首页 > 论文 > 光学学报 > 38卷 > 12期(pp:1229001--1)

基于径向基函数神经网络直接提取布里渊散射谱温度的方法

Method for Direct Temperature Extraction of Brillouin Scattering Spectra Based on Radial Basis Function Neural Network

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

为了简化布里渊散射提取温度的步骤并提高提取精度,提出利用径向基函数神经网络直接通过布里渊散射谱获取温度特征的一种新方案;将各温度布里渊散射谱作为训练集计算出温度模型,将待测布里渊散射谱直接输入至模型即可获取温度;对比平滑拟合、反向传播神经网络、径向基函数神经网络3种方案对温度测量的效果,分别选取扫频频率间隔为0.175,1,5,10,20 MHz时的77组数据,并对不同线宽进行扩展。结果表明:基于径向基函数神经网络方法的均方根误差较小,且随步进频率增加而增长缓慢;步进频率为20 MHz时,单线宽误差达到0.8002 ℃,多线宽误差为1.0814 ℃,分别是平滑拟合测量温度方法误差的33.04%和42.88%,是反向传播神经网络均方根误差的40.25%和55.89%;基于径向基函数神经网络的方法在一定程度上减少了计算步骤,提高了收敛性。

Abstract

To simplify the temperature extraction steps for Brillouin scattering and also improve the extraction precision, we propose a new method for directly obtaining the temperature characteristics of Brillouin gain spectra based on the radial basis function neural network. The Brillouin scattering spectra at various temperatures are used as the training set to establish the temperature model. The temperature can be obtained through directly inputting the Brillouin spectra into the model. The effects of three methods of smooth fitting, back propagation neural network and radial basis function neural network on the temperature measurements are compared. In the experiment, 77 groups of data at sweeping frequency intervals of 0.175, 1, 5, 10, and 20 MHz are selected and also those at different linewidths are expanded. The results show that, the root-mean-square error (RMSE) based on the radial basis function neural network is relatively small. Moreover, the RMSE increases slowly with the increase of step frequency. When the step frequency is 20 MHz, the error of single line width is up to 0.8002 ℃ and that of multiple line width is 1.0814 ℃, 33.04% and 42.88% of that by the smooth fitting method, and 40.25% and 55.89% of that by the back propagation neural network, respectively. The convergence is improved to a certain extent as a result of calculation step reduction in the method based on the radial basis function neural network.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:O437.2

DOI:10.3788/aos201838.1229001

所属栏目:散射

基金项目:吉林省科技发展计划(20160519010JH,20170204006GX,20180201032GX)

收稿日期:2018-03-30

修改稿日期:2018-07-23

网络出版日期:2018-07-28

作者单位    点击查看

隋阳:吉林大学电子科学与工程学院集成光电子国家重点联合实验室, 吉林 长春 130012
孟钏楠:吉林大学电子科学与工程学院集成光电子国家重点联合实验室, 吉林 长春 130012
董玮:吉林大学电子科学与工程学院集成光电子国家重点联合实验室, 吉林 长春 130012
张歆东:吉林大学电子科学与工程学院集成光电子国家重点联合实验室, 吉林 长春 130012

联系人作者:董玮(dongw@jlu.edu.cn); 隋阳(suiyang16@mail.jlu.edu.cn);

【1】Xu J, Zou X F, Wang J H. Realization of data acquisition with DLL in LabVIEW[J]. Microcomputer Information, 2008, 24(5): 95-96, 67.
许剑, 邹小芳, 王建华. 在LabVIEW中利用DLL实现数据采集[J]. 微计算机信息, 2008, 24(5): 95-96, 67.

【2】Ye F H, Zhou X C, Bai X Q, et al. Design of data acquisition program based on queued state machine in LabVIEW[J]. Modern Electronics Technique, 2010, 33(4): 204-207, 210.
叶枫桦, 周新聪, 白秀琴, 等. 基于LabVIEW队列状态机的数据采集系统设计[J]. 现代电子技术, 2010, 33(4): 204-207, 210.

【3】Liu D S. The design of integrated control and data process in BOTDA system[D]. Beijing: North China Electric Power University, 2012: 61.
刘东升. BOTDA系统综合控制及数据处理设计[D]. 北京: 华北电力大学, 2012: 61.

【4】Mirzaei A, Bahrampour A R, Taraz M, et al. Transient response of buried oil pipelines fiber optic leak detector based on the distributed temperature measurement[J]. International Journal of Heat and Mass Transfer, 2013, 65: 110-122.

【5】Zheng Y L, Liu Y M. Summary of progress in optical fiber sensing technology for pressure pipeline leakage monitoring[J]. Transducer and Microsystem Technologies, 2014, 33(9): 15-17, 21.
郑元辽, 刘月明. 光纤传感监测压力管道泄漏技术进展综述[J]. 传感器与微系统, 2014, 33(9): 15-17, 21.

【6】Zhou Z C, Wang X L, Su R T, et al. Application of distributed fiber sensing in fiber lasers[J]. Laser & Optoelectronics Progress, 2016, 53(8): 080006.
周子超, 王小林, 粟荣涛, 等. 分布式光纤传感在光纤激光中的应用研究[J]. 激光与光电子学进展, 2016, 53(8): 080006.

【7】Dominguez-Lopez A, Soto M A, Martin-Lopez S, et al. Resolving 1 million sensing points in an optimized differential time-domain Brillouin sensor[J]. Optics Letters, 2017, 42(10): 1903-1906.

【8】Alahbabi M, Cho Y T, Newson T P. Comparison of the methods for discriminating temperature and strain in spontaneous Brillouin-based distributed sensors[J]. Optics Letters, 2004, 29(1): 26-28.

【9】Xiao S H, Li L. New fitting method for Brillouin-based scattering spectrum of fibre-optic distributed sensing systems[J]. Optical Technique, 2009, 35(6): 897-900, 904.
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, 904.

【10】Liang H, Zhang X P, Li X H, et al. Design and implementation of data fitting algorithm for Brillouin back scattered-light spectrum data[J]. Acta Photonica Sinica, 2009, 38(4): 875-879.
梁浩, 张旭苹, 李新华, 等. 布里渊背向散射光谱数据拟合算法设计与实现[J]. 光子学报, 2009, 38(4): 875-879.

【11】Liu Y, Fu G W, Zhang Y J, et al. 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.
刘银, 付广伟, 张燕君, 等. 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.

【12】Zhang Y J, Liu W Z, Fu X H, et al. The high precision analysis research of multichannel BOTDR scattering spectrum information based on the TTDF and CNS algorithm[J]. Spectroscopy and Spectral Analysis, 2015, 35(7): 1802-1807.
张燕君, 刘文哲, 付兴虎, 等. 基于TTDF和CNS算法的多路BOTDR散射谱信息高精度分析研究[J]. 光谱学与光谱分析, 2015, 35(7): 1802-1807.

【13】Zhang Y D, Li J Q, Meng C N, et al. Hybird optimization algorithm of Brillouin scattering spectra fitting[J]. High Power Laser and Particle Beams, 2015, 27(9): 87-93.
张有迪, 李嘉琪, 孟钏楠, 等. 布里渊散射谱拟合的混合优化算法[J]. 强激光与粒子束, 2015, 27(9): 87-93.

【14】Shang Q F, Hu Y T, Liu W. Feature extraction of Brillouin scattering spectrum based on cross-correlation convolution and high-order centroid calculation[J]. Chinese Journal of Lasers, 2017, 44(11): 1106011.
尚秋峰, 胡雨婷, 刘薇. 基于互相关卷积与高阶矩质心计算的布里渊散射谱特征提取[J]. 中国激光, 2017, 44(11): 1106011.

【15】Zhang Y J, Xu J R, Fu X H. Method of Brillouin scattering spectrum character extraction based on genetic algorithm and quantum-behaved particle swarm optimization hybrid algorithm[J]. Chinese Journal of Lasers, 2016, 43(2): 0205002.
张燕君, 徐金睿, 付兴虎. 基于GA-QPSO混合算法的Brillouin散射谱特征提取方法[J].中国激光, 2016, 43(2): 0205002.

【16】Azad A K, Wang L, Guo N, et al. Signal processing using artificial neural network for BOTDA sensor system[J]. Optics Express, 2016, 24(6): 6769-6782.

引用该论文

Sui Yang,Meng Chuannan,Dong Wei,Zhang Xindong. Method for Direct Temperature Extraction of Brillouin Scattering Spectra Based on Radial Basis Function Neural Network[J]. Acta Optica Sinica, 2018, 38(12): 1229001

隋阳,孟钏楠,董玮,张歆东. 基于径向基函数神经网络直接提取布里渊散射谱温度的方法[J]. 光学学报, 2018, 38(12): 1229001

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF