Machine Learning Process on Double Diffusive Convection in a Parallelogram-Shaped Cavity

Abstract

In this chapter, the average Nusselt number (https://www.w3.org/1998/Math/MathML" display="inline"> N u ¯ https://www.w3.org/1999/xlink" xlink:href="https://s3-euw1-ap-pe-df-pch-content-public-p.s3.eu-west-1.amazonaws.com/9781032688121/d82699f9-e28a-4668-8e97-d5089091366f/content/math8_184.tif"/>) and the average Sherwood number (https://www.w3.org/1998/Math/MathML" display="inline"> S h ¯ https://www.w3.org/1999/xlink" xlink:href="https://s3-euw1-ap-pe-df-pch-content-public-p.s3.eu-west-1.amazonaws.com/9781032688121/d82699f9-e28a-4668-8e97-d5089091366f/content/math8_185.tif"/>) of a double diffusive natural convection flow of Fe3O4–water nanofluid in a parallelogram-shaped cavity are modeled by neural networks. The data for modeling is obtained from the numerical simulation of the problem in different problem parameter combinations of Rayleigh (Ra), Lewis (Le) numbers, buoyancy ratio parameter (Nr), nanoparticle concentration (?), and the inclination angle of the parallelogram (?). The governing dimensionless equations are numerically solved by cubic polyharmonic spline radial basis function collocation method using Gauss–Chebyshev–Lobatto node distribution. Modeling of important problem features enables one to interpret the enhancement in convective heat and mass transfer immediately in some parameter concert instead of performing numerical calculations many times. The collaboration between computational fluid dynamics and artificial neural networks is a promising way to control heat and mass transfer characteristics fast and efficiently. © 2025 selection and editorial matter, J.P. Abraham and J.M. Gorman.