A novel design of Gaussian WaveNets for rotational hybrid nanofluidic flow over a stretching sheet involving thermal radiation

The aim of this study is to analysis the mass and heat transfer in radiative three dimensional flow of hybrid nanofluid over the stretchable sheet by exploiting the strength of integrated computational intelligent algorithm by utilization of Gaussian wavelet neural networks (GWNNs) trained with the...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International communications in heat and mass transfer Jg. 123; S. 105196
Hauptverfasser: Ilyas, Hira, Ahmad, Iftikhar, Raja, Muhammad Asif Zahoor, Shoaib, Muhammad
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.04.2021
Schlagworte:
Gaussian wavelets
Genetic algorithms
Hybrid nanofluid
Neural networks
Sequential quadratic programming
Stochastic numerical computing
Stretching sheet
Stochastic numerical computing
Sequential quadratic programming
Neural networks
Gaussian wavelets
Stretching sheet
Genetic algorithms
Hybrid nanofluid
ISSN:0735-1933, 1879-0178
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The aim of this study is to analysis the mass and heat transfer in radiative three dimensional flow of hybrid nanofluid over the stretchable sheet by exploiting the strength of integrated computational intelligent algorithm by utilization of Gaussian wavelet neural networks (GWNNs) trained with the genetic algorithms (GAs) based global search supported with sequential quadratic programming (SQP) based local refinements i.e., GWNN-GA-SQP. The mean squared error based cost function is developed for the fluidic problem by applying Gaussian WaveNet GWNNs optimize with GAs and SQP. The numerical outcomes of the fluidic model are obtained by the proposed GWNN-GA-SQP solver to examine the thermal and velocities profile effect for three physical quantities based on magnetic parameter, nanomaterial concentration and transformated angular velocity. Moreover, a exhaustive analysis of the numerical solutions of GWNN-GA-SQP solver with reference Adams method endorse the stability, accuracy and consistency on multiple autonomous runs through different statistical performance operators and complexity analysis. [Display omitted]
ISSN:0735-1933
1879-0178
DOI:10.1016/j.icheatmasstransfer.2021.105196