A modified independent component analysis-based fault detection method in plant-wide systems

• Autorzy: Teimoortashloo M. , Sedigh A. K.
• Języki publikacji: EN

Abstrakty

EN

This paper presents a modified Independent Component Analysis (ICA)-based Fault Detection Method (FDM). The proposed FDM constructs a set of matrices, revealingthe trend of the variable samples and execute ICA algorithm for each set of matrices in contrast to the FDM based on dynamic ICA (DICA) which constructs the high dimensional augmented matrix. This paper shows that the proposed FDM decreases the matrix dimensions and as a result compensates for some disadvantages of using the high dimensional matrix discussed in previous articles. Furthermore, other advantages of the proposed FDM are the decreases in the running time, computational cost of the algorithm and the orthogonalization estimation errors. Moreover, the proposed method improves the detectability for a class of faults compared to DICA-based FDM. This class of fault occurs when two or more consecutive samples of fault source signal have opposite signs and cancel out each other. Simulation results are provided to show the effectiveness of the proposed methodology.

Słowa kluczowe

EN

DICA; fault detection; running time; orthogonalization

• Wydawca: Systems Research Institute, Polish Academy of Sciences
• Czasopismo: Control and Cybernetics
• Rocznik: 2015
• Tom: Vol. 44, no. 2
• Strony: 287--310
• Opis fizyczny: Bibliogr. 24 poz., rys., tab.

Twórcy

autor

Teimoortashloo M.

• Department of Electrical Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran

autor

Sedigh A. K.

• Industrial Control Center of Excellence, Department of Electrical and Computer Engineering, K.N. Toosi University of Technology, Tehran, Iran

Bibliografia

• 1. Chun-Chin H., Mu-Chen C., and Long-Sheng C. (2010) A Novel Process Monitoring Approach with Dynamic Independent Component Analysis. Control Engineering Practice, 18(3), 242 − 253.
• 2. Deng W., Liu Y, Hu J. and Guo J. (2012) The small sample size problem of ICA: A comparative study and analysis. Proc. on Pattern Recognition 45(12), 4438 − 4450.
• 3. Ge Z., Song Z. (2007) Process Monitoring Based on Independent Component Analysis Principal Component Analysis (ICA-PCA) and Similarity Factors. Industrial and Engineering Chemistry Research, 46(7), 2054−2063.
• 4. Hehe M., Yi H. and Hongbo S. (2011) Statistics Kernel Principal Component Analysis for nonlinear process fault detection. Intelligent Control and Automation (WCICA), 2011, 9th World Congress. IEEE Press, 431–436. http://depts.washington.edu/control/larrry/TE/download.html
• 5. Hyvarinen A. (1999) Fast and Robust Fixed-Point Algorithms for Independent Component Analysis. IEEE Trans. on Neural Networks, 10(3), 626 − 634.
• 6. Hyvarinen A., Karhunen J. and Oja E. (2001) Independent Component Analysis. John Wiley & Sons Inc., New York. Isermann R. (2006) Fault Diagnosis Systems. An Introduction From Fault Detection to Fault Tolerance. Springer, Berlin.
• 7. Jelali M. (2006) An overview of control performance assessment technology and industrial applications. Control Engineering Practice, 14(5), 441 − 466.
• 8. Jockenhovel T., Biegler L. T., and Wachter A. (2003) Dynamic optimization of Tennessee Eastman Process using the OptControlCenter. Computer and Chemical Engineering, 27, 1513− 1531.
• 9. Ko C. C., Chen B. M., Chen J., Zhuang Y., and Chen Tan K. (2001) Development of a Web-Based Laboratory for Control Experiments on a Coupled Tank Apparatus. IEEE Trans. on Education, 44(1), 76 − 86.
• 10. Ku V., Storer R. H., and Georgakis C. (1995) Disturbance detection and isolation by dynamic principal component analysis. Chemometrics and Intelligent Laboratory System, 30(1), 179 − 196.
• 11. Le Q.V., Karpenko A., Ngiam J. and Ng A.Y.(2011) ICA with Reconstruction Cost for Efficient Overcomplete Feature Learning. Advances in Neural Information Processing Systems 24, 1017− 1025. Lee T. W. (1998) Independent Component Analysis. Theory and Applications, Springer.
• 12. Lee J. M., Yoo C. K., and Lee I. B. (2004a) Statistical monitoring of dynamic processes based on dynamic independent component analysis. Chemical Engineering Science, 59(14), 2995 − 3006.
• 13. Lee J. M., Yoo C. K., and Lee I. B. (2004b) Statistical Process Monitoring With Independent Component Analysis. J. Process Control, 14(5), 467− 485.
• 14. Lee J. M., Qin J., and Lee I. B. (2006) Fault Detection and Diagnosis Based on Modified Independent Component Analysis. AIChE Journal, 52(10), 3501 − 3514. Martin E. B., and Morris A. J. (1996) Non Parametric Confidence Bounds for Process Performance Monitoring Charts. J. Process Control, 6(6), 349 − 358.
• 15. Nguyen V.H. and Golinval J.C. (2010) Fault detection based on Kernel Principal Component Analysis. Engineering Structure, 32(11), 3683−369.
• 16. Puntonet C. G. and Prieto A. (2004) Independent Component Analysis and Blind Signal Separation. Springer.
• 17. Thornhill N. F., and Horch A. (2007) Advances and new directions in plant-wide disturbance detection and diagnosis. Control Engineering Practice, 15(10), 1196− 1206.
• 18. Tharrault Y., Mourot G., Ragot J. and Maquin D. (2008) Fault detection and isolation with rob ust principal component analysis. International Journal of Applied Mathematics and Computer Science, 18(4), 429−442.
• 19. Tian Y., Du W. and Qian F. (2013) Fault Detection and Diagnosis For NonGaussian Processes with Periodic Disturbance Based on ARMA − ICA. Industrial and Engineering Chemistry Research, 52 (34), 12082− 12107.
• 20. Vinzi V. E., Chin W.W., Henseler J. and Wang H. (2010) Handbook of Partial Least Squares Concept. Methods and Applications. Springer, Berlin.
• 21. Wang L., Shi H. (2014) Improved Kernel PLS-Based Fault Detection Approach for Nonlinear Chemical Processes. Chinese Journal of Chemical Engineering, 22(6), 657 − 663.
• 22. Zhang Yw. and Zhang Y. (2010) Fault detection of non-Gaussian processes based on modified independent component analysis. Chemical Engineering Science, 65(16), 4630 − 4639.
• 23. Zhao X., Xue Y. and Wang T. (2014) Fault detection of batch process based on multiway Kernel T − PLS. Journal of Chemical and Pharmaceutical Research, 6(7), 338 − 346.
• 24. Zhao X. and Xue Y. (2014) Output Relevant Fault Detection and Identification of Chemical Process Based on Hybrid Kernel T − PLS. The Canadian Journal of Chemical Engineering, 92(10), 1822 − 1828.