Machine Learning For A Vernier-effect-based Optical Fiber Sensor - readout with ML

Aug 4, 2026

Optical Vernier effect fiber sensors use two interferometers whose superposed output forms a Vernier envelope with magnified response to external perturbations. Conventional interrogation relies on broadband sources and optical spectrum analyzers, followed by multi-step processing such as detecting fringe dips and applying nonlinear curve fitting to recover the envelope, which can introduce errors and waste information in the full spectrum. This work proposes machine learning for demodulating Vernier-effect-based optical fiber sensors, enabling direct, fast, and reliable measurand readout from the optical spectrum while reducing cumbersome signal processing and improving overall sensing performance.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages5

Reading Time13 min

AccessFree to download

Introduction

Vernier-effect principle and sensitivity enhancement

Limitations of conventional demodulation

Proposal: machine learning for demodulation

Missouri University of Science and Technology Scholars' Mine | Electrical and Computer Engineering Faculty Research & Creative Works | Electrical and Computer Engineering | | --- | --- | | 01 May 2023
Machine Learning For A Vernier-effect-based Optical Fiber Sensor
Chen Zhu
Missouri University of Science and Technology, [cznwq@mst.edu](cznwq@mst.edu)[ ](cznwq@mst.edu)Osamah Alsalman
Wassana Naku
Follow this and additional works at: [https://scholarsmine.mst.edu/ele_comeng_facwork](https://scholarsmine.mst.edu/ele_comeng_facwork)
Part of the Electrical and Computer Engineering Commons | | Recommended Citation C. Zhu et al., "Machine Learning For A Vernier-effect-based Optical Fiber Sensor," Optics Letters, vol. 48, no. 9, pp. 2488-2491, Optica, May 2023. The definitive version is available at [https://doi.org/10.1364/OL.489471](https://doi.org/10.1364/OL.489471) This Article-Journal is brought to you for free and open access by Scholars' Mine. It has been accepted for inclusion in Electrical and Computer Engineering Faculty Research & Creative Works by an authorized administrator of Scholars' Mine. This work is protected by U. S. Copyright Law. Unauthorized use including reproduction for redistribution requires the permission of the copyright holder. For more information, please contact [scholarsmine@mst.edu](scholarsmine@mst.edu). 2488 Vol. 48, No. 9 / 1 May 2023 / Optics Letters Letter Machine learning for a Vernier-effect-based optical fiber sensor Chen Zhu,1,∗ Osamah Alsalman,2 AND Wassana Naku3 1 Research Center for Optical Fiber Sensing, Zhejiang Laboratory, Hangzhou 311100, China 2 Department of Electrical Engineering, College of Engineering, King Saud University, P. O. Box 800, Riyadh 11421, Saudi Arabia 3 Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO 65409, USA *[chenzhu@zhejianglab.com](chenzhu@zhejianglab.com) Received 8 March 2023; revised 4 April 2023; accepted 14 April 2023; posted 14 April 2023; published 1 May 2023 In recent years, the optical Vernier effect has been demonstrated as an effective tool to improve the sensitivity of optical fiber interferometer-based sensors, potentially facilitating a new generation of highly sensitive fiber sensing systems. Previous work has mainly focused on the physical implementation of Vernier-effect-based sensors using different combinations of interferometers, while the signal demodulation aspect has been neglected. However, accurate and reliable extraction of useful information from the sensing signal is critically important and determines the overall performance of the sensing system. In this Letter, we, for the first time, propose and demonstrate that machine learning (ML) can be employed for thedemodulation of optical Vernier-effect-based fiber sensors. ML analysis enables direct, fast, and reliable readout of the measurand from the optical spectrum, avoiding the complicated and cumbersome data processing required in the conventional demodulation approach. This work opens new avenues for the development of Vernier-effect-based high-sensitivity optical fiber sensing systems. © 2023 Optica Publishing Group [https://doi.org/10.1364/OL.489471](https://doi.org/10.1364/OL.489471) Sensors with high sensitivity and resolution are always desired in scientific and engineering applications. In the field of optical fiber sensing, the Vernier effect has been demonstrated as an effective tool to improve the sensitivity of interferometric sensors in recent years [1–3] . Inspired by the Vernier caliper, the implementation of the optical Vernier effect requires the integration of two interferometers in a single system. The superposition of the signals of the two interferometers generates a Vernier envelope (typical amplitude modulation) at the output spectrum of the system. Instead of tracking the spectral fringe shifts ofthe individual interferometers, the Vernier

FAQs

What problem does the paper address in Vernier-effect optical fiber sensors?

Conventional demodulation requires complex processing (fringe-dip detection and nonlinear curve fitting) and may introduce additional errors, while only using limited spectral points.

How does the proposed machine learning approach work?

Machine learning demodulates the sensor by extracting the measurand directly from the optical spectrum, leveraging global information rather than reconstructing the Vernier envelope through multi-step fitting.

What benefit does the approach bring to sensor performance?

It enables direct, fast, and reliable readout from the spectrum and opens a route to developing Vernier-effect-based high-sensitivity optical fiber sensing systems.

Aug 4, 2026

Upload by Emma Wilson