利用GEK代理模型的天线快速多目标优化设计

doi:10.3969/j.issn.1001-2400.2018.02.022

西安电子科技大学学报

利用GEK代理模型的天线快速多目标优化设计

王丹青;李萍

(武警工程大学信息工程系，陕西西安 710086)

收稿日期:2017-05-23 出版日期:2018-04-20 发布日期:2018-06-06
作者简介:王丹青(1990-)，女，武警工程大学博士研究生，E-mail：wangqingqing620@126.com
基金资助:
国家自然科学基金资助项目(61302051)

Expedited antenna multi-objective optimization method based on gradient-enhanced kriging surrogate model

WANG Danqing;LI Ping

(Department of Information Engineering, Engineering Univ. of PAP, Xi'an 710086, China)

Received:2017-05-23 Online:2018-04-20 Published:2018-06-06

摘要/Abstract

摘要：

传统方法进行天线优化设计主要利用经典优化算法调用电磁仿真软件，在求解复杂天线的多目标优化问题时效率不理想．针对该问题，在多梯度下降算法中引入遗传算子，提出了一种高效的全局多目标优化算法——混合遗传算子多梯度下降算法．该算法调用梯度增强型克里金模型进行天线优化．梯度增强型克里金模型建模所需的样本规模小、时间短，并且避免了电磁仿真软件的反复计算．利用该算法优化加载各向异性Ⅰ型周期结构覆层的警用超短波宽带单极子天线和某型直升机机载专用通信系统天线及其抗干扰阵列，在达到相同优化效果时，所需的模型仿真次数为利用改进的非支配排序遗传算法调用电磁仿真软件进行优化的10.30％和18.96％，验证了该优化算法的高效性．

关键词: 天线多目标优化, 多梯度下降算法, 遗传算子, 代理模型, 梯度增强型克里金模型

Abstract:

Based on classical optimization algorithms and electromagnetic simulations, traditional antenna optimization method is inefficient, especially when it is used to solve the complex antenna multi-objective optimization problem. With the introduction of the genetic operator, the paper proposes an efficient global optimization algorithm named the Multi-Gradient Descent Algorithm Hybrid with the Genetic Operator to alleviate the problem above. For the merits of quick establishment and reduced samples scale, the Gradient-Enhanced Kriging(GEK) model is invoked by the proposed algorithm as the surrogate of antenna electromagnetic analysis. A Novel broadband UHF monopole antenna enabled by anisotropic Ⅰ-shaped periodic structure cladding and a dual-band UHF antenna together with its anti-jamming array antenna reserved for the private airborne communication system are designed with the proposed optimization method. The necessary electromagnetic simulation time of the proposed method is 10.30％ and that of the traditional optimization method is 18.96％, which verifies the merit of high efficiency.

Key words: antenna multi-objective optimization, mulit-gradient descent algorithm, genetic operator, surrogate model, gradient-enhanced Kriging model

王丹青;李萍. 利用GEK代理模型的天线快速多目标优化设计[J]. 西安电子科技大学学报, 2018, 45(2): 129-134+165.

WANG Danqing;LI Ping. Expedited antenna multi-objective optimization method based on gradient-enhanced kriging surrogate model[J]. Journal of Xidian University, 2018, 45(2): 129-134+165.

参考文献

［1］ NAGAR J, WERNER D H. A Comparison of Three Uniquely Different State of the Art and Two Classical Multiobjective Optimization Algorithms as Applied to Electromagnetics［J］. IEEE Transactions on Antennas and Propagation, 2017, 65(3): 1267-1280.
［2］刘道华, 王淑礼, 薛瑞. 混合神经网络匹配响应面的多学科设计方法［J］. 西安电子科技大学学报, 2012, 39(5): 161-167.
LIU Daohua, WANG Shuli, XUE Rui. Multi-disciplinary Design Method for the Matched Response Surface Based on the Hybrid Neural Network［J］. Journal of Xidian University, 2012, 39(5): 161-167.
［3］ KUMAR A, SHUKLA C K. Artificial Neural Network Employed to Design Annular Ring Microstrip Antenna［J］. International Journal on Computer Science and Engineering, 2012, 4(4): 556-564.
［4］ AOAD A, SIMSEK M, AYDIN Z. Development of Knowledge Based Response Correction for a Reconfigurable N-shaped Microstrip Antenna Design［C］//Proceedings of the 2015 IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization. Piscataway: IEEE, 2015: 7415078.
［5］陈晓辉, 裴进明, 郭欣欣, 等. 一种基于多维均匀采样与Kriging模型的天线快速优化方法［J］. 电子与信息学报, 2014, 36(12): 3021-3026.
CHEN Xiaohui, PEI Jinming, GUO Xinxin, et al. An Efficient Antenna Optimization Method Based on Kriging Model and Multidimensional Uniform Sampling［J］. Journal of Electronics & Information Technology, 2014, 36(12): 3021-3026.
［6］ KOZIEL S, BEKASIEWICZ A, ZIENIUTYCZ W. Expedited EM-driven Multiobjective Antenna Design in Highly Dimensional Parameter Spaces［J］. IEEE Antennas and Wireless Propagation Letters, 2014, 13(1): 631-634.
［7］ KOZIEL S, BEKASIEWICZ A. Fast Multi-objective Surrogate-assisted Design of Multi-parameter Antenna Structures through Rotational Design Space Reduction［J］. IET Microwaves, Antennas and Propagation, 2016, 10(6): 624-630.
［8］ CHEN Y S, CHOU W H, CHEN S Y. Applications of Optimization Techniques to Designs of Ultra-wideband Planar Monopole Antennas［C］//Proceedings of the 2012 Asia-Pacific Microwave Conference. Piscataway: IEEE, 2012: 714-716.
［9］ KOZIEL S, OGURTSOV S. Computational-budget-driven Automated Microwave Design Optimization Using Variable-fidelity Electromagnetic Simulations［J］. International Journal of RF and Microwave Computer-Aided Engineering, 2013, 23(3): 349-356.
［10］ CHEN Y S. Multiobjective Optimization of Complex Antenna Structures Using Response Surface Models［J］. International Journal of RF and Microwave Computer-Aided Engineering, 2016, 26(1): 62-71.
［11］ ULAGANATHAN S, COUCKUYT I, DHAENE T, et al. Performance Study of Gradient-enhanced Kriging［J］. Engineering with Computers, 2016, 32(1): 15-34.
［12］ DEB K. Multi-objective Optimization Using Evolutionary Algorithms［M］. Chichester: John Wiley & Sons, 2001: 28-30.
［13］ DESIDERI J A. Multiple-gradient Descent Algorithm(MGDA) for Multiobjective Optimization［J］. Comptes Rendus - Mathematique, 2012, 350(5/6): 313-318.
［14］ DEUTSCH J L, DEUTSCH C V. Latin Hypercube Sampling with Multidimensional Uniformity［J］. Journal of Statistical Planning and Inference, 2012, 142(3): 763-772.
［15］ ULAGANATHAN S, KOZIEL S, BEKASIEWICZ A, et al. Cost-efficient Modeling of Antenna Structures Using Gradient-enhanced Kriging［C］//Proceedings of the 2015 Loughborough Antennas and Propagation Conference. Piscataway: IEEE, 2015: 7366125.

利用GEK代理模型的天线快速多目标优化设计

Expedited antenna multi-objective optimization method based on gradient-enhanced kriging surrogate model

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

Metrics

本文评价

推荐阅读 10