钦文雯1,
李莹娟1,
李茜茜1,
邓联文2
1.中南大学信息科学与工程学院 ??长沙 ??410083
2.中南大学物理与电子学院 ??长沙 ??410083
基金项目:国家重点研发计划 (2017YFA0204600),湖南省自然科学基金 (2018JJ2533)
详细信息
作者简介:董健:男,1980年生,副教授,研究方向为天线理论与设计、微波遥感、阵列信号处理等
钦文雯:女,1993年生,硕士生,研究方向为天线自动优化技术等
李莹娟:女,1994年生,硕士生,研究方向为天线自动优化技术等
李茜茜:女,1993年生,硕士生,研究方向为超宽带与多频带天线设计等
邓联文:男,1969年生,教授,研究方向为微波技术、天线等
通讯作者:董健 dongjian@csu.edu.cn
中图分类号:TN820计量
文章访问数:995
HTML全文浏览量:404
PDF下载量:58
被引次数:0
出版历程
收稿日期:2018-01-08
修回日期:2018-07-17
网络出版日期:2018-07-30
刊出日期:2018-11-01
Fast Multi-objective Antenna Design Based on Improved Back Propagation Neural Network Surrogate Model
Jian DONG1,,,Wenwen QIN1,
Yingjuan LI1,
Qianqian LI1,
Lianwen DENG2
1. School of Information Science and Engineering, Central South University, Changsha 410083, China
2. School of Physics and Electronics, Central South University, Changsha 410083, China
Funds:The National Key Research and Development Program of China (2017YFA0204600), The Natural Science Foundation of Hunan Province (2018JJ2533)
摘要
摘要:针对传统天线设计方法计算代价较大的缺陷,该文构建基于反向传播神经网络(BPNN)的新型天线代理模型。为解决BPNN训练易陷入局部最优的问题,采用粒子群优化(PSO)算法来改善神经网络初始结构参数,进而构建PSO-BPNN天线代理模型,并基于该模型提出多参数天线结构的快速多目标设计方法。设计实例表明,该方法在预测精度以及计算代价等方面优于现有的常用天线设计方法。所提方法对处理复杂高维参数空间天线设计问题具有实用价值。
关键词:天线设计/
性能预测/
代理模型/
反向传播神经网络/
粒子群优化
Abstract:Focusing on the problem of reducing the large computation cost of traditional antenna design methods, a new surrogate model based on Back Propagation Neural Networks (BPNN) is constructed. In order to solve the problem of easily falling into local optimum in BPNN, a PSO-BPNN surrogate model is developed by improving initial structural parameters of neural networks and applied to fast multi-objective optimization design of multi-parameter antenna structures. The design results show that the proposed PSO-BPNN outperforms other existing antenna surrogate models in terms of prediction accuracy and prediction speed. The proposed method is of value in dealing with complex antenna designs with high-dimensional parameter space.
Key words:Antenna design/
Performance prediction/
Surrogate model/
Back Propagation Neural Network (BPNN)/
Particle Swarm Optimization (PSO)
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=f5ddfba8-05a7-4b0b-bed0-af6cc81387b5