作者:
DOI: 10.5139/JKSAS.2009.37.5.425
关键词: Complex system 、 Mathematical optimization 、 Artificial neural network 、 Aerodynamic force 、 Computational fluid dynamics 、 Euler's formula 、 Engineering 、 Genetic algorithm 、 Process (computing) 、 Algorithm 、 Airfoil
摘要: In this study, the ability of neural network in modeling and predicting unsteady aerodynamic force coefficients 2D airfoil with data obtained from Euler CFD code has been confirmed. Neural models are constructed based on supervised training process using Levenberg-Marquardt algorithm, combining into genetic hybrid algorithm efficiency two cases analyzed compared. It is shown that hybrid-genetic more efficient for complex system predicted properties by confirmed to be similar numerical results verified as suitable representing reduced models.