Stiction is the most commonly found valve problem in the process industry. Valve stiction may cause oscillations in control loops which increases variability in product quality, accelerates equipment wear and tear, or leads to system instability. In this paper, a series-parallel Recurrent Neural Network (NARXSP)-based stiction model is developed and its robustness against the uncertainty in the stiction parameters is tested under various conditions. It is shown that the NARXSP-based stiction model is robust when the stiction is less than 6 of the valve travel span. © 2009 IEEE.