Real-time Event Recognition of Long-distance Distributed Vibration Sensing with Knowledge Distillation and Hardware Acceleration

TL;DR

This paper presents a real-time fiber-optic vibration event recognition system using a lightweight CNN with knowledge distillation and FPGA hardware acceleration, enabling long-distance, high-speed processing suitable for IoT applications.

Contribution

It introduces a novel FPGA-based hardware design and a knowledge distillation approach to significantly improve real-time event recognition accuracy and speed in distributed optical fiber vibration sensing.

Findings

Achieved 95.39% accuracy in event recognition.

Reduced inference time to 0.083 ms per sample.

Enabled real-time processing over 38.55 km of fiber.

Abstract

Fiber-optic sensing, especially distributed optical fiber vibration (DVS) sensing, is gaining importance in internet of things (IoT) applications, such as industrial safety monitoring and intrusion detection. Despite their wide application, existing post-processing methods that rely on deep learning models for event recognition in DVS systems face challenges with real-time processing of large sample data volumes, particularly in long-distance applications. To address this issue, we propose to use a four-layer convolutional neural network (CNN) with ResNet as the teacher model for knowledge distillation. This results in a significant improvement in accuracy, from 83.41% to 95.39%, on data from previously untrained environments. Additionally, we propose a novel hardware design based on field-programmable gate arrays (FPGA) to further accelerate model inference. This design replaces multiplication with binary shift operations and quantizes model weights, enabling high parallelism and low latency. Our implementation achieves an inference time of 0.083 ms for a spatial-temporal sample covering a 12.5 m fiber length and 0.256 s time frame. This performance enables real-time signal processing over approximately 38.55 km of fiber, about $2.14\times$ the capability of an Nvidia GTX 4090 GPU. The proposed method greatly enhances the efficiency of vibration pattern recognition, promoting the use of DVS as a smart IoT system. The data and code are available at https://github.com/HUST-IOF/Efficient-DVS.