文献类型：期刊文献

中文题名：改进灰狼算法及其应用

英文题名：Improved gray wolf optimization and its application

作者：袁岩[1];曹萃文[1]

机构：[1]华东理工大学化工过程先进控制和优化技术教育部重点实验室

年份：2020

卷号：41

期号：2

起止页码：513

中文期刊名：计算机工程与设计

外文期刊名：Computer Engineering and Design

收录：CSTPCD;;北大核心:【北大核心2017】；

基金：国家自然科学基金项目（61673175、61573144）

语种：中文

中文关键词：灰狼算法;正弦余弦搜索;自适应局部搜索;最小二乘支持向量机;数据建模

外文关键词：grey wolf optimizer algorithm;sine-cosine search;adaptive local search;least squares support vector machine;data modeling

摘要：为提高灰狼算法的探索与开发能力,提出一种改进的多策略灰狼算法。在标准灰狼算法基础上加入对立搜索策略,提高算法收敛速度;引入正弦余弦搜索策略,提高算法的寻优精度;引进自适应局部搜索策略,避免算法陷入局部最优解,提升算法全局勘探开发能力。8个Benchmark函数的仿真实验结果表明,改进算法显著提升了算法的寻优精度和收敛速度。将改进的灰狼算法结合最小二乘支持向量机应用于加氢裂化数据建模问题,仿真取得了较好的结果,进一步验证了改进算法的有效性。
To improve the exploration and exploitation ability of grey wolf optimizer algorithm,a multi-strategy grey wolf optimizer algorithm was proposed.The opposite search strategy was adopted to improve the convergence speed of the algorithm.The sine-cosine search strategy was used to enhance the search accuracy of the algorithm.The adaptive local search strategy was selected to prevent local optimal solutions and improve the global search ability of the algorithm.The simulation experiments on 8 benchmark functions were implemented,the simulation results indicate that the improved algorithm significantly improves the optimization accuracy and convergence speed.The improved grey wolf algorithm combined with least squares support vector machine was applied to the data modeling of hydrocracking.The obtained results verify the effective performance of proposed algorithm.