Comparative Analysis on the Deployment of Machine Learning Algorithms in the Distributed Brillouin Optical Time Domain Analysis (BOTDA) Fiber Sensor

This paper demonstrates a comparative analysis of five machine learning (ML) algorithms for improving the signal processing time and temperature prediction accuracy in Brillouin optical time domain analysis (BOTDA) fiber sensor. The algorithms analyzed were generalized linear model (GLM), deep learning (DL), random forest (RF), gradient boosted trees (GBT), and support vector machine (SVM). In this proof-of-concept experiment, the performance of each algorithm was investigated by pairing Brillouin gain spectrum (BGS) with its corresponding temperature reading in the training dataset. It was found that all of the ML algorithms have significantly reduced the signal processing time to be between 3.5 and 655 times faster than the conventional Lorentzian curve fitting (LCF) method. Furthermore, the temperature prediction accuracy and temperature measurement precision made by some algorithms were comparable, and some were even better than the conventional LCF method. The results obtained from the experiments would provide some general idea in deploying ML algorithm for characterizing the Brillouin-based fiber sensor signals.

[1]  Luc Thévenaz,et al.  Measurement of the distributed-Brillouingain spectrum in optical fibers by using a single laser source , 1994 .

[2]  Yongqian Li,et al.  Fitting of Brillouin Spectrum Based on LabVIEW , 2009, 2009 5th International Conference on Wireless Communications, Networking and Mobile Computing.

[3]  Ingo Mierswa,et al.  YALE: rapid prototyping for complex data mining tasks , 2006, KDD '06.

[4]  T. Horiguchi,et al.  BOTDA-nondestructive measurement of single-mode optical fiber attenuation characteristics using Brillouin interaction: theory , 1989 .

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

[6]  Eric R. Ziegel,et al.  Generalized Linear Models , 2002, Technometrics.

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

[8]  T. Horiguchi,et al.  The use of Walsh code in modulating the pump light of high spatial resolution phase-shift-pulse Brillouin optical time domain analysis with non-return-to-zero pulses , 2013 .

[9]  M. Newville,et al.  Lmfit: Non-Linear Least-Square Minimization and Curve-Fitting for Python , 2014 .

[10]  Jose Miguel Lopez-Higuera,et al.  Simultaneous Temperature and Strain Discrimination in a Conventional BOTDA via Artificial Neural Networks , 2018, Journal of Lightwave Technology.

[11]  Jose M. Lopez-Higuera,et al.  Brillouin Distributed Fiber Sensors: An Overview and Applications , 2012, J. Sensors.

[12]  Yuanhong Yang,et al.  Application of Levenberg-Marquardt algorithm in the Brillouin spectrum fitting , 2008, International Symposium on Instrumentation and Control Technology.

[13]  J. López-Higuera,et al.  Automatic strain detection in a Brillouin Optical Time Domain sensor using Principal Component Analysis and Artificial Neural Networks , 2014, IEEE SENSORS 2014 Proceedings.

[14]  Nazlia Omar,et al.  Study on feature selection and machine learning algorithms for Malay sentiment classification , 2014, Proceedings of the 6th International Conference on Information Technology and Multimedia.

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

[16]  T. Horiguchi,et al.  A Dual Golay Complementary Pair of Sequences for Improving the Performance of Phase-Shift Pulse BOTDA Fiber Sensor , 2012, Journal of Lightwave Technology.

[17]  C. Lu,et al.  Temperature profile extraction using artificial neural network in BOTDA sensor system , 2015, 2015 Opto-Electronics and Communications Conference (OECC).

[18]  Chao Lu,et al.  Temperature sensing in BOTDA system by using artificial neural network , 2015 .

[19]  P. Krippner,et al.  Distributed Temperature Sensing: Review of Technology and Applications , 2012, IEEE Sensors Journal.

[20]  T. Horiguchi,et al.  Distributed-temperature sensing using stimulated Brillouin scattering in optical silica fibers. , 1990, Optics letters.

[21]  A. Piccolo,et al.  Feasibility study of strain and temperature discrimination in a BOTDA system via artificial neural networks , 2017, 2017 25th Optical Fiber Sensors Conference (OFS).

[22]  Yongqian Li,et al.  Temperature extraction for Brillouin optical fiber sensing system based on extreme learning machine , 2019 .

[23]  Nur Dalilla Nordin,et al.  Generalized linear model for enhancing the temperature measurement performance in Brillouin optical time domain analysis fiber sensor , 2020 .

[24]  Toshio Kurashima,et al.  Measurement of temperature and strain distribution by Brillouin frequency shift in silica optical fibers , 1993, Other Conferences.

[25]  Shahnorbanun Sahran,et al.  Breast cancer mass localization based on machine learning , 2014, 2014 IEEE 10th International Colloquium on Signal Processing and its Applications.

[26]  M. A. Farahani,et al.  Accurate estimation of Brillouin frequency shift in Brillouin optical time domain analysis sensors using cross correlation. , 2011, Optics letters.

[27]  M. Tur,et al.  [INVITED] State of the art of Brillouin fiber-optic distributed sensing , 2016 .

[28]  Changyuan Yu,et al.  Brillouin optical time domain analyzer enhanced by artificial/deep neural networks , 2017, 2017 16th International Conference on Optical Communications and Networks (ICOCN).

[29]  Zhongyu Wang,et al.  Seventh International Symposium on Instrumentation and Control Technology: Optoelectronic Technology and Instruments, Control Theory and Automation, and Space Exploration , 2008 .

[30]  Zhiyong Zhao,et al.  Support Vector Machine based Differential Pulse-width Pair Brillouin Optical Time Domain Analyzer , 2018, IEEE Photonics Journal.

[31]  Mohsen Amiri Farahani,et al.  A Detailed Evaluation of the Correlation-Based Method Used for Estimation of the Brillouin Frequency Shift in BOTDA Sensors , 2013, IEEE Sensors Journal.

[32]  Songnian Fu,et al.  Distributed Brillouin frequency shift extraction via a convolutional neural network , 2020, 2001.03030.

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

[34]  Weiping Liu,et al.  Fast Frame Synchronization Design and FPGA Implementation in SF-BOTDA , 2020 .

[35]  Yongqian Li,et al.  Optimized neural network for temperature extraction from Brillouin scattering spectra , 2020 .

[36]  David J. Webb,et al.  Recent progress in distributed fiber optic sensors based upon Brillouin scattering , 1995, Other Conferences.

[37]  K. Shimizu,et al.  Development of a distributed sensing technique using Brillouin scattering , 1995 .

[38]  Salina Abdul Samad,et al.  Evaluation of face recognition system using Support Vector Machine , 2009, 2009 IEEE Student Conference on Research and Development (SCOReD).

[39]  Nazlia Omar,et al.  Experiments on the Use of Feature Selection and Machine Learning Methods in Automatic Malay Text Categorization , 2013 .