ABSTRACT
Accurate and effective identification of multi-vibration events detected based on the phase-sensitive optical time-domain reflectometer (Φ-OTDR) is an effective method to achieve precise alarm. This study proposes a real-time classification method of Φ-OTDR multi-vibration events based on the combination of convolutional neural network (CNN), bi-directional long short-term memory network (Bi-LSTM) and connectionist temporal classification (CTC), which can quickly and effectively identify the type and number of vibrations contained in the data image when multiple vibration signals are present in a single image, and manual alignment is not required for model training. Noncoherent integration and pulse cancellers are used for raw signal processing to generate spatio-temporal images. CNN is used to extract spatial dimensional features in spatio-temporal images, Bi-LSTM extracts temporal dimensional correlation features, and the hybrid features are automatically aligned with the labels by CTC. A dataset of 8,000 vibration images containing 17,589 abnormal vibration events is collected for model training, validation and testing. Experiments show that the recognition model C3B3 trained with this method can achieve 210 FPS and 99.62% F1 score on the test set. The system can achieve the real-time classification of multiple vibration targets at the perimeter of high-speed railway and effectively reduce the false alarm rate of the system.
- Liu, Shuaiqi, Yu, Feihong, Hong, Rui, Xu, Weijie, Shao, Liyang, and Wang, Feng, 2022. Advances in phase-sensitive optical time-domain reflectometry. Opto-Electronic Advances 5, 3, 200078. http://dx.doi.org/10.29026/oea.2022.200078.Google ScholarCross Ref
- Wang, Shulun, Liu, Feng, and Liu, Bin, 2021. Research on application of deep convolutional network in high-speed railway track inspection based on distributed fiber acoustic sensing. Optics Communications 492(Aug 1), 126981. http://dx.doi.org/10.1016/j.optcom.2021.126981.Google ScholarCross Ref
- Li, Gang, Zeng, Kehong, Zhou, Bin, Yang, Wenming, Lin, Xiaohui, Wang, Fei, Chen, Yun, Ji, Xutao, Zheng, Dahai, and Mao, Barerem-Melgueba, 2021. Vibration monitoring for the West-East Gas Pipeline Project of China by phase optical time domain reflectometry (phase-OTDR). Instrumentation Science & Technology 49, 1 (2021/01/02), 65-80. http://dx.doi.org/10.1080/10739149.2020.1780253.Google ScholarCross Ref
- Li, Z., Zhang, J., Wang, M., Chai, J., Wu, Y, and Peng, F., 2020. An anti-noise -OTDR based distributed acoustic sensing system for high-speed railway intrusion detection. Laser Physics 30, 8, 085103. http://dx.doi.org/https://doi.org/10.1088/1555-6611/ab9119.Google ScholarCross Ref
- Wang, Z., Lou, S., Liang, S., and Sheng, X., 2020. Multi-class Disturbance Events Recognition Based on EMD and XGBoost in ϕ-OTDR. IEEE Access 8, 63551 - 63558. http://dx.doi.org/https://doi.org/10.1109/ACCESS.2020.2984022.Google ScholarCross Ref
- Tejedor, Javier, Macias-Guarasa, Javier, Martins, Hugo, Martin-Lopez, Sonia, and Gonzalez-Herraez, Miguel, 2019. A Contextual GMM-HMM Smart Fiber Optic Surveillance System for Pipeline Integrity Threat Detection. Journal of Lightwave Technology 37, 18, 4514-4522. http://dx.doi.org/https://doi.org/10.1109/JLT.2019.2908816.Google ScholarCross Ref
- Soriano-Amat, Miguel, Martins, Hugo F., Durán, Vicente, Martin-Lopez, Sonia, Gonzalez-Herraez, Miguel, and Fernández-Ruiz, María R., 2021. Quadratic phase coding for SNR improvement in time-expanded phase-sensitive OTDR. Optics Letters 46, 17, 4406-4409. http://dx.doi.org/10.1364/ol.432350.Google ScholarCross Ref
- Adeel, M., Shang, C., Zhu, K., and Lu, C., 2019. Nuisance alarm reduction:Using a correlation based algorithm above differential signals in direct detected phase-OTDR systems. Optics Express 27, 5, 7685-7698. http://dx.doi.org/https://doi.org/10.1364/OE.27.007685.Google ScholarCross Ref
- Wu, Huijuan, Qian, Ya, Zhang, Wei, and Tang, Chenghao, 2017. Feature Extraction and Identification in Distributed Optical-Fiber Vibration Sensing System for Oil Pipeline Safety Monitoring. Photonic Sensors 7, 4 (Dec), 305-310. http://dx.doi.org/10.1007/s13320-017-0360-1.Google ScholarCross Ref
- Sun, Qian, Feng, Hao, Yan, Xueying, and Zeng, Zhoumo, 2015. Recognition of a Phase-Sensitivity OTDR Sensing System Based on Morphologic Feature Extraction. Sensors 15, 7 (Jul), 15179-15197. http://dx.doi.org/10.3390/s150715179.Google ScholarCross Ref
- Yang, Nachuan, Zhao, Yongjun, Chen, Jinyang, and Wang, Fuqiang, 2023. Real-time classification for Φ-OTDR vibration events in the case of small sample size datasets. Optical Fiber Technology 76(2023/03/01/), 103217. http://dx.doi.org/https://doi.org/10.1016/j.yofte.2022.103217.Google ScholarCross Ref
- Shi, Yi, Wang, Yuanye, Zhao, Lei, and Fan, Zhun, 2019. An Event Recognition Method for Φ-OTDR Sensing System Based on Deep Learning. Sensors 19, 15, 3421. http://dx.doi.org/https://doi.org/10.3390/s19153421.Google ScholarCross Ref
- Sun, Qian, Li, Qiaojun, Chen, Lei, Quan, Jianing, and Li, Lvjie, 2020. Pattern recognition based on pulse scanning imaging and convolutional neural network for vibrational events in Φ-OTDR. Optik 219(2020/10/01/), 165205. http://dx.doi.org/https://doi.org/10.1016/j.ijleo.2020.165205.Google ScholarCross Ref
- Li, Zhongqi, Zhang, Jianwei, Wang, Maoning, Zhong, Yuzhong, and Peng, Fei, 2020. Fiber distributed acoustic sensing using convolutional long short-term memory network: a field test on high-speed railway intrusion detection. Optics Express 28, 3 (Feb 3), 2925-2938. http://dx.doi.org/https://doi.org/10.1364/oe.28.002925.Google ScholarCross Ref
- Yang, Nachuan, Zhao, Yongjun, and Chen, Jinyang, 2022. Real-Time Φ-OTDR Vibration Event Recognition Based on Image Target Detection. Sensors 22, 3. http://dx.doi.org/https://doi.org/10.3390/s22031127.Google ScholarCross Ref
- Xu, Weijie, Yu, Feihong, Liu, Shuaiqi, Xiao, Dongrui, Hu, Jie, Zhao, Fang, Lin, Weihao, Wang, Guoqing, Shen, Xingliang, Wang, Weizhi, Wang, Feng, Liu, Huanhuan, Shum, Perry P., and Shao, Liyang, 2022. Real-Time Multi-Class Disturbance Detection for Φ-OTDR Based on YOLO Algorithm. Sensors 22, 5, 1994. http://dx.doi.org/10.3390/s22051994.Google ScholarCross Ref
- Zhang, Jiangwei, Mo, Jiaqing, Ma, Xinrong, Huang, Jincheng, and Song, Fubao, 2022. Optical Fiber Vibration Signal Identification Method Based on Improved YOLOv4. Sensors 22, 23, 9259. http://dx.doi.org/https://doi.org/10.3390/s22239259.Google ScholarCross Ref
- Graves, Alex, Fernández, Santiago, Gomez, Faustino, and Schmidhuber, Jürgen, 2006. Connectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks. In Proceedings of the 23rd International Conference on Machine Learning, A. GRAVES, S. FERNáNDEZ, F. GOMEZ and J. SCHMIDHUBER Eds. Association for Computing Machinery, 369-376. http://dx.doi.org/https://doi.org/10.1145/1143844.1143891.Google ScholarDigital Library
- Lu, Y. L., Zhu, T., Chen, L. A., and Bao, X. Y., 2010. Distributed Vibration Sensor Based on Coherent Detection of Phase-OTDR. Journal of Lightwave Technology 28, 22 (Nov), 3243-3249. http://dx.doi.org/https://doi.org/10.1109/jlt.2010.2078798.Google ScholarCross Ref
- Krizhevsky, Alex, Sutskever, Ilya, and Hinton, Geoffrey, 2012. ImageNet Classification with Deep Convolutional Neural Networks. Neural Information Processing Systems 25, 6 (01/01), 84–90. http://dx.doi.org/https://doi.org/10.1145/3065386.Google ScholarDigital Library
- Simonyan, Karen and Zisserman, Andrew, 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv(September 01, 2014), arXiv:1409.1556. http://dx.doi.org/https://doi.org/10.48550/arXiv.1409.1556.Google ScholarCross Ref
- Ioffe, Sergey and Szegedy, Christian, 2015. Batch normalization: accelerating deep network training by reducing internal covariate shift. In Proceedings of the 32nd International Conference on International Conference on Machine Learning, S. IOFFE and C. SZEGEDY Eds. JMLR.org, Lille, France, 448–456.Google Scholar
- Badshah, A. M., Ahmad, J., Rahim, N., and Baik, S. W., 2017. Speech Emotion Recognition from Spectrograms with Deep Convolutional Neural Network. In 2017 International Conference on Platform Technology and Service (PlatCon), A.M. BADSHAH, J. AHMAD, N. RAHIM and S.W. BAIK Eds. IEEE, 1-5. http://dx.doi.org/10.1109/PlatCon.2017.7883728.Google ScholarCross Ref
- Pan, Yining, Wen, Tingkun, and Ye, Wei, 2022. Time attention analysis method for vibration pattern recognition of distributed optic fiber sensor. Optik 251(2022/02/01/), 168127. http://dx.doi.org/https://doi.org/10.1016/j.ijleo.2021.168127.Google ScholarCross Ref
- Wu, Huijuan, Yang, Siqi, Liu, Xinyu, Xu, Chenrui, Lu, Hao, Wang, Chaoqun, Qin, Ke, Wang, Zhengning, Rao, Yunjiang, and Olaribigbe, Abdulafeez Olawale, 2021. Simultaneous Extraction of Multi-Scale Structural Features and the Sequential Information With an End-To-End mCNN-HMM Combined Model for Fiber Distributed Acoustic Sensor. Journal of Lightwave Technology 39, 20 (Oct 15), 6606-6616. http://dx.doi.org/https://doi.org/10.1109/jlt.2021.3102265.Google ScholarCross Ref
- He, K., Zhang, X., Ren, S., and Sun, J., 2015. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. In 2015 IEEE International Conference on Computer Vision (ICCV), K. HE, X. ZHANG, S. REN and J. SUN Eds., 1026-1034. http://dx.doi.org/10.1109/ICCV.2015.123.Google ScholarDigital Library
- He, K., Zhang, X., Ren, S., and Sun, J., 2016. Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), K. HE, X. ZHANG, S. REN and J. SUN Eds., 770-778. http://dx.doi.org/https://doi.org/10.1109/CVPR.2016.90.Google ScholarCross Ref
- Lecun, Y., Bottou, L., Bengio, Y., and Haffner, P., 1998. Gradient-based learning applied to document recognition. Proceedings of the IEEE 86, 11, 2278-2324. http://dx.doi.org/https://doi.org/10.1109/5.726791.Google ScholarCross Ref
Index Terms
- Fast Recognition of Distributed Fiber Optic Vibration Sensing Signal based on Machine Vision in High-speed Railway Security
Recommendations
Development of 3GHz Analog Fiber Optic Link for Ultra-fast Signal Transmission
ICICEE '12: Proceedings of the 2012 International Conference on Industrial Control and Electronics EngineeringA broad bandwidth analog fiber optic link is developed for ultra-fast signal transmission under the circumstance with complicated electromagnetic fields. The electrical ultra-fast signal is converted to optical ones by electro-optic conversion method ...
Fiber Optic Sensing Signal Monitoring System Based on FPGA
ICITEE '22: Proceedings of the 5th International Conference on Information Technologies and Electrical EngineeringAt present, the phase monitoring method of optical fiber sensor signal cannot meet the practical application requirements of optical fiber communication. This paper proposes an optical fiber sensor signal monitoring system based on FPGA to solve the ...
Comments