Fuzzy modeling and control of boiler-turbine unit using clustering and subspace method

This paper develops a fuzzy modeling method for nonlinear boiler-turbine unit using only the input output data. The structure of the fuzzy model is determined by clustering to achieve an appropriate division of the local models. Then, the subspace identification is extended to develop local state-space models, which are dependent on the fuzzy membership functions. Owing to the advantages of the both methods, the resulting fuzzy model can represent the boiler-turbine unit very closely, and a fuzzy model predictive controller is designed based on this model. The effectiveness of the proposed fuzzy modeling method is demonstrated through the simulation.