Early Safety Warnings for Long-Distance Pipelines: A Distributed Optical Fiber Sensor Machine Learning Approach

Automated pipeline safety early warning (PSEW) systems are designed to automatically identify and locate third-party damage events on oil and gas pipelines. They are intended to replace traditional, inefficient manual inspection methods. However, current PSEW methods cannot achieve universality for various complex environments because they are sensitive to the spatiotemporal stability of the signal obtained by its distributed sensors at various locations and times. Our research aimed to improve the accuracy of long-distance oil– gas PSEW systems through machine learning. In this paper, we propose a novel real-time action recognition method for long-distance PSEW systems based on a coherent Rayleigh scattering distributed optical fiber sensor. More specifically, we put forward two complementary feature calculation methods to describe signals and build a new action recognition deep learning network based on those features. Encouraging empirical results on the data collected at a real location confirm that the features can effectively describe signals in an environment with strong noise and weak signals, and the entire approach can identify and locate third-party damage events quickly under various hardware conditions with accuracies of 99.26% (500 Hz) and 97.20% (100 Hz). More generically, our method can be applied to other fields as well.

[1]  Arnold W. M. Smeulders,et al.  Timeception for Complex Action Recognition , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Yong Qin,et al.  Understanding and Learning Discriminant Features based on Multiattention 1DCNN for Wheelset Bearing Fault Diagnosis , 2020, IEEE Transactions on Industrial Informatics.

[3]  Jürgen Schmidhuber,et al.  LSTM: A Search Space Odyssey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[4]  Bo Yu,et al.  Convolutional Neural Networks for human activity recognition using mobile sensors , 2014, 6th International Conference on Mobile Computing, Applications and Services.

[5]  Wei Liang,et al.  Risk identification of third-party damage on oil and gas pipelines through the Bayesian network , 2018, Journal of Loss Prevention in the Process Industries.

[6]  Naila Murray,et al.  Generalized Max Pooling , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Yao Xiao,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 , 2019, Journal of Lightwave Technology.

[8]  Dianhui Wang,et al.  Stochastic Configuration Networks: Fundamentals and Algorithms , 2017, IEEE Transactions on Cybernetics.

[9]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[10]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[11]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[12]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[13]  Qing Lei,et al.  A Comprehensive Survey of Vision-Based Human Action Recognition Methods , 2019, Sensors.

[14]  David John Hill,et al.  Distributed fibre optic sensors for pipeline protection , 2009 .

[15]  Jun Li,et al.  Signal Analysis of Distributed Optic-Fiber Sensing Used for Oil and Gas Pipeline Monitoring , 2019, SSPS 2019.

[16]  Hongbin Sun,et al.  A novel data-driven approach for transient stability prediction of power systems considering the operational variability , 2019, International Journal of Electrical Power & Energy Systems.

[17]  Forrest N. Iandola,et al.  SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size , 2016, ArXiv.

[18]  Dezhi Han,et al.  Events detection and recognition by the fiber vibration system based on power spectrum estimation , 2018 .

[19]  Jian Sun,et al.  Identity Mappings in Deep Residual Networks , 2016, ECCV.

[20]  Weiwei Kong,et al.  Model building and simulation for intelligent early warning of long-distance oil & gas storage and transportation pipelines based on the probabilistic neural network , 2020 .

[21]  Jian Tang,et al.  Signal Status Recognition Based on 1DCNN and Its Feature Extraction Mechanism Analysis , 2019, Sensors.

[22]  Razvan Pascanu,et al.  On the difficulty of training recurrent neural networks , 2012, ICML.

[23]  Huijuan Wu,et al.  Feature extraction and identification in distributed optical-fiber vibration sensing system for oil pipeline safety monitoring , 2017, Photonic Sensors.

[24]  Rehan Sadiq,et al.  A fuzzy Bayesian belief network for safety assessment of oil and gas pipelines , 2016 .

[25]  Yuan Zhang,et al.  Optical fiber intrusion signal recognition method based on TSVD-SCN , 2019, Optical Fiber Technology.

[26]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[27]  Fei Jiang,et al.  An event recognition method for fiber distributed acoustic sensing systems based on the combination of MFCC and CNN , 2018, International Conference on Optical Instruments and Technology.

[28]  Liang Chen,et al.  Recent Progress in Distributed Fiber Optic Sensors , 2012, Sensors.

[29]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[30]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[31]  Lu Zhao,et al.  Optical Fiber Intrusion Signal Recognition Based on Improved Mel Frequency Cepstrum Coefficient , 2018, 2018 11th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI).

[32]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[33]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Sheng Huang,et al.  Distributed fiber sensor and machine learning data analytics for pipeline protection against extrinsic intrusions and intrinsic corrosions. , 2020, Optics express.