快速全局优化算法在电磁场逆问题中的应用

作者：张慧，杨仕友，倪光正 日期：2007-10-25/span> 浏览：3345 查看PDF文档

快速全局优化算法在电磁场逆问题中的应用

张慧，杨仕友，倪光正
（浙江大学 电气工程学院,浙江 杭州 310027）

摘要：为解决电磁场逆问题分析计算过度依赖计算机资源这一“瓶颈”问题，提出了一种新的快速全局优化算法。该算法首先应用基于紧支集径向基函数(CSRBF)的改进表面响应模型(RSM)重构原优化问题；然后应用改进的粒子群算法(PSO)对重构的优化问题进行快速全局寻优。研究表明，典型数学函数验证以及电磁场逆问题的分析和计算，验证了算法的全局搜索和快速寻优能力。
关键词：粒子群算法；表面响应模型；紧支集径向基函数；电磁场逆问题
中图分类号：TM154.4文献标识码：A文章编号：1001-4551(2007)10-0028-04

Application of fast global optimizer in Electromagnetic inverse problems
ZHANG Hui, YANG Shiyou, NI Guangzheng
(College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China)
Abstract: To release the requirement for tremendously heavy computation resources in the study of electromagnetic inverse problems, a fast global optimizer was proposed, based on the combination of the improved response surface mode (RSM) using compactly support radial basis functions (CSRBF) and an improved particle swarm optimization(PSO). Computer simulation results on a mathematical function and a practical engineering design problem were presented to demonstrate the efficiency and robustness of the proposed algorithm.
Key words: particle swarm optimization (PSO); response surface model (RSM); compactly support radial basis function (CSRBF); electromagnetic inverse problem
参考文献(Reference)：
［1］KENNEDY J, EBERHART R. Particle Swarm Optimization［C］. Proceedings of IEEE International Conference on Neural Networks, Perth, Australia,1995:1941-1948.
［2］EBERHART R C, KENNEDY J. A New Optimizer Using Particle Swarm theory［C］. Proceedings of 6th International Symposium on Micro Machine and Human Science,1995:39-43.
［3］DYCK D N, LOWER D A. Response surface modeling of magnetic device performance using function value and gradient［J］. Appl. Electromagn. Mesh., 1998,9:241-248.
［4］WENDLAND H. Piecewise polynominal［J］. positive definite radial functions, Adv. Comput. Math., 1995,4:389-396.
［5］EBERHART R C, SIMPSON P K, DOBBINS R W. Computational intelligence PC tool［J］. Academic, 1996(6):212-226.
［6］［作者不详］. Optimization benchmark problem 25［EB/OL］. ［日期不详］. http://www.compumag.co.uk/team.html.