Data Mining for Evolutionary Design Optimization
Yongsheng Lian, Meng‐Sing Liou · 34th AIAA Fluid Dynamics Conference and Exhibit · 2004
This paper focuses on integration of computational methods for design optimization based on data mining and knowledge discovery. We propose to use neural network approach to analyze the data generated from evolutionary computations and to extract hidden predictive information from large databases with the aim of providing designers with the most important information about the design problem under consideration. The proposed technique is applied to both academic problems and real engineering problems, including optimization of an airfoil and the turbopump of a cryogenic rocket engine. Our results demonstrate that these techniques can further improve the design already achieved by other optimization techniques with a slightly additional cost.