Application of Response Surface Methodology and Artificial Neural Network to Optimize the Curved Trapezoidal Winglet Geometry for Enhancing the Performance of a Fin-and-Tube Heat Exchanger

The present work aims at optimizing the geometry of curved trapezoidal winglets to enhance heat transfer rates (expressed as Colburn factor, j) and minimize pressure losses friction f). A fin-and-tube exchanger was analyzed with mounted on alternate tube either side fins. Multi-objective optimization performed using genetic algorithm (GA) maximize j f. Two surrogate models, viz. response surface methodology (RSM) artificial neural network (ANN), were considered inputs GA. To reduce number runs, a sensitivity analysis first select most influential geometrical parameters for optimization. values f in design experiments table computed CFD. Pareto front points elucidated significant improvement compared reference model along broad choice designers, not only condition but also off-design inlet condition.