Pipeline Degradation Evaluation Based on Distributed Fiber Sensors and Convolutional Neural Networks (CNNs)

Zekun Wu, Qirui Wang, Andrei V. Gribokb, Kevin P. Chen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We present a machine learning method to analyze data harnessed by distributed fiber sensors for pipeline monitoring. Convolutional neural networks are used to identify and classify pipeline internal defects with 99% and 94% accuracy, respectively.

Original languageEnglish
Title of host publicationOptical Fiber Sensors, OFS 2022
PublisherOptica Publishing Group (formerly OSA)
ISBN (Electronic)9781957171142
DOIs
StatePublished - 2022
Event27th International Conference on Optical Fiber Sensors, OFS 2022 - Alexandria, United States
Duration: Aug 29 2022Sep 2 2022

Publication series

NameOptics InfoBase Conference Papers
ISSN (Electronic)2162-2701

Conference

Conference27th International Conference on Optical Fiber Sensors, OFS 2022
Country/TerritoryUnited States
CityAlexandria
Period08/29/2209/2/22

Fingerprint

Dive into the research topics of 'Pipeline Degradation Evaluation Based on Distributed Fiber Sensors and Convolutional Neural Networks (CNNs)'. Together they form a unique fingerprint.

Cite this