Computer Engineering and Applications ›› 2007, Vol. 43 ›› Issue (21): 40-42.

• 学术探讨 • Previous Articles     Next Articles

Maximum entropy multi-objective evolutionary algorithm for nonlinear constrained programming

LIU Chun-an


  1. Computation and Information Institute,Baoji College of Arts and Science,Baoji,Shaanxi 721013,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-07-21 Published:2007-07-21
  • Contact: LIU Chun-an




  1. 宝鸡文理学院 计算与信息科学研究所,陕西 宝鸡 721013
  • 通讯作者: 刘淳安

Abstract: The difficult to solve the Nonlinear Constraint Programming problems(NCPs) is how to do with the constraint.In this paper,a new maximum entropy function based on the constraint conditions of NCPs is given.Then using the new maximum entropy function,the nonlinear constrained programming problems is transformed into a bi-objective optimization problem.By combining the reasonable design of the searching operation and different parameters,a new maximum entropy evolutionary algorithm is finally proposed.The computer simulations demonstrate the effectiveness of the proposed algorithm.

Key words: nonlinear programming, constrained programming, evolutionary algorithm, maximum entropy

摘要: 解非线性约束规划的困难在于如何处理问题的约束,从问题的约束条件出发构造了一个新的极大熵函数,利用此函数将原非线性约束规划问题转化成了两个目标的多目标优化问题。通过对搜索操作和参数的合理设计给出了一种新的极大熵多目标进化算法。计算机仿真表明该算法对带约束的非线性优化问题求解是非常有效的。

关键词: 非线性规划, 约束规划, 进化算法, 极大熵