额隆感知和围攻机制改进的白鲸优化算法  

Beluga Optimization Algorithm with Improved Melon Sensing and Siege Mechanism

作　　者：文裕杰 张达敏 邓佳欣 杨乐 WEN Yujie;ZHANG Damin;DENG Jiaxin;YANG Le(College of Big Data and Information Engineering,Guizhou University,Guiyang 550025,China)

机构地区：[1]贵州大学大数据与信息工程学院,贵阳550025

出　　处：《小型微型计算机系统》2024年第12期2858-2866,共9页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(62062021,61872034)资助;贵州省科学技术基金项目(黔科合基础[2020]1Y254)资助。

摘　　要：白鲸优化算法(BWO)是一种有效的元启发式算法,但存在种群多样性低、全局搜索能力不足等问题.为此,提出一种额隆感知和围攻机制改进的白鲸优化算法(MSBWO).受麻雀算法的启发,设置安全区域和额隆感知机制,增强白鲸的判断能力并加快收敛速度.然后引入多方式的围攻机制,丰富个体位置更新的多样性,增大全局搜索能力.同时加入了动态高斯变异进行扰动,以提高算法跳出局部极值的概率.通过14个基准函数和CEC2019进行算法有效性测试,并与其他优化算法进行了比较.结果表明,MSBWO取得更优的收敛速度和预测精度.最后,将该算法应用于2个工程设计问题.实验结果表明,所提出的MSBWO算法具有良好解决实际工程问题的能力.Beluga whale optimization(BWO)is an effective meta-heuristic algorithm,but it suffers from low population diversity and insufficient global search capability.To address these issues,an improved beluga whale optimization(MSBWO)with Melon sensing and Siege mechanism is proposed.Inspired by the sparrow search algorithm,the safe zone and the Melon sensing mechanism are set to enhance the judgment ability of beluga whales and improve the convergence speed.Then,a multi-mode siege mechanism is added to enrich the population′s diversity and increase the global search capability.In addition,dynamic Gaussian mutation is added to improve individual′s probability of jumping out of the local extremum.The effectiveness of the algorithm is verified by 14 benchmark functions and CEC2019,and compared with other optimization algorithms.The results show that MSBWO has faster convergence speed and better accuracy.Finally,the algorithm is applied to 2 engineering design problems.Experimental results show that the proposed MSBWO algorithm can deal with practical application problems effectively.

关 键 词：白鲸优化算法 额隆感知 围攻机制 动态高斯扰动 工程优化 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]