基于约束骨干粒子群算法的化工过程动态多目标优化  

Dynamic Multi-Objective Optimization of Chemical Processes Using Constrained Bare-Bones MOPSO Algorithm

作　　者：王珊珊[1] 杜文莉[1] 陈旭[1] 徐斌[1] 钱锋[1] 

机构地区：[1]华东理工大学化工过程先进控制和优化技术教育部重点实验室,上海200237

出　　处：《华东理工大学学报（自然科学版）》2014年第4期449-457,共9页Journal of East China University of Science and Technology

基　　金：国家自然科学基金(61222303;21276078);国家863计划(2012AA040307);教育部新世纪优秀人才计划(NCET-10-0885);上海市重点学科建设项目(B504)

摘　　要：大多数化工过程是动态过程,需同时优化多个目标,从而带来复杂的约束多目标动态优化问题。因此提出了一种动态约束多目标骨干粒子群算法,即采用一种新型约束处理方法,结合Pareto支配和ε约束支配技术的双档集机制;针对约束优化问题寻优难度更大,更易陷入局部最优的特点,采用局部搜索和混合变异策略,并自适应调整搜索步长,提高算法的探索和开发能力;采用分段线性函数参数化方法,构建一种动态约束多目标粒优化算法,并将其用于解决间歇反应器的动态多目标优化问题。测试实验表明:与NSGA-II和自适应差分进化算法(SADE-εCD)比较,该算法具有更优秀的收敛性与分布性;应用到化工过程多目标动态优化问题实例进行比较表明,多目标骨干粒子群算法在约束多目标动态优化问题的求解中表现出更好的应用前景。Most of chemical processes are dynamic and require optimization of multiple targets, wh yields the problem of constrained dynamic multi-objective optimization. Aiming at the above problem, t work proposes a constrained bare-bones MOPSO algorithm, which adopts double external archives inlegrating Pareto domination principle and e-constrained-domination princip convergence, a hybrid mutation operator is introduced. Meanwhile, an adapt strategy is used to enhance the exploratory ability. Thus, an approach combinin ich his by le. To avoid premature ive sampling distribution g bare-bones MOPSO and conlrol vector parameterization is proposed to solve the dynamic optimization problems. Finally, the comparison with NSGA Ⅱ and SADE-εCD algorithm is made to verify the advantageous performance of the proposed constrained bare-bones MOPSO algorithm in this work.

关 键 词：约束处理 动态多目标优化 骨干粒子群算法 化工过程 

分 类 号：TP182[自动化与计算机技术—控制理论与控制工程]