Modified Differential Evolution for Structural Optimization

• Main Authors: Ko-Ying Tseng, 曾科穎
• Other Authors: Chun-Yin Wu
• Format: Others
• Language: en_US
• Published: 2010
• Online Access: http://ndltd.ncl.edu.tw/handle/31731599346536819939

博士 === 大同大學 === 機械工程學系(所) === 98 === Differential evolution (DE) is a heuristic optimization method used to solve many optimization problems in real-valued search space. It has the advantage of incorporating a relatively simple and efficient form of mutation and crossover. In this study, two modified differential evolution algorithm, adaptive multi-population differential evolution and modified binary differential evolution, have been developed for dealing with different types of optimization problems. The adaptive multi-population differential evolution (AMPDE), including a proposed penalty-based self-adaptive strategy and multi-population mechanism, is developed in this study to enhance the performance of optimum search in truss structure optimization problems. Although the efficiency of proposed AMPDE is better than original DE and other population-based methods, it still has a difficulty in dealing with binary optimization problems due to the fact that the representation of design variable is a real-value type. In order to develop a differential evolution algorithm which can be suitable for both real-valued and binary optimization problems, a new modified binary differential evolution (MBDE) with a simple and new binary mutation mechanism based on a logical operation is proposed in this study. The developed MBDE is suitable for dealing with binary and real-valued optimization problems. Some numerical optimization problems, including test functions and a uniformity optimization of heat bonder, are first used to validate the correctness of architecture and performance of optimal search of the proposed MBDE algorithm. Different structural topology optimization problems are utilized to illustrate the high viability of the proposed algorithm in binary optimization problems. From the result of this study it is shown that the developed MBDE is suitable for dealing with real-valued and binary optimization problems. Besides, the proposed MBDE was observed to approach solutions better than those found in the references in the field of topology optimization of structures.