Study on Response Surface Methodology with Artificial Neural Networks Application in Aerodynamic Optimization

摘要

Response surface methodology is currently commonly used and solutes to engineering design aerodynamic optimization problem. Artificial neural networks is the familiar approximation methods. It is trained and tested using a relatively small number of high fidelity CFD flow simulations. The ANN approximation was found to save on the simulation computation time and improved the generalization capability of the ANN model by reducing the overtraining or memorization problem.