Abstract

A fiber directional position sensor based on multimode interference and image processing by machine learning is presented. Upon single-mode injection, light in multimode fiber generates a multi-ring-shaped interference pattern at the end facet, which is susceptible to the amplitude and direction of the fiber distortions. The fiber is mounted on an automatic translation stage, with repeating movement in four directions. The images are captured from an infrared camera and fed to a machine-learning program to train, validate, and test the fiber conditions. As a result, accuracy over 97% is achieved in recognizing fiber positions in these four directions, each with 10 classes, totaling an 8 mm span. The number of images taken for each class is merely 320. Detailed investigation reveals that the system can achieve over 60% accuracy in recognizing positions on a 5 µm resolution with a larger dataset, approaching the limit of the chosen translation stage.

© 2020 Optical Society of America

Machine learning for sensing with a multimode exposed core fiber specklegram sensor

Darcy L. Smith, Linh V. Nguyen, David J. Ottaway, Thiago D. Cabral, Eric Fujiwara, Cristiano M. B. Cordeiro, and Stephen C. Warren-Smith
Opt. Express 30(7) 10443-10455 (2022)

Distributed fiber sensor and machine learning data analytics for pipeline protection against extrinsic intrusions and intrinsic corrosions

Zhaoqiang Peng, Jianan Jian, Hongqiao Wen, Andrei Gribok, Mohan Wang, Hu Liu, Sheng Huang, Zhi-Hong Mao, and Kevin P. Chen
Opt. Express 28(19) 27277-27292 (2020)

Highly sensitive displacement sensor based on composite interference established within a balloon-shaped bent multimode fiber structure

Ke Tian, Gerald Farrell, Xianfan Wang, Elfed Lewis, and Pengfei Wang
Appl. Opt. 57(32) 9662-9668 (2018)

OPGW positioning and early warning method based on a Brillouin distributed optical fiber sensor and machine learning

Meng Xia, Xiaohui Tang, Ying Wang, Can Li, Yong Wei, Jiaju Zhang, Taofei Jiang, and Yongkang Dong
Appl. Opt. 62(6) 1557-1566 (2023)

Spatially-resolved bending recognition based on a learning-empowered fiber specklegram sensor

Han Gao and Haifeng Hu
Opt. Express 31(5) 7671-7683 (2023)