Applicability of connectionist methods to predict dynamic viscosity of silver/water nanofluid by using ANN-MLP, MARS and MPR algorithms
Dynamic viscosity considerably affects the heat transfer and flow of fluids. Due to improved thermophysical properties of fluids containing nanostructures, these types of fluids are widely employed in thermal mediums. The nanofluid's dynamic viscosity relies on different variables including siz...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Taylor & Francis Group
2019-01-01
|
Series: | Engineering Applications of Computational Fluid Mechanics |
Subjects: | |
Online Access: | http://dx.doi.org/10.1080/19942060.2019.1571442 |
id |
doaj-c977ea84788147878852ebd9a0aaae44 |
---|---|
record_format |
Article |
spelling |
doaj-c977ea84788147878852ebd9a0aaae442020-11-25T02:01:42ZengTaylor & Francis GroupEngineering Applications of Computational Fluid Mechanics1994-20601997-003X2019-01-0113122022810.1080/19942060.2019.15714421571442Applicability of connectionist methods to predict dynamic viscosity of silver/water nanofluid by using ANN-MLP, MARS and MPR algorithmsMohammad Hossein Ahmadi0Behnam Mohseni-Gharyehsafa1Mahmood Farzaneh-Gord2Ravindra D. Jilte3Ravinder Kumar4Kwok-wing Chau5Shahrood University of TechnologyShahrood University of TechnologyFerdowsi University of MashhadLovely Professional UniversityLovely Professional UniversityHong Kong Polytechnic UniversityDynamic viscosity considerably affects the heat transfer and flow of fluids. Due to improved thermophysical properties of fluids containing nanostructures, these types of fluids are widely employed in thermal mediums. The nanofluid's dynamic viscosity relies on different variables including size of solid phase, concentration and temperature. In the present study, three algorithms including multivariable polynomial regression (MPR), artificial neural network–multilayer perceptron (ANN-MLP) and multivariate adaptive regression splines (MARS) are applied to model the dynamic viscosity of silver (Ag)/water nanofluid. Recently published experimental investigations are employed for data extraction. The input variables considered in the modeling process to be the most important ones are the size of particles, fluid temperature and the concentration of Ag nanoparticles in the base fluid. The R2 values for the studied models are 0.9998, 0.9997 and 0.9996 for the ANN-MLP, MARS and MPR algorithms, respectively. In addition, based on importance analysis, the temperature is highly effective and the dominant parameter for the dynamic viscosity of the nanofluid in comparison with size and concentration.http://dx.doi.org/10.1080/19942060.2019.1571442nanofluiddynamic viscosityartificial neural networkconcentrationmultivariate adaptive regression splines (mars)multivariable polynomial regression (mpr) |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Mohammad Hossein Ahmadi Behnam Mohseni-Gharyehsafa Mahmood Farzaneh-Gord Ravindra D. Jilte Ravinder Kumar Kwok-wing Chau |
spellingShingle |
Mohammad Hossein Ahmadi Behnam Mohseni-Gharyehsafa Mahmood Farzaneh-Gord Ravindra D. Jilte Ravinder Kumar Kwok-wing Chau Applicability of connectionist methods to predict dynamic viscosity of silver/water nanofluid by using ANN-MLP, MARS and MPR algorithms Engineering Applications of Computational Fluid Mechanics nanofluid dynamic viscosity artificial neural network concentration multivariate adaptive regression splines (mars) multivariable polynomial regression (mpr) |
author_facet |
Mohammad Hossein Ahmadi Behnam Mohseni-Gharyehsafa Mahmood Farzaneh-Gord Ravindra D. Jilte Ravinder Kumar Kwok-wing Chau |
author_sort |
Mohammad Hossein Ahmadi |
title |
Applicability of connectionist methods to predict dynamic viscosity of silver/water nanofluid by using ANN-MLP, MARS and MPR algorithms |
title_short |
Applicability of connectionist methods to predict dynamic viscosity of silver/water nanofluid by using ANN-MLP, MARS and MPR algorithms |
title_full |
Applicability of connectionist methods to predict dynamic viscosity of silver/water nanofluid by using ANN-MLP, MARS and MPR algorithms |
title_fullStr |
Applicability of connectionist methods to predict dynamic viscosity of silver/water nanofluid by using ANN-MLP, MARS and MPR algorithms |
title_full_unstemmed |
Applicability of connectionist methods to predict dynamic viscosity of silver/water nanofluid by using ANN-MLP, MARS and MPR algorithms |
title_sort |
applicability of connectionist methods to predict dynamic viscosity of silver/water nanofluid by using ann-mlp, mars and mpr algorithms |
publisher |
Taylor & Francis Group |
series |
Engineering Applications of Computational Fluid Mechanics |
issn |
1994-2060 1997-003X |
publishDate |
2019-01-01 |
description |
Dynamic viscosity considerably affects the heat transfer and flow of fluids. Due to improved thermophysical properties of fluids containing nanostructures, these types of fluids are widely employed in thermal mediums. The nanofluid's dynamic viscosity relies on different variables including size of solid phase, concentration and temperature. In the present study, three algorithms including multivariable polynomial regression (MPR), artificial neural network–multilayer perceptron (ANN-MLP) and multivariate adaptive regression splines (MARS) are applied to model the dynamic viscosity of silver (Ag)/water nanofluid. Recently published experimental investigations are employed for data extraction. The input variables considered in the modeling process to be the most important ones are the size of particles, fluid temperature and the concentration of Ag nanoparticles in the base fluid. The R2 values for the studied models are 0.9998, 0.9997 and 0.9996 for the ANN-MLP, MARS and MPR algorithms, respectively. In addition, based on importance analysis, the temperature is highly effective and the dominant parameter for the dynamic viscosity of the nanofluid in comparison with size and concentration. |
topic |
nanofluid dynamic viscosity artificial neural network concentration multivariate adaptive regression splines (mars) multivariable polynomial regression (mpr) |
url |
http://dx.doi.org/10.1080/19942060.2019.1571442 |
work_keys_str_mv |
AT mohammadhosseinahmadi applicabilityofconnectionistmethodstopredictdynamicviscosityofsilverwaternanofluidbyusingannmlpmarsandmpralgorithms AT behnammohsenigharyehsafa applicabilityofconnectionistmethodstopredictdynamicviscosityofsilverwaternanofluidbyusingannmlpmarsandmpralgorithms AT mahmoodfarzanehgord applicabilityofconnectionistmethodstopredictdynamicviscosityofsilverwaternanofluidbyusingannmlpmarsandmpralgorithms AT ravindradjilte applicabilityofconnectionistmethodstopredictdynamicviscosityofsilverwaternanofluidbyusingannmlpmarsandmpralgorithms AT ravinderkumar applicabilityofconnectionistmethodstopredictdynamicviscosityofsilverwaternanofluidbyusingannmlpmarsandmpralgorithms AT kwokwingchau applicabilityofconnectionistmethodstopredictdynamicviscosityofsilverwaternanofluidbyusingannmlpmarsandmpralgorithms |
_version_ |
1724956414430937088 |