A novel fuzzy Wiener-based nonlinear modelling for engineering applications

Abstract

This study proposes a novel fuzzy Wiener structure for identifying engineering systems. The proposed model has a cascade structure; a nonlinear static part preceded by a linear dynamic part. The nonlinear static part is represented by an interval type-2 fuzzy Takagi–Sugeno–Kang (IT2TSK) system in which the antecedents of the rules are described by interval type-2 fuzzy sets (IT2FSs) and a TSK-type system describes the consequents. An autoregressive moving average (ARMA) model is developed for representing the linear dynamic part. The proposed structure parameters including the ARMA, antecedent and consequent parameters are updated using the Lyapunov function to ensure the model stability. The simulation results confirm that the proposed Wiener structure can successfully model nonlinear engineering applications in the existence of system uncertainties and noisy measurement data. Moreover, the proposed model consistently achieves higher fitness (FIT) and smaller root mean square error (RMSE) values than other existing schemes.