Fault detection and diagnosis in process data using one-class support vector machines

Abstract In this paper, a new approach for fault detection and diagnosis based on One-Class Support Vector Machines (1-class SVM) has been proposed. The approach is based on a non-linear distance metric measured in a feature space. Just as in principal components analysis (PCA) and dynamic principal components analysis (DPCA), appropriate distance metrics and thresholds have been developed for fault detection. Fault diagnosis is then carried out using the SVM-recursive feature elimination (SVM-RFE) feature selection method. The efficacy of this method is demonstrated by applying it on the benchmark Tennessee Eastman problem and on an industrial real-time Semiconductor etch process dataset. The algorithm has been compared with conventional techniques such as PCA and DPCA in terms of performance measures such as false alarm rates, detection latency and fault detection rates. It is shown that the proposed algorithm outperformed PCA and DPCA both in terms of detection and diagnosis of faults.

[1]  E. F. Vogel,et al.  A plant-wide industrial process control problem , 1993 .

[2]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[3]  Nina F. Thornhill,et al.  Automatic detection and quantification of stiction in control valves , 2006 .

[4]  Christos Georgakis,et al.  Plant-wide control of the Tennessee Eastman problem , 1995 .

[5]  Richard D. Braatz,et al.  Fault detection in industrial processes using canonical variate analysis and dynamic principal component analysis , 2000 .

[6]  Sachin C. Patwardhan,et al.  Plant-wide detection and diagnosis using correspondence analysis☆ , 2007 .

[7]  A. J. Morris,et al.  Statistical performance monitoring of dynamic multivariate processes using state space modelling , 2002 .

[8]  S. Joe Qin,et al.  Statistical process monitoring: basics and beyond , 2003 .

[9]  C. Yoo,et al.  Nonlinear process monitoring using kernel principal component analysis , 2004 .

[10]  Nina F. Thornhill,et al.  Advances and new directions in plant-wide disturbance detection and diagnosis , 2007 .

[11]  In-Beum Lee,et al.  Fault Detection of Non-Linear Processes Using Kernel Independent Component Analysis , 2008 .

[12]  Jin Wang,et al.  Fault Detection Using the k-Nearest Neighbor Rule for Semiconductor Manufacturing Processes , 2007, IEEE Transactions on Semiconductor Manufacturing.

[13]  Isabelle Guyon,et al.  Comparison of classifier methods: a case study in handwritten digit recognition , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5).

[14]  Yingwei Zhang,et al.  Fault Detection and Diagnosis of Nonlinear Processes Using Improved Kernel Independent Component Analysis (KICA) and Support Vector Machine (SVM) , 2008 .

[15]  Jason Weston,et al.  Gene Selection for Cancer Classification using Support Vector Machines , 2002, Machine Learning.

[16]  Chih-Jen Lin,et al.  Asymptotic Behaviors of Support Vector Machines with Gaussian Kernel , 2003, Neural Computation.

[17]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[18]  Ali Cinar,et al.  Statistical process and controller performance monitoring. A tutorial on current methods and future directions , 1999, Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251).

[19]  In-Beum Lee,et al.  Fault detection and diagnosis based on modified independent component analysis , 2006 .

[20]  Richard D. Braatz,et al.  Fault Detection and Diagnosis in Industrial Systems , 2001 .

[21]  Thomas E. Marlin,et al.  Multivariate statistical monitoring of process operating performance , 1991 .

[22]  Christopher J. C. Burges,et al.  A Tutorial on Support Vector Machines for Pattern Recognition , 1998, Data Mining and Knowledge Discovery.

[23]  P. Miller,et al.  Contribution plots: a missing link in multivariate quality control , 1998 .

[24]  J. Macgregor,et al.  Monitoring batch processes using multiway principal component analysis , 1994 .

[25]  Masayuki Tamura,et al.  A study on the number of principal components and sensitivity of fault detection using PCA , 2007, Comput. Chem. Eng..

[26]  Barry M. Wise,et al.  A comparison of principal component analysis, multiway principal component analysis, trilinear decomposition and parallel factor analysis for fault detection in a semiconductor etch process , 1999 .

[27]  V. Vapnik.  Estimation of Dependences Based on Empirical Data , 2006 .

[28]  Bernhard Schölkopf,et al.  Estimating the Support of a High-Dimensional Distribution , 2001, Neural Computation.

[29]  J. Macgregor,et al.  Experiences with industrial applications of projection methods for multivariate statistical process control , 1996 .

[30]  Christos Georgakis,et al.  Disturbance detection and isolation by dynamic principal component analysis , 1995 .