Predictive control of solid oxide fuel cell based on an improved Takagi–Sugeno fuzzy model

Thermal management of a solid oxide fuel cell (SOFC) stack essentially involves control of the temperature within a specific range in order to maintain good performance of the stack. In this paper, a nonlinear temperature predictive control algorithm based on an improved Takagi–Sugeon (T–S) fuzzy model is presented. The improved T–S fuzzy model can be identified by the training data and becomes a predictive model. The branch-and-bound method and the greedy algorithm are employed to set a discrete optimization and an initial upper boundary, respectively. Simulation results show the advantages of the model predictive control (MPC) based on the identified and improved T–S fuzzy model for an SOFC stack.