Adaptive Neural Controller for Maximum Power Point Tracking Of Ten Parameter Fuel Cell Model
Main Article Content
Abstract
Nonlinear characteristic and internal behavior of the Proton Exchange Membrane (PEM) Fuel Cells under different load conditions is of paramount importance. This paper presents an adaptive neural controller based on a back-propagation algorithm for maximum power control of PEM fuel cell system. The system consists of a buck-boost converter connected to the fuel cell. The adaptive neural controller receives the error and change of error signals as inputs during load changes and generates the DC-DC converter duty cycle. By using the inference, the duty ratio of the buck-boost converter is controlled so that the fuel cell can provide the maximum power. The ANN controller monitors also the temperature, the pressure and the cell voltage. In this paper the dynamic model for proton exchange membrane fuel cells using ten parameter model is used. The model has been implemented in MATLAB/SIMULINK. Both the double-layer charging effect and the thermodynamic characteristic inside the fuel cell are included in the model.