改进竞争粒子群算法及其应用  

Improved competitive swarm optimizer and its applications

作　　者：章强 程辉[1] 叶贞成 张广辉 ZHANG Qiang;CHENG Hui;YE Zhen-cheng;ZHANG Guang-hui(School of Information Science and Engineering,East China University of Science and Technology,Shanghai 200237,China;Key Laboratory of Advance Control and Optimization for Chemical Processes of Ministry of Education,East China University of Science and Technology,Shanghai 200237,China;School of Automotive and Rail Transit,Nanjing Institute of Technology,Nanjing 211167,China)

机构地区：[1]华东理工大学信息科学与工程学院,上海200237 [2]华东理工大学化工过程先进控制与优化技术教育部重点实验室,上海200237 [3]南京工程学院汽车与轨道交通学院,江苏南京211167

出　　处：《计算机工程与设计》2019年第2期376-383,共8页Computer Engineering and Design

基　　金：国家重点研发计划基金项目(2016YFB0303403);国家自然科学基金青年基金项目(21506050);上海市自然科学基金项目(16ZR1407300);中央高校基本科研业务费专项基金项目(22221817014)

摘　　要：为平衡种群的探索与开发,提出一种改进的竞争粒子群算法(CGCSO)。通过柯西高斯变异更新胜利者的位置,提高种群的开发能力;利用环形拓扑结构信息传递速度慢的特点,将其用于胜利者的学习过程,增强种群的多样性;采用可行解优先的约束处理技术,使该算法能够处理约束优化问题。进行8个标准测试函数的仿真实验,并研究比较其它算法,该算法在优化精度和收敛性上表现较好。将该算法应用于处理汽油调和配方在线优化问题,仿真取得了较好的结果,进一步验证了该算法的有效性。To balance the exploration and exploitation of the population,an improved competitive swarm optimizer was proposed(CGCSO).The Winners’positions were updated by Cauchy and Gaussian mutation,which improved the exploitation capability of the population.The ring topology with slow transmission of information was applied to the Winners’learning process,which enhanced the diversity of the population.Feasibility rules were adopted as constraint technique to deal with constrained optimization problems.According to the experiments on 8 benchmark functions,and compared with the other algorithms,the proposed algorithm shows better performance,especially on the optimization accuracy and convergence.The CGCSO algorithm was applied to deal with the real-time optimization of gasoline blending recipe,and the simulation results also verify the effective performance of the proposed algorithm.

关 键 词：竞争粒子群 柯西高斯变异 环形拓扑 约束优化 汽油调和 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]