Comparison of regression methods for transverse load sensor based on optical fiber long-period grating

Abstract In this work, we report the comparison of regression methods in a long-period grating (LPG) for transverse strain measurement. We analyze the transverse strain sensing characteristics, such as load intensity and azimuthal angle, based on the birefringence effect induced in LPG sensor. Therefore, we employ the different orthogonal responses of the grating to develop regression methods, which allow the estimation of the strain behavior of the LPG sensor. The predictive performances of these interrogation models are compared in terms of square correlation coefficient (R2) and root mean square error (RMSE). Finally, the results indicate that the best method to predict load intensity is the Fourth-Degree Polynomial Fit, whereas the artificial neural network (ANN) model could be successfully employed to predict the azimuthal angle.

[1]  V. Rodriguez-Galiano,et al.  Machine learning predictive models for mineral prospectivity: an evaluation of neural networks, random forest, regression trees and support vector machines , 2015 .

[2]  E. Hadavandi,et al.  Support vector regression modeling of coal flotation based on variable importance measurements by mutual information method , 2018 .

[3]  Ivica Kostanic,et al.  Principles of Neurocomputing for Science and Engineering , 2000 .

[4]  F. Baldini,et al.  Biosensing with optical fiber gratings , 2017 .

[5]  Yunjiang Rao,et al.  Asymmetric transverse-load characteristics and polarization dependence of long-period fiber gratings written by a focused CO(2) laser. , 2007, Applied optics.

[6]  Bangyong Sun,et al.  Evaluating the Performance of Polynomial Regression Method with Different Parameters during Color Characterization , 2014 .

[7]  Heaton T. Jeff,et al.  Introduction to Neural Networks with Java , 2005 .

[8]  Thomas K Gaylord,et al.  Polarization-dependent loss and birefringence in long-period fiber gratings. , 2003, Applied optics.

[9]  Felipe de Souza Delgado,et al.  Reduction of intrinsic polarization dependence in arc-induced long-period fiber gratings , 2018 .

[10]  Ian Bennion,et al.  Design and realization of long-period grating devices in conventional and high birefringence fibers and their novel applications as fiber-optic load sensors , 1999 .

[11]  Cosimo Trono,et al.  Manufacturing and Spectral Features of Different Types of Long Period Fiber Gratings: Phase-Shifted, Turn-Around Point, Internally Tilted, and Pseudo-Random , 2017 .

[12]  Ian Bennion,et al.  Fibre optic load sensors with high transverse strain sensitivity based on long-period gratings in B/Ge co-doped fibre , 1999 .

[13]  S. Chehreh Chelgani,et al.  Prediction of uniaxial compressive strength and modulus of elasticity for Travertine samples using regression and artificial neural networks , 2010 .

[14]  Francesco Baldini,et al.  Towards a Uniform Metrological Assessment of Grating-Based Optical Fiber Sensors: From Refractometers to Biosensors , 2017, Biosensors.

[15]  S. Matthai,et al.  Application of neural networks and fuzzy systems for the intelligent prediction of CO2-induced strength alteration of coal , 2019, Measurement.

[16]  Thiago V. N. Coelho,et al.  An Optical Fiber Sensor and Its Application in UAVs for Current Measurements , 2016, Sensors.

[17]  Gaspar M. Rego,et al.  Arc-Induced Long Period Fiber Gratings , 2016, J. Sensors.

[18]  Subhash Bhatia,et al.  Catalytic cracking of palm oil for the production of biofuels: optimization studies. , 2007, Bioresource technology.

[19]  Harris Drucker,et al.  Improving Regressors using Boosting Techniques , 1997, ICML.

[20]  T. Singh,et al.  Regression and soft computing models to estimate young’s modulus of CO2 saturated coals , 2018, Measurement.

[21]  Hongpu Li,et al.  Mode-couplings in two cascaded helical long-period fibre gratings and their application to polarization-insensitive band-rejection filter , 2018, Optics Communications.

[22]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[23]  F. Arı,et al.  Enhancing refractive index sensitivity using micro-tapered long-period fiber grating inscribed in biconical tapered fiber , 2018, Optical Fiber Technology.

[24]  Pramod K. Varshney,et al.  Decision tree regression for soft classification of remote sensing data , 2005 .

[25]  Durga L. Shrestha,et al.  Experiments with AdaBoost.RT, an Improved Boosting Scheme for Regression , 2006, Neural Computation.

[26]  Reza Nejabati,et al.  Load and nonlinearity aware resource allocation in elastic optical networks , 2017, 2017 Optical Fiber Communications Conference and Exhibition (OFC).

[27]  Rahul Khanna,et al.  Efficient Learning Machines , 2015, Apress.

[28]  Y. Rao,et al.  Novel fiber-optic sensors based on long-period fiber gratings written by high-frequency CO/sub 2/ laser pulses , 2003 .

[29]  Jinping Ou,et al.  Sensitivity characterization of cladding modes in long-period gratings photonic crystal fiber for structural health monitoring , 2015 .

[30]  Jie Zeng,et al.  Long period fiber grating transverse load effect-based sensor for the omnidirectional monitoring of rebar corrosion in concrete. , 2013, Applied optics.

[31]  M. Dong,et al.  All-Fiber Dual-Parameter Sensor Based on Cascaded Long Period Fiber Grating Pair Fabricated by Femtosecond Laser and CO2 Laser , 2018 .

[32]  Patrick K. Simpson,et al.  Artificial Neural Systems: Foundations, Paradigms, Applications, and Implementations , 1990 .

[33]  T. Sakamoto,et al.  Experimental verification of mode-dependent loss reduction by mode coupling using long-period grating , 2017, 2017 Optical Fiber Communications Conference and Exhibition (OFC).

[34]  Danial Jahed Armaghani,et al.  Utilizing regression models to find functions for determining ripping production based on laboratory tests , 2017 .

[35]  D. Basak,et al.  Support Vector Regression , 2008 .

[36]  Michael R. Lyu,et al.  Localized support vector regression for time series prediction , 2009, Neurocomputing.