Prediction of the heat transfer performance of mixed convection in a lid-driven enclosure with an elliptical cylinder using an artificial neural network
Hyun Woo Cho, Yong Gap Park, Young Min Seo, Man Yeong Ha
Abstract
This study examined the effects of an inclined elliptical cylinder on mixed convection in a square enclosure at three different Reynolds numbers, Re = 100, 500, and 1,000, and a fixed Grashof number of Gr = 105. The effects of the inclined angle of the elliptical cylinder (0° ≤ ϕ ≤ 180°) and aspect ratio on mixed convection were also analyzed by the distribution of the isotherms, streamlines, and the surface-averaged Nusselt number. The thermal and flow structures as well as the heat transfer performance were affected greatly by the inclined angle. In addition, the heat transfer performance for the variation in the inclined angle of the elliptical cylinder was predicted using an artificial neural network (ANN). The predicted values obtained from the ANN were matched well with the numerical data. The relative impact of the parameters on the heat transfer performance was estimated quantitatively. Overall, the heat transfer performance was affected in the order of the inclined angle, Reynolds number, and the aspect ratio.