具有适应度选择调整策略的混沌遗传算法及其应用

Chaos Genetic Algorithm with Fitness Selection Adjustment Strategy and Its Application

针对遗传算法在非线性系统优化问题中易陷入局部最优,且大量研究改进后仍存在不足的问题。根据混沌运动的结构特点,提出了一种解决非线性系统优化问题的混沌遗传算法(CGA,ChaosGeneticAlgorithm)。该算法将混沌变量引入遗传算法的优化变量中,使两者的取值范围相互映射,利用更新后的混沌变量转换为“染色体”进行遗传操作,同时根据适应度大小选择需要附加混沌扰动的群体,使变异操作具有导向性,经过多次进化,得出问题的最优解。仿真实验利用多种测试函数和相似的智能优化算法进行对比验证。结果表明,该算法保证了非线性系统优化问题动态响应的速度和寻优结果的精度,定量的评价了混沌遗传算法的优化效果。

For genetic algorithm,it is easy to fall into the local optimum in the nonlinear system optimization problem,and there are still many problems in the research after the improvement. According to the structural characteristics of chaotic motion,a Chaos Genetic Algorithm (CGA) is proposed to solve the nonlinear system optimization problem. The algorithm introduces chaotic variables into the optimized variables of the genetic algorithm,maps the range of values of the two,and uses the updated chaotic variables to transform into "chromosomes" for genetic manipulation. At the same time,the chaotic disturbances are selected according to the size of the fitness. It makes the mutation operation oriented,and after many evolutions,the optimal solution of the problem is obtained. Simulation experiments use multiple test functions and similar intelligent optimization algorithms for comparison verification. The results show that the algorithm guarantees the speed of the dynamic response of the nonlinear system optimization problem and the accuracy of the optimization result,and quantitatively evaluates the optimization effect of the chaotic genetic algorithm.