一种改进的自适应粒子群优化算法

针对粒子群优化算法中出现对大规模问题搜索失败，分析了粒子群优化算法的收敛性，指出了粒子速度与搜索失败的关系，提出了一种根据速度信息自适应调整参数的粒子群优化算法，该算法在满足收敛性的条件下，搜索过程中粒子根据理想的速度自适应调整参数进行搜索。修改后的算法经过大量测试函数上的模拟实验验证，并与其他算法进行了比较。实验结果表明，该算法能克服基本PSO算法在求解高维、多峰等复杂非线性优化问题时易陷入局部最优和不收敛等搜索失败的问题。

An Improved Adaptive Particle Swarm Optimizer

Aiming at the search failure of standard PSO algorithm in Large-scale question, the convergence of PSO algorithm is analysed and the relation between the velocity of particle swarm and search failure is pointed out. According to velocity information, one kind of adaptive parameter adjusting PSO algorithm is put forward. The modified algorithm is tested and compared with other published methods on many famous benchmark functions. The experimental results illustrate that the proposed algorithm has the potential to overcome local optimization and divergence that PSO algorithm is easy to sink into in multi-dimension and multi-peak questions.