一种基于量子行为的改进粒子群算法

研究粒子群优化算法（PSO）的收敛速度，以提高该算法性能是PSO的一个重要而且有意义的研究。Jun Sun 等人通过对PSO系统下的单个个体在量子多维空间的运动及其收敛性的分析，提出了具有函数形式的粒子群算法（Quantum Delta-Potential-Well-based PSO）。在此基础上进行了改进，用粒子的速度来产生一个随机数引导粒子向最优解快速靠拢，并对速度的处理采取了新的策略。仿真结果表明：该改进算法对收敛速度有非常好的改善，而且稳定性也较好。

Modified particle swarm optimization with particles having quantum behavior

It makes sense to search on the PSO from its convergence speed in order to improve its performance.Jun Sun etc proposed the QDPSO inspired by the analysis of convergence of PSO and individual particle moving in a quantum multi-dimension space in PSO system,and established a quantum Delt potential well model for PSO.The random number produced by speed of particles is used to guide particles converging to the optimal solution quickly.The modified QDPSO takes a new method for speed.The experiment result shows that the performance of modified algorithm is far better,faster and more stabile in convergence.