Applying neuro-fuzzy modelling and control to MD moisture content systems in paper machines

This paper presents a study on a possible application of neuro-fuzzy techniques to the modelling and control of machine direction (MD) moisture content in paper machines. Since the system is heavily coupled with another important system, the basis weight control system, the model for the system can therefore be expressed by an NARMAX model with its coefficients being the functions of the basis weights. As a result, the control strategy such as adaptive long-range predictive control can be directly applied together with neuro-fuzzy modelling. The overall algorithm is demonstrated through a simulated example and encouraging results have been obtained