基于神经网络的光纤温度估算方法的优化

李苏雅; 董艳唯; 李琳; 张弛; 李楠; 宁琦; 陈永辉

doi:10.13756/j.gtxyj.2025.230123

您当前的位置：

首页 >

文章列表页 >

基于神经网络的光纤温度估算方法的优化

光纤光缆技术与应用 | 更新时间：2025-02-17

- 基于神经网络的光纤温度估算方法的优化
- Optimized Neural Network Method for Temperature Estimation along Optical Fiber
- 光通信研究 2025年第1期
- 作者机构：
  
  1.国网天津市电力公司　电力科学研究院，天津　 300384
  2.华北电力大学　电子与通信工程系，河北　保定　 071003
- 作者简介：
  
  李苏雅（1986－），女，河北沧州人。高级工程师，硕士，主要研究方向为电气设备状态监测及故障诊断等。
  董艳唯，高级工程师。Email：joeldream@163.com
- 基金信息：
  
  国家自然科学基金资助项目(62171185)
- DOI：10.13756/j.gtxyj.2025.230123
  中图分类号： TN247
- 纸质出版日期：2025-02-10，
  
  收稿日期：2023-10-02，
  
  修回日期：2023-10-30，
- 稿件说明：
移动端阅览
李苏雅，董艳唯，李琳，等. 基于神经网络的光纤温度估算方法的优化[J]. 光通信研究，2025(1): 230123.

Li S Y, Dong Y W, Li L, et al. Optimized Neural Network Method for Temperature Estimation along Optical Fiber[J]. Study on Optical Communications，2025(1): 230123.
李苏雅，董艳唯，李琳，等. 基于神经网络的光纤温度估算方法的优化[J]. 光通信研究，2025(1): 230123. DOI： 10.13756/j.gtxyj.2025.230123.

Li S Y, Dong Y W, Li L, et al. Optimized Neural Network Method for Temperature Estimation along Optical Fiber[J]. Study on Optical Communications，2025(1): 230123. DOI： 10.13756/j.gtxyj.2025.230123.

摘要

【目的】

为了有效估算基于布里渊散射的分布式光纤传感中光纤的温度，文章将多层前馈人工神经网络（ANN）应用于温度的估算。

【方法】

文章在Matlab软件中编写了用于光纤温度计算的单斜坡法、基于伪Voigt模型的最小二乘拟合法和ANN程序，同时仿真产生了不同信噪比（SNR）下的布里渊谱，采用以上3种算法计算了光纤温度，验证了ANN方法的有效性。在此基础上基于以上仿真产生的布里渊谱研究了ANN的关键参数，即隐层数量、隐层神经元数量和训练目标对训练速度、温度计算时间和准确性的影响规律。

【结果】

结果表明，ANN方法在SNR为22和37 dB时最大温度误差分别仅为1.18和0.63 ℃，且计算时间仅为最小二乘拟合法的1/1 000左右。当隐层神经元数量不变时，随着隐层层数的增加，训练时间明显下降，计算时间线性增加，但其对温度估算的准确性几乎无影响；随着隐层神经元数量的增加，训练时间和计算时间均增加，隐层有21个神经元时，训练时间近似为1个神经元的67倍，但其对温度估算的准确性几乎无影响；训练目标（布里渊频移误差的平方）小于临界值（约为1 MHz

）时，随着训练目标的增加，温度误差几乎不变，超过临界值后，随着训练目标的增加，温度误差增大。

【结论】

采用多层前馈ANN应用于基于布里渊散射的分布式光纤传感中的光纤温度估算时，建议选择单隐层且隐层神经元选择1个，训练目标选择1 MHz

。

Abstract

【Objective】

To effectively estimate the optical fiber temperature of distributed optical fiber sensing based on Brillouin scattering

a multi-layer feedforward Artificial Neural Network (ANN) is introduced to estimate the temperature.

【Methods】

The article has developed programs in Matlab for fiber optic temperature calculation using the single slope method

the least squares fitting method based on the pseudo-Voigt model，and an ANN. At the same time

the Brillouin spectra with different Signal-to-Noise Ratios (SNR) are simulated. Based on the Brillouin spectrum generated from the above simulations

the study investigates the key parameters of the ANN

namely the number of hidden layers

the number of neurons in the hidden layers

and the training objectives

and their influence on training speed

temperature calculation time

and accuracy.

【Results】

The maximum temperature error of ANN is only 1.18 and 0.63 ℃ at 22 and 37 dB respectively

and the calculation time of ANN is only about 1/1 000 of that of the least-squares fit method. When the number of hidden layer neurons remains constant，the training time decreases obviously with the number of hidden layer and the computation time increases linearly with the number of hidden layer. However

it has little effect on the accuracy of temperature estimation. Both the training time and computation time increase with the number of neurons in the hidden laye

r. When there are 21 neurons in the hidden layer

the training time is approximately 67 times that of only one neuron in the hidden layer. However

it also has little effect on the accuracy of temperature estimation. When the training goal (square of the Brillouin shift error) is less than the critical value (about 1 MHz

)

the temperature error is almost independent. However

when the training goal exceeds the critical value

the temperature error increases with the training goal.

【Conclusion】

When ANN is used to estimate optical fiber temperature of distributed optical fiber sensing based on Brillouin scattering

it is recommended to select a single-hidden-layer ANN and the number of hidden layer neurons is set to one. The training goal is set to 1 MHz

关键词

Keywords

references

Wang B , Fan B , Zhou D , et al . High-performance Optical Chirp Chain BOTDA by Using a Pattern Recognition Algorithm and the Differential Pulse-width Pair Technique [J ] . Photonics Research , 2019 , 7 ( 6 ): 652 － 658 .

Gyger F , Rochat E , Chin S , et al . Extending the Sensing Range of Brillouin Optical Time-domain Analysis up to 325 km Combining Four Optical Repeaters [C ] // SPIE Proceedings, 23rd International Conference on Optical Fibre Sensors . Santander, Spain : SPIE , 2014 : 91576Q .

Zhang H , Cheng Y , Wu K , et al . Liquid-level Sensing Method based on Differential Pulse-width Pair Brillouin Optical Time-domain Analysis and a Self-heated High Attenuation Fiber [J ] . Applied Optics , 2020 , 59 ( 3 ): 795 － 799 .

Chao J , Wen X , Zhu W , et al . Subdivision of Brillouin Gain Spectrum to Improve the Spatial Resolution of a BOTDA System [J ] . Applied Optics , 2019 , 58 ( 2 ): 466 － 472 .

Hong C Y , Zhang Y F , Li G W , et al . Recent Pro-gress of Using Brillouin Distributed Fiber Optic Sen-sors for Geotechnical Health Monitoring [J ] . Sensors and Actuators A: Physical , 2017 , 258 : 131 － 145 .

王健健 , 李永倩 . 分布式光纤传感技术在OPGW监测中的应用现状 [J ] . 光通信研究 , 2018 ( 3 ): 25 － 27 .

Wang J J , Li Y Q . Progress on Distributed Optical Fiber Sensing Technology in OPGW Monitoring [J ] . Study on Optical Communications , 2018 ( 3 ): 25 － 27 .

李晓娟 , 李建科 , 刘力军 , 等 . 基于自发布里渊散射的电缆弧垂在线监测研究 [J ] . 光通信研究 , 2023 ( 5 ): 63 － 66 .

Li X J , Li J K , Liu L J , et al . Research on the Cable Sag On-line Monitoring Using Spontaneous Brillouin Scattering [J ] . Study on Optical Communications , 2023 ( 5 ): 63 － 66 .

Bao X , Chen L . Recent Progress in Brillouin Scattering based Fiber Sensors [J ] . Sensors , 2011 , 11 ( 4 ): 4152 － 4187 .

Sun X , Hong X , Wang S , et al . Frequency Shift Estimation Technique Near the Hotspot in BOTDA Sensor [J ] . Optics Express , 2019 , 27 ( 9 ): 12899 － 12913 .

Kwon H , Kim S , Yeom S , et al . Analysis of Nonlin-ear Fitting Methods for Distributed Measurement of Temperature and Strain over 36 km Optical Fiber based on Spontaneous Brillouin Backscattering [J ] . Optics Communications , 2013 , 294 : 59 － 63 .

Xu Z N , Zhao L J , Qin H . Selection of Spectrum Model in Estimation of Brillouin Frequency Shift for Distributed Optical Fiber Sensor [J ] . Optik , 2019 , 199 : 163355 .

Bernini R , Minardo A , Zeni L . Dynamic Strain Measurement in Optical Fibers by Stimulated Brillouin Scattering [J ] . Optics Letters , 2009 , 34 ( 17 ): 2613 － 2615 .

Peled Y , Motil A , Yaron L , et al . Slope-assisted Fast Distributed Sensing in Optical Fibers with Arbitrary Brillouin Profile [J ] . Optics Express , 2011 , 19 ( 21 ): 19845 － 19854 .

Lü C , Liang Y , Jia X , et al . Artificial Neural Network for Accurate Retrieval of Fiber Brillouin Frequency Shift with Non-local Effects [J ] . IEEE Sensors Journal , 2020 , 20 ( 15 ): 8559 － 8569 .

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 .

Lü T , Ye X , Zheng Y , et al . Error Estimation of BFS Extraction with Optimized Neural Network & Frequency Scanning Range [J ] . Journal of Lightwave Technology , 2021 , 39 ( 15 ): 5149 － 5155 .

Bao X , Brown A , DeMerchant M , et al . Characterization of the Brillouin-loss Spectrum of Single-mode Fibers by Use of very Short (<10 ns) Pulses [J ] . Optics Letters , 1999 , 24 ( 8 ): 510 － 512 .

Horiguchi T , Shimizu K , Kurashima T , et al . Development of a Distributed Sensing Technique Using Brillouin Scattering [J ] . Journal of Lightwave Technology , 1995 , 13 ( 7 ): 1296 － 1302 .

浏览量

下载量

CSCD

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于BOTDA的分布式光纤传感技术研究进展

分布式光纤温度和应变传感技术的研究进展

BOTDR在光缆生产工艺中的应用

光子脉冲神经网络研究历程与展望

基于布里渊散射的光纤温度和应变快速感知