Incremental Fault Diagnosis for Nonlinear Processes

Abstract:

A new faults classification method based on on-line independent support vector machine (OISVM) is proposed for fault diagnosis in nonlinear processes. Fault diagnosis can be taken as a pattern recognition problem. As most processes are intrinsically nonlinear, support vector machines (SVMs) are one of the most popular and promising classification algorithms. The fatal drawbacks of standard SVM is the computing overhead grows with the number of training samples, where as training samples from real industrial processes are increasing with time grows. An incremental fault diagnosis approach based on OISVM is proposed in this work. Some related problem such as variable selection and parameter setting are also discussed in this work. Simulation results on the Tennessee Eastman process (TEP) demonstrate the effectiveness of the proposed method.

• Periodical: Advanced Materials Research (Volumes 433-440)
• Pages: 6430-6436
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.433-440.6430
• Online since: January 2012
• Authors: Ke Chang Fu, Zhu Ming, Peng Liu, Guo Jiang Wang
• Keywords: Classification, Incremental Fault Diagnosis, Support Vector Machine (SVM)

References

[1] J. Gertler, W. Li, Y. Huang, T. J. McAvoy, Isolation enhanced principal component analysis, AIChE Journal, vol. 45, no. 2, 1999, pp.323-334.

DOI: 10.1002/aic.690450213

[2] S. J. Qin, W. Li, Detection, identification and reconstruction of faulty sensors with maximized sensitivity, AIChE Journal, vol. 45, no. 9, 1999, p.1963-(1976).

DOI: 10.1002/aic.690450913

[3] S. J. Qin, W. Li, Detection and identification of faulty sensors in dynamic processes, AIChE Journal, vol. 47(7) , 2001, pp.1581-1593.

DOI: 10.1002/aic.690470711

[4] L. H. Chiang, M. E. Kotanchek, A. K. Kordon, Fault diagnosis based on Fisher discriminant analysis and support vector machines, Computers & Chemical Engineering, vol. 28, 2008, pp.1389-1401.

DOI: 10.1016/j.compchemeng.2003.10.002

[5] O. Francesco, C. Claudio, C. Barbara, J. Luo, S. Giulio, On-line independent support vector machines, Pattern Recognition, vol. 43, 2010, pp.1401-1412.

[6] K. Manabu, S. Tannaka, S. Hasebe, I. Hashimoto, Monitoring independent components for fault detection, AIChE Journal, vol. 49, no. 4, 2003, pp.969-976.

DOI: 10.1002/aic.690490414

[7] J. Bins and B. Draper, Feature selection from huge feature sets, in Proc. Int. Conf. Comput. Vis., Vancouver, BC, Canada, Jul. 2001, p.159–165.

DOI: 10.1109/iccv.2001.937619

[8] M. A. Hall, Correlation-based feature selection for machine learning, Ph.D. dissertation, Dept. Comput. Sci., Univ. Waikato, Waikato, New Zealand, (1999).

[9] G. Lashkia and L. Anthony, Relevant, irredundant feature selection and noisy example elimination, IEEE Trans. Syst. Man Cybern. B, Cybern., vol. 34, no. 2, Apr. 2004, p.888–897.

DOI: 10.1109/tsmcb.2003.817106

[10] L. Yu, H. Liu, Efficient feature selection via analysis of relevance and redundancy, , Jounal of Machine Learning Research, vol. 5, 2004, pp.1205-1224.

[11] J. Downs, E. Vogel, Plant-wide industrial process control problem, Computers and Chemical Engineering, vol. 17, no. 3, 1993, 245–255.

DOI: 10.1016/0098-1354(93)80018-i

[12] P.R. Lyman, C. Georgakis, Plant-wide control of the Tennessee Eastman problem, Computers and Chemical Engineering, vol. 19, 1995, p.321–331.

DOI: 10.1016/0098-1354(94)00057-u

[13] A. Kulkarni, V. Jayaraman, B. Kulkarni, Knowledge incorporated support vector machines to detect faults in tennessee eastman process, Computers and Chemical Engineering, vol. 29, no. 10, 2005, p.2128–2133.

DOI: 10.1016/j.compchemeng.2005.06.006

[14] S. Verron *, T. Tiplica, A. Kobi, Fault detection and identification with a new feature selection based on mutual information, Journal of Process Control, vol. 18, 2008, p.479–490.

DOI: 10.1016/j.jprocont.2007.08.003

[15] S. Canu, Y. Grandvalet, V. Guigue, A. Rakotomamonjy, SVM and Kernel Methods Matlab Toolbox , Perception Systèmes et Information, INSA de Rouen, Rouen, France，(2005).