Thermal stress management of a solid oxide fuel cell using neural network predictive control

• Published in: Energy (Oxford) Vol. 62; pp. 320 - 329
• Main Authors: Hajimolana, S.A., Tonekabonimoghadam, S.M., Hussain, M.A., Chakrabarti, M.H., Jayakumar, N.S., Hashim, M.A.
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 01.12.2013; Elsevier
• Subjects: air flow; ammonia; Applied sciences; Cell-tube temperature; ceramics; Computer simulation; Control systems; electrochemistry; electrodes; electrolytes; Electrolytic cells; Energy; Energy. Thermal use of fuels; Equipments for energy generation and conversion: thermal, electrical, mechanical energy, etc; Exact sciences and technology; Fuel cells; fuels; Inlets; Mathematical models; momentum; Neural network predictive control; Neural networks; porous media; Solid oxide fuel cell; Solid oxide fuel cells; Streams; stress management; Thermal stress; Thermal stresses; water temperature; Thermal stress; Solid oxide fuel cell; Cell-tube temperature; Neural network predictive control; Neural network; Fuel cell; Predictive control
• ISSN: 0360-5442
• DOI: 10.1016/j.energy.2013.08.031

In SOFC (solid oxide fuel cell) systems operating at high temperatures, temperature fluctuation induces a thermal stress in the electrodes and electrolyte ceramics; therefore, the cell temperature distribution is recommended to be kept as constant as possible. In the present work, a mathematical model based on first principles is presented to avert such temperature fluctuations. The fuel cell running on ammonia is divided into five subsystems and factors such as mass/energy/momentum transfer, diffusion through porous media, electrochemical reactions, and polarization losses inside the subsystems are presented. Dynamic cell-tube temperature responses of the cell to step changes in conditions of the feed streams is investigated. The results of simulation indicate that the transient response of the SOFC is mainly influenced by the temperature dynamics. It is also shown that the inlet stream temperatures are associated with the highest long term start-up time (467 s) among other parameters in terms of step changes. In contrast the step change in fuel velocity has the lowest influence on the start-up time (about 190 s from initial steady state to the new steady state) among other parameters. A NNPC (neural network predictive controller) is then implemented for thermal stress management by controlling the cell tube temperature to avoid performance degradation by manipulating the temperature of the inlet air stream. The regulatory performance of the NNPC is compared with a PI (proportional–integral) controller. The performance of the control system confirms that NNPC is a non-linear-model-based strategy which can assure less oscillating control responses with shorter settling times in comparison to the PI controller. •Effect of the operating parameters on the fuel cell temperature is analysed.•A neural network predictive controller (NNPC) is implemented.•The performance of NNPC is compared with the PI controller.•A detailed model is used for the NNPC for the first time in the literature.