一种基于新移动策略的灰狼优化算法

Improved grey wolf optimization algorithm based on a new movement strategy

针对标准灰狼算法存在的收敛速度慢和容易陷入局部最优的问题,提出一种改进的灰狼优化算法(dynamic approach grey wolf optimization,DAGWO)。该算法采用新的个体位置移动策略,增加狼群攻击的多样性和随机性,提高了收敛速度;同时,引入基于停滞检测的随机初始化策略增加种群多样性,提高了全局搜索能力。通过12个基准测试函数的仿真实验,表明DAGWO算法的收敛速度和求解精度均明显优于其他算法。此外,将DAGWO算法应用于减速器设计问题,证明了其在工程优化问题上的可行性和有效性。

Aiming at the problems of slow convergence speed and easy to fall into local optimum of the standard GWO algorithm,an improved GWO algorithm,dynamic approach grey wolf optimizer(DAGWO),is proposed.The algorithm adopts a new individual position movement strategy,which increases the diversity and randomness of wolves'attacks and improves the convergence speed.Meanwhile,the introduction of a random initialization strategy based on stagnation detection increases population diversity and improves the global search ability.The simulation experiments of 12 benchmark functions show that the DAGWO algorithm significantly outperforms other algorithms in terms of convergence speed and solution accuracy.In addition,the application of DAGWO algorithm to the reducer design proves its feasibility and effectiveness in engineering optimization problems.