广义多目标minmax问题的最优性条件和极大熵方法  

The Optimality Conditions and the Maximum Entropy Method for the Generalized Multiobjective Minmax Problem

作　　者：刘三明[1] 冯恩民[2] 

机构地区：[1]江苏科技大学数理系,江苏镇江212003 [2]大连理工大学应用数学系,辽林大连116023

出　　处：《运筹与管理》2005年第6期19-22,28,共5页Operations Research and Management Science

基　　金：国家自然科学基金资助项目(19871009)

摘　　要：本文讨论了广义多目标minmax问题的最优性条件。利用极大熵逼近函数,研究了广义多目标minmax问题的逼近问题,在较弱的条件下,证明了由极大熵逼近函数导出的多目标逼近问题的临界点的任一极限点均为原广义多目标minmax问题的临界点。In this paper, the optimality conditions for the generalized multiobjective minimax problem are derived. Based on the maximum entropy principle, the approximating problem for the generalized multiobjective minmax problem is discussed. It is proved that any limit point of the critical point of the approximating problem is the critical point of the generalized mulitiobjective minmax problem under weaker conditions.

关 键 词：运筹学 广义多目标minmax问题 极大熵方法 最优性条件 

分 类 号：O221.6[理学—运筹学与控制论]