[[alternative]]Memetic Algorithm for Optimization of Engineering Design

博士工業教育與技術學系[[abstract]]本研究提出混合基因演算法於工程設計最佳化問題之應用。混合基因演算法整合了基因演算法之整體最佳化與局部搜尋最小化之方法，同時改善基因演算法花費較長時間在尋找最佳解的問題上，可以有效改進最佳化問題之設計。 本研究之混合基因演算法針對工程設計最佳化之問題作探討，包括：最佳化問題評估之應用、PID控制器設計之應用、壁型裱裝容器最佳化設計之應用、離散系統強健穩定度分析之應用、多目標最佳化問題之應用、無限脈衝響應主動式噪音控制之應用、未知訊號分離之應用等。 透過電腦程式模擬結果發現，混合基因演算法成功的應用在最佳化問題之設計上，同時比基因演算法具有最佳化之結果，並能有效縮短程式執行時間。[[abstract]]This dissertation examined the performance of memetic algorithm for optimization of engineering design problems. The memetic algorithm used local improvement procedures as part of the evaluation of individuals. For many problems there exists a well-developed, efficient search strategy for local improvement, e.g., hill-climbers for optimization. These local search strategies compliment the global search strategy of the genetic algorithms, yielding a more efficient overall search strategy. In this thesis, the memetic algorithm was applied to the evaluation of optimization problems, design of optimal PID controllers, wall mounting container optimization problems, discrete time uncertain systems, non-dominated solutions of multiobjective optimization problem, adaptive IIR active noise control, and blind signal separation network. Experimental evaluation and comparison with genetic algorithm on these problems showed that memetic algorithm compared very favorably to genetic algorithm outperforming many of them. When compared to genetic algorithm, memtic algorithm not only shortens convergence time and optimizes more efficiently