Real-time statistical detection and identification of sensor incipient fault using Kalman filter

This article describes a real-time statistical approach of fault detection for linear time-invariant (LTI) system subject to incipient fault profile. The proposed methodology combines Kalman filter for fault detection index generation and Generalized Likelihood Ratio (GLR) test that cancels out the monitored fault effect dynamics. Maximum Likelihood Estimation (MLE) has been used for signature correlation, statistical distance measure between defined hypotheses and estimation of an unknown parameter to carry out fault identification. To illustrate the effectiveness of proposed method numerical results for temperature sensor incipient fault detection and identification have been presented for a pressurizer of the Pressurized Water Reactor (PWR).

[1]  Donald E. Gustafson,et al.  ECG/VCG Rhythm Diagnosis Using Statistical Signal Analysis-I. Identification of Persistent Rhythms , 1978, IEEE Transactions on Biomedical Engineering.

[2]  Harold Lee Jones,et al.  Failure detection in linear systems , 1973 .

[3]  A. Willsky,et al.  A generalized likelihood ratio approach to state estimation in linear systems subjects to abrupt changes , 1974, CDC 1974.

[4]  Janos J. Gertler,et al.  Analytical Redundancy Methods in Fault Detection and Isolation , 1991 .

[5]  Marios M. Polycarpou,et al.  Incipient fault diagnosis of dynamical systems using online approximators , 1998 .

[6]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[7]  John F. MacGregor,et al.  Process monitoring and diagnosis by multiblock PLS methods , 1994 .

[8]  Asok Ray,et al.  A fault detection and isolation methodology , 1981, 1981 20th IEEE Conference on Decision and Control including the Symposium on Adaptive Processes.

[9]  Catherine M.F. Rae,et al.  An Improved Nickel Based MIMS Thermocouple for High Temperature Gas Turbine Applications , 2013 .

[10]  H. Hashemian.  On-line monitoring applications in nuclear power plants , 2011 .

[11]  Andrei V. Gribok,et al.  Regularization of Feedwater Flow Rate Evaluation for Venturi Meter Fouling Problem in Nuclear Power Plants , 2001 .

[12]  Józef Korbicz,et al.  A Knowledge-Based System with Embedded Estimation Components for Fault Detection and Isolation in Process Plants , 1992 .

[13]  Rolf Isermann,et al.  Model-based fault-detection and diagnosis - status and applications , 2004, Annu. Rev. Control..

[14]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part I: Quantitative model-based methods , 2003, Comput. Chem. Eng..

[15]  J. Louis Tylee,et al.  A Generalized Likelihood Ratio Approach to Detecting and Identifying Failures in Pressurizer Instrumentation , 1982 .

[16]  F. Gustafsson.  The marginalized likelihood ratio test for detecting abrupt changes , 1996, IEEE Trans. Autom. Control..

[17]  A. Benveniste,et al.  Desgin and comparative study of some sequential jump detection algorithms for digital signals , 1983 .

[18]  R. K. Mehra,et al.  Correspondence item: An innovations approach to fault detection and diagnosis in dynamic systems , 1971 .

[19]  Kallol Roy,et al.  Performance Evaluation of Statistical Method for Incipient Fault Detection under Noisy Environment , 2017 .

[20]  George V. Moustakides,et al.  Detection and diagnosis of changes in the eigenstructure of nonstationary multivariable systems , 1987, Autom..

[21]  Michèle Basseville,et al.  Statistical detection and isolation of additive faults in linear time-varying systems , 2014, Autom..

[22]  E. Gilles,et al.  Multiple filter methods for detection of hazardous states in an industrial plant , 1990 .

[23]  Janos Gertler,et al.  A new structural framework for parity equation-based failure detection and isolation , 1990, Autom..