Optimization of maximum lift to drag ratio on airfoil design based on artificial neural network utilizing genetic algorithm

Abstract

This paper deals with an alternative design method of airfoil for wind turbine blade for low wind speed based on combination of smart computing and numerical optimization. In this work, a simulation of Artificial Neural Network (ANN) for determining the relation between airfoil geometry and its aerodynamic characteristics was conducted. First, several airfoil geometries were generated through transformation of complex variables (Joukowski transformation), and then lift and drag coefficients of each airfoil were determined using CFD (Computational Fluid Dynamics). In present study, the ANN training was conducted using airfoil geometry and its aerodynamic characteristics as input and output, respectively. Therefore, lift and drag coefficients can be directly determined only by giving the airfoil geometry without having to perform wind tunnel experiment or numerical computation. Moreover, the optimization was conducted to obtain an airfoil geometry which gives maximum lift to drag ratio (CL/CD) for specific Reynolds number. For this purpose Genetic Algorithm (GA) was applied as optimizer. The results were validated using commercial CFD and it can be shown that the result are satisfactory with error approximately of 6%.