Data mining for aerodynamic design space

In this paper, analysis of variance (ANOVA) and self-organizing map (SOM) are applied to data mining for aerodynamic design space. These methods make it possible to identify the effect of each design variable on objective functions. ANOVA shows the information quantitatively while SOM shows it qualitatively. Furthermore, ANOVA can show the effect of interaction between design variables on objective functions and SOM can visualize the trade-off among objective functions. This information will be helpful for designer to determine the final design from the non-dominated solutions of multi-objective problem. These methods are applied to a fly-back booster of reusable launch vehicle design which has 4 objective functions and 71 design variables, and a transonic airfoil design performed with adaptive search region method.