基于SQP局部搜索的混沌粒子群优化算法  

Chaos particle swarm optimization algorithm integrated with sequential quadratic programming local search

作　　者：徐文星[1] 耿志强[1] 朱群雄[1] 顾祥柏[1,2] 

机构地区：[1]北京化工大学信息科学与技术学院,北京100029 [2]中国石化集团炼化工程公司,北京100029

出　　处：《控制与决策》2012年第4期557-561,共5页Control and Decision

基　　金：国家863计划项目(2006AA04Z184);中央高校科研业务费项目(ZZ1136)

摘　　要：提出一种基于序贯二次规划(SQP)法的混沌粒子群优化方法(CPSO-SQP).将混沌PSO作为全局搜索器,并用SQP加速局部搜索,使得粒子能够在快速局部寻优的基础上对整个空间进行搜索,既保证了算法的收敛性,又大大增加了获得全局最优的几率.仿真结果表明,算法精度高、成功率大、全局收敛速度快,明显优于现有算法.将所提出的算法用于高密度聚乙烯(HDPE)装置串级反应过程的乙烯单耗优化,根据工业反应机理以及现场操作经验分析可知,所提出的算法是可行的.A sequential quadratic programming integrated particle swarm optimization algorithm （CPS-SQP） is proposed. This new algorithm uses CPSO, which makes the best of ergodicity of chaos mappimg, as the global optimizer while the SQP is employed for accelerating the local search. Thus, the particles are able to search the whole space while finding local optima fast, which increases the possibility of exploring a global optimum in problems with more local optima while ensuring the convergence of algorithm. The simulation results for benchmark functions show that CPSO-SQP has better accuracy, more probability of finding global optimum and faster speed of convergence than those reported in the literature. The feasibility of the method is illustrated with the challenging ethylene piece yardage optimization problem of a cascade I-IDPE reaction COurSe.

关 键 词：粒子群优化 序贯二次规划 混沌映射 非线性约束优化 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TQ015.9[自动化与计算机技术—控制科学与工程]