@article{XIE2026, 
author = {Lang XIE and Juxiang QIU and Hechao WANG and Haitao HUANG and Shibo HAN and Huicong PENG and Huijuan WU and Yu WU},
title = {Review of DAS for Monitoring Industrial Infrastructures},
year = {2026},
journal = {Photonic Sensors},
volume = {16},
number = {1},
pages = {9560010},
keywords = {Distributed optical fiber sensing, phase-sensitive optical time domain reflectometry, distributed acoustic sensing, artificial intelligence, industrial infrastructure monitoring},
url = {https://www.sciopen.com/article/10.26599/PhoS.2026.9560010},
doi = {10.26599/PhoS.2026.9560010},
abstract = {Distributed acoustic sensing (DAS), based on phase-sensitive optical time-domain reflectometry (Φ-OTDR), transforms optical fibers into distributed vibration sensors through Rayleigh backscattering, enabling real-time industrial monitoring with extensive coverage and high spatial resolution. This review systematically presents key advances and industrial applications made by the optical fiber sensing (OFS) group at University of Electronic Science and Technology of China (UESTC), which include a differential-frequency modulation scheme integrated with a polarization-multifrequency diversity fusion algorithm and achieve pε-level strain sensitivity and suppressed signal fading down to 0.1%, enabling high-fidelity and long-distance sensing using low-cost commercial DAS units. Based on the advanced sensing capability, our developed adaptive feature enhancement method combined with an incremental tree classifier achieves the remarkable 96.55% recognition accuracy for ten types of pipeline intrusion events while reducing retraining time by 98.5% and further attains 99.96% accuracy for five major intrusion types in real field deployments. For railway infrastructure monitoring, our RailFusion-DAS framework utilizes existing fiber-optic cables along the railway to precisely identify three typical track defects with the 98.73% accuracy. Furthermore, by implementing time-frequency analysis and a two-dimensional convolutional neural network classifier on an artificial intelligence (AI) hardware accelerator, we realize an on-chip AI-DAS system that achieves 98.7% accuracy in online fault detection for belt conveyor idlers.}
}