数据受限下的分布式光纤事件识别方法研究进展

张磊; 李越文; 施羿

doi:10.13756/j.gtxyj.2026.260033

您当前的位置：

首页 >

文章列表页 >

数据受限下的分布式光纤事件识别方法研究进展

光传感与检测技术 | 更新时间：2026-10-21

- 数据受限下的分布式光纤事件识别方法研究进展
- Research Progress on Distributed Fiber Optic Event Recognition Methods Under Data Constraints
- 光通信研究 2026年第5期页码：229-239
- 作者机构：
  
  1.国家能源集团宁夏电力公司，银川　750001
  2.国能宁夏六盘山能源发展有限公司，宁夏　固原　756000
  3.汕头大学工学院，广东　汕头　515063
- 作者简介：
  
  张磊（1982-），男，宁夏银川人。高级工程师，硕士，主要研究领域为电力技术及光纤传感技术。
  施羿，副教授。E-mail：shy_xflx@163.com
- 基金信息：
  
  国家自然科学基金资助项目(61801283);国能宁夏六盘山能源发展有限公司资助项目(E770200006)
- DOI：10.13756/j.gtxyj.2026.260033
  中图分类号： TP212
- 收稿：2026-01-29，
  
  修回：2026-04-01，
  
  纸质出版：2026-10-10
- 稿件说明：
移动端阅览
张磊，李越文，施羿. 数据受限下的分布式光纤事件识别方法研究进展[J]. 光通信研究，2026(5): 229-239.

Zhang L, Li Y, Shi Y. Research Progress on Distributed Fiber Optic Event Recognition Methods Under Data Constraints[J]. Study on Optical Communications, 2026(5): 229-239.
张磊，李越文，施羿. 数据受限下的分布式光纤事件识别方法研究进展[J]. 光通信研究，2026(5): 229-239. DOI： 10.13756/j.gtxyj.2026.260033.

Zhang L, Li Y, Shi Y. Research Progress on Distributed Fiber Optic Event Recognition Methods Under Data Constraints[J]. Study on Optical Communications, 2026(5): 229-239. DOI： 10.13756/j.gtxyj.2026.260033.

摘要

分布式光纤振动（DAS）/声波传感技术凭借独特的全域分布式动态感知优势，已在众多工业场景落地。深度学习显著提升了光纤传感事件识别的精度，但实际工程中监测事件样本稀缺、类别分布失衡，极易造成网络泛化性能劣化。文章系统梳理数据受限场景下分布式光纤事件识别相关研究，聚焦数据扩增、迁移学习两大主流技术路线，剖析各类方案核心机理、优势与现存技术瓶颈，并对未来发展方向予以展望，为该领域后续研究提供系统性参考。

Abstract

Due to the dynamic monitoring capability

Distributed Acoustic Sensing (DAS) has been widely deployed in various industrial scenarios. Deep learning greatly boosts the event detection accuracy of fiber sensing systems. Nevertheless

practical engineering suffers from limited labeled samples and imbalanced class distribution

which severely degrades the generalization of deep neural networks. This paper systematically reviews state-of-the-art distributed fiber event recognition algorithms under data scarcity. Two mainstream technical frameworks

i.e.

data augmentation and transfer learning

are elaborated in detail. We analyze the core mechanisms

merits and technical bottlenecks of each method

and prospect future research trends

offering comprehensive references for follow-up investigations.

关键词

Keywords

references

Chen J , Shi Y , Wei C , et al . Φ-OTDR Event Recognition System based on Reconstructed Signal Feature Space [J ] . IEEE Internet of Things Journal , 2025 , 12 ( 13 ): 25346 - 25356 .

王龙生 , 谢欣 , 姚猛 , 等 . 分布式光纤声波传感及其进展研究 [J ] . 光通信研究 , 2025 ( 5 ): 240100 .

Wang L S , Xie X , Yao M , et al . Distributed Optical Fiber Acoustic Wave Sensing and Its Progress [J ] . Study on Optical Communications , 2025 ( 5 ): 240100 .

柏彬 , 俞越中 , 赵会龙 , 等 . 光纤分布式传感系统在变电站维护中的应用 [J ] . 光通信研究 , 2023 ( 1 ): 53 - 57 .

Bai B , Yu Y Z , Zhao H L , et al . Application of Optical Fiber Distributed Sensing System in Substation Maintenance [J ] . Study on Optical Communications , 2023 ( 1 ): 53 - 57 .

Fernández-Ruiz M R , Soto M A , Williams E F , et al . Distributed Acoustic Sensing for Seismic Activity Monitoring [J ] . APL Photonics , 2020 , 5 ( 3 ): 030901 .

Yang Y , Zhang H , Li Y . Long-Distance Pipeline Safety Early Warning: a Distributed Optical Fiber Sensing Semi-Supervised Learning Method [J ] . IEEE Sensors Journal , 2021 , 21 ( 17 ): 19453 - 19461 .

Wu H , Liu X , Xiao Y , et al . A Dynamic Time Sequence Recognition and Knowledge Mining Method based on the Hidden Markov Models (HMMS) for Pipeline Safety Monitoring with Φ-OTDR [J ] . Journal of Lightwave Technology , 2019 , 37 ( 19 ): 4991 - 5000 .

张驰 , 邹宁睦 , 宋金玉 , 等 . Φ-OTDR系统的数字信号处理及应用 [J ] . 光电工程 , 2023 , 50 ( 2 ): 220088 .

Zhang C , Zou N M , Song J Y , et al . Digital Signal Processing and Application of Φ-OTDR System [J ] . Opto-Electronic Engineering , 2023 , 50 ( 2 ): 220088 .

吴明埝 , 沈一春 , 陈青青 , 等 . 基于多分类高斯SVM的光纤信号的模式识别方法 [J ] . 激光技术 , 2025 , 49 ( 1 ): 128 - 134 .

Wu M N , Shen Y C , Chen Q Q , et al . Pattern Recognition Method of Distributed Optical Fiber Sensing Signal based on Multi-Classification Gaussian SVM [J ] . Laser Technology , 2025 , 49 ( 1 ): 128 - 134 .

Li Z , Zhang J , Wang M , et al . Fiber Distributed Acoustic Sensing Using Convolutional Long Short-Term Memory Network: a Field Test on High-Speed Railway Intrusion Detection [J ] . Optics Express , 2020 , 28 ( 3 ): 2925 .

Lv A , Li J . On-Line Monitoring System of 35 kV 3-Core Submarine Power Cable based on Φ-OTDR [J ] . Sensors and Actuators A: Physical , 2018 , 273 : 134 - 139 .

Filograno M L , Riziotis C , Kandyla M . A Low-Cost Phase-OTDR System for Structural Health Monitoring: Design and Instrumentation [J ] . Instruments , 2019 , 3 ( 3 ): 46 .

Xu J T , Luo L , Saw J , et al . Structural Health Monitoring of Offshore Wind Turbines Using Distributed Acoustic Sensing (DAS) [J ] . Journal of Civil Structural Health Monitoring , 2025 , 15 ( 2 ): 445 - 463 .

张博智 , 刘柯 , 刘琨 , 等 . 基于分布式光纤振动检测系统的动态方差阈值算法研究 [J ] . 光电工程 , 2023 , 50 ( 2 ): 220205 .

Zhang B Z , Liu K , Liu K , et al . Research on Dynamic Variance Threshold Algorithm based on Distributed Fiber Vibration Sensor System [J ] . Opto-Electronic Engineering , 2023 , 50 ( 2 ): 220205 .

Li C , Chen X , Shi Y . An Event Recognition Method for a Φ-OTDR System based on CNN-BiGRU Network Model with Attention [J ] . Photonics , 2025 , 12 ( 4 ): 313 .

Li K , Zhen Y , Li P , et al . Optical Fiber Vibration Signal Recognition based on the EMD Algorithm and CNN-LSTM [J ] . Sensors , 2025 , 25 ( 7 ): 2016 .

Wang Y Y , Zhao S W , Wang C , et al . Intelligent Detection and Recognition of Multi-Vibration Events based on Distributed Acoustic Sensor and Improved YOLOv8 Model [J ] . Optical Fiber Technology , 2024 , 84 : 103706 .

Shi Y , Chen J , Dai S , et al . Φ-OTDR Event Recognition System based on Valuable Data Selection [J ] . Journal of Lightwave Technology , 2024 , 42 ( 2 ): 961 - 969 .

Li Y , Zeng X , Shi Y . A Spatial and Temporal Signal Fusion based Intelligent Event Recognition Method for Buried Fiber Distributed Sensing System [J ] . Optics & Laser Technology , 2023 , 166 : 109658 .

Wu H , Zhou B , Zhu K , et al . Pattern Recognition in Distributed Fiber-Optic Acoustic Sensor Using an Intensity and Phase Stacked Convolutional Neural Network with Data Augmentation [J ] . Optics Express , 2021 , 29 ( 3 ): 3269 .

Zhou Y , Liu S , Wang L , et al . Accurate Recognition of Mixed Events Using Two-Dimensional Time-Frequency Domain Feature and Data Augmentation for Phase-OTDR Sensing System [C ] // 2022 Asia Communications and Photonics Conference (ACP) . Shenzhen, China . IEEE : 2022 : 10088659 .

Bengio Y , Bastien F , Bergeron A , et al . Deep Learners Benefit more from out-of-distribution Examples [C ] // International Conference on Artificial Intelligence and Statistics . Fort Lauderdale, USA : JMLR : 2011 : 164–172 .

Zhang H , Cisse M , Dauphin Y , et al . Mixup: Beyond Empirical Risk Minimization [C ] // International Conference on Learning Representations . Vancouver, Canada : ICLR , 2018 : 1 - 13 .

Cubuk E D , Zoph B , Shlens J , et al . Randaugment: Practical Automated Data Augmentation with a Reduced Search Space [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) . Seattle, WA, USA : IEEE , 2020 : 3008 - 3017 .

Cubuk E D , Zoph B , Mané D , et al . AutoAugment: Learning Augmentation Strategies from Data [C ] // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Long Beach, CA, USA : IEEE , 2019 : 8953317 .

Hendrycks D , Mu N , Cubuk E , et al . Augmix: A Simple Data Processing Method to Improve Robustness and Uncertainty [C ] // International Conference on Learning Representations . Addis Ababa, Ethiopia : ICLR , 2020 : 1 - 15 .

Zhang S , He T , Li H , et al . Modified Data Augmentation Integration Method for Robust Intrusion Events Recognition with Fiber Optic DAS System [J ] . Journal of Lightwave Technology , 2024 , 42 ( 1 ): 453 - 462 .

Zhang T , Peng X , Liu Y , et al . A Contrastive Representation Learning Method for Event Classification in Φ-OTDR Systems [J ] . Sensors , 2025 , 25 ( 15 ): 4744 .

Shiloh L , Eyal A , Giryes R . Efficient Processing of Distributed Acoustic Sensing Data Using a Deep Learning Approach [J ] . Journal of Lightwave Technology , 2019 , 37 ( 18 ): 4755 - 4762 .

Shi Y , Dai S , Liu X , et al . Event Recognition Method based on Dual-Augmentation for a Φ-OTDR System with a few Training Samples [J ] . Optics Express , 2022 , 30 ( 17 ): 31232 .

Shi Y , Kang X , Lin Z , et al . CycleGAN-Based Data Augmentation for Enhancing Classification Accuracy in Φ-OTDR Systems [C ] // 2024 22nd International Conference on Optical Communications and Networks (ICOCN) . Harbin, China : IEEE , 2024 : 10648440 .

Ni W , Hu L , Yu K . A Ф-OTDR Event Identification based on Data Augmentation with TSG [C ] // Proceedings of SPIE Conference on Asia-Pacific Optical Sensors Conference (APOS 2023) . Tianjin, China : SPIE , 2023 : 12 .

Hu L , Ni W , Li Y , et al . Enhancing Φ-OTDR Classification Performance through Event Augmentation [J ] . Optics Communications , 2024 , 569 : 130818 .

张印 , 胡挺 , 李猷兴 , 等 . 基于条件对抗生成网络数据增强的相敏光时域反射仪模式识别 [J ] . 光学学报 , 2024 , 44 ( 1 ): 0106026 .

Zhang Y , Hu T , Li Y X , et al . Pattern Recognition of Phase-Sensitive Optical Time-Domain Reflectometer Based on Conditional Generative Adversarial Network Data Augmentation [J ] . Acta Optica Sinica , 2024 , 44 ( 1 ): 0106026 .

Shen W , Huang Y , Zhang Y , et al . High-Quality Data Augmentation Method based on Multi-Scale Dense Attention-Enhanced CGAN for Φ-OTDR Event Recognition [J ] . Optics Communications , 2025 , 596 : 132429 .

Shi Y , Kang X , Wei Z , et al . A Data Augmentation Approach Combining Time Series Reconstruction and VAEGAN for Improved Event Recognition in Φ-OTDR [J ] . Optical Fiber Technology , 2025 , 90 : 104135 .

Shi Y , Liu H , Zhang W , et al . Event Recognition Method based on Feature Synthesizing for a Zero-Shot Intelligent Distributed Optical Fiber Sensor [J ] . Optics Express , 2024 , 32 ( 5 ): 8321 .

Shi Y , Pan L , Liu H . Multisource Event Classification in ϕ-OTDR through Sample Feature Synthesis [J ] . IEEE Sensors Journal , 2024 , 24 ( 20 ): 32196 - 32202 .

Hu X , Dong H , Kong Y , et al . Effective Zero-Shot Learning Method for Event Classification in Φ-OTDR Sensing Systems [J ] . Optics Express , 2024 , 32 ( 20 ): 35495 .

Xie Y , Wang M , Zhong Y , et al . Label-Free Anomaly Detection Using Distributed Optical Fiber Acoustic Sensing [J ] . Sensors , 2023 , 23 ( 8 ): 4094 .

Kozmin A , Kalashev O , Chernenko A , et al . Semi-Supervised Learned Autoencoder for Classification of Events in Distributed Fibre Acoustic Sensors [J ] . Sensors , 2025 , 25 ( 12 ): 3730 .

Shi Y , Li Y , Zhang Y , et al . An Easy Access Method for Event Recognition of Φ-OTDR Sensing System based on Transfer Learning [J ] . Journal of Lightwave Technology , 2021 , 39 ( 13 ): 4548 - 4555 .

Li Y , Zeng X , Shi Y . Quickly Build a High-Precision Classifier for Φ-OTDR Sensing System based on Transfer Learning and Support Vector Machine [J ] . Optical Fiber Technology , 2022 , 70 : 102868 .

Gan J , Xiao Y . Signal Recognition based on Transfer Learning for Φ-OTDR Fiber Optic Distributed Disturbance Sensor [J ] . Journal of Physics: Conference Series , 2024 , 2822 ( 1 ): 012086 .

Gan J , Xiao Y , Zhang A . Fused Feature Extract Method for Φ-OTDR Event Recognition based on VGGish Transfer Learning [J ] . Applied Optics , 2024 , 63 ( 20 ): 5411 - 5420 .

申永旭 . 基于分布式光纤周界安防入侵信号迁移场景的识别研究 [D ] . 济南 : 齐鲁工业大学 , 2025 .

Shen Y X . Research on the Identification of Intrusion Signal Migration Scenarios based on Distributed Fiber Optic Perimeter Security [D ] . Jinan : Qilu University of Technology , 2025 .

温江涛 , 王涛 , 孙洁娣 , 等 . 基于深度迁移学习的复杂环境下油气管道周界入侵事件识别 [J ] . 仪器仪表学报 , 2019 , 40 ( 8 ): 12 - 19 .

Wen J T , Wang T , Sun J D , et al . Perimeter Intrusion Event Identification of Oil and Gas Pipelines under Complex Conditions based on Deep Transfer Learning [J ] . Chinese Journal of Scientific Instrument , 2019 , 40 ( 8 ): 12 - 19 .

王涛 . 基于迁移学习的复杂环境下油气管道周界入侵事件识别 [D ] . 秦皇岛 : 燕山大学 , 2020 .

Wang T . Recognition of Intrusion Events in the Periphery of Oil and Gas Pipelines under Complex Environment based on Transfer Learning [D ] . Qinhuangdao : Yanshan University , 2020 .

王璟伦 . 跨场景少标签DAS信号识别方法 [D ] . 成都 : 电子科技大学 , 2024 .

Wang J L . Cross-scene DAS Signal Recognition with insufficient Labeled Samples [D ] . Chengdu : University of Electronic Science and Technology of China , 2024 .

陈帅 , 厉小润 , 李东明 , 等 . 基于跨模型知识蒸馏的φ-OTDR模式识别 [J ] . 激光与光电子学进展 , 2024 , 61 ( 13 ): 205 - 211 .

Chen S , Li X R , Li D M , et al . Pattern Recognition Of φ-OTDR based on Cross-Model Knowledge Distillation [J ] . Laser & Optoelectronics Progress , 2024 , 61 ( 13 ): 205 - 211 .

Hu J , Cheng X , Liu H , et al . An Event Recognition Method with Self-Distillation for Φ-OTDR Sensing System [J ] . Optics Communications , 2025 , 577 : 131393 .

浏览量

下载量

CSCD

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

卫星互联网的高效频谱共享研究综述

基于FPGA的UWOC链路对准与信号重构研究

集成互耦合半导体激光器的动力学特性

光通信中非线性均衡方法与泛化性研究进展

面向商用车的车载光纤通信技术需求与挑战