Designing an artificial neural network to predict thermal conductivity and dynamic viscosity of ferromagnetic nanofluid. (November 2015)

• Record Type: Journal Article
• Authors: Hemmat Esfe, Mohammad; Saedodin, Seyfolah; Sina, Nima; Afrand, Masoud; Rostami, Sara
• Is Part Of: International communications in heat and mass transfer. Volume 68(2015:Nov.)
• Page Start: 50
• Page End: 57
• Publication Date: 2015-11
• Subjects: Artificial neural network -- Nanofluids -- Dynamic viscosity -- Thermal conductivity; Heat -- Transmission -- Periodicals; Mass transfer -- Periodicals; Chaleur -- Transmission -- Périodiques; Transfert de masse -- Périodiques; Heat -- Transmission; Mass transfer; Periodicals; 621.4022
• DOI: 10.1016/j.icheatmasstransfer.2015.06.013
• Languages: English
• ISSNs: 0735-1933

Abstract

Abstract: This paper focuses on designing an artificial neural network which can predict thermal conductivity and dynamic viscosity of ferromagnetic nanofluids from input experimental data including temperature, diameter of particles, and solid volume fraction. The experimental data were extracted and they were used as learning dataset to train the neural network. To find a proper architecture for network, an iteration method was used. Based on the results, there was no over-fitting in designed neural network and the neural network was able to track the data. ANN outputs showed that the maximum errors in predicting thermal conductivity and dynamic viscosity are 2% and 2.5%, respectively. Based on the ANN outputs, two sets of correlations for estimating the thermal conductivity and dynamic viscosity were presented. The comparisons between experimental data and the proposed correlations showed that the presented correlations were in an excellent agreement with experimental data.