New Features for Fault Diagnosis by Supervised Classification

The purpose of this article is to present a method for industrial process diagnosis. We are interested in fault diagnosis considered as a supervised classification task. The interest of the proposed method is to take into account new features (and so new informations) in the classifier. These new features are probabilities extracted from a Bayesian network comparing the faulty observations to the normal operating conditions. The performances of this method are evaluated on the data of a benchmark example: the Tennessee Eastman Process. Three kinds of fault are taken into account on this complex process. We show on this example that the addition of these new features allows to decrease the misclassification rate.

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

[2]  N. Lawrence Ricker,et al.  Decentralized control of the Tennessee Eastman Challenge Process , 1996 .

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

[4]  Balbir S. Dhillon,et al.  Reliability, Quality, and Safety for Engineers , 2004 .

[5]  Rolf Isermann,et al.  Fault-diagnosis systems : an introduction from fault detection to fault tolerance , 2006 .

[6]  Douglas C. Montgomery,et al.  Introduction to Statistical Quality Control , 1986 .

[7]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[8]  Jianjun Shi,et al.  Causation-Based T2 Decomposition for Multivariate Process Monitoring and Diagnosis , 2008 .

[9]  Paul M. Frank,et al.  Issues of Fault Diagnosis for Dynamic Systems , 2010, Springer London.

[10]  H. Hotelling,et al.  Multivariate Quality Control , 1947 .

[11]  Nola D. Tracy,et al.  Decomposition of T2 for Multivariate Control Chart Interpretation , 1995 .

[12]  Finn Verner Jensen,et al.  Introduction to Bayesian Networks , 2008, Innovations in Bayesian Networks.

[13]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part III: Process history based methods , 2003, Comput. Chem. Eng..

[14]  M. Aizerman,et al.  Theoretical Foundations of the Potential Function Method in Pattern Recognition Learning , 1964 .

[15]  Stephen P. Gurden,et al.  Standardized Q‐statistic for improved sensitivity in the monitoring of residuals in MSPC , 2000 .

[16]  Manabu Kano,et al.  Comparison of multivariate statistical process monitoring methods with applications to the Eastman challenge problem , 2002 .

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