Identifying mode coupling wavelengths in doubly-clad optical fibers with deep learning

IF 2.6 3区计算机科学 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC

Optical Fiber Technology Pub Date : 2024-08-30 DOI:10.1016/j.yofte.2024.103952

Pengyu An, Kanglei Wang, Wenjuan Li, Shujun Men, Jiamin Wang, Yutong Yuan, Lei Zhang

{"title":"Identifying mode coupling wavelengths in doubly-clad optical fibers with deep learning","authors":"Pengyu An, Kanglei Wang, Wenjuan Li, Shujun Men, Jiamin Wang, Yutong Yuan, Lei Zhang","doi":"10.1016/j.yofte.2024.103952","DOIUrl":null,"url":null,"abstract":"<div><p>Understanding the transmission of light waves in optical fibers and accurately determining the locations of mode coupling are crucial for enhancing the efficiency of optical devices and advancing innovative technologies such as fiber optic sensors, lasers, and modulators. This study utilizes deep learning and image recognition techniques to identify the wavelengths at which mode coupling occurs in optical fibers. Our research findings show that using the ResNet-18 model allows for the rapid and accurate identification of the wavelengths at which mode coupling occurs in optical fibers, as well as the modes involved, achieving an accuracy close to 100 %. We experimented with sampling the dataset at 5 nm and 10 nm intervals to create smaller training and validation sets. Despite the reduced data volume, high accuracy rates were maintained, exceeding 99 % and 97 % respectively. This study provides new insights into the use of deep learning for precise localization of mode coupling points and tracking of transmission modes in optical fibers.</p></div>","PeriodicalId":19663,"journal":{"name":"Optical Fiber Technology","volume":"87 ","pages":"Article 103952"},"PeriodicalIF":2.6000,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Optical Fiber Technology","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1068520024002979","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}

引用次数: 0

Abstract

Understanding the transmission of light waves in optical fibers and accurately determining the locations of mode coupling are crucial for enhancing the efficiency of optical devices and advancing innovative technologies such as fiber optic sensors, lasers, and modulators. This study utilizes deep learning and image recognition techniques to identify the wavelengths at which mode coupling occurs in optical fibers. Our research findings show that using the ResNet-18 model allows for the rapid and accurate identification of the wavelengths at which mode coupling occurs in optical fibers, as well as the modes involved, achieving an accuracy close to 100 %. We experimented with sampling the dataset at 5 nm and 10 nm intervals to create smaller training and validation sets. Despite the reduced data volume, high accuracy rates were maintained, exceeding 99 % and 97 % respectively. This study provides new insights into the use of deep learning for precise localization of mode coupling points and tracking of transmission modes in optical fibers.

查看原文本刊更多论文

利用深度学习识别双包层光纤中的模式耦合波长

了解光波在光纤中的传输以及准确确定模式耦合的位置，对于提高光学设备的效率以及推动光纤传感器、激光器和调制器等创新技术的发展至关重要。本研究利用深度学习和图像识别技术来识别光纤中发生模式耦合的波长。我们的研究结果表明，使用 ResNet-18 模型可以快速准确地识别出光纤中发生模式耦合的波长以及所涉及的模式，准确率接近 100%。我们尝试以 5 nm 和 10 nm 的间隔对数据集进行采样，以创建更小的训练集和验证集。尽管数据量减少了，但准确率仍然很高，分别超过 99% 和 97%。这项研究为利用深度学习精确定位光纤中的模式耦合点和跟踪传输模式提供了新的见解。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Optical Fiber Technology 工程技术-电信学

CiteScore

4.80

自引率

11.10%

发文量

327

审稿时长

63 days

期刊介绍： Innovations in optical fiber technology are revolutionizing world communications. Newly developed fiber amplifiers allow for direct transmission of high-speed signals over transcontinental distances without the need for electronic regeneration. Optical fibers find new applications in data processing. The impact of fiber materials, devices, and systems on communications in the coming decades will create an abundance of primary literature and the need for up-to-date reviews. Optical Fiber Technology: Materials, Devices, and Systems is a new cutting-edge journal designed to fill a need in this rapidly evolving field for speedy publication of regular length papers. Both theoretical and experimental papers on fiber materials, devices, and system performance evaluation and measurements are eligible, with emphasis on practical applications.