基于混沌序列的粒子群优化算法

提出一种改进粒子群局部搜索能力的优化算法,对于陷入局部极小点的情性粒子，引入混沌序列重新初始化，在迭代中产生局部最优解的邻域点，帮助情性粒子逃商束缚并快速搜寻到最优解．对经典函数的测试计算表明。改进的混合算法通过微粒自适应更新机制确保了全局搜索性能和局部搜索性能的动态平衡，而且保持了PSO计算简洁的特点，在收敛速度和精度上均优于普通的PSO算法.

Particle Swarm Optimization Algorithm Based on Chaotic Series

An advanced particle swarm optimization algorithm is presented to enhance the local searching ability. Some particles trapped in local minimums are initialized again by chaotic series in order to introduce neighboring regions of local minimums in the iteration and help them break away from local optimum to find the globe optimal solution rapidly. The experimental results of classic functions show that the improved hybrid method makes use of the ergodicity of chaotic search to improve the capability of precise search and keep the balance between the global search and the local search, and maintain the concise calculation of particle swarm optimization (PSO)property. The enhanced algorithm has great advantage of convergence property and robustness compared to genetic algorithm and PSO algorithm.