Modeling of Direct Methanol Fuel Cell Using the Artificial Neural Network

Abstract

The performance of a direct methanol fuel cell (DMFC) has complex nonlinear characteristics. In this paper, the performance of a DMFC has been modeled using a neural network approach. The input parameters of the DMFC model include cell geometrical and operational parameters such as the cell temperature, oxygen flow rate, channel depth of the bipolar plate, methanol concentration, cathode back pressure, and current density and the output parameter is the cell voltage. In order to predict the performance of a DMFC single cell, two types of artificial neural network (ANN) have been developed to correlate the input parameters of the DMFC to the cell voltage. The performance of the networks was investigated by varying the number of neurons, number of layers, and transfer function of the ANNs and the best one is selected based on the mean square error. The results indicated that the neural network models can predict the cell voltage with an acceptable accuracy.