Benchmark for Peak Detection Algorithms in Fiber Bragg Grating Interrogation and a New Neural Network for its Performance Improvement

This paper presents a benchmark for peak detection algorithms employed in fiber Bragg grating spectrometric interrogation systems. The accuracy, precision, and computational performance of currently used algorithms and those of a new proposed artificial neural network algorithm are compared. Centroid and gaussian fitting algorithms are shown to have the highest precision but produce systematic errors that depend on the FBG refractive index modulation profile. The proposed neural network displays relatively good precision with reduced systematic errors and improved computational performance when compared to other networks. Additionally, suitable algorithms may be chosen with the general guidelines presented.

[1]  M. Yamada,et al.  Analysis of almost-periodic distributed feedback slab waveguides via a fundamental matrix approach. , 1987, Applied optics.

[2]  Kyriacos Kalli,et al.  Fiber Bragg Gratings: Fundamentals and Applications in Telecommunications and Sensing , 2000 .

[3]  W. Press,et al.  Numerical Recipes in C++: The Art of Scientific Computing (2nd edn)1 Numerical Recipes Example Book (C++) (2nd edn)2 Numerical Recipes Multi-Language Code CD ROM with LINUX or UNIX Single-Screen License Revised Version3 , 2003 .

[4]  W. Jin,et al.  Improving the wavelength detection accuracy of FBG sensors using an ADALINE network , 2003, IEEE Photonics Technology Letters.

[5]  Christian Igel,et al.  Improving the Rprop Learning Algorithm , 2000 .

[6]  Hypolito José Kalinowski,et al.  Radial-basis function network for the approximation of FBG sensor spectra with distorted peaks , 2006 .

[7]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[8]  Alexander W. Koch,et al.  Comparison of different peak detection algorithms with regards to spectrometic fiber Bragg grating interrogation systems , 2009, 2009 International Symposium on Optomechatronic Technologies.

[9]  Robert F. Stengel,et al.  Smooth function approximation using neural networks , 2005, IEEE Transactions on Neural Networks.

[10]  B. Kim,et al.  Interrogation of fiber grating sensor arrays with a wavelength-swept fiber laser. , 1998, Optics letters.

[11]  B.M. Wilamowski,et al.  Neural network architectures and learning algorithms , 2009, IEEE Industrial Electronics Magazine.

[12]  Hao Yu,et al.  Improved Computation for Levenberg–Marquardt Training , 2010, IEEE Transactions on Neural Networks.

[13]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[14]  Alexander N. Gorban,et al.  Approximation of continuous functions of several variables by an arbitrary nonlinear continuous function of one variable, linear functions, and their superpositions , 1998 .

[15]  A. Othonos.  Fiber Bragg gratings , 1999 .

[16]  Shellee D. Dyer,et al.  Fundamental limits in fiber Bragg grating peak wavelength measurements (Invited Paper) , 2005, International Conference on Optical Fibre Sensors.

[17]  Jagath C. Rajapakse,et al.  FPGA Implementations of Neural Networks , 2006 .

[18]  Hyoung-Jun Park,et al.  Accuracy improvement in peak positioning of spectrally distorted fiber Bragg grating sensors by Gaussian curve fitting. , 2007, Applied optics.

[19]  G. Kane.  Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol 1: Foundations, vol 2: Psychological and Biological Models , 1994 .

[20]  F. A. Seiler,et al.  Numerical Recipes in C: The Art of Scientific Computing , 1989 .