融合鲸鱼算法的混合灰狼优化算法

Hybrid Grey Wolf Optimization Algorithm Fused with Whale Algorithm

针对灰狼优化(GWO)算法存在容易陷入局部最优、收敛速度慢、求解精度不高等问题,提出一种融合鲸鱼算法的混合灰狼优化(HWGWO)算法.首先在鲸鱼算法的螺旋泡网狩猎行为中融入Levy飞行并将其整体引入灰狼优化算法;然后将动态权重和差分进化思想引入灰狼优化算法;最后利用贪婪选择策略来保留较好的灰狼位置.选取23个测试函数进行数值试验,结果表明,HWGWO算法在收敛速度和求解精度上都有所提升.此外,利用HWGWO算法求解拉伸/压缩弹簧设计问题得到的设计方案更有效.

Aiming at the problems of grey wolf optimization(GWO) algorithm that are easy to fall into local optimality,slow convergence speed,and low solution accuracy,a hybrid grey wolf optimization(HWGWO) algorithm fused with Levy flight and whale algorithm is proposed.First,the spiral bubble net hunting behavior of the whale algorithm is incorporated;then the dynamic weight and differential evolution ideas are introduced into the grey wolf optimization algorithm;finally,the greedy selection strategy is used to retain a better grey wolf position.23 test functions are selected for numerical experiments,and the results show that the HWGWO algorithm has improved the convergence speed and solution accuracy.In addition,the design scheme obtained by using the HWGWO algorithm to solve the tension/compression spring design problem is more effective.