Evolutionary extreme learning machine for the behavioral modeling of RF power amplifiers

被引：2

作者：

Fu, Haipeng ^{[1
,2
]}

Wan, Kaikai ^{[1
,2
,3
,4
]}

Ma, Kaixue ^{[1
,2
]}

Xing, Guangyu ^{[1
,3
]}

Ma, Jianguo ^{[3
,4
,5
]}

机构：

[1] Tianjin Univ, Sch Microelect, Tianjin 300072, Peoples R China

[2] Tianjin Key Lab Imaging & Sensing Microelect Tech, Tianjin, Peoples R China

[3] Qingdao Key Lab Ocean Percept & Informat Transmis, Qingdao, Shandong, Peoples R China

[4] Tianjin Univ, Qingdao Inst Ocean Engn, Qingdao, Shandong, Peoples R China

[5] Guangdong Univ Technol, Guangzhou, Guangdong, Peoples R China

来源：

INTERNATIONAL JOURNAL OF NUMERICAL MODELLING-ELECTRONIC NETWORKS DEVICES AND FIELDS | 2020年 / 33卷 / 02期

基金：

中国国家自然科学基金; 国家重点研发计划;

关键词：

behavioral modeling; differential evolution; extreme learning machine; power amplifiers;

D O I：

10.1002/jnm.2659

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In this paper, evolutionary extreme learning machine (E-ELM) is first introduced for RF power amplifiers (PAs) behavioral modeling. This approach combined differential evolution (DE) and extreme learning machine (ELM) to effectively solve the problem that more neurons of hidden layer are required, and repeated trials are necessary in behavioral modeling PAs by conventional ELM. As revealed in the modeling practices on Class-AB and Class-E PAs, fewer hidden layer neurons are used than the condition of conventional ELM. Meanwhile, it is found that ELM's unstable generalization ability in modeling PAs is also significantly improved, thanks to the internal DE method in the E-ELM.

引用

页数：15

共 19 条

[1] Handwritten character recognition using wavelet energy and extreme learning machine [J].