A well-trained artificial neural network for predicting the rheological behavior of MWCNT–Al2O3 (30–70%)/oil SAE40 hybrid nanofluid
Abstract In this study, the influence of different volume fractions ( $$\phi$$ ϕ ) of nanoparticles and temperatures on the dynamic viscosity ( $$\mu_{nf}$$ μ nf ) of MWCNT–Al2O3 (30–70%)/oil SAE40 hybrid nanofluid was examined by ANN. For this reason, the $$\mu_{nf}$$ μ nf was derived for 203 vario...
Guardado en:
Autores principales: | , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/6087d6258bcf4ba4983592ec947f8106 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:6087d6258bcf4ba4983592ec947f8106 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:6087d6258bcf4ba4983592ec947f81062021-12-02T15:28:47ZA well-trained artificial neural network for predicting the rheological behavior of MWCNT–Al2O3 (30–70%)/oil SAE40 hybrid nanofluid10.1038/s41598-021-96808-42045-2322https://doaj.org/article/6087d6258bcf4ba4983592ec947f81062021-08-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-96808-4https://doaj.org/toc/2045-2322Abstract In this study, the influence of different volume fractions ( $$\phi$$ ϕ ) of nanoparticles and temperatures on the dynamic viscosity ( $$\mu_{nf}$$ μ nf ) of MWCNT–Al2O3 (30–70%)/oil SAE40 hybrid nanofluid was examined by ANN. For this reason, the $$\mu_{nf}$$ μ nf was derived for 203 various experiments through a series of experimental tests, including a combination of 7 different $$\phi$$ ϕ , 6 various temperatures, and 5 shear rates. These data were then used to train an artificial neural network (ANN) to generalize results in the predefined ranges for two input parameters. For this reason, a feed-forward perceptron ANN with two inputs (T and $$\phi$$ ϕ ) and one output ( $$\mu_{nf}$$ μ nf ) was used. The best topology of the ANN was determined by trial and error, and a two-layer with 10 neurons in the hidden layer with the tansig function had the best performance. A well-trained ANN is created using the trainbr algorithm and showed an MSE value of 4.3e−3 along 0.999 as a correlation coefficient for predicting $$\mu_{nf}$$ μ nf . The results show that an increase $$\phi$$ ϕ has a significant effect on $$\mu_{nf}$$ μ nf value. As $$\phi$$ ϕ increases, the viscosity of this nanofluid increases at all temperatures. On the other hand, with increasing temperature, the viscosity of this nanofluid decreases. Based on all of the diagrams presented for the trained ANNs, we can conclude that a well-trained ANN can be used as an approximating function for predicting the $$\mu_{nf}$$ μ nf .Mohammad Hemmat EsfeS. Ali EftekhariMaboud HekmatifarDavood ToghraieNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Mohammad Hemmat Esfe S. Ali Eftekhari Maboud Hekmatifar Davood Toghraie A well-trained artificial neural network for predicting the rheological behavior of MWCNT–Al2O3 (30–70%)/oil SAE40 hybrid nanofluid |
description |
Abstract In this study, the influence of different volume fractions ( $$\phi$$ ϕ ) of nanoparticles and temperatures on the dynamic viscosity ( $$\mu_{nf}$$ μ nf ) of MWCNT–Al2O3 (30–70%)/oil SAE40 hybrid nanofluid was examined by ANN. For this reason, the $$\mu_{nf}$$ μ nf was derived for 203 various experiments through a series of experimental tests, including a combination of 7 different $$\phi$$ ϕ , 6 various temperatures, and 5 shear rates. These data were then used to train an artificial neural network (ANN) to generalize results in the predefined ranges for two input parameters. For this reason, a feed-forward perceptron ANN with two inputs (T and $$\phi$$ ϕ ) and one output ( $$\mu_{nf}$$ μ nf ) was used. The best topology of the ANN was determined by trial and error, and a two-layer with 10 neurons in the hidden layer with the tansig function had the best performance. A well-trained ANN is created using the trainbr algorithm and showed an MSE value of 4.3e−3 along 0.999 as a correlation coefficient for predicting $$\mu_{nf}$$ μ nf . The results show that an increase $$\phi$$ ϕ has a significant effect on $$\mu_{nf}$$ μ nf value. As $$\phi$$ ϕ increases, the viscosity of this nanofluid increases at all temperatures. On the other hand, with increasing temperature, the viscosity of this nanofluid decreases. Based on all of the diagrams presented for the trained ANNs, we can conclude that a well-trained ANN can be used as an approximating function for predicting the $$\mu_{nf}$$ μ nf . |
format |
article |
author |
Mohammad Hemmat Esfe S. Ali Eftekhari Maboud Hekmatifar Davood Toghraie |
author_facet |
Mohammad Hemmat Esfe S. Ali Eftekhari Maboud Hekmatifar Davood Toghraie |
author_sort |
Mohammad Hemmat Esfe |
title |
A well-trained artificial neural network for predicting the rheological behavior of MWCNT–Al2O3 (30–70%)/oil SAE40 hybrid nanofluid |
title_short |
A well-trained artificial neural network for predicting the rheological behavior of MWCNT–Al2O3 (30–70%)/oil SAE40 hybrid nanofluid |
title_full |
A well-trained artificial neural network for predicting the rheological behavior of MWCNT–Al2O3 (30–70%)/oil SAE40 hybrid nanofluid |
title_fullStr |
A well-trained artificial neural network for predicting the rheological behavior of MWCNT–Al2O3 (30–70%)/oil SAE40 hybrid nanofluid |
title_full_unstemmed |
A well-trained artificial neural network for predicting the rheological behavior of MWCNT–Al2O3 (30–70%)/oil SAE40 hybrid nanofluid |
title_sort |
well-trained artificial neural network for predicting the rheological behavior of mwcnt–al2o3 (30–70%)/oil sae40 hybrid nanofluid |
publisher |
Nature Portfolio |
publishDate |
2021 |
url |
https://doaj.org/article/6087d6258bcf4ba4983592ec947f8106 |
work_keys_str_mv |
AT mohammadhemmatesfe awelltrainedartificialneuralnetworkforpredictingtherheologicalbehaviorofmwcntal2o33070oilsae40hybridnanofluid AT salieftekhari awelltrainedartificialneuralnetworkforpredictingtherheologicalbehaviorofmwcntal2o33070oilsae40hybridnanofluid AT maboudhekmatifar awelltrainedartificialneuralnetworkforpredictingtherheologicalbehaviorofmwcntal2o33070oilsae40hybridnanofluid AT davoodtoghraie awelltrainedartificialneuralnetworkforpredictingtherheologicalbehaviorofmwcntal2o33070oilsae40hybridnanofluid AT mohammadhemmatesfe welltrainedartificialneuralnetworkforpredictingtherheologicalbehaviorofmwcntal2o33070oilsae40hybridnanofluid AT salieftekhari welltrainedartificialneuralnetworkforpredictingtherheologicalbehaviorofmwcntal2o33070oilsae40hybridnanofluid AT maboudhekmatifar welltrainedartificialneuralnetworkforpredictingtherheologicalbehaviorofmwcntal2o33070oilsae40hybridnanofluid AT davoodtoghraie welltrainedartificialneuralnetworkforpredictingtherheologicalbehaviorofmwcntal2o33070oilsae40hybridnanofluid |
_version_ |
1718387203693871104 |