https://doi.org/10.1140/epjp/s13360-023-04327-0
Regular Article
Estimation of nanofluids viscosity using artificial neural network: application on the lubricant poly-alpha-olefin boron nitride
1
Faculty of Sciences Gabes, PEESE, LR18ES34, University of Gabes, 6072, Zirig, Gabes, Tunisia
2
Faculty of Sciences Tunis, LETTM, El Manar, University of El Manar, 2092, Tunis, Tunisia
Received:
7
March
2023
Accepted:
28
July
2023
Published online:
7
August
2023
This study aimed to develop two artificial neural network models to estimate the viscosity of PAO/hBN (poly-alpha-olefin boron nitride) nanofluid using different input sets. The first one (ANN1) uses temperature, nanoparticles concentration, and shear rate, and the second (ANN2) uses only temperature and nanoparticles concentration as inputs. The ANNs were trained and validated using a database of 537 experimentally measured datasets. 66.6% of this database was used to evaluate the performance of developed models to predict PAO/hBN viscosity on unseen datasets in the training phase. Results show that both ANNs produced accurate viscosity estimations, with RMSE values of approximately 3E−03. In particular, the ANN2 model, which only uses temperature and nanoparticle concentration as inputs, achieved similar levels of accuracy compared to ANN1, indicating that the shear rate input was not necessary for accurate viscosity predictions. The evaluation of the ANN models using datasets that were not included in the training phase provided additional confirmation of their ability to accurately predict the viscosity of PAO/hBN nanofluid. This highlights the potential of the ANN models to offer a practical and cost-effective approach to predicting nanofluid viscosity.
Copyright comment Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
© The Author(s), under exclusive licence to Società Italiana di Fisica and Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
