论文部分内容阅读
微粒群算法因其实现简单及优化效果较好而得到广泛应用,但也存在易早熟和局部收敛的缺点;结合Lévy飞行的特性,提出了一种新的带Lévy变异的微粒群算法,并对其收敛性进行分析,指出该算法依概率收敛于全局最优解.通过对8个标准测试函数的仿真实验,结果表明改进算法中的Lévy变异能够利用粒子的当前知识并增加群体的多样性,从而能够更有效地平衡局部搜索和全局搜索,使其具有更好的性能,最后对改进算法的各参数设置进行了探讨分析.
Particle swarm optimization is widely used due to its simple implementation and good optimization effect, but it also has some shortcomings such as premature convergence and local convergence. Based on the characteristics of Lévy flight, a new particle swarm optimization algorithm with Lévy mutation is proposed. The results show that the Lévy mutation in the improved algorithm can make use of the current knowledge of particles and increase the diversity of the population, Which can more effectively balance the local search and global search to make it have better performance. Finally, the parameters of the improved algorithm are discussed and analyzed.