Neural Network-Based Modeling for A Solid-Oxide Fuel Cell Stack

Abstract

With the growing concerns about the environment, more effort has been put towards reducing the pollutant gases generated in the electric power sector by integrating distributed energy conversion devices with high efficiency and low emission. However, these devices such as fuel cells come with their shortcomings and challenges of meeting lifetime and availability goals, especially when operated outside their safe operational range. Therefore, the need to develop not just good controls but also intelligent controls arise to help respect these constraints while meeting up with the load demands. In this paper, Neural Networks (NN s) were used as a system identifier to model the dynamics of a solid-oxide fuel cell (SOFC) stack to be used in the controller design. The proposed NN model was validated by comparing its results with that of an already validated mathematical model.