Robust Vector BOTDA Signal Processing with Probabilistic Machine Learning

This paper presents a novel probabilistic machine learning (PML) framework to estimate the Brillouin frequency shift (BFS) from both Brillouin gain and phase spectra of a vector Brillouin optical time-domain analysis (VBOTDA). The PML framework is used to predict the Brillouin frequency shift (BFS) along the fiber and to assess its predictive uncertainty. We compare the predictions obtained from the proposed PML model with a conventional curve fitting method and evaluate the BFS uncertainty and data processing time for both methods. The proposed method is demonstrated using two BOTDA systems: (i) a BOTDA system with a 10 km sensing fiber and (ii) a vector BOTDA with a 25 km sensing fiber. The PML framework provides a pathway to enhance the VBOTDA system performance.

[1]  Hua Zheng,et al.  Deep Learning Enhanced Long-Range Fast BOTDA for Vibration Measurement , 2022, Journal of Lightwave Technology.

[2]  Kevin P. Chen,et al.  Recent Advances in Machine Learning for Fiber Optic Sensor Applications , 2021, Adv. Intell. Syst..

[3]  A. Pázman,et al.  Nonlinear Regression , 2020, Statistical Learning with Math and R.

[4]  Thomas Schneider,et al.  Characterization of the Noise Induced by Stimulated Brillouin Scattering in Distributed Sensing , 2020, Sensors.

[5]  Nageswara Lalam,et al.  Raman-assisted BOTDA performance improvement with the differential pulse-width pair technique and an artificial neural network based fitting algorithm , 2020 .

[6]  Changyuan Yu,et al.  Robust and Fast Temperature Extraction for Brillouin Optical Time-Domain Analyzer by Using Denoising Autoencoder-Based Deep Neural Networks , 2020, IEEE Sensors Journal.

[7]  Lijuan Zhao,et al.  Selection of spectrum model in estimation of Brillouin frequency shift for distributed optical fiber sensor , 2019 .

[8]  Nageswara Lalam,et al.  Distributed optical fiber sensing: Review and perspective , 2019, Applied Physics Reviews.

[9]  W. Pan,et al.  Efficient Demodulation of Brillouin Phase Spectra and Performance Enhancement in BOTDA Incorporating Phase Noise Elimination , 2019, Journal of Lightwave Technology.

[10]  Sebastian Nowozin,et al.  Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift , 2019, NeurIPS.

[11]  Ming Tang,et al.  Real-Time Denoising of Brillouin Optical Time Domain Analyzer With High Data Fidelity Using Convolutional Neural Networks , 2019, Journal of Lightwave Technology.

[12]  Bo Liu,et al.  Vector Brillouin optical time-domain analysis with Raman amplification and optical pulse coding , 2019, OPTO.

[13]  Changyuan Yu,et al.  Deep neural networks assisted BOTDA for simultaneous temperature and strain measurement with enhanced accuracy. , 2019, Optics express.

[14]  Lijuan Zhao,et al.  Key Parameter Extraction for Fiber Brillouin Distributed Sensors Based on the Exact Model , 2018, Sensors.

[15]  Cicero Martelli,et al.  NARX neural network model for strong resolution improvement in a distributed temperature sensor. , 2018, Applied optics.

[16]  T. Chen,et al.  Multi point strain and temperature sensing based on Brillouin optical time domain reflectometry , 2018, 2018 11th International Symposium on Communication Systems, Networks & Digital Signal Processing (CSNDSP).

[17]  Wai Pang Ng,et al.  Performance Improvement of Brillouin Ring Laser Based BOTDR System Employing a Wavelength Diversity Technique , 2018, Journal of Lightwave Technology.

[18]  Xizhao Wang,et al.  A review on neural networks with random weights , 2018, Neurocomputing.

[19]  Chester Shu,et al.  Support vector machine assisted BOTDA utilizing combined Brillouin gain and phase information for enhanced sensing accuracy. , 2017, Optics express.

[20]  Chao Lu,et al.  Temperature extraction in Brillouin optical time-domain analysis sensors using principal component analysis based pattern recognition. , 2017, Optics express.

[21]  Songnian Fu,et al.  BOTDA using channel estimation with direct-detection optical OFDM technique. , 2017, Optics express.

[22]  Qi An,et al.  High-accuracy Brillouin frequency shift measurement system based on stimulated Brillouin scattering phase shift , 2017 .

[23]  Moshe Tur,et al.  Analytical expression and experimental validation of the Brillouin gain spectral broadening at any sensing spatial resolution , 2017, 2017 25th Optical Fiber Sensors Conference (OFS).

[24]  Charles Blundell,et al.  Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles , 2016, NIPS.

[25]  Luc Thévenaz,et al.  Evaluation of the accuracy of BOTDA systems based on the phase spectral response. , 2016, Optics express.

[26]  Marcelo A. Soto,et al.  Gain vs phase in BOTDA setups , 2016, European Workshop on Optical Fibre Sensors.

[27]  Chao Lu,et al.  Signal processing using artificial neural network for BOTDA sensor system. , 2016, Optics express.

[28]  Marcelo A. Soto,et al.  Sources of noise in Brillouin optical time-domain analyzers , 2015, International Conference on Optical Fibre Sensors.

[29]  Yonas Muanenda,et al.  Long-range accelerated BOTDA sensor using adaptive linear prediction and cyclic coding. , 2014, Optics letters.

[30]  Wei Chen,et al.  Vector Brillouin Optical Time-Domain Analysis With Heterodyne Detection and IQ Demodulation Algorithm , 2014, IEEE Photonics Journal.

[31]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[32]  Luc Thévenaz,et al.  Modeling and evaluating the performance of Brillouin distributed optical fiber sensors. , 2013, Optics express.

[33]  Yanjun Zhang,et al.  A novel fitting algorithm for Brillouin scattering spectrum of distributed sensing systems based on RBFN networks , 2013 .

[34]  Johan A. K. Suykens,et al.  Confidence bands for least squares support vector machine classifiers: A regression approach , 2012, Pattern Recognit..

[35]  Liang Chen,et al.  Recent Progress in Brillouin Scattering Based Fiber Sensors , 2011, Sensors.

[36]  Michel Dossou,et al.  Vector Brillouin optical time-domain analyzer for high-order acoustic modes. , 2010, Optics letters.

[37]  Kevin P. Chen,et al.  Enhanced Signal Processing of Distributed Brillouin Fiber Sensors using a Decoupled Radial Basis Function Network , 2021, Optical Fiber Sensors Conference 2020 Special Edition.

[38]  Yarin Gal,et al.  Uncertainty in Deep Learning , 2016 .

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

[40]  David Hinkley,et al.  Bootstrap Methods: Another Look at the Jackknife , 2008 .

[41]  A. Weigend,et al.  Estimating the mean and variance of the target probability distribution , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).