Combining point and distributed strain sensor for complementary data-fusion: A multi-fidelity approach

Abstract The aim of this paper is to develop a complementary data-fusion algorithm for monitoring of the strain over whole structural system. Point strain sensors measure accurate strains (high-accuracy) at discrete measurement positions (low-spatial resolution), while a distributed strain sensor enables a quasi-continuous distributed measurement (high-spatial resolution) with less accurate strains (low-accuracy). This study firstly investigates the complementary data-fusion for the point and distributed strain sensor to combine their advantages in order to obtain the accurate strain distribution (i.e., high-accuracy and high-spatial resolution). For this purpose, a traditional multi-fidelity data-fusion framework can be applied based on Gaussian process regression in the form of auto-regressive scheme. However, the traditional method is not efficient to learn complex cross-correlations. To enable flexible learning for the complex cross-correlations, this study introduces a multi-fidelity data-fusion framework using the input-connected Gaussian process mapping. The numerical and experimental studies demonstrate that the proposed method outperforms the traditional methods with more accurate predictions by using fewer samples for the high-fidelity data. In this context, the proposed method has potential for monitoring the strain distribution over whole structural systems under limited budgets.

[1]  Charles R. Farrar,et al.  The fundamental axioms of structural health monitoring , 2007, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[2]  Sang Bae Lee,et al.  Differential measurement scheme for Brillouin optical correlation domain analysis. , 2012, Optics express.

[3]  Sung-Han Sim,et al.  Traffic Safety Evaluation for Railway Bridges Using Expanded Multisensor Data Fusion , 2016, Comput. Aided Civ. Infrastructure Eng..

[4]  Kun Liu,et al.  Long Measurement Range OFDR Beyond Laser Coherence Length , 2013, IEEE Photonics Technology Letters.

[5]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[6]  Yizheng Chen,et al.  Kilometer-Long Optical Fiber Sensor for Real-Time Railroad Infrastructure Monitoring to Ensure Safe Train Operation , 2015 .

[7]  Bin Xu,et al.  KF-Based Multiscale Response Reconstruction under Unknown Inputs with Data Fusion of Multitype Observations , 2019, Journal of Aerospace Engineering.

[8]  Simon Laflamme,et al.  Reconstruction of unidirectional strain maps via iterative signal fusion for mesoscale structures monitored by a sensing skin , 2018, Mechanical Systems and Signal Processing.

[9]  Dragan Coric,et al.  High-speed internal strain measurements in composite structures under dynamic load using embedded FBG sensors , 2010 .

[10]  Egidio Rizzi,et al.  Effective Heterogeneous Data Fusion procedure via Kalman filtering , 2018 .

[11]  S. Marelli,et al.  The Gaussian Process modelling module in UQLab , 2017, 1709.09382.

[12]  Carl E. Rasmussen,et al.  A Unifying View of Sparse Approximate Gaussian Process Regression , 2005, J. Mach. Learn. Res..

[13]  Rih-Teng Wu,et al.  Data fusion approaches for structural health monitoring and system identification: Past, present, and future , 2018, Structural Health Monitoring.

[14]  Andreas C. Damianou,et al.  Nonlinear information fusion algorithms for data-efficient multi-fidelity modelling , 2017, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[15]  Simon Laflamme,et al.  Fusion of sensor geometry into additive strain fields measured with sensing skin , 2018, Smart Materials and Structures.

[16]  Julián Sierra-Pérez,et al.  In-flight and wireless damage detection in a UAV composite wing using fiber optic sensors and strain field pattern recognition , 2020 .

[17]  Arthur H. Hartog,et al.  An Introduction to Distributed Optical Fibre Sensors , 2017 .

[18]  Feng Li,et al.  A Highly Integrated BOTDA/XFG Sensor on a Single Fiber for Simultaneous Multi-Parameter Monitoring of Slopes , 2019, Sensors.

[19]  B. Soller,et al.  Distributed Strain and Temperature Discrimination in Unaltered Polarization Maintaining Fiber , 2006 .

[20]  Farhad Ansari,et al.  Detection and monitoring of surface micro-cracks by PPP-BOTDA. , 2015, Applied optics.

[21]  Fred W. Glover,et al.  Scatter Search and Local Nlp Solvers: A Multistart Framework for Global Optimization , 2006, INFORMS J. Comput..

[22]  B. Sudret,et al.  Hierarchical Kriging for multi-fidelity aero-servo-elastic simulators-application to extreme loading on wind turbines , 2017 .

[23]  M. S. Safizadeh,et al.  Using multi-sensor data fusion for vibration fault diagnosis of rolling element bearings by accelerometer and load cell , 2014, Inf. Fusion.

[24]  A. O'Hagan,et al.  Bayesian calibration of computer models , 2001 .

[25]  Avishay Eyal,et al.  Distributed acoustic and vibration sensing via optical fractional Fourier transform reflectometry. , 2015, Optics express.

[26]  X. Bao,et al.  Distributed optical fiber vibration sensor based on spectrum analysis of Polarization-OTDR system. , 2008, Optics express.

[27]  Eleni Chatzi,et al.  Online correction of drift in structural identification using artificial white noise observations and an unscented Kalman Filter , 2015 .

[28]  G. Kaklauskas,et al.  Performance of Distributed Optical Fiber Sensors (DOFS) and Digital Image Correlation (DIC) in the monitoring of RC structures , 2019, IOP Conference Series: Materials Science and Engineering.

[29]  Ryan P. Adams,et al.  Avoiding pathologies in very deep networks , 2014, AISTATS.

[30]  Neil A. Hoult,et al.  Distributed Strain Behavior of a Reinforced Concrete Bridge: Case Study , 2014 .

[31]  Wei Pan,et al.  Multiple vibrations measurement using phase-sensitive OTDR merged with Mach-Zehnder interferometer based on frequency division multiplexing. , 2016, Optics express.

[32]  B. Soller,et al.  High resolution optical frequency domain reflectometry for characterization of components and assemblies. , 2005, Optics express.

[33]  Daniele Venturi,et al.  Multifidelity Information Fusion Algorithms for High-Dimensional Systems and Massive Data sets , 2016, SIAM J. Sci. Comput..

[34]  Loic Le Gratiet,et al.  RECURSIVE CO-KRIGING MODEL FOR DESIGN OF COMPUTER EXPERIMENTS WITH MULTIPLE LEVELS OF FIDELITY , 2012, 1210.0686.

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

[36]  A. Zadok,et al.  Random‐access distributed fiber sensing , 2012 .

[37]  Nobuo Takeda,et al.  Temperature-compensated strain measurement using fiber Bragg grating sensors embedded in composite laminates , 2003 .

[38]  Xuping Zhang,et al.  Enhancing the performance of BOTDR based on the combination of FFT technique and complementary coding. , 2017, Optics express.

[39]  Hyung-Jo Jung,et al.  Vibration-based damage detection using online learning algorithm for output-only structural health monitoring , 2018 .

[40]  G. Karniadakis,et al.  Multi-fidelity modelling of mixed convection based on experimental correlations and numerical simulations , 2016, Journal of Fluid Mechanics.

[41]  Kenichi Soga,et al.  Distributed fiber optics sensors for civil engineering infrastructure sensing , 2018 .

[42]  Mark Seaver,et al.  Bragg grating-based fibre optic sensors in structural health monitoring , 2007, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[43]  Nobuo Takeda,et al.  Detecting Water Accumulation in Honeycomb Sandwich Structures by Optical-fiber-based Distributed Temperature Measurement , 2009 .

[44]  Yuan Sun,et al.  Multi-rate data fusion for dynamic displacement measurement of beam-like supertall structures using acceleration and strain sensors , 2020, Structural Health Monitoring.

[45]  António Barrias,et al.  A Review of Distributed Optical Fiber Sensors for Civil Engineering Applications , 2016, Sensors.

[46]  Trevor P. Newson,et al.  A distributed optical fibre dynamic strain sensor based on phase-OTDR , 2013 .

[47]  Richard J. Beckman,et al.  A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output From a Computer Code , 2000, Technometrics.

[48]  Yi Liu,et al.  FBG-based online monitoring for uncertain loading-induced deformation of heavy-duty gantry machine tool base , 2020 .

[49]  Raphael T. Haftka,et al.  Remarks on multi-fidelity surrogates , 2016, Structural and Multidisciplinary Optimization.

[50]  Nobuo Takeda,et al.  Barely visible impact damage detection for composite sandwich structures by optical-fiber-based distributed strain measurement , 2009 .

[51]  Carlos Gil Berrocal,et al.  Distributed Optical Fiber Sensing Bonding Techniques Performance for Embedment inside Reinforced Concrete Structures , 2020, Sensors.

[52]  Bo Li,et al.  Time and Frequency Localized Pulse Shape for Resolution Enhancement in STFT-BOTDR , 2016, J. Sensors.

[53]  Seung-Seop Jin,et al.  Compositional kernel learning using tree-based genetic programming for Gaussian process regression , 2020 .

[54]  Stefano Marelli,et al.  UQLab: a framework for uncertainty quantification in MATLAB , 2014 .

[55]  Paris Perdikaris,et al.  Inferring solutions of differential equations using noisy multi-fidelity data , 2016, J. Comput. Phys..

[56]  G. Karniadakis,et al.  Model inversion via multi-fidelity Bayesian optimization: a new paradigm for parameter estimation in haemodynamics, and beyond , 2016, Journal of The Royal Society Interface.

[57]  Billie F. Spencer,et al.  Visual–inertial displacement sensing using data fusion of vision‐based displacement with acceleration , 2018 .

[58]  Alfredo Güemes,et al.  Optical Fiber Distributed Sensing - Physical Principles and Applications , 2010 .

[59]  Jinping Ou,et al.  Simultaneous measurement of strain and temperature using a hybrid local and distributed optical fiber sensing system , 2014 .

[60]  Seung-Seop Jin,et al.  Accelerating Gaussian Process surrogate modeling using Compositional Kernel Learning and multi-stage sampling framework , 2020, Appl. Soft Comput..

[61]  Kazuo Hotate,et al.  Fiber Distributed Brillouin Sensing with Optical Correlation Domain Techniques , 2013, 2014 Asia Communications and Photonics Conference (ACP).

[62]  Gul Agha,et al.  Structural health monitoring of a cable-stayed bridge using smart sensor technology: deployment and evaluation , 2010 .

[63]  I. N. Shardakov,et al.  Measurement of strains by optical fiber Bragg grating sensors embedded into polymer composite material , 2018 .

[64]  Jianzhi Li,et al.  FBG-Based Positioning Method for BOTDA Sensing , 2016, IEEE Sensors Journal.

[65]  Fakhri Karray,et al.  Multisensor data fusion: A review of the state-of-the-art , 2013, Inf. Fusion.

[66]  Jeong-Rae Cho,et al.  Measurement of Mechanical and Thermal Strains by Optical FBG Sensors Embedded in CFRP Rod , 2019, J. Sensors.

[67]  Romeo Bernini,et al.  High-Spatial Resolution DPP-BOTDA by Real-Time Balanced Detection , 2014, IEEE Photonics Technology Letters.

[68]  Joris Degrieck,et al.  Strain Measurements of Composite Laminates with Embedded Fibre Bragg Gratings: Criticism and Opportunities for Research , 2010, Sensors.

[69]  Haitao Liu,et al.  Cope with diverse data structures in multi-fidelity modeling: A Gaussian process method , 2018, Eng. Appl. Artif. Intell..

[70]  Xingwei Wang,et al.  A review of railway infrastructure monitoring using fiber optic sensors , 2020 .

[71]  Zhenyang Ding,et al.  Distributed Optical Fiber Sensors Based on Optical Frequency Domain Reflectometry: A review , 2018, Sensors.

[72]  Alan J. Rogers,et al.  Distributed optical-fibre sensing , 1999 .

[73]  Zoubin Ghahramani,et al.  Sparse Gaussian Processes using Pseudo-inputs , 2005, NIPS.

[74]  A. Smyth,et al.  Multi-rate Kalman filtering for the data fusion of displacement and acceleration response measurement in dynamic system monitoring , 2007 .

[75]  Andreas Krause,et al.  A tutorial on Gaussian process regression: Modelling, exploring, and exploiting functions , 2016, bioRxiv.

[76]  D. Krohn,et al.  Fiber Optic Sensors: Fundamentals and Applications , 1988 .

[77]  Haitao Liu,et al.  When Gaussian Process Meets Big Data: A Review of Scalable GPs , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[78]  Alexander I. J. Forrester,et al.  Multi-fidelity optimization via surrogate modelling , 2007, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.