计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (34): 35-37.DOI: 10.3778/j.issn.1002-8331.2009.34.011

• 研究、探讨 • 上一篇    下一篇

人工神经网络与改进遗传算法的协作求解

张 斌1,武广号2   

  1. 1.西安电力高等专科学校,西安 710032
    2.西安交通大学,西安 710043
  • 收稿日期:2009-02-25 修回日期:2009-03-31 出版日期:2009-12-01 发布日期:2009-12-01
  • 通讯作者: 张 斌

Coopration of artifical neural networks and improved genetic algorithms for solving

ZHANG Bin1,WU Guang-hao2   

  1. 1.Xi’an Electrical Power College,Xi’an 710032,China
    2.Xi’an Jiaotong University,Xi’an 710043,China
  • Received:2009-02-25 Revised:2009-03-31 Online:2009-12-01 Published:2009-12-01
  • Contact: ZHANG Bin

摘要: 简要介绍了改进遗传算法求解问题的步骤以及解决实际问题的特点。为了利用改进遗传算法的优点,提高其收敛速度,提出改进遗传算法与人工神经网络(BP网络)利用神经网络的联想记忆、特征提取功能辅助遗传算法求解结构优化设计问题,以避免在遗传算法中所作的那些不必要的分析计算,从而节省了计算时间。最后通过算例证实,比简单遗传算法与人工神经网络协作计算时间减少约25%。

关键词: 人工神经网络, 改进遗传算法, 适度值函数, 优化设计

Abstract: An improved genetic algorithm for solving practical problems in steps is proposed.To take advantages of the improved genetic algorithm to accelerate the convergence rate,which is combined with artificial neural network(BP network),especially the associative memory,feature extraction,in structural optimization design for avoiding the unnecessary computing tasks in the traditional genetic algorithm.The example demonstrates that the artificial neural network enables to reduce the computing period by 25%.

Key words: artifical neural networks, improved genetic algorithms, moderate function structure, optimization design

中图分类号: