Fault diagnosis for unknown non-linear systems via neural networks and its comparisons and combinations with recursive least-squares based techniques

Abstract

In this paper, an algorithm for the detection and diagnosis of faults in sensors and actuators in unknown non-linear systems is presented. Firstly, the normal operation of the non-linear system is modelled via a feedforward neural network in order to produce a healthy model which is used later as a redundant relation. It is assumed that every faulty sensor or actuator can be modelled by a single parameter f. Such a parameter is defined to be f=1 when the system is healthy and 0 < f < 1 otherwise. A residual signal is evaluated from the difference of the output of the healthy model and that of the system. A simple threshold function is used to detect the faulty behaviour of the system. The estimation of f is then computed by minimizing the differences between the output of the system and that of the healthy neuro model with the help of the gradient descent rule. It has been shown that the algorithm is able to estimate the fault with large magnitude accurately. However, if the deviation of f from its healthy value is small, a linearized healthy model, together with the recursive least-squares algorithm, can be used to estimate the fault. As a result, a combination of both methods will provide a powerful technique for accurate fault diagnosis.

Keywords

fault detection and diagnosis non-linear dynamic systems actuators and sensors neural networks least-squares estimation non-linear autoregressive moving-average model with exogenous input (NARMAX model)

Get full access to this article

View all access options for this article.

References

Frank

P. M.

Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy. Automatica, 1990, 26, 459–474.

Frank

P. M.

Enhancement of robustness in observer-based fault detection. Int. J. Control, 1994, 59, 955–981.

Sadrnia

M. A.

Chen

Patton

R. J.

Robust fault detection observer design using techniques for uncertain flight control systems. In Proceedings of the Second IFAC Symposium on

Robust Control and Design (RECOND'97), 1997, pp. 531–536.

Peel

Morris

A. J.

Kiparissides

Process condition monitoring and neural network feature detection. In Proceedings of the 11th IFAC World Congress, Sydney, Australia, 1993. pp. 314–317.

Isermann

Process fault diagnosis with parameter estimation methods. In Proceedings of the IFAC Symposium on

Digital Computer Applications to Process Control, Vienna, Austria, 1985, pp. 63–68.

Patton

R. J.

Robust model-based fault diagnosis, the state of the art. In Proceedings of the IFAC Symposium SAFEPROCESS'94, Helsinki, Finland, June 1994, pp. 102–110.

Zhang

Roberts

P. D.

On-line process fault diagnosis using neural network techniques. Trans. Inst. Measmt Control, 1992, 14, 179–188.

Wang

Daley

An approach to fault detection using nonlinear modelling and estimation. In Proceedings of the 11th IFAC World Congress, Sydney, Australia, 1993, pp. 291–294.

Hammestrom

Neural networks at work. IEEE Spectrum, 1993, 30, 217–218.

10.

Widrow

Lehr

M. A.

30 years of adaptive neural networks: Perceptron, madaline and backpropagation. Proc. IEEE, 1990, 9, 1415–1441.

11.

Narendra

Parthasarathy

Identification and control of dynamical systems using neural networks. IEEE Trans. Neural Networks, 1990, 1, 4–27.

12.

Seliger

Frank

P. M.

Robust nonlinear observer-based fault detection for an overhead crane. In Proceedings of the 11th IFAC World Congress, Sydney, Australia, 1993, pp. 284–289.

13.

Sorsa

Suontausta

Korvo

H. N.

Fault diagnosis of dynamic systems using neural networks. In Proceedings of the 11th IFAC World Congress, Sydney, Australia, 1993, pp. 280–283.

14.

Lin

Wang

Linearization techniques in fault diagnosis of non-linear systems. Proc. Instn Mech. Engrs, Part I, Journal of Systems and Control Engineering, 2000, 214 (14), 241–245.

15.

Trunov

Polycarpou

M. M.

Robust fault diagnosis of state and sensor faults in nonlinear multivariable systems. In Proceedings of the American Control Conference, 1998, pp. 608–612.

16.

Wang

Daley

Actuator fault diagnosis: An adaptive observer-based technique. IEEE Trans. Autom. Control, 1996, 41, 1073–1078.

17.

Wang

Lin

Applying observer based FDI techniques to detect faults in dynamic and bounded stochastic distributions. Int. J. Control, 2000, 73, 1424–1436.

18.

Kadirkamanathan

Jaward

M. H.

Fabri

S. G.

Fault detection in nonlinear systems: The particle filtering approach. In Proceedings of the UKACC International Conference on

CONTROL'2000, 2000.

19.

Documentation for the Bytronic Process Control Unit (IBM Version), 1995 (Bytronics plc, Birmingham).

20.

Patton

R. J.

Chen

Siew

T. M.

Fault diagnosis in nonlinear dynamic systems via neural networks. In Proceedings of the IEE Conference on

Control'94, March 1994, pp. 568–571.