基于径向基函数神经网络的传感布里渊散射谱特征提取

刘银; 付广伟; 张燕君; 毕卫红

doi:doi:10.3788/aos201232.0206002

光学学报, 2012, 32 (2): 0206002, 网络出版: 2011-12-16

基于径向基函数神经网络的传感布里渊散射谱特征提取

A Novel Method for Brillouin Scattering Spectrum of Distributed Sensing Systems Based on Radial Basis Function Neural Networks to Extract Features

论文大纲

刘银 ^*付广伟张燕君毕卫红

作者单位

燕山大学信息科学与工程学院, 河北秦皇岛 066004

摘要

基于布里渊效应的分布式光纤传感器以其可在沿光纤中同时获得被测量场时间和空间上的连续分布信息，成为当前国际的研究热点。根据光纤中布里渊散射谱的传输特点和高精度特征提取的要求，提出了利用莱文伯马夸特(L-M)算法调节权值的径向基函数神经网络(RBFN)对布里渊散射谱进行特征提取。通过与反向传播(BP)神经网络、五次多项式曲线拟合法和三次样条插值法进行预测比较，在中心频率为11.213 GHz，权重比为4∶1的仿真散射谱模型中，本方法相对误差最小，仅0.0015179%，温度相对误差仅为0.152 ℃，且拟合度较好。在不同脉宽和不同温度下的同一检测系统中，前者的综合评价指标优于其他三种拟合方法。数值分析和实验研究均表明径向基函数神经网络适用于对布里渊散射谱进行拟合，有效提高了预测精度。

Abstract

Distributed optical fiber sensing system based on Brilouin scattering has attracted wide attention for its ability of sensing the measured field by detecting the continuously distributed information in time and space. Considering the trait of the spectral shape variance during the Brillouin scattering process in optical fiber and the requirement of high accuracy, a novel method based on radial basis function neural (RBFN) networks in which the output layer weights are adjusted by Levenberg-Marquardt method is presented. A model of actual Brillouin spectrum is constructed by Gaussian white noise on the theoretical spectrum, the core frequency is 11.213 GHz and the weight is 4∶1. Comparing the proposed algorithm with traditional back propagation (BP) neural networks, polynomial five times curve fitting and piecewise cubic spline interpolation, the relative error of the new method is 0.0015179% and the temperature error is 0.152 ℃. The appraised parameters are better than other three algorithms at the same test system under different pulse widths and temperatures. The numerical and experimental results show that the RBFN networks is suitable for the fitting of Brillouin scattering spectrum, and the forecast accuracy is improved efficiently.

参考文献

[1] 李科, 施斌, 唐朝生等. 黏性土体干缩变形分布式光纤检测试验研究［J］. 岩土力学, 2010, 31(6): 1781～1785

Li Ke, Shi Bin, Tang Chaosheng et al.. Feasibility research on soil deformation monitoring with distributed optical fiber sensing technique［J］. Rock and Soil Mechanics, 2010, 31(6): 1781～1785

[2] Fabien Ravet, Xiaoyi Bao, Jeff Snoddy et al.. Characterization of Brillouin fiber generator and amplifier for optimized working condition of distributed sensors［J］. Optical Fiber Technology, 2009, 15(3): 304～309

[3] Xinhong Jia, Yunjiang Rao, Kun Deng et al.. Experimental demonstration on 2.5-m spatial resolution and 1 ℃ temperature uncertainty over long-distance BOTDA with combined Raman amplification and optical pulse coding［J］. IEEE Photon. Technol. Lett., 2011, 23(7): 435～437

[4] Yongkang Dong, Xiaoyi Bao, Liang Chen. Distributed temperature sensing based on birefringence effect on transient Brillouin grating in a polarization-maintaining photonic crystal fiber［J］. Opt. Lett., 2009, 34(17): 2590～2592

[5] 肖尚辉, 李立. 一种新的光纤布里渊传感散射谱拟合方法［J］. 光学技术, 2009, 35(6): 897～900

Xiao Shanghui, Li Li. New fitting method for Brillouin-based scattering spectrum of fibre-optic distributed sensing systems［J］. Optical Technique, 2009, 35(6): 897～900

[6] 刘迪仁, 宋牟平, 章献民等. 应变梯度对布里渊光时域反射计测量精度的影响［J］. 光学学报, 2005, 25(4): 501～505

Liu Diren, Song Muping, Zhang Xianmin et al.. Influence of stress gradient on measurement accuracy of Brillouin optical time-domain-reflectometry［J］. Acta Optica Sinica, 2005, 25(4): 501～505

[7] Marc Nikles, Luc Thevenaz, Philippe A. Robert. Brillouin gain spectrum characterization in single-mode optical fibers［J］. J. Lightwave Technol., 1997, 15(10): 1842～1851

[8] 程光煦. 拉曼布里渊散射［J］. 北京：科学出版社,2008. 24～43

Cheng Guangxu. Raman and Brillouin Scattering ［M］. Beijing: Science Press, 2008. 24～26

[9] Hao Liang, Wenhai Li, Nicolas Linze et al.. High-resolution DPP-BOTDA over 50 km LEAF using return-to-zero coded pulses［J］. Opt. Lett., 2010, 35(10): 1503～1505

[10] 董玉明, 张旭苹, 路元刚等. 布里渊散射谱光纤传感器的交叉敏感问题［J］. 光学学报, 2007, 27(2): 197～201

Dong Yuming, Zhang Xuping, Lu Yuangang et al.. Cross sensitivity of Brillouuin scattering distributed fiber sensor［J］. Acta Optica Sinica, 2007, 27(2): 197～201

[11] Natsuki Nitta, Mitsuhiro Tateda, Takashige Omatsu. Spatial resolution enhancement in BOTDR by spectrum separation method［J］. Opt. Rev., 2002, 9(2): 49～53

[12] M. Alahbabi, Y. T. Cho, T. P. Newson. Comparison og the mothods for discriminating temperature and strain in spontaneous Brillouin-based distributed sensors［J］. Opt. Lett., 2004, 29(1): 26～28

[13] 宋牟平, 鲍翀, 裘超等. 结合布里渊光时域分析和光时域反射的分布式光纤传感器［J］. 光学学报, 2010, 30(3): 650～654

Song Muping, Bao Chong, Qiu Chao et al.. A distributed optical-fiber sensor combined Brillouin optical time-domain analyzer with Brillouin optical time-domain reflectometer［J］. Acta Optica Sinica, 2010, 30(3): 650～654

[14] W. Lin, C. Hong, T. Ou et al.. Hybrid intelligent contral of PMSG wind generation system using pitch angle control with RBFN［J］. Energy Conversion and Management, 2011, 52: 1244～1251

[15] A. Kleefeld, M. Reiel. The Levenberg-Marquardt method applied to a parameter estimation problem arising from electrical resistivity tomography［J］. Applied Mathematics and Computation, 2011, 217(9): 4490～4501

刘银, 付广伟, 张燕君, 毕卫红. 基于径向基函数神经网络的传感布里渊散射谱特征提取[J]. 光学学报, 2012, 32(2): 0206002. Liu Yin, Fu Guangwei, Zhang Yanjun, Bi Weihong. A Novel Method for Brillouin Scattering Spectrum of Distributed Sensing Systems Based on Radial Basis Function Neural Networks to Extract Features[J]. Acta Optica Sinica, 2012, 32(2): 0206002.

基于径向基函数神经网络的传感布里渊散射谱特征提取

关于本站 Cookie 的使用提示

全站搜索

基于径向基函数神经网络的传感布里渊散射谱特征提取

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索