شماره ركورد كنفرانس :
3256
عنوان مقاله :
Hybrid Genetic Algorithm-Neural Network for Membrane RI Measurement Error Modeling in PEM Fuel Cells
Author/Authors :
Saeed Olyaee Nano-Photonics and Optoelectronics Research Laboratory - Faculty of Electrical and Computer Engineering - Shahid Rajaee TeacherTraining University , Reza Ebrahimpour Nano-Photonics and Optoelectronics Research Laboratory - Faculty of Electrical and Computer Engineering - Shahid Rajaee TeacherTraining University , Somayeh Esfandeh Nano-Photonics and Optoelectronics Research Laboratory - Faculty of Electrical and Computer Engineering - Shahid Rajaee TeacherTraining University
كليدواژه :
Artificial neural network , Genetic algorithm , Heterodyne interferometer , Multi layer perceptrons , Nonlinearity error
عنوان كنفرانس :
ششمين سمينار پيل سوختي ايران
چكيده لاتين :
In this paper, a method for determination of refractive index (RI) in membrane of fuel cell on basis of three-longitudinal-mod laser heterodyne interferometer is presented. The optical path difference between 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 artificial neural network (ANN) and hybrid genetic algorithm–neural network (hybrid GA–ANN) methods. The real code version of genetic algorithm (GA) is used. Genetic operators and parameters are set and designed accurately to optimize the neural network. Results indicate that nonlinearity error can be effectively modeled by hybrid GA–ANN method and contains minimum mean square error (MSE) compared to neural network
