Fuzzy internal model controller of MCFC

A kind of fuzzy internal model controller (FIMC) is posed for molten carbonate fuel cell stack (MCFCS). MCFCS is a complex electrochemical system. It is difficult to control by the traditional controller. The new controller not only has the well-established structure of internal model controller (IMC), but also has the ability to deal with the nonlinear system or complex system with the help of fuzzy model. A fuzzy neural network (FNN) is used to model MCFCS. FNN structure and parameters are easier to comprehend than artificial neural network. After self-learning of structure and parameters of FNN, the fuzzy relational model (FRM) of MCFCS can be deduced from FNN model. Using the novel inversion method FRM is inverted and used in the internal model control structure. The performance of the control system is tested in the paper too.