An online outlier detection method for process control time series

Author

Fang, Liu ; Zhi-zhong, Mao

Author_Institution

Sch. of Inf. Sci. & Eng., Northeastern Univ., Shenyang, China

fYear

2011

fDate

23-25 May 2011

Firstpage

3263

Lastpage

3267

Abstract

The ability to detect outlier online in process control filed is essential in many real-world system analysis applications. Previous algorithms require some ”clean” data to construct the statistical model at beginning, which was used to detect outlier. But actually, these clean data can not obtain at all. In this paper, we investigate a machine learning, descriptor-based approach that dose not require clean data to model, based on least square support vector outlier detection. A online window-based learn algorithm is introduced. Theoretical consideration as well as simulations on real process data demonstrate its practical efficiency.

Keywords

arc furnaces; data analysis; learning (artificial intelligence); least squares approximations; process control; production engineering computing; statistical analysis; support vector machines; time series; arc furnace; descriptor-based approach; least square support vector outlier detection; machine learning; online outlier detection method; online window-based learning algorithm; process control time series; statistical model; system analysis application; Artificial neural networks; Data models; Detection algorithms; Indexes; Process control; Support vector machines; Training; least square support vector; online detection; outlier detection; process control;

fLanguage

English

Publisher

ieee

Conference_Titel

Control and Decision Conference (CCDC), 2011 Chinese

Conference_Location

Mianyang

Print_ISBN

978-1-4244-8737-0

Type

conf

DOI

10.1109/CCDC.2011.5968820

Filename

5968820