An improved methodology for outlier detection in dynamic datasets. Issue 2 (12th October 2014)

• Record Type: Journal Article
• Authors: Xu, Shu; Baldea, Michael; Edgar, Thomas F.; Wojsznis, Willy; Blevins, Terrence; Nixon, Mark
• Is Part Of: AIChE journal. Volume 61:Issue 2(2015:Feb.)
• Page Start: 419
• Page End: 433
• Publication Date: 2014-10-12
• Subjects: Chemical engineering -- Periodicals; Génie chimique -- Périodiques; 660.28
• DOI: 10.1002/aic.14631
• Languages: English
• ISSNs: 0001-1541

Abstract

<abstract abstract-type="main"> <title> <x xml:space="preserve">Abstract</x> </title> <p>A time series Kalman filter (TSKF) is proposed that successfully handles outlier detection in dynamic systems, where normal process changes often mask the existence of outliers. The TSKF method combines a time series model fitting procedure with a modified Kalman filter to deal with additive outlier and innovational outlier detection problems in dynamic process dataset. Compared with current outlier detection methods, the new method enjoys the following advantages: (a) no prior knowledge of the process model is needed; (b) it is easy to tune; (c) it can be applied to both univariate and multivariate outlier detection; (d) it is applicable to both on‐line and off‐line operation; (e) it cleans outliers while maintains the integrity of the original dataset. © 2014 American Institute of Chemical Engineers <italic>AIChE J</italic>, 61: 419–433, 2015</p> </abstract>