基于Hénon映射的自适应克隆选择优化算法

Adaptive Clone Selection Optimization Algorithm Based on Hénon Map

免疫算法与遗传算法都存在的不成熟收敛问题。混沌优化方法是近年出现一种新的优化技术,通常使用Logistic或Tent映射产生混沌序列进行搜索,Logistic映射产生的混沌序列的概率密度函数切比雪夫型分布,当最优值落在[0,1]的中间位置时,这种分布特性会影响全局搜索能力和效率。而Tent映射也存在迭代易落入小周期循环的问题。针对免疫算法和混沌优化算法中存在的缺陷,该文用变尺度的搜索策略,提出了一种基于Hénon映射的自适应克隆选择的优化算法,数值仿真结果表明,该文提出的算法提高了局部搜索的能力及其计算效率,算法可行有效。

Both genetic algorithm and immune algorithm are still unable to overcome premature convergence problem effectively.Chaos optimization method,as a new optimization technology in recent years,is usually based on Logistic or Tent map to produce chaos sequence and uses the properties of periodicity and randomness of the chaos sequence for local searching.However,the probability density function of chaotic sequence of Logistic map is a Chebyshev type function,which may affect the global searching ability and computational efficiency of chaos optimization algorithm severely when optimal point is located in the middle part of interval [O,1],On the other hand,the Tent map based algorithms are easy to run into small periodic cycle.In order to overcome the demerits mentioned above,a Hénon map based adaptive clone selection optimization algorithm is proposed by using mutative scale searching strategy.Simulation results of four testing functions show that the approach can improve global searching ability and computational efficiency greatly,and the new algorithm is feasible and effective.