Automated optimization system for aircraft wing design
Abstract
The optimization of a transonic civil transport aircraft is a complex and difficult task, due to the complexity of the cost surfaces and the human expertise that is necessary in order to achieve high quality results. In this paper we describe an Automated Optimization System that provide recommendations to design engineers on the choice of optimization search technique to sue, especially when searching within familiar domains. The Automated optimization System uses Artificial Intelligence, specifically machine learning techniques to perform knowledge discovery from past optimization search and reuses this knowledge to facilitate intelligent recommendations for search routines selection. Results of a case study on the design of a transonic civil transport aircraft wing using the Automated Optimization System are presented in the paper. It is shown that the Automated Optimization System not only aids design engineers to make improved decisions when working on complex aircraft wing but also helps improve design search performance.
Authors: Yew-Soon Ong, Andy J. Keane
Published in: ePrints Soton (University of Southampton) (2002)