Multi-model predictive control based on the Takagi–Sugeno fuzzy models: a case study

Multiple model predictive control (MMPC) strategy based on the Takagi–Sugeno (T–S) model is proposed in this paper. A T–S modeling method using fuzzy satisfactory clustering (FSC) algorithm is introduced at first. FSC is designed to help quickly determine satisfactory number of rules of a T–S model. Based on the T–S model, MMPC strategy is presented using parallel distribution compensation (PDC) method, i.e. different predictive controllers are designed for different rules (local sub-systems). The global controller output is the fuzzy weighted integration of local ones. MMPC with system constraints are also considered in this paper. The presented modeling and controller design procedure is demonstrated on an MIMO simulated pH neutralization process.