基于云边协同与深度学习的长输管道分布式光纤智能预警系统研究
Research on Distributed Fiber-Optic Intelligent Early Warning System for Long-Distance Pipelines Based on Cloud-Edge Collaboration and Deep Learning
摘要: 针对长输管道沿线外力破坏、车辆扰动、施工活动与复杂环境噪声交织导致的预警不及时、误报率高和定位偏差问题，本文提出一种基于云边协同与深度学习的分布式光纤智能预警系统。系统采用φ-OTDR实现沿线振动连续感知，在边缘端完成解调、降噪、事件触发与本地初判，在云端完成模型训练、GIS联动、样本复核与版本管理。算法上，采用小波包分解增强破土冲击频段，构建多尺度1D-CNN-BiLSTM-Attention模型识别机械破土、人工敲击、车辆经过、人员走动和环境干扰等事件，并利用光学里程–管道桩号–GIS坐标映射矩阵修正余缆和盘缆引起的定位畸变。现场样本验证表明，该方案能够降低无效数据回传量，缩短告警链路时延，并为长输管道巡检处置提供可定位、可复核的事件证据。
Abstract: To improve early warning reliability for long-distance pipelines exposed to excavation, traffic interference, construction activities and non-stationary environmental noise, this paper proposes a distributed fiber-optic intelligent warning system based on cloud-edge collaboration and deep learning. Phase-sensitive optical time-domain reflectometry is used for continuous vibration sensing along the pipeline. Edge nodes perform demodulation, denoising, event triggering and local inference, while the cloud platform supports model training, GIS linkage, sample review and version management. Wavelet packet decomposition is adopted to enhance impact-related frequency bands, and a multi-scale 1D-CNN-BiLSTM-Attention model is designed for event classification. A dynamic mapping matrix between optical distance, pipeline stake number and GIS coordinates is further introduced to compensate localization errors caused by fiber coils and redundant cable sections. Field-oriented evaluation indicates that the framework reduces invalid uplink traffic, shortens warning latency and provides traceable evidence for pipeline inspection and emergency response.
文章引用：史峰旭, 冯文娟. 基于云边协同与深度学习的长输管道分布式光纤智能预警系统研究[J]. 石油天然气学报, 2026, 48(3): 469-479. https://doi.org/10.12677/jogt.2026.483051

参考文献

[1] 吴德胜. 管道完整性管理[M]. 北京: 石油工业出版社, 2018.
[2] Hartog, A.H. (2017) An Introduction to Distributed Optical Fibre Sensors. CRC Press.
[3] Rao, Y.J., Wang, Z.N., Wu, H.J., Ran, Z.L. and Han, B. (2021) Recent Advances in Phase-Sensitive Optical Time Domain Reflectometry (φ-OTDR). Photonic Sensors, 11, 1-30.
https://doi.org/10.1007/s13320-021-0619-4
[4] Zhu, H.H., Liu, W., Wang, T., Su, J.W. and Shi, B. (2022) Distributed Acoustic Sensing for Monitoring Linear Infrastructures: Current Status and Trends. Sensors, 22, 7550.
https://doi.org/10.3390/s22197550
[5] Lu, Y., Zhu, T., Chen, L. and Bao, X. (2010) Distributed Vibration Sensor Using Coherent Detection of Phase-OTDR. Journal of Lightwave Technology, 28, 3243-3249.
[6] Tejedor, J., Macias-Guarasa, J., Martins, H., Pastor-Graells, J., Corredera, P. and Martin-Lopez, S. (2017) Machine Learning Methods for Pipeline Surveillance Systems Based on Distributed Acoustic Sensing: A Review. Applied Sciences, 7, Article 841.
https://doi.org/10.3390/app7080841
[7] Bublin, M. (2021) Event Detection for Distributed Acoustic Sensing: Combining Knowledge-Based, Classical Machine Learning, and Deep Learning Approaches. Sensors, 21, Article 7527.
https://doi.org/10.3390/s21227527
[8] Barantsov, I.A., Pnev, A.B., Koshelev, K.I., Tynchenko, V.S., Nelyub, V.A. and Borodulin, A.S. (2023) Classification of Acoustic Influences Registered with Phase-Sensitive OTDR Using Pattern Recognition Methods. Sensors, 23, Article 582.
https://doi.org/10.3390/s23020582
[9] Jiang, F., Zhang, Z.H., Lu, Z.X., Li, H.L., Tian, Y.H., Zhang, Y.X., et al. (2021) High-Fidelity Acoustic Signal Enhancement for Phase-OTDR Using Supervised Learning. Optics Express, 29, 33467-33480.
https://doi.org/10.1364/oe.439646
[10] Muñoz, F. and Soto, M.A. (2022) Enhancing Fibre-Optic Distributed Acoustic Sensing Capabilities with Blind Near-Field Array Signal Processing. Nature Communications, 13, Article No. 4019.
https://doi.org/10.1038/s41467-022-31681-x
[11] Lindsey, N.J., Martin, E.R., Dreger, D.S., Freifeld, B., Cole, S., James, S.R., et al. (2017) Fiber‐Optic Network Observations of Earthquake Wavefields. Geophysical Research Letters, 44, 11792-11799.
https://doi.org/10.1002/2017gl075722
[12] Williams, E.F., Fernández-Ruiz, M.R., Magalhaes, R., Vanthillo, R., Zhan, Z., González-Herráez, M., et al. (2019) Distributed Sensing of Microseisms and Teleseisms with Submarine Dark Fibers. Nature Communications, 10, Article No. 5778.
https://doi.org/10.1038/s41467-019-13262-7
[13] Jousset, P., Currenti, G., Schwarz, B., Chalari, A., Tilmann, F., Reinsch, T., et al. (2022) Fibre Optic Distributed Acoustic Sensing of Volcanic Events. Nature Communications, 13, Article No. 1753.
https://doi.org/10.1038/s41467-022-29184-w
[14] Donoho, D.L. and Johnstone, I.M. (1994) Ideal Spatial Adaptation by Wavelet Shrinkage. Biometrika, 81, 425-455.
https://doi.org/10.1093/biomet/81.3.425
[15] Donoho, D.L. (1995) De-Noising by Soft-Thresholding. IEEE Transactions on Information Theory, 41, 613-627.
https://doi.org/10.1109/18.382009
[16] Michau, G., Frusque, G. and Fink, O. (2022) Fully Learnable Deep Wavelet Transform for Unsupervised Monitoring of High-Frequency Time Series. Proceedings of the National Academy of Sciences of the United States of America, 119, e2106598119.
https://doi.org/10.1073/pnas.2106598119
[17] LeCun, Y., Bengio, Y. and Hinton, G. (2015) Deep Learning. Nature, 521, 436-444.
https://doi.org/10.1038/nature14539
[18] Hochreiter, S. and Schmidhuber, J. (1997) Long Short-Term Memory. Neural Computation, 9, 1735-1780.
https://doi.org/10.1162/neco.1997.9.8.1735
[19] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L. and Polosukhin, I. (2017) Attention Is All You Need. Advances in Neural Information Processing Systems 2017, Long Beach, 4-9 December 2017, 5998-6008.
[20] Lim, B. and Zohren, S. (2021) Time-Series Forecasting with Deep Learning: A Survey. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 379, Article ID: 20200209.
https://doi.org/10.1098/rsta.2020.0209
[21] Zeng, A., Chen, M., Zhang, L. and Xu, Q. (2023) Are Transformers Effective for Time Series Forecasting? Proceedings of the AAAI Conference on Artificial Intelligence, 37, 11121-11128.
https://doi.org/10.1609/aaai.v37i9.26317
[22] Shi, W., Cao, J., Zhang, Q., Li, Y. and Xu, L. (2016) Edge Computing: Vision and Challenges. IEEE Internet of Things Journal, 3, 637-646.
https://doi.org/10.1109/jiot.2016.2579198
[23] Satyanarayanan, M. (2017) The Emergence of Edge Computing. Computer, 50, 30-39.
https://doi.org/10.1109/mc.2017.9
[24] Liang, F., Yu, W., Liu, X., Griffith, D. and Golmie, N. (2020) Toward Edge-Based Deep Learning in Industrial Internet of Things. IEEE Internet of Things Journal, 7, 4329-4341.
https://doi.org/10.1109/jiot.2019.2963635
[25] Bao, G. and Guo, P. (2022) Federated Learning in Cloud-Edge Collaborative Architecture: Key Technologies, Applications and Challenges. Journal of Cloud Computing, 11, Article No. 94.
https://doi.org/10.1186/s13677-022-00377-4
[26] OASIS (2019) MQTT Version 5.0: OASIS Standard.