Modelling the Single Chamber Solid Oxide Fuel Cell by Artificial Neural Network

The fuel cell is currently considered as one of the most promising technologies for future energy demand. Solid oxide fuel cells (SOFCs) have several advantages including flexibility of fuel used and relatively inexpensive materials due to high temperature operation. SOFCs operate easily in the single-chamber mode due to the simplified, compact, sealing-free cell structure. An artificial neural network (ANN) can be used as a black-box tool to simulate systems without solving the physical equations merely by utilizing available experimental data. In this study, the ANN is used for modelling a singular cell behavior. The error backpropagation algorithm was used for an ANN training procedure. Experiments of a planar button solid oxide fuel cell were used to train and verify the networks. The fuel cell system is fed by methane and oxygen. The cathode is LSCF6482, the anode is GDC-Ni, the electrolyte is LDM and the operating pressure is 1 atm. The ANN based SOFC model has the following input parameters: current density, temperature; and the cell voltage is predicted by the model. Obtained results show that the ANN can be successfully used for modelling the single chamber solid oxide fuel cell without knowledge of numerous physical, chemical, and electrochemical factors.