Mixed kernel canonical variate dissimilarity analysis for incipient fault monitoring in nonlinear dynamic processes

Simple item page
dc.contributor.authorPilario, Karl Ezra
dc.contributor.authorCao, Yi
dc.contributor.authorShafiee, Mahmood
dc.date.accessioned2019-02-18T16:16:57Z
dc.date.available2019-02-18T16:16:57Z
dc.date.issued2018-12-25
dc.description.abstractIncipient fault monitoring is becoming very important in large industrial plants, as the early detection of incipient faults can help avoid major plant failures. Recently, Canonical Variate Dissimilarity Analysis (CVDA) has been shown to be an efficient technique for incipient fault detection, especially under dynamic process conditions. CVDA can be extended to nonlinear processes by introducing kernel-based learning. Incipient fault monitoring requires kernels with both good interpolation and extrapolation abilities. However, conventional single kernels only exhibit one ability or the other, but not both. To overcome this drawback, this study presents a Mixed Kernel CVDA method for incipient fault monitoring in nonlinear dynamic processes. Due to the use of mixed kernels, both enhanced detection sensitivity and a better depiction of the growing fault severity in the monitoring charts are achieved. Looking ahead, this work takes a step towards understanding the impact of kernel behavior in process monitoring performance.en_UK
dc.identifier.citationPilario KE, Cao Y, Shafiee M. Mixed kernel canonical variate dissimilarity analysis for incipient fault monitoring in nonlinear dynamic processes. Computers and Chemical Engineering, Volume 123, April 2019, pp. 143-154en_UK
dc.identifier.issn0098-1354
dc.identifier.urihttps://doi.org/10.1016/j.compchemeng.2018.12.027
dc.identifier.urihttp://dspace.lib.cranfield.ac.uk/handle/1826/13913
dc.language.isoenen_UK
dc.publisherElsevieren_UK
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjectFault detectionen_UK
dc.subjectCanonical variate analysisen_UK
dc.subjectGlobal kernelen_UK
dc.subjectLocal kernelen_UK
dc.subjectKernel density estimationen_UK
dc.titleMixed kernel canonical variate dissimilarity analysis for incipient fault monitoring in nonlinear dynamic processesen_UK
dc.typeArticleen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Mixed_kernel_canonical_variate_dissimilarity_analysis-2018.pdf
Size:
2.62 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (SWEE)