期刊
IEEE PHOTONICS TECHNOLOGY LETTERS
卷 26, 期 20, 页码 2031-2034出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LPT.2014.2345062
关键词
Fiber Bragg grating (FBG); fiber-optic sensors; wavelength division multiplexing (WDM); extreme learning machine (ELM)
This letter presents a novel learning-based method called extreme learning machine (ELM) to solve the Bragg wavelength detection problem in the fiber Bragg grating (FBG) sensor network. Based on building up a regression model, the proposed approach is divided into two phases: 1) offline training phase and 2) online detection phase. Due to the good generalization capability of ELM, the well-trained detection model can directly and accurately determine the Bragg wavelengths of the sensors even when the spectra of FBGs are completely overlapped. The results demonstrate that the proposed method is efficient and stable. It has shown competitive advantages in terms of the detection accuracy, the offline training speed, as well as the real-time detection efficiency.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据