PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
March 27, 2026Heat Transfer2 citations

Artificial Neural Network and Taguchi Optimisation Approach on Ag–ZnO Infused Radiative Time‐Dependent Flow Due to Squeezing Porous Slider

View Full Paper
JSJyothi Kiran SiddagangaiahMNMurulidhara NagarajaiahKPKiran D. Parmar

Key Points

  • The study aims to investigate the effects of thermal radiation and relaxation on heat transfer and flow in a porous slider system.
  • Used similarity transformations to convert PDEs into ODEs for numerical analysis.
  • Applied Runge–Kutta–Fehlberg method to solve the differential equations.
  • Implemented an artificial neural network model to estimate fluid profiles.
  • Employed Taguchi optimisation strategy to identify optimal parameter combinations.
  • Increased radiation parameter leads to higher temperature distribution and thicker thermal boundary layers.
  • Higher Reynolds number results in thinner thermal boundary layers due to stronger convection.
  • Radiation explains 75.65% of variability in heat transfer.
  • Maximum heat transfer rate achieved is 2.7229 with minimal variance of 0.1%.
  • ANN predictions closely align with numerical results, validating the models used.

Abstract

ABSTRACT To achieve efficient heat transfer in lubrication systems, cooling equipment, and microfluidic technologies, fluid models with the ability to model realistic behaviour of heat transfer accurately are required. Inspired by these applications, the current research examines the unsteady heat transfer and flow nature of an Ag–ZnO hybrid nanofluid in a porous slider system under the combined influence of nonlinear thermal radiation and the Cattaneo‐Christov heat flux model. The aim is to discuss the effects of thermal relaxation and radiation on the heat transport and fluid flow in porous‐slider‐based engineering systems. Similarity transformations are used to convert the governing partial differential equations (PDEs) into nonlinear ordinary differential equations (ODEs), which are then numerically solved by the Runge–Kutta–Fehlberg fourth‐fifth order (RKF‐45) method. Also, an artificial neural network (ANN) model is used to estimate fluid profiles, whereas the Taguchi optimisation strategy is used to find the best parameter combination that will maximise heat transfer. The findings show that a higher radiation parameter leads to a distribution of the temperature and increases the thermal boundary‐layer thickness, and a higher Reynolds number leads to a thinner thermal boundary‐layer because of stronger convective influences. The Taguchi analysis indicates that radiation accounts 75.65% of the variability in heat transfer, and the maximum heat transfer rate at the best parameter set is 2.7229, with the least variance of 0.1%. The predictions of the ANN are in great agreement with the numerical results, which prove the correctness of the suggested models.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Siddagangaiah et al. (2026) studied this question.

synapsesocial.com/papers/69c6206115a0a509bde18d68https://doi.org/10.1002/htj.70227
Ask AI
Helpful
Bookmark
Share
View Full Paper