A nonlinear predictive control algorithm based on fuzzy online modeling and discrete optimization

A multivariable nonlinear predictive control algorithm based on online fuzzy modeling and discrete optimization is presented for a family of complex systems with strong nonlinearity. The algorithm consists of two part: The first part is online fuzzy modeling using fuzzy clustering and linear identification, the second part is discrete optimization of the control action based on the principle of Branch and Bound method. In the process of fuzzy modeling, the unsupervised fuzzy competitive algorithm and a discarding criterion are introduced to ensure the fuzzy model can trace the system dynamics in time. The effectiveness and advantage of the presented algorithm are illustrated two numerical examples.

[1]  Magne Setnes,et al.  Fuzzy predictive filters in model predictive control , 1999, IEEE Trans. Ind. Electron..

[2]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[3]  Robert Babuska,et al.  Fuzzy model-based predictive control using Takagi-Sugeno models , 1999, Int. J. Approx. Reason..

[4]  D. Oudheusden,et al.  A branch and bound algorithm for the traveling purchaser problem , 1997 .

[5]  Korris Fu-Lai Chung,et al.  Fuzzy competitive learning , 1994, Neural Networks.

[6]  Ai Poh Loh,et al.  Modeling pH neutralization processes using fuzzy-neural approaches , 1996, Fuzzy Sets Syst..

[7]  Vincent Wertz,et al.  Fuzzy model-based predictive control , 1998, Proceedings of the 37th IEEE Conference on Decision and Control (Cat. No.98CH36171).