Fault pattern recognition using dynamic independent component based sparse kernel classifier

In order to diagnose fault source effectively, this paper proposed a novel fault pattern recognition method called dynamic independent component based sparse kernel classifier (DICSKC). In the proposed method, fault pattern recognition is viewed as a classification problem and kernel trick is applied to construct nonlinear classifier for each fault scene. To improve classification performance, dynamic independent component analysis is used to extract data features which substitute for original measured variables as the input of classifier. For obtaining a sparse classifier to reduce the computation complexity, an orthogonal forward subset selection procedure is utilized to minimize the leave one out classification error. Simulation on the Tennessee Eastman benchmark process shows that the proposed method has a good fault pattern recognition performance.