带LMI约束的混合整数二次规划问题的全局最优性条件  

Sufficient global optimality conditions for mix-integer quadratic minimization problem with LMI constraints

作　　者：秦帅[1] 祁云峰[1] 李倩[1] 祁艳妮[1] 

机构地区：[1]重庆师范大学数学学院,重庆400047

出　　处：《重庆文理学院学报（自然科学版）》2011年第1期29-32,共4页Journal of Chongqing University of Arts and Sciences

摘　　要：推导出带LM I约束的非凸二次规划的全局最优充分性条件.其中,主要是利用一种研究全局最优化问题的全局最优性条件的新方法,来对这类特殊非凸二次规划问题的全局最优充分性条件进行研究.通过利用一个拉格朗日函数和L-次微分相结合的方法,然后再利用这两个已证明的结论推导出带LM I约束的混合整数二次规划最小问题的全局极小点的全局最优性充分条件,而且在推导出的定理基础上得到了一些推论.In this paper,the global optimality conditions for some noncovex quadratic problems with LMI constraints by using an approach to establish sufficient global conditions were discussed.Making use of Lagrangian function and L-sub differential approach,then using two proved conclusions global sufficient optimality conditions with LMI constraints were deduced and some known conditions were extended.Lastly,some numeral examples illustrated the effectiveness and feasibility of sufficient optimality conditions.

关 键 词：二次混合整数规划 LMI约束 充分性条件 

分 类 号：O221[理学—运筹学与控制论]