Using Neural Network and Genetic Algorithm For Modeling and Multi-Objective Optimal Heat Exchange Through A Tube Bank

In this study, a multi-objective optimization technique was applied to predict the optimal design points of forced convective heat transfer in tubular arrangements upon the size, pitch and geometric configurations of a tube bank. it was used to gain the wide range of design point candidates, a novel multi-objective and variable prediction model. 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 using the fluent software. afterwards, the group method of data handling (gmdh)-type neural network and the evolutionary algorithm (eas) were used to model the effects of design parameters, i.e. horizontal diameter of ellipse (a), vertical diameter of ellipse (b), transverse pitch (sn), and longitudinal pitch (sp) on pressure loss (?p) and the temperature difference (?t) to achieve a meta- model through a prediction procedure using evolved gmdh neural network. finally, the model was used to gain the multi-objective pareto-curves to depict the optimal design zones.