一种解决约束优化问题的模糊粒子群算法

魏静萱; 王宇平

doi:10.3724/SP.J.1146.2007.00689

一种解决约束优化问题的模糊粒子群算法

doi: 10.3724/SP.J.1146.2007.00689

魏静萱^{①;王宇平},
王宇平

基金项目:

国家自然科学基金(60374063)资助课题

计量
- 文章访问数: 3304
- HTML全文浏览量: 98
- PDF下载量: 1269
- 被引次数: 0
出版历程
- 收稿日期: 2007-05-08
- 修回日期: 2007-12-25
- 刊出日期: 2008-05-19

Fuzzy Particle Swarm Optimization for Constrained Optimization Problems

Wei Jing-xuan^{①;王宇平},
Wang Yu-ping

摘要

摘要: 该文针对复杂约束优化问题,提出了一种模糊粒子群算法(FPSO),设计了一个新的扰动算子,在此基础上定义了模糊个体极值和模糊全局极值,利用这两个定义改进了粒子群进化的方程,利用该方程更新粒子的速度与位置,可以避免早熟收敛问题;定义了不可行度阈值,利用此定义给出了新的粒子比较准则,该准则可以保留一部分性能较优的不可行解微粒。用概率论的有关知识证明了算法的收敛性。仿真结果表明,对于复杂约束优化问题,算法寻优性能优良,特别是对于超高维约束优化问题,该算法获得了更高精度的解。
- 粒子群算法; 约束优化; 模糊个体极值; 模糊全局极值
Abstract: A fuzzy particle swarm optimization is proposed for solving complex constrained optimization problems. Firstly, a new perturbation operator is designed, and the concepts of fuzzy personal best value and fuzzy global best value are given based on the new operator. Particle updating equations are revised based upon the two new concepts to discourage the premature convergence. Secondly, a new comparison strategy is proposed based on the new concept of infeasible threshold value. It can preserve some infeasible solutions with high quality. Finally, the convergence of this algorithm is proved. The simulation results show that the proposed algorithm is effective, especially for the problems with high dimensions.

HTML全文

参考文献(1)

Kennedy I and Eberhart R C. Particle swarm optimization[A]. Proc. IEEE Int. Conf. On Neural Networks [C]. Perth,WA, Australia, 1995: 1942-1948.[2]Shi Y and Eberhart R C. A modified swarm optimizer [A].IEEE international conference of Evolutionary Computation[C]. Anchorage, Alaska, 1998: 125-129.[3]Voss M S and Feng Xin. A RMA model selection usingparticle swarm optimization and AIC criteria [A]. 15thTriennial World Congress [C]. Barcelona, Spain: IFAC, 2002:41-45.[4]Bergh F and Engelbrecht A P. Cooperative learning in neuralnetworks using particle swarm optimizers [J]. South Africancomputer Journal, 2000, 11(6): 84-90.[5]Andrews P S. An investigation into mutation operators forparticle swarm optimization [A]. Proceeding of the 2006IEEE Congress on Evolutionary Computation[C], Canada,2006: 1044-1051.[6]李炳宇, 萧蕴诗, 吴启迪. 一种基于微粒群算法求解约束优化问题的混合算法[J]. 控制与决策, 2004, 19(7): 804-807.Li Bing-yu, Xiao Yun-shi, and Wu Qi-di. Hybrid algorithmbased on particle swarm optimization for solving constrainedoptimization problems [J]. Control and Decision, 2004, 19(7):804-807.[7]于繁华, 杨威, 张利彪. 基于模糊的多目标粒子群优化算法及应用[J]. 计算机仿真, 2007, 24(2): 153-156.Yu Fan-hua, Yang-Wei, and Zhang Li-biao. An optimizationarithmetic for multi-objective particle swarm based onfuzziness and its application[J]. Simulation of Computer, 2007,24(2): 153-156.[8]Runarsson T P and Yao X. Stochastic ranking forconstrained evolutionary optimization [J].IEEE Trans. onEvolutionary Computation.2000, 4(3):284-294[9]Venkatraman S and Yen G G. A genetic framework forconstrained optimization using genetic algorithms [J].IEEETrans. on Evolutionary Computation.2005, 9(4):424-435[10]Farmani R and wright J A. Self-adaptive fitness formulationfor constrained optimization [J].IEEE Trans. onEvolutionary Computation.2003, 7(5):445-455[11]Back T. Evolutionary Algorithms in Theory and Practice [M].New York: Oxford University Press, 1996: 21-28.[12]Rudolph G and Agapie A. Convergence properties of somemulti-objective evolutionary algorithms [A]. Proceeding ofthe Congress on Evolutionary Computation[C], Piscataway,2000: 1010-1016.[13]刘淳安, 王宇平. 约束多目标优化问题的进化算法及其收敛性[J]. 系统工程与电子技术, 2007, 29(2): 276-280.Liu Chun-an and Wang Yu-ping. Evolutionary algorithm forconstrained multi-objective optimization problems and itsconvergence [J]. Systems Engineering and Electronics, 2007,29(2): 276-280.

施引文献

资源附件(0)

访问统计