A new fault detection scheme based on canonical independent component analysis with application to hot strip mill process

Abstract

Aiming at the problems of inaccurate fault detection and error alarm in the process of hot strip mill process, a fault detection scheme of canonical independent component analysis is proposed. The new scheme first uses canonical variable analysis to calculate the canonical variable matrix of observation data, which effectively solves the problem of autocorrelation and cross-correlation. Then the canonical variable matrix is decomposed by independent component analysis to obtain independent elements. Finally, the data are monitored online through constructing statistics. It is proved that the accuracy of the scheme for identifying fault data is reached to 100%, and the misjudgment rate data are reduced to less than 0.6% through the simulation study of the hot strip mill process data.

Keywords

Fault detection canonical variable analysis independent component analysis hot strip mill process dynamic system

Get full access to this article

View all access options for this article.

References

Chen

Zhang

, et al. Fault detection for turbine engine disk using adaptive Gaussian mixture model. Proc IMechE, Part I: J Systems and Control Engineering 2017; 231(10): 827–835.

Xie

Wang

PCA model principal component number determination based on fault reconstruction. J Northeastern Univ 2004; 1: 20–23.

Sharmin

Shah

Sundararaj

A PCA based fault detection scheme for an industrial high pressure polyethylene reactor. Macromol React Eng 2008; 2(1): 12–30.

Samuel

Cao

Nonlinear process fault detection and identification using kernel PCA and kernel density estimation. Syst Sci Control Eng 2016; 4(1): 165–174.

Zhang

Zong

Ling

. Fault diagnosis using kernel principal component analysis for hot strip mill. J Eng 2017(9): 527–535.

Guo

Dong

JK.

Fault diagnosis for the landing phase of the aircraft based on an adaptive kernel principal component analysis algorithm. Proc IMechE, Part I: J Systems and Control Engineering 2015; 229(10): 917–926.

Kano

Tanaka

Hasebe

, et al. Monitoring independent components for fault detection. AIChE J 2003; 49(4): 969–976.

Hau

Chen

LS.

Integrating independent component analysis and support vector machine for multivariate process monitoring. Comput Ind Eng 2010; 59(1): 145–156.

Wang

. Chiller gradual fault detection based on independent component analysis. In: 27th Chinese control and decision conference (CCDC), Qingdao, China, 23–25 May 2015, pp.2435–2439. New York: IEEE.

10.

Zhang

Deng

XG.

Multimode non-Gaussian process monitoring based on local entropy independent component analysis. Canad J Chem Eng 2017; 95(2): 319–330.

11.

Deng

Tian

XM.

Fault diagnosis method based on robust canonical variate analysis. Control Decis 2008; 4: 415–419.

12.

Stubbs

Zhang

Morris

Fault detection in dynamic processes using a simplified monitoring-specific CVA state space modelling approach. Comput Chem Eng 2012; 41: 77–87.

13.

Yin

Wei

Gao

, et al. Data-driven quality related prediction and monitoring. In: 38th annual conference on IEEE industrial electronics society, Montreal, QC, Canada, 25–28 October 2012, pp.3874–3879. New York: IEEE.

14.

Zhang

Dong

Peng

KX.

A novel dynamic non-Gaussian approach for quality-related fault diagnosis with application to the hot strip mill process. J Franklin Inst 2017; 354(2): 702–721.

15.

Dong

Peng

, et al. A novel data-based quality-related fault diagnosis scheme for fault detection and root cause diagnosis with application to hot strip mill process. Control Eng Pract 2017; 67: 43–51.

16.

Wang

Pan

Yang

Fault diagnosis of rolling bearing using CVA based detector. J Vibroeng 2016; 18(7): 4285–4298.

17.

Odiowei

Cao

Nonlinear dynamic process monitoring using canonical variate analysis and kernel density estimations. IEEE T Ind Inform 2010; 6(1): 36–45.