Fuzzy modeling based on fuzzy ARMAX model
基于模糊ARMAX模型的模糊建模

The MGS (modified Gram-Schmidt) algorithm is proposed to construct the fuzzy ARMAX model. An integrated algorithm for structure identification and parameter identification of fuzzy model is given based on MGS algorithm. The result from GK fuzzy clustering is transformed to confirm the important rules and to remove the less important rules by means of MGS transformation. The parameters of fuzzy model are estimated via the proposed method; and the structure and parameters of fuzzy model are optimized. Simulation results show that the fuzzy ARMAX model of non-linear system can be built by the proposed algorithm.