关键词: 遗传算法, 全局优化, 适应度, 混合选择, 交叉策略

Abstract: A modified real-coding genetic algorithm is brought out aiming at the deficiency of general real-coding genetic algorithm in solving complex function global optimization problem on a bounded area.In the modified algorithm，the fitness values of the individuals are gotten directly from the objective values’ orders to refrain from falling into local optimum at the late stage of evolution.The algorithm uses a crossover strategy with a linear approximation concept according to function fitness，a hybrid selection strategy which combines selection of stochastic universal sampling with the elitist method and the selection of offspring replacing the worst individuals of parents，and a real-valued mutation strategy of the changing mutation probability.The modification can converge to the global optimum more quickly.The simulation results of twelve typical complex functions show that the modified algorithm can not only converge fast and have a strong robustness，but also get more precise results.

Key words: genetic algorithm, global optimization, fitness, hybrid selection, crossover strategy