Using Neural Networks and Genetic Algorithms for Modelling and Multi-objective Optimal Heat Exchange through a Tube Bank

Abstract

In this study, by using a multi-objective optimization technique, the optimal design points of forced convective heat transfer in tubular arrangements were predicted upon the size, pitch and geometric configurations of a tube bank. In this way, the main concern of the study is focused on calculating the most favorable geometric characters which may gain to a maximum heat exchange as well as a minimum pressure loss. Gathering the required wide range of set of design information, a numerical simulation of various configurations of the elliptic tubular arrangements was performed by using the FLUENT software. Afterwards, the group method of data handling (GMDH)-type neural networks and the evolutionary algorithms (EAs) were used to model the effects of design parameters; horizontal diameter of ellipse (a), vertical diameter of ellipse (b), transverse pitch (Sn), and longitudinal pitch (Sp), on pressure loss (ΔP) and, the temperature difference (ΔT) to achieve a meta- model through a prediction procedure by using evolved GMDH neural networks and finally, the model was used to gain the multi-objective Pareto-curves to depict the optimal design zones.