Stochastic Levenberg–Marquardt Neural Network Implementation for Analyzing the Convective Heat Transfer in a Wavy Fin

The present research examines the steady, one-dimensional thermal distribution and heat transfer of a wavy fin. This analysis considers convective effects as well temperature-dependent conductivity. Furthermore, novel implementation neural network with backpropagated Levenberg–Marquardt algorithm (NN-BLMA)-based machine learning intelligent strategies is provided to interpret non-linear ordinary differential equation (ODE) study problem converted into its non-dimensional form using similarity transformation technique. dimensionless obtained then numerically explored via Runge–Kutta–Fehlberg scheme. A data set for varying pertinent parameters generated, an artificial model designed estimate behavior effectiveness proposed NN-BLMA subsequently endorsed by analyses regression model, mean square error, histograms. findings comprehensive computational parametric studies illustrate that presented technique, effective convergent stochastic numerical solver employed fin’s temperature dispersion optimizes conductivity parameter rises. Heat rate higher in fin compared rectangular