In this study, the results of two optimized and base blades of a horizontal axis wind turbine with aeroelastic point of view are compared . In order to optimization, the chord length and the twist angle of the blade at various radiuses have been calculated by BEM. The Results which are obtained from 2D Computational Fluid Dynamics (CFD) have been utilized to train a Neural Network (NN). In the process of airfoil optimization, Genetic Algorithm (GA) is coupled with trained NN to attain the best airfoil shape at each angle of the attack. Finally, the optimized blade is derived. In order to simulate the flow on two blades and obtain the aerodynamic forces, the blades and their surrounding regions are organized by unstructured grid. The SIMPLE algorithm and second order upwind scheme are used in numerical fluid flow simulation. The aerodynamic forces on the blades have been used for stress and strain analysis. At this point, in addition to the aerodynamic forces, inertia forces resulting from the rotation of the wind turbine blade is also considered. The aerodynamic results show that optimized blade has high efficiency. The results of the analysis of the stress - strain showed that maximum stress on optimized blade is less than base blade and optimized blade design is also more reliable than the blade base.

Keywords: BEM, Genetic algorithm, Neural Network, Optimization

Full-Text [PDF 914 kb]   (6526 Downloads)