Prediction of Cattaneo–Christov heat flux with thermal slip effects over a lubricated surface using artificial neural network

The lubricated systems containing fluid lubricants have the load-carrying ability. Suitable lubrication permits smooth, incessant operation of machine elements. The significant applications in engineering and industry are drag reduction, cooling of electronic devices and cooling of nuclear reactors,...

Full description

Saved in:
Bibliographic Details
Published in:European physical journal plus Vol. 139; no. 9; p. 851
Main Authors: Sadiq, M. N., Shahzad, Hasan, Alqahtani, Hassan, Tirth, Vineet, Algahtani, Ali, Irshad, Kashif, Al-Mughanam, Tawfiq
Format: Journal Article
Language:English
Published: Berlin/Heidelberg Springer Berlin Heidelberg 24.09.2024
Springer Nature B.V
Subjects:
Accuracy
Applied and Technical Physics
Artificial neural networks
Atomic
Back propagation networks
Complex Systems
Condensed Matter Physics
Constitutive relationships
Cooling
Datasets
Differential equations
Drag reduction
Engineering
Error analysis
Fluid flow
Fluid mechanics
Heat conductivity
Heat flux
Heat transfer
Lubricants
Lubricants & lubrication
Lubrication
Mathematical and Computational Physics
Molecular
Neural networks
Nuclear power plants
Nuclear reactors
Optical and Plasma Physics
Optimization techniques
Ostwald ripening
Partial differential equations
Physics
Physics and Astronomy
Power law
Regression models
Regular Article
Shear stress
Temperature
Theoretical
Thermal analysis
Variable thickness
Velocity
ISSN:2190-5444, 2190-5444
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The lubricated systems containing fluid lubricants have the load-carrying ability. Suitable lubrication permits smooth, incessant operation of machine elements. The significant applications in engineering and industry are drag reduction, cooling of electronic devices and cooling of nuclear reactors, and many other hydrodynamic processes. In the industries, lubricants frequently exhibit non-Newtonian properties and conform to various constitutive relations. One prevalent type of lubricant is the power law fluid, which adheres to the Ostwald procedure. The present investigation focuses on the analysis of fluid flow in the purlieu of a lubricated surface, where a thin layer of variable-thickness power law fluid is used for lubrication. The effects of velocity and thermal slip with Cattaneo–Christov heat transfer are taken into account. A conversion from partial to ordinary system of equations is happened utilizing similarities. To acquire a dataset, the shooting method is utilized. An artificial neural network procedure is utilized to envisage the fluid flow by solving the governing system of partial differential equations, and testing, training, and validation procedures are arranged to generate results under different circumstances and cases of Levenberg–Marquardt backpropagation neural network. The precision of the proposed model is established by comparing the outcomes with the reference dataset. The Levenberg–Marquardt backpropagation neural network output is evaluated using mean regression illustrations, analysis of error histograms, mean square error, and dynamics of state transition. The results indicate that developed neural network models can accurately envisage thermal analysis. Furthermore, compared to other numerical performances, the current artificial neural network model can be employed in more complicated scientific models while decreasing the time and processing ability needed to solve the problem. Graphic abstract
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2190-5444
2190-5444
DOI:10.1140/epjp/s13360-024-05625-x