Data‐based linear Gaussian state‐space model for dynamic process monitoring

Abstract

This article develops a data‐based linear Gaussian state‐space model for monitoring of dynamic processes under noisy environment. The Kalman filter is introduced for construction of the linear Gaussian state‐space model, and an iterative expectation‐maximization algorithm is used for model parameters learning. With the incorporation of the dynamic data information, a new fault detection and identification approach is proposed. The feasibility and effectiveness of the two monitoring statistics in the new method are theoretically evaluated and further confirmed through two case studies. Furthermore, detailed fault smearing effect analysis of the proposed method is provided and compared with other identification methods. Based on the simulation results of two case studies, the superiority of the proposed method is explored. © 2012 American Institute of Chemical Engineers AIChE J, 2012

A New Method of Dynamic Latent-Variable Modeling for Process Monitoring

“…The RBC for each sample and each variable is drawn by a color tape, where the darker color represents the higher RBC. From the plot, it is observed that variables 18 and 19 are indeed the most significant candidates for this fault, which is consistent with the conclusions in [15] and [24]. However, traditional dynamic methods such as DPCA, SIM, and CVA do not reveal a structure in the lagged variables, which makes the diagnosis analysis difficult to implement.…”

“…For multiple indexes in a method, if any statistic exceeds its control limit, the fault is detected. From the FDRs for all faults (except IDV 3,9,15), it can be seen that the DLV-based method can detect faults more stably than DPCA and outperforms PCA and SIMbased methods in most cases. Although CVA-based method has a higher FDR, its FAR is also high, which is caused by the inversion of the small values of R 0 in (8).…”

“…Using the linear dynamic state-space description of processes, the residual generator of the parity space method after identifying a subspace model is equivalent to IDPCA modeling for normal data. Another dynamic probabilistic model termed the linear Gaussian statespace model was proposed for dynamic process monitoring by Wen et al [15], which uses the expectation-maximization algorithm for the structure selection and the Kalman filter for the innovation estimation.…”

Supervised linear dynamic system model for quality related fault detection in dynamic processes

“…(12)- (16) are calculated through the iterative manner. When t = 1, the initial value of f 1 and F 1 are given as…”

“…For the fault detection purpose, the LDS model has already been introduced. For example, a data-based linear Gaussian state-space model was constructed upon the framework of LDS for dynamic process monitoring [16], a switching LDS-based approach has been proposed for fault detection and classification [17].…”