Nonlinear Gaussian Belief Network based fault diagnosis for industrial processes. (November 2015)

• Record Type: Journal Article
• Authors: Yu, Hongyang; Khan, Faisal; Garaniya, Vikram
• Is Part Of: Journal of process control. Volume 35(2015:Nov.)
• Page Start: 178
• Page End: 200
• Publication Date: 2015-11
• Subjects: Online fault diagnosis -- Nonlinear and noisy processes -- Nonlinear Gaussian Belief Network -- PCA -- KPCA -- KICA -- SPA -- MWKPCA; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2015.09.004
• Languages: English
• ISSNs: 0959-1524

Abstract

Highlights: A network-based fault diagnosis technique is proposed for industrial processes. A three-layer network is trained to extract features from noisy process data. A monitoring index denoted G-index is proposed for fault detection and diagnosis. The proposed technique has been verified by two case studies. Abstract: A Nonlinear Gaussian Belief Network (NLGBN) based fault diagnosis technique is proposed for industrial processes. In this study, a three-layer NLGBN is constructed and trained to extract useful features from noisy process data. The nonlinear relationships between the process variables and the latent variables are modelled by a set of sigmoidal functions. To take into account the noisy nature of the data, model variances are also introduced to both the process variables and the latent variables. The three-layer NLGBN is first trained with normal process data using a variational Expectation and Maximization algorithm. During real-time monitoring, the online process data samples are used to update the posterior mean of the top-layer latent variable. The absolute gradient denoted as G-index to update the posterior mean is monitored for fault detection. A multivariate contribution plot is also generated based on the G-index for fault diagnosis. The NLGBN-based technique is verified using two case studies. The results demonstrate that the proposed technique outperforms the conventional nonlinear techniques such as KPCA, KICA, SPA, and Moving Window KPCA.