Prediction of Force Measurements of a Microbend Sensor Based on an Artificial Neural Network

Artificial neural network (ANN) based prediction of the response of a microbend fiber optic sensor is presented. To the best of our knowledge no similar work has been previously reported in the literature. Parallel corrugated plates with three deformation cycles, 6 mm thickness of the spacer material and 16 mm mechanical periodicity between deformations were used in the microbend sensor. Multilayer Perceptron (MLP) with different training algorithms, Radial Basis Function (RBF) network and General Regression Neural Network (GRNN) are used as ANN models in this work. All of these models can predict the sensor responses with considerable errors. RBF has the best performance with the smallest mean square error (MSE) values of training and test results. Among the MLP algorithms and GRNN the Levenberg-Marquardt algorithm has good results. These models successfully predict the sensor responses, hence ANNs can be used as useful tool in the design of more robust fiber optic sensors.

[1]  Mohd Nasir Taib,et al.  Applications of artificial neural network on signal processing of optical fibre pH sensor based on bromophenol blue doped with sol–gel film , 2003 .

[2]  Jacek M. Zurada,et al.  Introduction to artificial neural systems , 1992 .

[3]  Tülay Yildirim,et al.  Genetic Optimizations for Radial Basis Function and General Regression Neural Networks , 2006, MICAI.

[4]  W. Jin,et al.  Simultaneous measurement of temperature and strain: an artificial neural network approach , 1998, IEEE Photonics Technology Letters.

[5]  Orlando Frazão,et al.  Intelligent Optical Sensors Using Artificial Neural Network Approach , 2008, BASYS.

[6]  Ö. Galip Saracoglu,et al.  An Artificial Neural Network Approach for the Prediction of Absorption Measurements of an Evanescent Field Fiber Sensor , 2008, Sensors.

[7]  Tulay Yildirim,et al.  The effects of training algorithms in MLP network on image classification , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[8]  J. H. Cole,et al.  Microbend fiber-optic sensor as extended hydrophone , 1982 .

[9]  Thomas Philip,et al.  Humidity estimation using neural network and optical fiber sensor , 2009 .

[10]  J. W. Berthold,et al.  Historical review of microbend fiber-optic sensors , 1995 .

[11]  C. Butler,et al.  Sensor signal processing using neural networks for a 3-D fibre-optic position sensor , 1994 .

[12]  Fei Luo,et al.  A fiber optic microbend sensor for distributed sensing application in the structural strain monitoring , 1999 .

[13]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[14]  Shanglian Huang,et al.  Two kinds of neural network algorithms suitable for fiber optic sensing array signal processing , 1996 .

[15]  K Rottwitt,et al.  Simple fiber-optic low-temperature sensor that uses microbending loss. , 1991, Optics letters.

[16]  P. Radhakrishnan,et al.  A microbent fiber optic pH sensor , 2002 .

[17]  H. Ewald,et al.  A 3 sensor multipoint optical fibre water sensor utilising artificial neural network pattern recognition , 2002, 2002 15th Optical Fiber Sensors Conference Technical Digest. OFS 2002(Cat. No.02EX533).

[18]  Elfed Lewis,et al.  An optical fibre ethanol concentration sensor utilizing Fourier transform signal processing analysis and artificial neural network pattern recognition , 2003 .

[19]  J. H. Cole,et al.  Microbend fiber-optic sensor. , 1987, Applied optics.

[20]  Tinko Eftimov,et al.  Autocalibration of fiber-optic strain sensor using a self-learning system , 1993, 1993 IEEE Instrumentation and Measurement Technology Conference.