Sage Journals: Discover world-class research

Abstract

The application of a neural network (NN) to diagnose faults in a machine tool coolant system is described. The measured variable in the system is the pump outlet pressure; the transient response of this as the flow valve is closed is used as a pattern for fault recognition.

A two-stage diagnostic system using a back propagation NN at each stage is described and this is trained by using data from the coolant system under healthy (i. e. unfaulty) and faulty conditions. The faults are simulated on the real coolant system. Novel (i. e. previously unmet) faults are defined by maximum values of a ‘deviation’ which is used to allocate faults.

The diagnostic system is shown to be capable of first deciding whether the system is healthy or faulty; if faulty, it then decides whether one of the three common faults or a novel fault is occurring. Having made the decision that one of the common faults is occurring, it is then capable of deciding, from four different levels, the approximate severity level of the fault. Of 345 tests on the coolant system the diagnostic system allocated the fault 99 per cent correctly and the severity level 96 per cent correctly.

Keywords

neural networks coolant system diagnostics novel faults

Get full access to this article

View all access options for this article.

References

Marcu

Voicu

Miscellaneous pattern classification techniques for process fault detection and isolation. In Proceedings of the IFAC-IMACS Symposium on

Safe Processing, 10–13 September 1991, Vol. 1, pp. 175–180.

Martin

K. F.

Thorpe

Coolant system health monitoring and fault diagnosis via health parameters and fault dictionary. Int. J. Adv. Mfg Technology, 1990, 5, 66–85.

Isermann

Model based fault diagnosis and supervision of machines and drives. In Proceedings of the 11th IFAC World Congress on

Automatic Control, Tallin, USSR, 1990.

Gertler

Analytical redundancy methods in fault detection and solution. In Proceedings of the IFAC-IMACS Symposium on

Safe Processing, 10–13 September 1991, Vol. 1, pp. 9–21.

Horne

Jamshidi

Vadiee

Neural network in robotics: A survey. J. Intelligent Robotic Systems, 1990, 3 (1), 51–66.

Barto

A. G.

Sutton

R. S.

Anderson

C. W.

Neuronlike adaptive elements that can solve difficult learning control problems. IEEE Trans. Systems, Man Cybernetics, July 1983, 13, 834–846.

Qin

McAvoy

T. J.

Comparison of four neural net learning methods for dynamics system identification. IEEE Trans. Neural Networks, January 1992, 3 (1), 122–130.

Lengelle

Schaltenbrand

Cornu

Gaillard

Pattern recognition using neural networks. Comparison to the nearest neighbour rule. In Proceedings of the IFAC Symposium on

Advanced Information Processing in Automatic Control, Nancy, France, 1989.

Murphy

O. J.

Nearest neighbour pattern classification. Proc. IEEE, October 1990, 78 (10), 1595–1598.

10.

Vaidyanathan

Venkatasubramanian

Representing and diagnosing dynamic process data using neural networks. Engng Applic. Artif. Intelligence, 1992, 5 (1), 11–21.

11.

Vaidyanathan

Venkatasubramanian

On the nature of fault space classification structure developed by neural networks. Engng Applic. Artif. Intelligence, 1992, 5 (4), 289–297.

12.

Marzi

M. H.

Martin

K. F.

Artificial neural network in condition monitoring and fault diagnosis. In Proceedings of the Conference of the International Association for Advanced Modelling and Simulation Techniques in Enterprise, California, 29–31 May 1991, pp. 113–124.

13.

Martin

K. F.

Marzi

M. H.

Neural network solution to coolant system diagnostics. In Proceedings of the Fourth International Conference on

Profitable Condition Monitoring, 8–10 December 1992, pp. 217–227 (Kluwer Academic, Dordrecht, The Netherlands).

14.

Martin

K. F.

Marzi

M. H.

Defining novel faults in a neural network fault diagnostic system. In Proceedings of the Fifth International Conference on

Profitable Condition Monitoring, December 1996, pp. 257–273.

15.

NCSR 1988, AMTA Reliability Publications 1, CN Machining Centre, National Centre for System Reliability, Risley, 1988.

16.

17.

McClelland

J. L.

Rumelhart

D. E.

Exploration in parallel distributed processing. A Handbook of Models, Programs and Exercises, 1987 (MIT Press, Cambridge, Massachusetts).

Diagnostics of a coolant system via neural networks

Abstract

Abstract

Keywords

Get full access to this article

References