Structural Optimization Using Genetic Algorithms with Fuzzy Rule-Based Systems

具有模糊規則庫系統之結構最佳化遺傳演算法

鍾添東(Tien-Tung Chung) ； 施嘉勝(Chia-Sheng Shih)

《中國機械工程學刊》 28卷5期 (2007/10) Pp. 523-532

https://doi.org/10.29979/JCSME.200710.0007

摘要

本文提出兩個模糊規則庫系統以調整遺傳演算法之遺傳參數及懲罰因子，並應用於結構最佳化設計。首先以一個改良式動態懲罰法，將具有限制條件的結構最佳化問題轉換成無限制條件之問題，以便利用遺傳演算法進行最佳化搜尋。第一個模糊規則庫系統根據目前族群的資訊，動態地調整遺傳演算法的交配率和突變率；另一個模糊規則庫系統則根據個體違反限制條件的數量及程度來調整懲罰因子。將本文發展出的程式，應用於數個具限制條件的結構最佳化問題。由結果顯示，本文發展的方法可成功地應用於一般的結構最佳化問題。

並列摘要

This paper presents two fuzzy rule-based systems to adapt parameters of genetic operators and a penalty factor in genetic algorithms for optimum design of structures. An improved dynamic penalty method is applied to transform the constrained structural optimization problem into an unconstrained problem for the optimization procedure using genetic algorithms. The first fuzzy rule-based system adjusts the crossover rate and the mutation rate dynamically according to the information of current population. The other fuzzy rule-based system adjusts the penalty factor according to the amount and level of constraint violations of all individuals. With the developed program, several constrained structural optimization problems are investigated. The results demonstrate that the developed algorithm can be applied successfully to general structural optimization problems.

並列關鍵字

genetic algorithm ； fuzzy rule-based system ； structural optimization ； penalty method