Multi-objective wolf pack algorithm based on adaptive grouping strategy and crowding distance

作     者：Zhao, Jia Lv, Feng Xiao, Ren-Bin Fan, Tang-Huai Dong, Wen-Fei Wang, Hui 

作者机构：School of Information Engineering Nanchang Institute of Technology Nanchang 330000 China Nanchang Key Laboratory of IoT Perception and Collaborative Computing for Smart City Nanchang Institute of Technology Nanchang 330099 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan 430074 China 

出 版 物：《Kongzhi yu Juece/Control and Decision》 (Control and Decision)

年 卷 期：2024年第39卷第11期

页      面：3772-3780页

核心收录：

学科分类：0711[理学-系统科学] 12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 081402[工学-结构工程] 0835[工学-软件工程] 0814[工学-土木工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：创新科技2030-“新一代人工智能”重大项目(2018AAA0101200) 国家自然科学基金(52069014) 

主　　题：Optimization algorithms 

摘      要：In view of the wolf pack algorithm has good solving ability in single objective optimization problems, a multi-objective wolf pack algorithm (MOWPA-AG) based on adaptive grouping and updating of crowded distance is proposed by taking the advantages of the wolf pack biological habit and being used to solve multi-objective optimization problems. Firstly, an adaptive grouping strategy considering population diversity and dispersed search is proposed to simulate family aggregation in wolf packs. The strategy stratifies populations, separates populations and helps population diffusion search Pareto optimal solutions. Then, a population renewal mechanism based on crowding distance is designed, which enables the population to maintain rapid evolution while obtaining the optimal solution set. In order to verify the performance of the proposed algorithm, nine different benchmark testing problems are tested, and the effectiveness of the proposed algorithm is verified by comparing with other classic and recent multi-objective optimization algorithms. Finally, the MOWPA-AG is applied to solve the problem of four-bar truss structure in practical engineering, which shows the universality of the proposed algorithm. © 2024 Northeast University. All rights reserved.