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.

Fiber-optic distributed acoustic sensing (DAS) offers a promising solution for continuous traffic monitoring; however, its widespread deployment is often hindered by poor signal quality, resulting in fragmented and faint vehicle trajectories. Existing techniques − including conventional signal processing and deep learning models − struggle to accurately reconstruct trajectories and estimate traffic parameters under such challenging conditions. To overcome these limitations, we propose the DAS-hierarchical vehicle estimation network (DAS-HiVENet), an end-to-end framework that fundamentally advances the state-of-the-art through three key innovations: a two-stage preprocessing pipeline for noise suppression and trajectory preservation; a novel generative adversarial network (GAN) with an enhanced U-shaped convolutional neural network (U-net) generator to reconstruct high-fidelity trajectories from degraded inputs; a rotated-you only look once (R-YOLO) detector using oriented bounding boxes to accurately detect slanted trajectories. Extensive field evaluations on multiple expressways confirm that it surpasses existing methods with breakthrough performance: a trajectory intersection over union (IoU) of 0.7076, vehicle counting detection rate of 96.7%, and speed estimation errors as low as 1.422 km/h for the mean absolute error (MAE) and 1.796% for the mean absolute percentage error (MAPE) over 30 minutes. Even in challenging bridge scenarios with severe trajectory adhesion, DAS-HiVENet maintains an over 96% detection rate and under 4% MAPE in speed estimation − significantly outperforming alternatives.

High sensitivity of a distributed optical-fiber vibration sensing (DOVS) system based on the phase-sensitivity optical time domain reflectometry (Φ-OTDR) technology also brings in high nuisance alarm rates (NARs) in real applications. In this paper, feature extraction methods of wavelet decomposition (WD) and wavelet packet decomposition (WPD) are comparatively studied for three typical field testing signals, and an artificial neural network (ANN) is built for the event identification. The comparison results prove that the WPD performs a little better than the WD for the DOVS signal analysis and identification in oil pipeline safety monitoring. The identification rate can be improved up to 94.4%, and the nuisance alarm rate can be effectively controlled as low as 5.6% for the identification network with the wavelet packet energy distribution features.

A real-time intelligent fiber-optic perimeter intrusion detection system (PIDS) based on the fiber Bragg grating (FBG) sensor network is presented in this paper. To distinguish the effects of different intrusion events, a novel real-time behavior impact classification method is proposed based on the essential statistical characteristics of signal’s profile in the time domain. The features are extracted by the principal component analysis (PCA), which are then used to identify the event with a K-nearest neighbor classifier. Simulation and field tests are both carried out to validate its effectiveness. The average identification rate (IR) for five sample signals in the simulation test is as high as 96.67%, and the recognition rate for eight typical signals in the field test can also be achieved up to 96.52%, which includes both the fence-mounted and the ground-buried sensing signals. Besides, critically high detection rate (DR) and low false alarm rate (FAR) can be simultaneously obtained based on the autocorrelation characteristics analysis and a hierarchical detection and identification flow.

A novel multi-channel distributed optical fiber intrusion monitoring system with smart fiber link backup and on-line fault diagnosis functions was proposed. A 1×N optical switch was intelligently controlled by a peripheral interface controller (PIC) to expand the fiber link from one channel to several ones to lower the cost of the long or ultra-long distance intrusion monitoring system and also to strengthen the intelligent monitoring link backup function. At the same time, a sliding window auto-correlation method was presented to identify and locate the broken or fault point of the cable. The experimental results showed that the proposed multi-channel system performed well especially whenever any a broken cable was detected. It could locate the broken or fault point by itself accurately and switch to its backup sensing link immediately to ensure the security system to operate stably without a minute idling. And it was successfully applied in a field test for security monitoring of the 220-km-length national borderline in China.