Model Augmentation for Hybrid Fuel-Cell/Gas Turbine Power Plant

Fuel cell power plant is a novel, clean and efficient energy source in distributed generation. To guarantee plant efficiency and reliability, advanced plant control theories and algorithms were investigated based on the model of the hybrid direct fuel cell and turbine (DFC/T) plant. However, due to assumptions and uncertainties, the error of this model cannot be neglected and constrains the applicabilities of the control algorithms developed based on the model. Thus, it is a necessity to improve the accuracy of the plant model. In this paper, an analytical approach and a numerical approach using online operational data are presented. Taking fuel-cell stack as an example, an internal energy dynamic model is implemented, and parameters are identified from online data. Artificial neural networks are finally applied to compensate the model error. Simulation results are provided and compared with experimental results to verify the performance of the augmented model.