权重自适应调整的混沌量子粒子群优化算法

摘要

A novel algorithm is presented on the base of quantum behaved particle swarm optimization, which is aimed at resolving the problem of slow convergence rate in optimizing higher dimensional sophisticated functions and being trapped into local minima easily.Chaos algorithm is incorporated to traverse the whole solution space. First ,rate of cluster focus distance changing was introduced in this new algorithm and the weight was formulated as a function of this factor which provides the algorithm with effective dynamic adaptability. Secondly, a method of effective judgment of early stagnation is embedded in the algorithm. Once the early maturity is retrieved, the algorithm mutates particles to jump out of the local optimum particle according to the structure mutation so as to reduce invalid iteration. Experiments on high-dimension test functions indicate that the improved algorithm is superior to classical PSO algorithm and quantum-behaved PSO algorithm.%针对量子粒子群优化算法在处理高维复杂函数收敛速度慢、易陷入局优的问题,利用混沌算子的遍历性提出了基于惯性权重自适应调整的混沌量子粒子群优化算法.新算法首先引入聚焦距离变化率的概念,将惯性因子表示为关于聚焦距离变化率的函数,从而使算法具有动态自适应性;其次,在算法中嵌入有效判断早熟停滞的方法,一旦检索到早熟迹象,根据构造的变异概率对粒子进行变异使粒子跳出局部最优,从而减少无效迭代.对高维测试函数的实验表明:改进算法的性能优于经典的PSO算法,基于量子行为的PSO算法.