An Improved Diagnostic Tool for Control Valve Stiction Based on Nonlinear Principle Component Analysis

Control valves suffer from wear and aging as the valves open and close. Such continuous movements result in many operational issues, and one of the widely known problems is stiction nonlinearity. Stiction results in inferior quality of the products, large rejection rates, increased energy consumption, and reduced profitability. In this paper, a simple algorithm that combines preprocessing and postprocessing as well as average crossing autocovariance (AC) together with the nonlinear principal component analysis (NLPCA) is investigated. The results obtained from the simulated and industrial case studies show that the proposed NLPCA-AC method has favorable proficiencies for control valve stiction detection.