Diagnosis of Multivariate Process via Nonlinear Kernel Method Combined with Qualitative Representation of Fault Patterns

The fault detection and diagnosis of complicated production processes is one of essential tasks needed to run the process safely with good final product quality. Unexpected events occurred in the process may have a serious impact on the process. In this work, triangular representation of process measurement data obtained in an on-line basis is evaluated using simulation process. The effect of using linear and nonlinear reduced spaces is also tested. Their diagnosis performance was demonstrated using multivariate fault data. It has shown that the nonlinear technique based diagnosis method produced more reliable results and outperforms linear method. The use of appropriate reduced space yielded better diagnosis performance. The presented diagnosis framework is different from existing ones in that it attempts to extract the fault pattern in the reduced space, not in the original process variable space. The use of reduced model space helps to mitigate the sensitivity of the fault pattern to noise.

Authors:

• Hyun-Woo Cho

Keywords:

• Real-time Fault diagnosis
• triangular representation of patterns in reduced spaces
• Nonlinear kernel technique
• multivariate statistical modeling.

References:

[1] F. Akbaryan, and P. R. Bishnoi, "Fault diagnosis of multivariate systems
using pattern recognition and multisensor data analysis technique,"
Computers and Chemical Engineering, vol. 25, pp. 1313-1339, 2001.
[2] A. K. S. Jardine, D. Lin, D. Banjevic, "A review on machinery diagnostics
and prognostics implementing condition-based maintenance,"
Mechanical Systems and Signal Processing, vol. 20, pp. 1483-1510,
2006.
[3] V. A. Sotiris, P. W. Tse, and M. G. Pecht, "Anomaly detection through a
bayesian support vector machine," IEEE Transactions on Reliability, vol.
59, pp. 277-286 , 2010.
[4] R. Lombardo, J.-F. Durand, A. P. Leone, "Multivariate additive PLS
spline boosting in agro-chemistry studies," Current Analytical Chemistry,
vol. 8, pp. 236-253, 2012.
[5] L. H. Chiang, E. L. Russell, and R. D. Braatz, "Fault diagnosis in chemical
processes using Fisher discriminant analysis, discriminant partial least
squares, and principal component analysis," Chemometrics and
Intelligent Laboratory Systems, vol. 50, pp. 243-252, 2000.
[6] J. C. Wong, K. A. Mcdonald, and A. Palazoglu, "Classification of
abnormal plant operation using multiple process variable trends," Journal
of Process Control, vol. 11, pp. 409-418. 2001.
[7] A. Bakhtazad, A. Palazoglu, and J. A. Romagnoli, "Detection and
classification of abnormal process situations using multidimensional
wavelet domain hidden markov trees," Computers and Chemical
Engineering, vol. 24, pp. 769-775. 2000.
[8] M. Misra, S. J. Qin, H. Yue, and C. Ling, "Multivariate process
monitoring and fault identification using multi-scale PCA," Computers
and Chemical Engineering, vol. 26, pp. 1281-1293, 2002.
[9] P. K. Kankar, S. C. Sharma, and S. P. Harsha, "Faultdiagnosis of ball
bearings using machine learning methods," Expert Systems with
Applications, vol. 38, pp. 1876-1886, 2011.
[10] L. Dobos, and J. Abonyi, "On-line detection of homogeneous operation
ranges by dynamic principal component analysis based time-series
segmentation," Chemical Engineering Science, vol. 75, pp. 96-105, 2012.
[11] J. McBain, and M. Timusk, " Feature extraction for novelty detection as
applied to fault detection in machinery," Pattern Recognition Letters, vol.
32, pp. 1054-1061, 2011.
[12] J. T.-Y. Cheung, and G. Stephanopoulos, "Representation of process
trends-part I. a formal representation framework," Computers and
Chemical Engineering, vol. 14, pp. 495-510, 1990.
[13] J. J. Downs, and E. F. Vogel, "A plant-wide industrial process problem,"
Computers and Chemical Engineering, vol. 7, pp. 245-255, 1993.