全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

高维多目标电磁场逆问题计算的改进多重单目标Pareto采样算法

, PP. 9-15

Keywords: 高维多目标优化算法,进化算法,多重单目标Pareto采样算法,多样性保持

Full-Text   Cite this paper   Add to My Lib

Abstract:

电气工程中的优化设计(电磁场逆)问题一般为多极值点的非线性全局优化问题。当需要考虑不同性能指标时,又必须同时给出多个非控解以供决策。这进一步加剧了问题的复杂度。虽然进化算法在多目标优化设计中获得了广泛应用,但对于目标函数超过三维的高维多目标优化问题,目前基于非控关系的多目标进化算法很难获得满意的优化结果。为此,人们提出了高维多目标优化的多重单目标Pareto采样(MSOPS)算法。该算法具有结构简单,计算复杂度低等优点。然而,研究表明,MSOPS算法收敛速度慢,优化结果往往缺乏多样性。为此,本文对MSOPS算法进行了改进研究,提出了目标矢量的拥挤操作以增加解的多样性,借助非均匀的目标矢量更新以及附加外部档案等改进措施对搜索区域进行有效地搜索,加快算法收敛。直线阵列和Yagi-Uda天线阵的实例分析、计算证明了本文算法的优越性和可靠性。

References

[1]  Ishibuchi H, Tsukamoto N, Nojima Y. Evolutionary many-objective optimization [C]. Proceedings of the 3rd International Workshop on Genetic and Evolving Systems, Germany, 2008: 47-52.
[2]  Ikeda K, Kita H, Kobayashi S. Failure of pareto-based MOEAS: Does non-dominated really mean near to optimal [C]. Proceedings of the IEEE Congress on Evolutionary Computation, Seoul, South Korea, 2001, 2: 957-962.
[3]  Sato H, Aguirre H E, Tanaka K. Local Dominance Including Control of Dominance Area of Solutions in MOEAs[C]. Proceedings of the IEEE Symposium on Computational Intelligence in Multicriteria Decision Making, Honolulu, HI, 2007, 310-317.
[4]  Marco Laumanns, Lothar Thile, Kalyanmoy Deb, et al. combining convergence and diversity in Evolutionary Multiobjective Optimization[J]. IEEE Transactions on Evolutionary Computation, 2002, 10(3): 263-282.
[5]  Johannes M. Bader. Hypervolume-based search for multiobjective optimization: theory and methods [D]. PhD Dissertation Zurich, ETH, 2009.
[6]  Ishibuchi H, Doi T, Nojima Y. Incorporation of scalarizing fitness functions into evolutionary multiobjective optimization algorithms[C]. Proceedings of the Parallel Problem Solving from Nature, Berlin: Springer, 2008: 493-502.
[7]  Hughes E J. Multiple Single Objective Pareto Sampling[C]. Proceedings of the Congress on Evolutionary Computation, Canberra, Australia, 2006: 2678-2684.
[8]  Hughes E J. Evolutionary many-objective optimiz- ation: many once or one many[C]. Proceedings of the Congress on Evolutionary Computation, Edinburgh, Scotland, 2005, 1: 222-227.
[9]  Hughes, E J. MSOPS-II: A general purpose many-objective optimizer[C]. Proceedings of the Congress on Evolutionary Computation, Singapore, 2007: 3944-3951.
[10]  Sato H, Aguirre H E, Tanaka K. On the locality of dominance and recombination in multiobjective evolutionary algorithms [C]. Proceedings of the Congress on Evolutionary Computation, Edinburgh, Scotland, 2005, 1: 451-458.
[11]  Deb K, Pratap A, Agarwal S, et al. A fast and elitist multiobjective genetic algorithm:NSGA-II[J]. IEEE Transactions on Evolutionary Computation, 2002, 6(2): 182-197.
[12]  Eckart Zitzler, Marco Laumanns, Lothar Thiele. SPEA2: Improving the strength pareto evolutionary algorithm for multiobjective optimization[R]. TIK Report 103, Computer Engineering and Networks Laboratory (TIK), Zurich, ETH,2001.
[13]  Bader J, Zitzler E. HypE: An algorithm for fast hypervolume-based many-objective optimization [J]. IEEE Transactions on Evolutionary Computation, 2011, 19(1):45-76.
[14]  Storn R, Price K. Differential evolution - a simple and efficient adaptive scheme for global optimization over continuous spaces[R]. Technical Report TR-95-012. ICSI Berkeley. Available at http://www. icsi. berkeley. edu/~storn /code.html.
[15]  Filiz Gunes, Fikret Tokan. Pattern search optimization with applications on synthesis of linear antenna array [J]. Expert Systems with Applications, 2010, 37(6): 4698-4705.
[16]  Neelakantam V Venkatarayalu, Tapabrata Ray. Optimum design of yagi-uda antennas using computational intelligence [J]. IEEE Transactions on Antennas and Propagation, 2004, 52(7): 1811-1818.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133