Over the past years, we have established collaborations with various research teams and industry partners to implement our DOFS systems across multiple fields.

1. Leveraging Optical Communication Fiber and AI for Distributed Water Pipe Leak Detection

Detecting leaks in water networks is a costly challenge. We collaborated with the Hydraulics research group at PolyU and introduced a solution - the integration of an optical network that uses fiber-optic cable measure vibrations, enabling accurate leak detection and localization by an intelligent algorithm. We also propose a method to assess leak severity for prioritized repairs. Our solution is capable of detecting even small leaks with a flow rate as low as 0.027 L/s, offering a cost-effective way to improve leak detection, enhance water management, and optimize operational efficiency.

Further research with large-scale experiments will be conducted at Q-Leak underground water mains leak detection training center and Anderson Road Quarry Site in Hong Kong to explore the challenges and opportunities of integrating optical networks and water distribution networks (WDNs).

Project: Consultancy study on distributed fiber optic system for leak detection for water mains in Anderson Road Quarry Development Site

2. Novel Mining Conveyor Monitoring System based on Quasi-Distributed Optical Fiber Accelerometer Array and Self-supervised Learning

Belt conveyors play a critical role in the mining industry, and any downtime they experience can lead to significant financial losses and safety risks. Unplanned shutdowns are primarily caused by failures in rotating components, particularly idlers. An online condition monitoring system is necessary to continuously assess idler health and provide early warnings. Considering the large number and dense spatial distributions of idlers over long distances, we proposed a system that utilizes a quasi-distributed optical fiber accelerometer array for our funding sponsor.

The sensor array incorporates phase-sensitive optical time domain reflectometry (Phase-OTDR) interrogation technology and ultra-weak fiber Bragg gratings (UWFBGs) with an enhanced signal-to-noise ratio (SNR) to effectively capture idler vibrations over long distances. The designed array achieves high-sensitivity vibration sensing with a sensitivity of 2.4 rad/g and a resolution of 0.0146 g. After collecting the vibrations of idlers by the designed accelerometer array, an automatic fault classification algorithm based on self-supervised learning (SSL) is introduced, which requires only a small number of labeled samples. By leveraging a large amount of unlabeled data in the pretext task, the algorithm efficiently extracts latent features from the quasi-distributed accelerometer array. A diagnosis accuracy of 95.37% can be achieved on a seven-class classification task with only 3.6% labeled data (16 samples/class). This system offers a promising solution for idler monitoring, combining high sensitivity, distributed measurement capabilities, enhanced security, and superior fault detection accuracy.

3. Brillouin Optical Time-Domain Sensing System for Railway Monitoring

Railways are subject to significant temperature variations throughout the year. Extreme temperatures, especially in hot weather, can cause the tracks to expand, leading to buckling and deformation. In colder climates, freezing temperatures can contract the tracks, potentially causing track fractures. Monitoring the temperature helps identify critical temperature thresholds and prevents potential track failures, ensuring the safety and integrity of the railway infrastructure.

We developed a Brillouin optical time-domain analyzer (BOTDA) sensing system for our funding sponsor.

4. Crowd Surveillance based on Fiber-Optics

Crowd surveillance plays a vital role in enhancing public safety and security in diverse settings, such as public spaces, transportation hubs, and large events. By enabling authorities to monitor and manage crowds, detect potential threats, and respond swiftly to emergencies, crowd surveillance contributes significantly to overall safety measures.

we conducted a trail test for crowd monitoring by laying a fiber-optic cable beneath the newly built footbridge at PolyU. The fiber-optic-based solution offers an alternative approach for crowd surveillance without raising privacy concerns, maintaining public trust in the surveillance system.