计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (18): 230-232.

• 工程与应用 • 上一篇    下一篇

正交差分演化算法在工程优化设计中的应用

陈文霞,龚文引,蔡之华   

  1. 中国地质大学 计算机学院,武汉 430074
  • 收稿日期:2007-09-25 修回日期:2007-11-26 出版日期:2008-06-21 发布日期:2008-06-21
  • 通讯作者: 陈文霞

Orthogonal differential evolution algorithm for engineering optimum design

CHEN Wen-xia,GONG Wen-yin,CAI Zhi-hua   

  1. School of Computer Sciences,China University of Geosciences,Wuhan 430074,China
  • Received:2007-09-25 Revised:2007-11-26 Online:2008-06-21 Published:2008-06-21
  • Contact: CHEN Wen-xia

摘要: 提出一种基于正交设计的快速差分演化算法,并把它应用于工程优化设计中。新算法在保留传统差分演化算法简单、有效等特性的同时,还具有以下一些特点:(1)引入一种基于正交设计的杂交算子,并结合约束统计优生法来产生最好子个体;(2)提出一种简单的多样性规则,以处理约束条件;(3)简化基本差分演化算法的缩放因子,尽量减少算法的控制参数,方便工程人员的使用。通过对2个工程优化实例进行实验,并与其他算法的结果作比较,其结果表明,新算法在解的精度、稳定性、收敛性和收敛速度上表现出很好的性能,并且对所优化的问题没有特殊的要求,具有很好的普适性。

Abstract: A fast and robust differential evolution based on Orthogonal Design(ODE) is proposed,and then it is used to solve engineering optimum design problems.The ODE combines the Conventional DE(CDE),which is simple and efficient,with the orthogonal design,which can exploit the optimum offspring.The ODE has some features.(1)It uses a robust crossover based on orthogonal design and an optimal offspring is generated with the constrained statistical optimal method.(2)It uses simple diversity rules to handle the constraints and maintain the diversity of the population.(3)The ODE simplifies the scaling factor F of the CDE,which can reduce the parameters of the algorithm and make it easy to use for engineers.The authors execute the proposed algorithm to solve 2 engineering optimum designs with linear or/and nonlinear constraints.Through comparison with some other algorithms,the experimental results demonstrate that the performance of the ODE outperforms other algorithms in terms of the quality of the final solution and the stability.Moreover,the new algorithm has no special requirements on the characteristics of optimal designing problems;it has a fairly good universal adaptability and a reliable operation of program with a strong ability of overall convergence.