Skip to main content
SpringerLink
Log in

A deep learning model enabled multi-event recognition for distributed optical fiber sensing

  • Research Paper
  • Published:
Science China Information Sciences Aims and scope Submit manuscript

Abstract

Fiber optic sensors that utilize backscattered light offer distributed real-time measurements and have been seen tremendous improvements in sensing distance and spatial resolution over the last decades. However, these improvements in sensor capabilities lead to a significant increase in the amount of data that needs to be processed. Traditional processing schemes are no longer adequate, so the development of novel signal processing methods is critical. Phase-sensitive optical time domain reflectometry (Φ-OTDR) is now applied in various applications for multi-event recognition, and it would usually be difficult, sometimes even unrealistic to label all the acquired samples due to its real-time and seamless monitoring nature. To fully take advantage of the information contained within the large number of unlabeled samples, which were formerly not utilized and hence wasted, we propose a semi-supervised model to boost the event classification performance of Φ-OTDR. The model extracts respectively the temporal features and the spatial bidirectional features together with a dual attention mechanism. Its classification accuracy has been improved up to 96.9% with only 1230 labeled samples. In addition, our model shows significant advantages when the number of labeled samples is reduced. Importantly, our method improves the accuracy of multi-event classification without any modification to the optical setup.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Huang L J, He Z Y, Fan X Y. Simplified single-end Rayleigh and Brillouin hybrid distributed fiber-optic sensing system. Sci China Inf Sci, 2023, 66: 129404

    Article  Google Scholar 

  2. Kandamali D F, Cao X, Tian M, et al. Machine learning methods for identification and classification of events in Φ-OTDR systems: a review. Appl Opt, 2022, 61: 2975–2997

    Article  ADS  PubMed  Google Scholar 

  3. Liang Y X, Wang Z N, Lin S T, et al. Optical-pulse-coding phase-sensitive OTDR with mismatched filtering. Sci China Inf Sci, 2022, 65: 192303

    Article  Google Scholar 

  4. Li H, Fan C Z, Liu T, et al. Time-slot multiplexing based bandwidth enhancement for fiber distributed acoustic sensing. Sci China Inf Sci, 2022, 65: 119303

    Article  Google Scholar 

  5. Tan D, Tian X, Sun W, et al. An oil and gas pipeline pre-warning system based on Φ-OTDR. In: Proceedings of the 23rd International Conference on Optical Fibre Sensors, Santander, 2014. 1269–1272

  6. Juarez J C, Taylor H F. Field test of a distributed fiber-optic intrusion sensor system for long perimeters. Appl Opt, 2007, 46: 1968–1971

    Article  ADS  PubMed  Google Scholar 

  7. Juarez J C, Maier E W, Choi K N, et al. Distributed fiber-optic intrusion sensor system. J Lightwave Technol, 2005, 23: 2081–2087

    Article  ADS  Google Scholar 

  8. Juarez J C, Taylor H F. Polarization discrimination in a phase-sensitive optical time-domain reflectometer intrusion-sensor system. Opt Lett, 2005, 30: 3284–3286

    Article  ADS  PubMed  Google Scholar 

  9. Qin Z, Chen L, Bao X. Wavelet denoising method for improving detection performance of distributed vibration sensor. IEEE Photon Technol Lett, 2012, 24: 542–544

    Article  ADS  Google Scholar 

  10. Wu H J, Liu X Y, Rao Y J. Processing and application of fiber optic distributed sensing signal based on Φ-OTDR (in Chinese). Laser Optoelectron Prog, 2021, 58: 1306003

    Google Scholar 

  11. Xu C, Guan J, Bao M, et al. Pattern recognition based on time-frequency analysis and convolutional neural networks for vibrational events in ϕ-OTDR. Opt Eng, 2018, 57: 1

    Google Scholar 

  12. Shi Y, Wang Y, Zhao L, et al. An event recognition method for Φ-OTDR sensing system based on deep learning. Sensors, 2019, 19: 3421

    Article  ADS  PubMed  PubMed Central  Google Scholar 

  13. Sun Q, Li Q, Chen L, et al. Pattern recognition based on pulse scanning imaging and convolutional neural network for vibrational events in ΦOTDR. Optik, 2020, 219: 165205

    Article  ADS  Google Scholar 

  14. Chen J, Wu H, Liu X, et al. A real-time distributed deep learning approach for intelligent event recognition in long distance pipeline monitoring with DOFS. In: Proceedings of International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC), Zhengzhou, 2018. 290–2906

  15. Chen X, Xu C. Disturbance pattern recognition based on an ALSTM in a long-distance ϕ-OTDR sensing system. Micro Opt Tech Lett, 2020, 62: 168–175

    Article  Google Scholar 

  16. Manie Y C, Li J W, Peng P C, et al. Using a machine learning algorithm integrated with data de-noising techniques to optimize the multipoint sensor network. Sensors, 2010, 20: 1070

    Article  ADS  Google Scholar 

  17. Wu J, Guan L, Bao M, et al. Vibration events recognition of optical fiber based on multi-scale 1-D CNN. Opto-Electron Eng, 2019, 46: 180493

    Google Scholar 

  18. Wu H, Yang M, Yang S, et al. A novel DAS signal recognition method based on spatiotemporal information extraction with 1DCNNs-BiLSTM network. IEEE Access, 2020, 8: 119448

    Article  Google Scholar 

  19. Tian M, Dong H, Cao X, et al. Temporal convolution network with a dual attention mechanism for ϕ-OTDR event classification. Appl Opt, 2022, 61: 5951–5956

    Article  ADS  CAS  PubMed  Google Scholar 

  20. Tian M, Dong H, Yu K. Attention based Temporal convolutional network for ΦOTDR event classification. In: Proceedings of the 19th International Conference on Optical Communications and Networks (ICOCN), Qufu, 2021. 1–3

  21. Yang Y, Zhang H, Li Y. Long-distance pipeline safety early warning: a distributed optical fiber sensing semi-supervised learning method. IEEE Sens J, 2021, 21: 19453–19461

    Article  ADS  Google Scholar 

  22. He J, Hu X, Zhang D, et al. Semi-supervised learning for optical fiber sensor road intrusion signal detection. Appl Opt, 2022, 61: C65

    Article  ADS  PubMed  Google Scholar 

  23. Wang S, Liu F, Liu B. Semi-supervised deep learning in high-speed railway track detection based on distributed fiber acoustic sensing. Sensors, 2022, 22: 413

    Article  ADS  CAS  PubMed  PubMed Central  Google Scholar 

  24. Cao X. Recognition of ΦOTDR disturbed signal based on semi-supervised learning. Dissertation for the Master’s Degree. Beijing: Beijing Jiaotong University, 2023

    Google Scholar 

  25. Bachman P, Alsharif O, Precup D. Learning with pseudo-ensembles. In: Proceedings of the 27th International Conference on Neural Information Processing Systems, 2014. 3365–3373

  26. Lee D H. Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: Proceedings of Workshop on Challenges in Representation Learning, 2013

  27. Li Z, Ko B, Choi H. Pseudo-labeling using Gaussian process for semi-supervised deep learning. In: Proceedings of IEEE International Conference on Big Data and Smart Computing (BigComp), Shanghai, 2018. 263–269

  28. Wu H, Prasad S. Semi-supervised deep learning using pseudo labels for hyperspectral image classification. IEEE Trans Image Process, 2017, 27: 1259–1270

    Article  ADS  MathSciNet  Google Scholar 

  29. Rasmus A, Berglund M, Honkala M, et al. Semi-supervised learning with ladder networks. In: Proceedings of the 28th International Conference on Neural Information Processing Systems, 2015

  30. Laine S, Aila T. Temporal ensembling for semi-supervised learning. In: Proceedings of International Conference on Learning Representation (ICLR), 2016

  31. Tarvainen A, Valpola H. Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017

  32. Hu J, Shen L, Albanie S, et al. Squeeze-and-excitation networks. IEEE Trans Pattern Anal Mach Intell, 2020, 42: 2011–2023

    Article  PubMed  Google Scholar 

  33. Woo S, Park J, Lee J Y, et al. CBAM: convolutional block attention module. In: Proceedings of 15th European Conference, 2018. 3–19

  34. Cao X, Su Y, Jin Z, et al. An open dataset of φ-OTDR events with two classification models as baselines. Results Opt, 2023, 10: 100372

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported in part by Fundamental Research Funds for Central Universities (Grant No. 021314380211), National Key Research and Development Program of China (Grant No. 2021YFB2900704), and Outstanding Chinese and Foreign Youth Exchange Program of China Association for Science and Technology. We are especially grateful to Ms. Manling TIAN, whose previous research on the semi-supervised model provided strong support for our research in this paper. At the same time, we would like to thank Ms. Shuman SUN for her help in setting 2D-CNN model’s parameters.

Author information

Authors and Affiliations

  1. Institute of Information Science, School of Computer and Information Technology, Beijing Jiaotong University, Beijing, 100044, China

    Yujiao Li, Xiaomin Cao, Wenhao Ni & Kuanglu Yu

  2. Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing Jiaotong University, Beijing, 100044, China

    Yujiao Li, Xiaomin Cao, Wenhao Ni & Kuanglu Yu

Authors
  1. Yujiao Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xiaomin Cao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Wenhao Ni
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Kuanglu Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Kuanglu Yu.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, Y., Cao, X., Ni, W. et al. A deep learning model enabled multi-event recognition for distributed optical fiber sensing. Sci. China Inf. Sci. 67, 132404 (2024). https://doi.org/10.1007/s11432-023-3896-4

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11432-023-3896-4

Keywords

Search

Navigation