FAULT DETECTION AND IDENTIFICATION USING MULTIPLE MODELS

The multiple model framework provides an elegant solution to various estimation problems. We are particularly interested in applying this framework to fault detection and identification problems because it allows modelling of a large class of faults. Two important issues in the multiple model framework are how the model sets are designed and how the filtering is performed. For both these issues, we shall discuss the existing mainstream solutions and shall also give our own philosophy on how these existing solutions can be improved in some aspects. Several simulation examples will be given of the application of both our newly developed algorithms and the conventional solutions. These simulation examples involve a model of a diesel engine actuator benchmark for fault detection and identification.

[1]  M. Massoumnia.  A geometric approach to the synthesis of failure detection filters , 1986 .

[2]  Thia Kirubarajan,et al.  Estimation with Applications to Tracking and Navigation: Theory, Algorithms and Software , 2001 .

[3]  Youmin Zhang,et al.  Detection and diagnosis of sensor and actuator failures using IMM estimator , 1998 .

[4]  Robert Babuska,et al.  MODEL WEIGHT AND STATE ESTIMATION FOR MULTIPLE MODEL SYSTEMS APPLIED TO FAULT DETECTION AND IDENTIFICATION , 2006 .

[5]  Thomas F. Coleman,et al.  Optimization Toolbox User's Guide , 1998 .

[6]  Mogens Blanke,et al.  Fault detection for a diesel engine actuator - A benchmark for FDI , 1994 .

[7]  X. Rong Li,et al.  General model-set design methods for multiple-model approach , 2005, IEEE Transactions on Automatic Control.

[8]  Nando de Freitas,et al.  Diagnosis by a waiter and a Mars explorer , 2004, Proceedings of the IEEE.

[9]  Michel Verhaegen,et al.  Model Weight Estimation for FDI Using Convex Fault Models , 2007 .

[10]  X. Rong Li,et al.  Multiple-Model Estimation with Variable Structure—Part II: Model-Set Adaptation , 2000 .

[11]  Michael Athans,et al.  ISSUES ON ROBUST ADAPTIVE FEEDBACK CONTROL , 2005 .

[12]  Stanislav Funiak,et al.  State estimation of probabilistic hybrid systems with particle filters , 2004 .

[13]  Sebastian Thrun,et al.  Real-time fault diagnosis [robot fault diagnosis] , 2004, IEEE Robotics & Automation Magazine.

[14]  Thomas B. Schön,et al.  Marginalized particle filters for mixed linear/nonlinear state-space models , 2005, IEEE Transactions on Signal Processing.

[15]  B. Williams,et al.  Multi-Modal Particle Filtering for Hybrid Systems with Autonomous Mode Transitions , 2003 .

[16]  Kumpati S. Narendra,et al.  Adaptive control using multiple models , 1997, IEEE Trans. Autom. Control..

[17]  Arnaud Doucet,et al.  Particle filters for state estimation of jump Markov linear systems , 2001, IEEE Trans. Signal Process..

[18]  Y. Arkun,et al.  Estimation of nonlinear systems using linear multiple models , 1997 .

[19]  X. R. Li,et al.  Model-Set Design, Choice, and Comparison for Multiple-Model Approach to Hybrid Estimation , 2002 .

[20]  Stephen L. Campbell,et al.  Auxiliary signal design for active failure detection in uncertain linear systems with a priori information , 2006, Autom..

[21]  P. Dooren,et al.  Numerical aspects of different Kalman filter implementations , 1986 .

[22]  György Elekes,et al.  A geometric inequality and the complexity of computing volume , 1986, Discret. Comput. Geom..

[23]  Rolf Isermann,et al.  Supervision, fault-detection and fault-diagnosis methods — An introduction , 1997 .

[24]  V. Jilkov,et al.  Survey of maneuvering target tracking. Part V. Multiple-model methods , 2005, IEEE Transactions on Aerospace and Electronic Systems.

[25]  Hans Driessen,et al.  Hybrid state estimation: a target tracking application , 2002, Autom..

[26]  Stoyan Kamenov Kanev,et al.  Robust fault-tolerant control , 2004 .

[27]  George W. Irwin,et al.  Multiple model bootstrap filter for maneuvering target tracking , 2000, IEEE Trans. Aerosp. Electron. Syst..