A JITL-Based Probabilistic Principal Component Analysis for Online Monitoring of Nonlinear Processes

Abstract

There exists nonlinear information and strong correlation among variables in modern industrial processes. As a typical linear process monitoring method, probabilistic principal component analysis (PPCA) cannot capture the nonlinear information among process data. To cope with this problem and improve real time performance, a new just-in-time-learning based PPCA (JITL–PPCA) method is proposed in this paper. In JITL–PPCA, an online local model structure is first designed for extracting nonlinear features, by incorporating an improved JITL approach and least squares support vector regression (LSSVR) model. Then, the remaining linear residuals are input into the PPCA scheme for final process monitoring and fault detection. A simulated numerical case and a real industrial process case are used to evaluate the performance and effectiveness of the proposed method. The monitoring results show the effectiveness of the proposed JITL–PPCA method.