粒子群优化算法中的惯性权值非线性调整策略

摘要

To improve the performance of Particle Swarm Optimization(PSO) algorithm, nonlinear strategy based on sinusoid, tangential and logarithmic curve is proposed in this paper. At the same time, a strategy on processing the particles out of range is proposed. Several classical benchmark functions are used to evaluate the strategies. Experimental results show that for continuous optimization problem, the proposed sinusoid and logarithmic curve strategies gain advantages over the classical linear strategy, while the linear strategy outperforms the tangential curve strategy.%为提升粒子群优化算法的性能,提出基于正弦曲线、正切曲线和对数曲线的非线性惯性权值调整策略.采用镜像策略对越界粒子进行处理,利用标准测试函数测试这些策略对算法的影响.实验结果表明,对于连续函数优化问题,正弦曲线和对数曲线策略优于传统的线性调整策略,而传统的线性调整策略又优于正切曲线策略.