求解带约束函数优化的两级自适应遗传算法.pdf

22 2 Systems Engineering and Electronics Vol22, No2 2000 : 1001506X( 2000) 蔡良伟 雍正正 深圳大学电子工程系, 518060 针对带约束的非线性函数优化问题, 提出一个两级自适应遗传 法根据待优化函数和约束构造拉 格朗日对偶函数,在下级对给定的拉格朗日乘子, 用遗传 法搜索变量的最优解;在上级针对拉格朗日对偶函数, 用遗传 法搜索拉格朗日乘子的最优解采用自适应的方法,根据 个体的适配值和种群的适配值统计特性确定交 叉概率和变异概率计 结果表明, 该 法是有效的 约束 非线性优化 自适应控制 遗传 法 :TP2732; O224 Using Two- Level Adaptive Genetic Algorithm to Sovle Constrained Function Optimization Problems Cai Liangwei Yong Zhengzheng Department of Electronic Engineering, Shenzhen University, 518060 Abstract A two- level adaptive genetic algorithm is proposed to solve constrained nonlinear function optimization problems. At first, the Lagrangian function is constructed according to the optimization function and constraints. At the lower level, genetic algo rithm is used to search the optimal values of variables for fixedLagrangian multipliers. At the upper level, genetic algorithm is used to searchthe optimalvalues of Lagrangian multipliersto the Lagrangianfunction. The probabilities of crossover andmutation are adap tively determined according to fitnesses and fitness statistics of chromosomes. Computation shows that this algorithm is efficient. Ke words Constraint Function optimization Genetic algorithm , 1 (2) , , , [ 1~ 3] : , !( i = 1, ∀, popsize) ( popsize i [4, 5] ) f () i ,