Modeling of measurement error in refractive index determination of fuel cell using neural network and genetic algorithm

Document Type : Research Paper


1 Shahid Rajaee Teacher Training University



Abstract: In this paper, a method for determination of refractive index in membrane of fuel cell on basis of three-longitudinal-mode laser heterodyne interferometer is presented. The optical path difference between the target and reference paths is fixed and phase shift is then calculated in terms of refractive index shift. The measurement accuracy of this system is limited by nonlinearity error. In this study, nonlinearity error is modeled by multi-layer perceptrons (MLPs) and stacked generalization method (Stacking), using two learning methods; back propagation (BP) and genetic algorithm. Training neural networks with genetic algorithm, improves modeling of nonlinearity error in this system. In the proposed technique, a real code version of genetic algorithm is used. Parameters and genetic operators are set and designed accurately. The results indicate that the nonlinearity error can be effectively modeled by training the stacking with the genetic algorithm which has minimum mean square error (MSE).
Keywords: Fuel cell, Genetic algorithm, Heterodyne interferometer, Multi-layer perceptrons, Nonlinearity error, Refractive index, Stacked Generalization.


Main Subjects

  1. Yazici M. S., “Hydrogen and fuel cell activities at UNIDO-ICHET”, Int. J. Hydrogen Energy 2010, 35: 2754.
  2. Thomas S. and Zalbowitz M., Fuel Cells – Green Power Hand Book. U.S. Department of Energy, Office of Transportation Technologies, 2010.
  3. Kirubakaran A. and Jain R.K., “A review on fuel cell technologies and power electronic interface”, Renewable and Sustainable Energy Reviews, 2009, 13: 2430.
  4. Motupally S., Becker A.J. and Weidner J.W., “Diffusion of water in nafion 115 membranes”, J. Electrochemical Society, 2000, 147: 3171.
  5. Tsushim S. and Aotani K., “Magnetic resonance imaging of a polymer electrolyte membrane under water meation”, Experimental Heat Transfer, 2009, 22: 1.
  6. Waller L., Kim J., Shao-Horn Y. and Barbastathis G., “Interferometric tomography of fuel cells for monitoring membrane water content”, Opt. Express, 2009, 17: 16806.
  7. Olyaee S. Abadi M.S.E., Hamedi S. and Finizadeh F., “Refractive index determination and nonlinearity modeling in fuel cells using laser heterodyne interferometer”, Int. J. Hydrogen Energy, 2011, 36: 13255.
  8. Quenelle R.C., “Nonlinearity in interferometric measurements”, Hewlett-Parkard J., 1983, 34, 10.
  9.  Sutton C.M., “Nonlinearity in the length measurement using heterodyne laser Michelson interferometery”, J. Phys. E: Sci. Instrum., 1987, 20: 1290.
  10.  Olyaee S., Yoon T.H., and Hamedi S., “Jones matrix analysis of frequency mixing error in three-longitudinal-mode laser heterodyne interferometer”, IET Optoelectron., 2009, 3: 215.
  11.  Li Z., Herrmann K. and Pohlenz F., “A neural network approach to correcting nonlinearity in optical interferometers”, Meas. Sci. Technol., 2003, 14: 376.
  12.  Heo G., Lee W., Choi S., Lee J. and You K., Adaptive neural network approach for nonlinearity compensation in laser interferometer. Springer Press,, 2007.
  13.  Olyaee S., Ebrahimpour R. and Hamedi S., “Modeling and compensation of periodic nonlinearity in two-mode interferometer using neural networks”, IETE J. Research, 2010, 56: 102.
  14.  Hornik K., Stinchcombe M. and White H., “Multi-layer feed forward networks are universal approximators”, Neural Networks, 1989: 2, 359.
  15.  Sedki A., Ouazar D., and El-Mazoudi E., “Evolving neural network using real coded genetic algorithm for daily rainfall–runoff forecasting”,. Expert Systems with Applications, 2009, 36: 4523.
  16.  Wolpert D. H., “Stacked generalization”, Neural Networks, 1992, 5: 241.
  17.  Fogel D. B., “An introduction to simulated evolutionary optimization”, J. IEEE Trans., 1994, 5, 3.
  18. Ganatra A., Kosta Y. P., Panchal G. and Gajjar C, “Initial classification through back propagation in a neural network following optimization through GA to evaluate the fitness of an algorithm, International Journal of Computer Science & Information Technology (IJCSIT), 2011, 3, 98.
  19. Hertz J., Krogh A. and Palmer R., An Introduction to the Theory of Neural Computation, Addison-Wesley, 1991.
  20. Whitfield D. and Martin E. H., “New directions in cryptography”, IEEE Transactions on Information Theory, 1986, 14: 644.
  21.  Michalewicz Z., Genetic Algorithms + Data Structures = Evolution Programs. Springer-Verlag, New York, 1992.