Integrate weighted dependence and skewness based multiblock principal component analysis with Bayesian inference for large-scale process monitoring

Abstract In a large-scale process, variables are correlated, and are Gaussian and non-Gaussian coexisted. The decentralized monitoring methods divide variables into blocks and carry out local monitoring is aimed at reducing the process complexity. Recently, the weighted copula-correlation-based multiblock principal component analysis (WCMBPCA) considering the correlation degree and correlation patterns was proposed to monitor a correlated process. While its monitoring efficiency has been shown, the WCMBPCA method has some drawbacks: 1) monitoring performance relies on the selection of copula function; 2) computation time for the weight matrix is long; 3) without considering the distribution information. This study proposes a novel weight strategy for multiblock PCA by developing a measurement, which simultaneously estimates the dependence and skewness of data, such that the distribution information is additionally considered. The proposed weight matrix is based on the use of non-parametric ranks, prompting the short computation time. The experiment results from Tennessee Eastman (TE) process monitoring shows the average fault detection rate for the proposed method is 84.19% that outperforms regular PCA, dynamic PCA, multiblock PCA, and WCMBPCA. Moreover, the weight matrix calculation takes 0.000635 s for the proposed method, while 195.040282 s for WCMBPCA.

[1]  John F. MacGregor,et al.  Process monitoring and diagnosis by multiblock PLS methods , 1994 .

[2]  Michael J. Piovoso,et al.  On unifying multiblock analysis with application to decentralized process monitoring , 2001 .

[3]  Christos Georgakis,et al.  Disturbance detection and isolation by dynamic principal component analysis , 1995 .

[4]  Wenli Du,et al.  Decentralized monitoring for large‐scale process using copula‐correlation analysis and Bayesian inference–based multiblock principal component analysis , 2019, Journal of Chemometrics.

[5]  Pavel Krupskii,et al.  Copula-based monitoring schemes for non-Gaussian multivariate processes , 2019, Journal of Quality Technology.

[6]  Zhiqiang Ge,et al.  Two-level multiblock statistical monitoring for plant-wide processes , 2009 .

[7]  Yu Song,et al.  Distributed Statistical Process Monitoring Based on Four-Subspace Construction and Bayesian Inference , 2013 .

[8]  Ying Tian,et al.  Plant-wide process monitoring by using weighted copula-correlation based multiblock principal component analysis approach and online-horizon Bayesian method. , 2019, ISA transactions.

[9]  Zhi-huan Song,et al.  Distributed PCA Model for Plant-Wide Process Monitoring , 2013 .

[10]  Sherzod B. Akhundjanov,et al.  Copula-based control charts for monitoring multivariate Poisson processes with application to hepatitis C counts , 2020, Journal of Quality Technology.

[11]  Jian Huang,et al.  Dynamic process fault detection and diagnosis based on dynamic principal component analysis, dynamic independent component analysis and Bayesian inference , 2015 .

[12]  Xuefeng Yan,et al.  Process monitoring using principal component analysis and stacked autoencoder for linear and nonlinear coexisting industrial processes , 2020 .

[13]  Hanyuan Zhang,et al.  Dynamic nonlinear batch process fault detection and identification based on two‐directional dynamic kernel slow feature analysis , 2020 .

[14]  J. Macgregor,et al.  Analysis of multiblock and hierarchical PCA and PLS models , 1998 .

[15]  Biao Huang,et al.  Performance-Driven Distributed PCA Process Monitoring Based on Fault-Relevant Variable Selection and Bayesian Inference , 2016, IEEE Transactions on Industrial Electronics.