Nonlinear Process Fault Diagnosis Using Kernel Slow Feature Discriminant Analysis

Slow feature analysis (SFA) is an unsupervised liner learning algorithm and lacks the ability to consider class label information and data nonlinearity. In this paper, a novel nonlinear process fault diagnosis approach is proposed based on kernel slow feature discriminant analysis (kernel SFDA), which incorporates the discriminative information into SFA learning and uses the kernel trick to deal with nonlinear characteristics of process data. The directions of fault data that maximize the temporal variation of between-class pseudo-time series and minimize the temporal variation of within-class pseudo-time series simultaneously are calculated by pairwise kernel SFDA. Then, the fault pattern is identified by measuring the similarity between its own fault direction and the directions of historical fault datasets. The simulation results on the continuous stirred tank reactor system demonstrate that the proposed method can recognize the pattern of fault snapshot data more effectively than conventional methods.