Computational Heat Transfer Analysis and Genetic Algorith–Artificial Neural Network–Genetic Algorithm-Based Multiobjective Optimization of Rectangular Perforated Plate Fins

Numerical studies on plate fins with longitudinal rectangular perforations placed perpendicular to an aluminum base plate are carried out under laminar natural convection conditions. In this paper, a detailed parametric study by varying the dimensions of fin and perforation is carried out to obtain a physical insight into the enhanced heat transfer characteristics of a perforated fin. The perforated fins are found to have an augmented heat transfer rate compared to the solid fins having same contact area. This paper uses a computationally efficient algorithm using soft computing to determine the optimized geometry with a limited set of numerical solutions. This is achieved with the help of artificial neural network (ANN). To reduce the effort in determining suitable parameters for ANN, genetic algorithm (GA) is used. The ANN is trained based on a minimal set of numerical/computational fluid dynamics (CFD) results. The trained ANN can then predict the base plate temperature for any other untrained set of parameters in the same range. A multiobjective optimization of the perforated fin is carried out with two objectives: minimum base plate temperature and maximum weight reduction. This is carried out by applying the GA on the ANN as the fitness function to obtain the multiobjective optimal. The obtained optimized fin geometry can thus be used effectively in many heat transfer applications that necessitate heat transfer enhancement with reduced weight compared to the conventional fins.