Modeling of PEM Fuel Cell Stack System using Feed-forward and Recurrent Neural Networks for Automotive Applications

摘要

Artificial Neural Network (ANN) has become a significant modeling tool for predicting the performance of complex systems that provide appropriate mapping between input-output variables without acquiring any empirical relationship due to the intrinsic properties. This paper is focussed towards the modeling of Proton Exchange Membrane (PEM) Fuel Cell system using Artificial Neural Networks especially for automotive applications. Three different neural networks such as Static Feed Forward Network (SFFN), Cascaded Feed Forward Network (CFFN) & Fully Connected Dynamic Recurrent Network (FCRN) are discussed in this paper for modeling the PEM Fuel Cell System. The numerical analysis is carried out between the three Neural Network architectures for predicting the output performance of the PEM Fuel Cell. The performance of the proposed Networks is evaluated using various error criteria such as Mean Square Error, Mean Absolute Percentage Error, Mean Absolute Error, Coefficient of correlation and Iteration Values. The optimum network with high performance indices (low prediction error values and iteration values) can be used as an ancillary model in developing the PEM Fuel Cell powered vehicle system. The development of the fuel cell driven vehicle model also incorporates the modeling of DC-DC Power Converter and Vehicle Dynamics. Finally the Performance of the Electric vehicle model is analyzed for two different drive cycle such as M-NEDC & M-UDDS.