Adaptive predictor for control of nonlinear systems based on neurofuzzy models

This paper proposes a general nonlinear adaptive predictor using a class of neurofuzzy models. The obtained predictor may be seen as a linear predictor network consisting of a global linear predictor and several local linear predictors with interpolation. It has distinctive features as well as good prediction ability: its parameters have explicit meanings useful for initial values setting: it may be transformed into a form linear for the variables synthesized in control systems, making deriving a control law straightforward.