Hata bulma yöntemlerinin yanlış alarm oranları

Bu çalışma bağımsız bileşen analiz (BBA) ve temel bileşen analiz (TBA) algoritmalarının Tennessee Eastman (TE) süreci üzerindeki hata bulma ve yanlış alarm oranları (YAO) üzerine yoğunlaşmaktadır. TBA ve ICA algoritmaları, veri tabanlı hata bulmak için oldukça fazla uygulanmalarına rağmen, algoritmaların YAO üzerine sınırlı çalışma vardır. Bu çalışmada, algoritmaların YAO’ları TE süreci üzerinde incelenecektir. Simülasyon çalışmaları, sunulan algoritmalar hata bulmada oldukça doğruyken, YAO’ları için BBA’nın TBA’dan daha yüksek performansa sahip olduğunu göstermiştir.

Anahtar Kelimeler:

Süreç Gözlemleme, Hata Bulma, Bağımsız Bileşen Analiz, Temel Bileşen Analiz, T^2 istatistik

False alarm rates of fault detection methods

This study focuses on the fault detection (FD) and false alarm rates (FAR) of Principal component analysis (PCA) and independent component analysis (ICA) algorithms on the Tennessee Eastman (TE) process. However, PCA and ICA algorithms have been applied widely to systems for data driven fault detection, there are limited work on FARs of the algorithms. In this work, FARs of the algorithms are investigated on TE process. Simulation study indicates that the proposed algorithms are robust for fault detection, and ICA has higher performance than PCA for FARs.

Keywords:

Process Monitoring, Fault Detection, Independent Component Analysis, Principal Component Analysis, T^2 Statistics,

PDF

___

[1] J. Chen ve R. J. Patton, Robust Model-Based Diagnosis for Dynamics Systems, Kluber Academic Publisher, 1999.
[2] T. Kourti, “Process analysis and abnormal situation detection: from theory to practice,” Control Systems, IEEE 22.5, 10-25, 2002.
[3] S. Yin, ve ark., “A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark Tennessee Eastman process,” Journal of Process Control 22.9, 1567-1581, 2012.
[4] T. Villegas, M. J. Fuente ve M. Rodríguez, “Principal component analysis for fault detection and diagnosis. experience with a pilot plant,” in CIMMACS'10 Proceedings of the 9th WSEAS international conference on computational intelligence, man-machine systems and cybernetics, 2010.
[5] J. Lee, C. K. Yoo ve I. Lee, “Statistical process monitoring with independent component analysis,” Journal of Process Control14.5, 467-485, 2004.
[6] H. Abdi ve J. W. Lynne, “Principal component analysis,” Wiley Interdisciplinary Reviews: Computational Statistics 2.4, 433-459, 2010.
[7] A. Hyvärinen, “Fast and robust fixed-point algorithms for independent component analysis,” Neural Networks, IEEE Transactions on 10.3, 626-634, 1999.
[8] J. F. MacGregor, T. Kourti ve P. Nomikos, “Analysis, monitoring and fault diagnosis of industrial processes using multivariate statistical projection methods,” in Proceedings of 13th IFAC World Congress, San Francisco, USA, 1996.
[9] B. Wise ve N. B. Gallagher, “The process chemometrics approach to process monitoring and fault detection,” Journal of Process Control 6.6, 329-348, 1996.
[10] D. Dong ve T. J. McAvoy, “Nonlinear principal component analysis—based on principal curves and neural networks,” Computers & Chemical Engineering 20.1, 65-78, 1996.
[11] A. Belouchrani ve ark., “A blind source separation technique using second-order statistics,” Signal Processing, IEEE Transactions on 45.2, 434-444, 1997.
[12] A. Yeredor, “Blind separation of Gaussian sources via second-order statistics with asymptotically optimal weighting,” IEEE Signal Processing Letters 7.7, 197-200, 2000.
[13] S. Ding ve ark., “On the application of PCA technique to fault diagnosis,” Tsinghua Science & Technology 15.2, 138-144, 2010.
[14] J. E. Jackson ve G. S. Mudholkar, “Control procedures for residuals associated with principal component analysis,” Technometrics 21.3, 341-349, 1979.