基于卷积神经网络的增敏型光纤弯曲传感器

谭中伟; 杨婧雅; 刘艳; 卢顺; 张利伟; 牛慧

doi:10.37188/OPE.20202807.1454

您当前的位置：

首页 >

文章列表页 >

基于卷积神经网络的增敏型光纤弯曲传感器

现代应用光学 | 更新时间：2020-08-13

- 基于卷积神经网络的增敏型光纤弯曲传感器
- Enhanced fiber optic bending senor based on convolutional neural network
- 光学精密工程 2020年28卷第7期页码：1454-1461
- 作者机构：
  
  北京交通大学, 北京 100044
- 作者简介：
  
  [ "谭中伟(1978-), 男, 河南信阳人, 博士, 教授, 博士生导师, 2000年、2005年于北京交通大学分别获得学士、博士学位, 主要从事全光交换、特种光纤、光电器件及基于智能光纤传感的物联网等方面的研究。E-mail:zhwtan@bjtu.edu.cn" ]
  [ "杨婧雅(1996-), 女, 河南商丘人, 硕士研究生, 2018年于河南农业大学获得学士学位, 主要从事光纤传感、深度学习方面的研究。E-mail:18120159@bjtu.edu.cn" ]
- 基金信息：
  
  国家自然科学基金资助项目(No.61875008);国家自然科学基金资助项目(No.61975009)
- DOI：10.37188/OPE.20202807.1454
  中图分类号： TP212;TN253
- 收稿日期：2019-12-23，
  
  修回日期：2020-02-25，
  
  录用日期：2020-2-25，
  
  纸质出版日期：2020-07-15
- 稿件说明：
移动端阅览
谭中伟, 杨婧雅, 刘艳, 等. 基于卷积神经网络的增敏型光纤弯曲传感器[J]. 光学精密工程, 2020,28(7):1454-1461.

Zhong-wei TAN, Jing-ya YANG, Yan LIU, et al. Enhanced fiber optic bending senor based on convolutional neural network[J]. Optics and precision engineering, 2020, 28(7): 1454-1461.
谭中伟, 杨婧雅, 刘艳, 等. 基于卷积神经网络的增敏型光纤弯曲传感器[J]. 光学精密工程, 2020,28(7):1454-1461. DOI： 10.37188/OPE.20202807.1454.

Zhong-wei TAN, Jing-ya YANG, Yan LIU, et al. Enhanced fiber optic bending senor based on convolutional neural network[J]. Optics and precision engineering, 2020, 28(7): 1454-1461. DOI： 10.37188/OPE.20202807.1454.

摘要

为了提高光纤弯曲传感器的灵敏度，增大线性范围，降低成本，本文提出一种基于深度神经网络分类塑料光纤弯曲角度及方向的方法。使用进行侧抛增敏处理的塑料光纤，在光纤输出端采集不同弯曲角度的散斑图。制作了包含五类弯曲角度的数据集一以及包含七类弯曲角度的数据集二，在预处理图像数据之后，利用多层卷积神经网络对散斑图像进行卷积和池化处理，得到散斑图像的特征图，softmax分类器用来得到分类准确率，最后对两种不同卷积神经网络模型的分类效果进行对比。结果显示：数据集一光纤弯曲的角度间隔为5°时分类准确率达到了96%，理论和实际分析结果表明该方案识别率较高，基于该方法有望实现一种简单、高效的光纤弯曲传感器。

Abstract

To improve the sensitivity and cost-efficiency of a fiber bending sensor and to increase its linear range

a method based on a deep neural network was proposed to classify different bending angles and directions of plastic fiber. Plastic fiber with side throw sensitization processing was used to collect speckle images of different bending angles at the output end of the fiber. Data set one was made with five types of bending angle and data set two contained seven types of bending angle. After the pretreatment of image data

a multilayer convolution neural network was used to analyze the speckle image. The convolution and pooling provided speckle image features. A softmax classification was used for classification accuracy. Finally

the effect of two different convolutions on the classification of the neural network model was compared. The results show that the classification accuracy reaches 96% when the angle interval of fiber bending in the data set one is 5°. The theoretical and practical analysis results show that the scheme has a high recognition rate. Moreover

the realization of this method is expected to provide a new type of simple and efficient fiber bending sensor.

关键词

Keywords

references

K T V GRATTAN , T SUN . Fiber optic sensor technology:an overview . Sensors and Actuators A(Physical) , 2000 . 82 ( 1/3 ): 40 - 61 . http://d.old.wanfangdata.com.cn/Periodical/shdxxb201401003 http://d.old.wanfangdata.com.cn/Periodical/shdxxb201401003 .

H L ZHANG , Z F WU , P P SHUM , 等 . Fiber Bragg gratings in heterogeneous multicore fiber for directional bending sensing . Journal of Optics , 2016 . 18 ( 8 ): 085705 DOI: 10.1088/2040-8978/18/8/085705 http://doi.org/10.1088/2040-8978/18/8/085705 .

K YANG , J HE , C LIAO , 等 . Femtosecond laser inscription of fiber Bragg grating in twin-core few-mode fiber for directional bend sensing . Journal of Lightwave Technology , 2017 . 35 ( 21 ): 4670 - 4676 . DOI: 10.1109/JLT.2017.2750407 http://doi.org/10.1109/JLT.2017.2750407 .

孙广开 , 曲道明 , 闫光 , 等 . 软体气动驱动器弯曲变形光纤传感与形状重构 . 光学精密工程 , 2019 . 27 ( 5 ): 1052 - 1059 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201905007 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201905007 .

G K SUN , D M QU , G YAN , 等 . Bending deformation of optical fiber sensing and shape reconstruction of soft pneumatic driver . Opt. Precision Eng , 2019 . 27 ( 5 ): 1052 - 1059 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201905007 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201905007 .

何彦霖 , 张旭 , 孙广开 , 等 . 复合基底柔性光纤曲率传感器设计 . 光学精密工程 , 2019 . 27 ( 6 ): 1270 - 1276 . http://www.cqvip.com/QK/92835X/201906/7002462031.html http://www.cqvip.com/QK/92835X/201906/7002462031.html .

Y L HE , X ZHANG , G K SUN , 等 . Flexible curvature sensor based on composite substrate . Opt. Precision Eng , 2019 . 27 ( 6 ): 1270 - 1276 . http://www.cqvip.com/QK/92835X/201906/7002462031.html http://www.cqvip.com/QK/92835X/201906/7002462031.html .

Q WANG , Y LIU . Optical fiber curvature sensor based on MMF-SCF-MMF structur . Optical Fiber Technology , 2018 . 43 ( 10 ): 1 - 5 . https://www.sciencedirect.com/science/article/pii/S1068520018300531 https://www.sciencedirect.com/science/article/pii/S1068520018300531 .

L A DANISCH . Bend enhanced fiber optic sensors . SPIE , 1993 . 1795 204 - 214 . http://d.old.wanfangdata.com.cn/NSTLHY/NSTL_HYCC025739658/ http://d.old.wanfangdata.com.cn/NSTLHY/NSTL_HYCC025739658/ .

DANISCH L A. Fiber optic bending and positioning sensor including a light emission surface formed on a portion of a light guide, United States[P]. 5321257, 1994-6-14.

申亚萍.曲率光纤传感器关键技术的研究[D].北京: 北京交通大学, 2019.

SHEN Y P. Research on the Key Technology of Curvature Fiber Optic Sensor[D].Beijing: Beijing Jiaotong University, 2019. (in Chinese)

H T DI , Y T LI , K Y LIU , 等 . Hand gesture monitoring using fiber-optic curvature sensors . Applied Optics , 2019 . 58 ( 29 ): 7935 - 7942 . DOI: 10.1364/AO.58.007935 http://doi.org/10.1364/AO.58.007935 .

R FLORENTIN , V KERMENE , J BENOIST , 等 . Shaping the light amplified in a multimode fiber . Light:Science & Applications , 2016 . 6 ( 2 ): e16208 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gkxyyy-e201701014 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gkxyyy-e201701014 .

L C YI , BENGIO Y , HINTON G. . Deep learning . Nature , 2015 . 521 ( 7553 ): 436 - 444 . DOI: 10.1038/nature14539 http://doi.org/10.1038/nature14539 .

J SCHMIDHUBER . Deep learning in neural networks:An overview . Neural Networks , 2015 . 61 85 - 117 . DOI: 10.1016/j.neunet.2014.09.003 http://doi.org/10.1016/j.neunet.2014.09.003 .

KRIZHEVSKY A, SUTSKEVER I, HINTON G.E. Image Net classification with deep convolutional neural networks[C]. International Conference on Neural Information Processing Systems. NY USA: Advances in neural information processing systems, 2012: 1097-1105.

P WANG , J DI . Deep learning-based object classification through multimode fiber via a CNN-architecture SpeckleNet . Applied Optics , 2018 . 57 ( 28 ): 8258 - 8263 . DOI: 10.1364/AO.57.008258 http://doi.org/10.1364/AO.57.008258 DOI: 10.1364/AO.57.008258 http://doi.org/10.1364/AO.57.008258 .

N BOTHANI , E KAKKAVA , M CHRISTOPHE , 等 . Learning to see through multimode fibers . Optical , 2018 . 5 ( 8 ): 960 - 966 . https://arxiv.org/pdf/1805.05614 https://arxiv.org/pdf/1805.05614 .

DI H T, SUN S, YU J, et al. Novel optical fiber sensor for deformation measurement[C].5th International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optical Test and Measurement Technology and Equipment. Washington: Proceeding of SPIE, 2010: 7656, 76561C-1-76561C-7.

浏览量

761

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

水浴处理对塑料光纤传感器灵敏度及温度独立性的影响

老化处理对塑料光纤传感器光传输及灵敏度的影响

准确测量微藻生物量的塑料光纤倏逝波传感器