基于ELM和MA的微型四频天线设计

A Miniature Four-Band Antenna Design Using ELM and MA

提出一个基于极限学习机ELM(Extreme Learning Machine)和文化基因算法MA(Memetic Algorithm)的微型四频(0.92/2.4/3.5/5.8GHz)天线设计算法AntMA-ELM.为了提高天线的性能,算法在MA框架下引入基于综合学习粒子群优化算法CLPSO(Comprehensive Learning Particle Swarm Optimizer)全局搜索和DSCG(Davies,Swann,and Campey with Gram-schmidt)局部搜索,用于确定天线的几何参数.同时,建立ELM回归模型用于直接评估MA优化的适应值函数.实验结果表明,ELM回归模型能够根据输入参数正确估算天线的回波损耗,使MA算法有效提高设计性能和加速优化过程.天线在四个目标频段的回波损耗值均优于-10dB,满足设计要求.

This paper proposes an extreme learning machine （ELM） and memetic algorithm （MA） based miniature four-band （0.92/2.4/3.5/5.8GHz ） antenna design algorithm namely the AntMA-ELM .It combines a comprehensive learning particle swarm optimizer （CLPSO ） based global search and a DSCG （Davies ,Swann ,and Campey with Gram-schmidt ） orthogonalization based local search in the MA framework to form a novel optimization algorithm for the geometrical parameters selection of the an-tenna .An ELM based regression model is introduced to estimate antenna performance ,and accelerate the search speed .Experimental results show that the AntMA-ELM obtains promising performance with short computational time .Particularly ,the return losses at all targeted frequency bands are smaller than -10dB .