A Black-Box Approach in Modeling Valve Stiction

Several valve stiction models have been proposed in
the literature to help understand and study the behavior of sticky
valves. In this paper, an alternative black-box modeling approach
based on Neural Network (NN) is presented. It is shown that with
proper network type and optimum model structures, the performance
of the developed NN stiction model is comparable to other
established method. The resulting NN model is also tested for its
robustness against the uncertainty in the stiction parameter values.
Predictive mode operation also shows excellent performance of the
proposed model for multi-steps ahead prediction.