Abstract
A multivariate method for fault diagnosis and process monitoring is proposed. This technique is based on a statistical pattern (SP) framework integrated with a self-organizing map (SOM). An SP-based SOM is used as a classifier to distinguish various states on the output map, which can visually monitor abnormal states. A case study of the Tennessee Eastman (TE) process is presented to demonstrate the fault diagnosis and process monitoring performance of the proposed method. Results show that the SP-based SOM method is a visual tool for real-time monitoring and fault diagnosis that can be used in complex chemical processes. Compared with other SOM-based methods, the proposed method can more efficiently monitor and diagnose faults.
Similar content being viewed by others
References
CHIANG L H, BRAATZ R D, RUSSELL E L. Fault detection and diagnosis in industrial systems [M]. Berlin, Germany: Springer, 2001.
GE Zhi-qiang, SONG Zhi-huan. Multivariate statistical process control: Process monitoring methods and applications [M]. Berlin, Germany: Springer, 2013.
CHIANG L H, RUSSELL E L, BRAATZ R D. Fault diagnosis in chemical processes using Fisher discriminant analysis, discriminant partial least squares, and principal component analysis [J]. Chemometrics and intelligent laboratory systems, 2000, 50(2): 243–252.
JIANG Qing-chao, YAN Xue-feng. Statistical monitoring of chemical processes based on sensitive kernel principal components [J]. Chinese Journal of Chemical Engineering, 2013, 21(6): 633–643.
ODIOWEI P E P, CAO Yi. Nonlinear dynamic process monitoring using canonical variate analysis and kernel density estimations [J]. IEEE Transactions on Industrial Informatics, 2010, 6(1): 36–45.
KANO M, HASEBE S, HASHIMOTO I, OHNO H. Statistical process monitoring based on dissimilarity of process data [J]. AIChE Journal, 2002, 48(6): 1231–1240.
YELAMOS I, ESCUDERO G, GRAELLS M, PUIGJANER L. Performance assessment of a novel fault diagnosis system based on support vector machines [J]. Computers & Chemical Engineering, 2009, 33(1): 244–255.
YU J, QIN S J. Multimode process monitoring with Bayesian inference-based finite Gaussian mixture models [J]. AIChE Journal, 2008, 54(7): 1811–1829.
YU Jian-bo. Hidden Markov models combining local and global information for nonlinear and multimodal process monitoring [J]. Journal of Process Control, 2010, 20(3): 344–359.
WANG Cun-jie, ZHAO Yu-hong. A new fault detection method based on artificial immune systems [J]. Asia-Pacific Journal of Chemical Engineering, 2008, 3(6): 706–711.
ZHAO Jin-song, SHU Yi-dan, ZHU Jian-feng, DAI Yi-yang. An online fault diagnosis strategy for full operating cycles of chemical processes [J]. Industrial & Engineering Chemistry Research, 2014, 53(13): 5015–5027.
HE Q P, WANG J. Statistics pattern analysis: A new process monitoring framework and its application to semiconductor batch processes [J]. AIChE Journal, 2011, 57(1): 107–121.
WANG J, HE Q P. Multivariate statistical process monitoring based on statistics pattern analysis [J]. Industrial & Engineering Chemistry Research, 2010, 49(17): 7858–7869.
GALICIA H J, HE Q P, WANG J. A comprehensive evaluation of statistics pattern analysis based process monitoring [C]// International Symposium on Advanced Control of Chemical Processes, Furama Riverfront, Singapore: ADCHEM. 2012: 39–44.
CHEN Xin-yi, YAN Xue-feng. Fault diagnosis in chemical process based on self-organizing map integrated with fisher discriminant analysis [J]. Chinese Journal of Chemical Engineering, 2013, 21(4): 382–387.
WU Si-tao, CHOW T W S. Induction machine fault detection using SOM-based RBF neural networks [J]. IEEE Transactions on Industrial Electronics, 2004, 51(1): 183–194.
SIROLA M, TALONEN J, LAMPI G. SOM based methods in early fault detection of nuclear industry [C]// 17th European Symposium on Artificial Neural Networks, Burge, Belgium: ESANN, 2009.
ZHONG Fei, SHI Tie-lin, HE Tao. Fault diagnosis of motor bearing using self-organizing maps [C]// Electrical Machines and Systems, 2005. ICEMS 2005. Proceedings of the Eighth International Conference on. Nanjing: IEEE, 2005: 2411–2414.
CHEN Xin-yi, YAN Xue-feng. Using improved self-organizing map for fault diagnosis in chemical industry process [J]. Chemical Engineering Research and Design, 2012, 90(12): 2262–2277.
KOHONEN T. Self-organizing maps [M]. Germany: Springer, 2001.
ULTSCH A. U*-matrix: A tool to visualize clusters in high dimensional data [M]. Berlin: Fachbereich Mathematik und Informatik, 2003.
NG Y S, SRINIVASAN R. Multivariate temporal data analysis using self-organizing maps. 2. Monitoring and diagnosis of multistate operations [J]. Industrial & Engineering Chemistry Research, 2008, 47(20): 7758–7771.
DOWMS J J, VOGEL E F. A plant-wide industrial process control problem [J]. Computers & Chemical Engineering, 1993, 17(3): 245–255.
LYMAN P R, GEORGAKIS C. Plant-wide control of the Tennessee Eastman problem [J]. Computers & Chemical Engineering, 1995, 19(3): 321–331.
ZHU Zhi-bo, SONG Zhi-huan, PALAZOGLU A. Transition process modeling and monitoring based on dynamic ensemble clustering and multiclass support vector data description [J]. Industrial & Engineering Chemistry Research, 2011, 50(24): 13969–13983.
Author information
Authors and Affiliations
Corresponding author
Additional information
Foundation item: Project(2013CB733605) supported by the National Basic Research Program of China; Project(21176073) supported by the National Natural Science Foundation of China; Project supported by the Fundamental Research Funds for the Central Universities, China
Rights and permissions
About this article
Cite this article
Song, Y., Jiang, Qc. & Yan, Xf. Fault diagnosis and process monitoring using a statistical pattern framework based on a self-organizing map. J. Cent. South Univ. 22, 601–609 (2015). https://doi.org/10.1007/s11771-015-2561-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11771-015-2561-3