Parametric Fault Detection in Nonlinear Systems - A Recursive Subspace-based Approach

This paper deals with the problem of detecting nolinear systems’ parametric faults modeled as changes in the eigenvalues of a local linear state-space model. The linear state-space model approximations are obtained by recursive subspace system identification techniques, from which the eigenvalues are extracted at each sampling time. Residuals are generated by comparing the eigenvalues against those associated with a local nominal model derived from a neural network predictor describing the nonlinear plant dynamics in free fault conditions. Parametric fault symptoms are generated from the eigenvalues residuals, whenever a given predefined threshold is exceeded. The feasibility and effectiveness of the proposed framework is demonstrated in a practical case study.

[1]  Rolf Isermann,et al.  Trends in the Application of Model Based Fault Detection and Diagnosis of Technical Processes , 1996 .

[2]  Marco Lovera,et al.  CONVERGENCE ANALYSIS OF INSTRUMENTAL VARIABLE RECURSIVE SUBSPACE IDENTIFICATION ALGORITHMS , 2006 .

[3]  K. Matsui,et al.  Existence and stability of periodic solutions for Hopfield neural network equations with periodic input , 2002 .

[4]  Hong Chen,et al.  Approximation capability in C(R¯n) by multilayer feedforward networks and related problems , 1995, IEEE Trans. Neural Networks.

[5]  Hidenori Kimura,et al.  Recursive 4SID algorithms using gradient type subspace tracking , 2002, Autom..

[6]  Inseok Hwang,et al.  A Survey of Fault Detection, Isolation, and Reconfiguration Methods , 2010, IEEE Transactions on Control Systems Technology.

[7]  Guillaume Mercère.  Contribution à l'identification récursive des systèmes par l'approche des sous-espaces , 2004 .

[8]  Janos Gertler,et al.  Fault detection and diagnosis in engineering systems , 1998 .

[9]  Gilles Y. Delisle,et al.  Spatial analysis using new properties of the cross-spectral matrix , 1991, IEEE Trans. Signal Process..

[10]  L. Brito Palma,et al.  Diagnosis of Parametric Faults Based on Identification and Statistical Methods , 2005, Proceedings of the 44th IEEE Conference on Decision and Control.

[11]  Michèle Basseville,et al.  Subspace-based fault detection algorithms for vibration monitoring , 2000, Autom..

[12]  Maurice Goursat,et al.  Subspace-Based Algorithms for Structural Identification, Damage Detection, and Sensor Data Fusion , 2007, EURASIP J. Adv. Signal Process..

[13]  Allan Pinkus,et al.  Multilayer Feedforward Networks with a Non-Polynomial Activation Function Can Approximate Any Function , 1991, Neural Networks.

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

[15]  Rolf Isermann,et al.  Fault-Diagnosis Applications , 2011 .

[16]  Stéphane Lecoeuche,et al.  Propagator-based methods for recursive subspace model identification , 2008, Signal Process..

[17]  Bart De Moor,et al.  Algorithms for Subspace State-Space System Identification: An Overview , 1999 .

[18]  Jie Chen,et al.  Robust Model-Based Fault Diagnosis for Dynamic Systems , 1998, The International Series on Asian Studies in Computer and Information Science.

[19]  P. L. dos Santos,et al.  Improving the numerical efficiency of the B and D estimates produced by the combined deterministic-stochastic subspace identification algorithms , 2003 .

[20]  M. Lovera,et al.  Recursive subspace identification based on instrumental variable unconstrained quadratic optimization , 2004 .