智慧型垃圾桶決策之進化演算法於全域最佳化問題

An Intelligent Garbage Can Decision-Making Model Evolution Algorithm for Global Optimizations

邱進東(J. T. Chiu) ； 郭信川(H. C. Kuo) ； 林青海(C. H. Lin)

《中國造船暨輪機工程學刊》 30卷3期 (2011/08) Pp. 131-138

https://doi.org/10.29982/JTSNAME.201108.0001

摘要

智慧型垃圾桶決策之進化演算法（Inlelligenl Garbage Can Decision-Making Model Evolution AIgorithm, IGCMEA），基於差分進化演算法（Differenlial Evollltion AIgorilhm, DE），採用垃圾桶決策模式為邏輯架構，此演算法之族群系統係模擬人類社會組織，在進行決策的過程中，遇到問題與目標不明確、方法不明確及人員流動性等問題等情境時，與與會各方代表人員相互溝通、互斥、妥協與孵化，研擬對應之解決方針，並採用分組與分群之研議機制，進行較客觀、合理且迅速確實的擇優方式。本文利用IGCMEA先對30維樣竿函數問題進行全域最佳化探討與比較，搜尋結果顯示比差分進化被算法可達令人滿意結果，撥著以香蕉函數進行IGCMEA的兩參數（評估世代數與嫂尋區域之放寬比例）之搜尋影響分析，最後利用對平面鋼梁橋樑，進行形狀最佳化，結果與文獻［17］利用最陡下降法所搜尋效果好，說明IGCMEA具有卓越的尋優性能。

關鍵字

最佳化設計 ； 差分進化演算法 ； 垃圾桶決策模式 ； 結構最佳化設計

並列摘要

The Intelligent Garbage Can Decision-Making Model Evolution Algorithm (IGCMEA), which introduces a framework of garbage can decision-making model into the differential evolution algorithm, is to simulate the decision-making process in human social organizations. In a decision-making process, when faced with issues such as unclear goals and technologies, participators turnover. etc., representatives of all participating parties will communicate, argue, compromise and adapt with each other, in order to find a solution to the problems. Group meetings are conducted to choose the best solution in a more objective, reasonable and efficient way.We firstly used IGCMEA to carry out seven 30-dimensional benchmark optimizations including three uni-modal and four multi-modal problems. And then the study of the parameters of evaluated generation numbers and broaden ratio for promising search space is to conduct with the Rosenbrock Function. Finally, we also optimized the structure of plane fran1e bridges using IGCMEA and got a better result than that using the steepest descent method as in the literature [17], illustrating the superior power of IGCMEA.

並列關鍵字

optimum design ； differential evolution algorithms ； garbage can decision-making model ； design optimization of structures