指導教授：王偉仲臺灣大學：數學研究所李其澔Li, Chi-HaoChi-HaoLi2014-11-302018-06-282014-11-302018-06-282014http://ntur.lib.ntu.edu.tw//handle/246246/264025Uniformity of experimental designs is an important issue in computer experiments recent years. To reduce the cost of handling experiment, we need to find usable designs effectively and effeciently. A design with good space-filling and non-collapsing properties may help us get the most information under some specific cost. Since a lot amount of real problems require grid discretization, based on the framework of the discrete particle swarm optimization (DPSO), we try several strategies and propose several applied methods to discuss the multi-objective issue, and will illustrate it by handling experiments on several regular and irregular feasible domains by some DPSO-based algorithms.誌謝---i Table of Content---ii List of Figures---iv List of Tables---v 中文摘要---vi Abstract---vii 1 Introduction---1 2 Problem Formulation and Algorithms---4 2.1 Uniform Design and Objective Criteria---4 2.1.1 The Feasible Domain and Grid Discretization---5 2.1.2 Space-filling Property and the Maximin Pairwise Distance---6 2.1.3 Non-collapsing Property and the Projected Distance---9 2.2 Methods and Algorithms---11 2.2.1 Discrete Particle Swarm Optimization (DPSO)---12 2.2.2 A-DPSO (DPSO with Aggrgated Criteiron)---14 2.2.3 P-DPSO (DPSO with Penalty Criterion)---17 2.2.4 C-DPSO (Conditioned DPSO)---18 3 Numerical Results and Discussion---22 3.1 Experimental Regions---22 3.2 Tuning Parameters---25 3.3 Comparison of the DPSO-based Algorithms---26 3.3.1 Linear Constraint for n=10 and K=2,4 (Domain D_1 and D_2)---28 3.3.2 Semi-circle/ball for n=10, K=2,3---30 3.3.3 Linear Constraint and Semi-Circle, n=50, K=2---32 3.3.4 Flexible Region for m=9999, 2, 1, 0.5, 0.3, K=2 ---33 3.4 Discussion---38 3.4.1 The Solution Set---38 3.4.2 The design size n and the dimensionality K---39 3.4.3 Further Investigation if C-DPSO and P-DPSO---39 4 Real Application---42 5 Conclusion and Future Works---47 Appendix---48 Bibliography---58631067 bytesapplication/pdf論文公開時間：2014/03/09論文使用權限：同意有償授權(權利金給回饋學校)電腦實驗試驗設計均勻性質無摺疊性質離散粒子群演算法thesishttp://ntur.lib.ntu.edu.tw/bitstream/246246/264025/1/ntu-103-R00221027-1.pdf