Fault detection and isolation in transient states using principal component analysis

Garcia-Alvarez, D.; Fuente, José Luis de la; Sainz, Gregorio

doi:10.1016/j.jprocont.2012.01.007

Cited by 51 publications

(26 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It produces new variables that are uncorrelated with each other and are linear combinations of original variables. [18,19] For a given data matrix X ∈ R n × m that represents m columns of measured variables at n rows of sample points, PCA decomposes the data matrix X as…”

Section: Pca Methodsmentioning

confidence: 99%

“…Principal component analysis is a powerful dimension‐reducing technique. It produces new variables that are uncorrelated with each other and are linear combinations of original variables . For a given data matrix X ∈ R n × m that represents m columns of measured variables at n rows of sample points, PCA decomposes the data matrix X as

X = {boldt}_{1} {boldp}_{1}^{normalT} + {boldt}_{2} {boldp}_{2}^{normalT} + \dots + {boldt}_{normalk} {boldp}_{normalk}^{normalT} + E

where t i (1 ≤ i ≤ k ) is the i th score vector, p i (1 ≤ i ≤ k ) is the i th loading vector, k is the number of principal components (PCs) retained in the PC model, and E is the residual matrix.…”

Section: Related Workmentioning

confidence: 99%

“…3) Compute the entropy vector h t,new , and apply mean centering and variance scaling according to the entropy variable means and variances in the step 2 of the offline modeling stage. 4) Obtain the projections for the entropy vector h t, new according to (18), and compute the monitoring statistics according to (19) and (20). 5) Compare the monitoring statistics with their corresponding confidence limits.…”

Section: Online Detection Stagementioning

confidence: 99%

See 2 more Smart Citations

Entropy principal component analysis and its application to nonlinear chemical process fault diagnosis

Deng

Tian

2014

Asia-Pacific J Chem Eng

View full text Add to dashboard Cite

Most chemical processes generally exhibit the characteristics of nonlinear variation. In this paper, an improved principal component analysis method using information entropy theory, called entropy principal component analysis (EPCA), is proposed for nonlinear chemical process fault diagnosis. This approach applies information entropy theory to build an explicit nonlinear transformation, which provides a convenient way for nonlinear extension of principal component analysis. The information entropy can capture the Gaussian and non‐Gaussian information in the measured variables via probability density function estimation. With the entropy of original measured variables, the entropy principal components are calculated using a simple eigenvalue decomposition procedure, and two monitoring statistics are built for fault detection. Once a fault is detected, EPCA similarity factors between the occurred fault dataset and historical fault pattern datasets are computed for fault recognition. Simulations on a continuous stirred tank reactor system show that EPCA performs well in terms of fault detection and recognition. © 2014 Curtin University of Technology and John Wiley & Sons, Ltd.

show abstract

Section: Pca Methodsmentioning

confidence: 99%

X = {boldt}_{1} {boldp}_{1}^{normalT} + {boldt}_{2} {boldp}_{2}^{normalT} + \dots + {boldt}_{normalk} {boldp}_{normalk}^{normalT} + E

Section: Related Workmentioning

confidence: 99%

Section: Online Detection Stagementioning

confidence: 99%

See 1 more Smart Citation

Entropy principal component analysis and its application to nonlinear chemical process fault diagnosis

Deng

Tian

2014

Asia-Pacific J Chem Eng

View full text Add to dashboard Cite

show abstract

“…Hereby process data are usually plentifully stored in the database of process control computer. Thereby, the data-driven one is far more preferred and has gained increasing interests in recent studies [8,[17][18][19][20]. Actually, for the PM-FD purpose, lots of efforts have been made by us only for a single batch process.…”

Section: State Of the Artmentioning

confidence: 99%

Quality-relevant fault detection and diagnosis for hot strip mill process with multi-specification and multi-batch measurements

Peng

Zhang

Dong

et al. 2015

Journal of the Franklin Institute

View full text Add to dashboard Cite

“…Multivariate statistical methods, such as principal component analysis (PCA) and partial least squares (PLS), are widely used in industry for process monitoring (Nomikos and MacGregor, 1995;Qin, 2003;Ge and Song, 2008;Garcia-Alvarez et al, 2012). Other complementary multivariate statistical process monitoring methods, including canonical variate analysis, kernel PCA, dynamic PCA, and independent component analysis, have been proposed to address the limitations of PCA-or PLSbased monitoring strategies (Russell et al, 2000;Juricek et al, 2004;Lee et al, 2004a;2006).…”

Section: Introductionmentioning

confidence: 99%

Statistical process monitoring based on improved principal component analysis and its application to chemical processes

Tong

Yan

2013

J. Zhejiang Univ. Sci. A

View full text Add to dashboard Cite

Abstract:In this paper, a novel criterion is proposed to determine the retained principal components (PCs) that capture the dominant variability of online monitored data. The variations of PCs were calculated according to their mean and covariance changes between the modeling sample and the online monitored data. The retained PCs containing dominant variations were selected and defined as correlative PCs (CPCs). The new Hotelling's T 2 statistic based on CPCs was then employed to monitor the process. Case studies on the simulated continuous stirred tank reactor and the well-known Tennessee Eastman process demonstrated the feasibility and effectiveness of the CPCs-based fault detection methods.

show abstract

Fault detection and isolation in transient states using principal component analysis

Cited by 51 publications

References 33 publications

Entropy principal component analysis and its application to nonlinear chemical process fault diagnosis

Entropy principal component analysis and its application to nonlinear chemical process fault diagnosis

Quality-relevant fault detection and diagnosis for hot strip mill process with multi-specification and multi-batch measurements

Statistical process monitoring based on improved principal component analysis and its application to chemical processes

Contact Info

Product

Resources

About