改进鲸鱼算法及其在乘员约束系统中的应用  

Modified whale optimization algorithm and its application in occupant restraint system

作　　者：黄岳竹 尹安东 王笑乐 谷先广 HUANG Yuezhu;YIN Andong;WANG Xiaole;GU Xianguang(School of Automobile and Traffic Engineering, Hefei University of Technology, Hefei 230009, China;School of Engineering, Anhui Agricultural University, Hefei 230036, China;TaiHangChangQing Automobile Safety System(Suzhou) Co., Ltd., Suzhou 215100, China)

机构地区：[1]合肥工业大学汽车与交通工程学院,安徽合肥230009 [2]安徽农业大学工学院,安徽合肥230036 [3]太航常青汽车安全系统(苏州)股份有限公司,江苏苏州215100

出　　处：《合肥工业大学学报（自然科学版）》2022年第2期165-170,230,共7页Journal of Hefei University of Technology：Natural Science

基　　金：中国博士后科学基金资助项目(2018M640524);中国博士后基金特别资助项目(2019T120460l)。

摘　　要：针对鲸鱼优化算法(whale optimization algorithm,WOA)“早熟收敛”的缺陷,文章提出一种改进的鲸鱼优化算法(modified whale optimization algorithm,MWOA)。该算法在WOA的基础上嵌入自适应权重来协调算法的全局搜索与局部开发,同时引入反向学习策略和相关性指标优化全局极值,指引种群向更有希望的区域运动,提高算法的开发效率;利用4个基准测试函数对MWOA性能进行测试,结果表明算法性能得到了有效提升;基于有限元仿真分析,运用MWOA算法优化汽车正面100%碰撞工况下乘员约束系统性能,结果表明,该算法极大地改善了乘员约束系统的性能。Aiming at the defect of premature convergence of whale optimization algorithm(WOA),a modified WOA(MWOA)is proposed.The algorithm embeds adaptive weight on the basis of WOA to balance the global exploration and local exploitation.In addition,the opposition-based learning(OBL)strategy and correlation index are introduced to update the global optimum,so as to guide the population to move to more promising areas and improve the efficiency of exploitation.Four benchmark functions are used to test the performance of MWOA,and the results show that the performance is improved effectively.Finally,based on the simulation analysis,MWOA is used to optimize the performance of occupant restraint system under 100%frontal impact condition,and the conclusion shows that the algorithm greatly improves the performance of occupant restraint system.

关 键 词：改进的鲸鱼优化算法(MWOA) 自适应权重 反向学习策略 相关性指标 乘员约束系统 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]