particle swarm optimization (PSO) algorithm. Nanofluid concentration, Reynolds number, and Prandtl number are input for the ANN and the nanofluid Nusselt number is its output. There exists an excellent agreement between the ANN predicted values and experimental data. The average and maximum differences between experimental data and those predicted by ANN are about 0.8 and 5.6 %, respectively. It was also found that ANN predicts the Nusselt number of nanofluids more accurately than the previously proposed correlation. |
| first_indexed | 2024-12-21T09:07:46Z |
| format | Article |
| id | doaj.art-ee414e0fecfa4ef2b397e3852d35e683 |
| institution | Directory Open Access Journal |
| issn | 2423-4087 2423-4079 |
| language | English |
| last_indexed | 2024-12-21T09:07:46Z |
| publishDate | 2017-12-01 |
| publisher | Iranian Research Organization for Science and Technology (IROST) |
| record_format | Article |
| series | Journal of Particle Science and Technology |
| spelling | doaj.art-ee414e0fecfa4ef2b397e3852d35e6832022-12-21T19:09:18ZengIranian Research Organization for Science and Technology (IROST)Journal of Particle Science and Technology2423-40872423-40792017-12-013423324110.22104/jpst.2018.2677.1107646Modeling heat transfer of non-Newtonian nanofluids using hybrid ANN-Metaheuristic optimization algorithmMohammad Hojjat0Department of Chemical Engineering, Faculty of Engineering, University of Isfahan, Isfahan, IranAn optimal artificial neural network (ANN) has been developed to predict the Nusselt number of non-Newtonian nanofluids. The resulting ANN is a multi-layer perceptron with two hidden layers consisting of six and nine neurons, respectively. The tangent sigmoid transfer function is the best for both hidden layers and the linear transfer function is the best transfer function for the output layer. The network was trained by a particle swarm optimization (PSO) algorithm. Nanofluid concentration, Reynolds number, and Prandtl number are input for the ANN and the nanofluid Nusselt number is its output. There exists an excellent agreement between the ANN predicted values and experimental data. The average and maximum differences between experimental data and those predicted by ANN are about 0.8 and 5.6 %, respectively. It was also found that ANN predicts the Nusselt number of nanofluids more accurately than the previously proposed correlation.http://jpst.irost.ir/article_646_2d7f512d4bea2469940147e65ebd323a.pdfNanofluidsNon-NewtonianArtificial neural networkMulti-layer perceptronParticle swarm Optimization |
| spellingShingle | Mohammad Hojjat Modeling heat transfer of non-Newtonian nanofluids using hybrid ANN-Metaheuristic optimization algorithm Journal of Particle Science and Technology Nanofluids Non-Newtonian Artificial neural network Multi-layer perceptron Particle swarm Optimization |
| title | Modeling heat transfer of non-Newtonian nanofluids using hybrid ANN-Metaheuristic optimization algorithm |
| title_full | Modeling heat transfer of non-Newtonian nanofluids using hybrid ANN-Metaheuristic optimization algorithm |
| title_fullStr | Modeling heat transfer of non-Newtonian nanofluids using hybrid ANN-Metaheuristic optimization algorithm |
| title_full_unstemmed | Modeling heat transfer of non-Newtonian nanofluids using hybrid ANN-Metaheuristic optimization algorithm |
| title_short | Modeling heat transfer of non-Newtonian nanofluids using hybrid ANN-Metaheuristic optimization algorithm |
| title_sort | modeling heat transfer of non newtonian nanofluids using hybrid ann metaheuristic optimization algorithm |
| topic | Nanofluids Non-Newtonian Artificial neural network Multi-layer perceptron Particle swarm Optimization |
| url | http://jpst.irost.ir/article_646_2d7f512d4bea2469940147e65ebd323a.pdf |
| work_keys_str_mv | AT mohammadhojjat modelingheattransferofnonnewtoniannanofluidsusinghybridannmetaheuristicoptimizationalgorithm |