Robust fault detection based on compensation of the modelling error

The problem of compensation of modelling errors for the purpose of robust fault detection based on parity relations is addressed. The idea is to approximate unmodelled non-linear dynamics by a neural network model and then to remove the effects of unmodelled dynamics from the primary residuals. The design of such a compensator takes two steps. In the first, a subset of the most informative regressors is selected. The second step entails structure determination and parameter estimation by means of numerical optimization of a criterion function. The criterion reflects a compromise between the quality of approximation and the complexity of the model structure. The results from the study on a three-tank test rig are presented and a comparison between compensated and uncompensated residuals made. It is shown that the compensated residuals represent a good basis for reliable, yet sensitive enough, fault detection and isolation.

[1]  Atsushi Aoyama,et al.  Nonlinear modelling of LPG %C5 content of catalytic reformer debutaniser column , 1997 .

[2]  James T. Kwok,et al.  Constructive algorithms for structure learning in feedforward neural networks for regression problems , 1997, IEEE Trans. Neural Networks.

[3]  Dong Dong,et al.  Nonlinear principal component analysis-based on principal curves and neural networks , 1994, Proceedings of 1994 American Control Conference - ACC '94.

[4]  Thomas Pfeufer,et al.  Detection of Additive and Multiplicative Faults - Parity Space vs. Parameter Estimation , 1994 .

[5]  C. J. Harris,et al.  Neural Networks for Modelling and Control , 1994 .

[6]  Niels Kjølstad Poulsen,et al.  Neural Networks for Modelling and Control of Dynamic Systems: A Practitioner’s Handbook , 2000 .

[7]  Jie Chen,et al.  Optimal unknown input distribution matrix selection in robust fault diagnosis , 1993, Autom..

[8]  Ron J. Patton,et al.  Robust Model-Based Fault Diagnosis: The State of the ART , 1994 .

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

[10]  Oliver Nelles,et al.  Local Linear Model Trees for On-Line Identification of Time-Variant Nonlinear Dynamic Systems , 1996, ICANN.

[11]  Jie Chen,et al.  On-Line Residual Compensation in Robust Fault Diagnosis of Dynamic Systems , 1992 .

[12]  Julian Morris,et al.  Dynamic neural networks in non-linear predictive control (an industrial application) , 1996 .

[13]  Dale E. Seborg,et al.  Nonlinear Process Control , 1996 .

[14]  J. Zhou,et al.  Adaptive error compensation for robust fault detection , 1998, Int. J. Syst. Sci..