Fault identification in rotating machinery using artificial neural networks

Abstract

In this paper, an artificial neural network system is designed and employed for fault prediction of rotating machinery systems. Multi-layer feedforward networks, constituted of non-linear neurons, have been employed. A normalization scheme is implemented on the input and output vectors. The performance of the expert structure is optimized to encounter input data with different intensities and non-regular data. More than 40 rotating machinery faults are introduced into the algorithm. To train the network, the data in the vibration identification chart consisting of vibration signals of common rotating machinery faults are used. Computer software is developed to detect machinery faults by using the above techniques and is validated for fault detection of different machinery systems. It is found that the designed network is capable of identifing unknown faults in rotating machinery. The effectiveness of the proposed neural network algorithm is displayed by several tests.

Keywords

vibration analysis rotating machinery faults neural networks fault identification

Get full access to this article

View all access options for this article.

References

Shenoy

Bhadury

Maintenance Resources Management, 1998, pp. 1798–1998 (Taylor & Francis, London).

Luo

M. F.

Kuhnell

B. T.

Fault detection of bearing and gearbox using gray relational grade analysis. Bull. CMCM - Monash, 1993, 5 (1), 36–43.

Huang

Y-P.

Wang

S-F.

The identification of fuzzy grey prediction system by genetic algorithms. Int. J. Systems Sci., 1997, 28, 15–24.

Kim

Shin

Carlson

Machinery diagnostics for rotating machinery using back-propagation neural networks. In Proceedings of the 3rd International Machinery Monitoring and Diagnostics Conference, Las Vegas, Nevada, USA, 1991, pp. 309–320.

Lindu

Zhaohan

Discrete cosine transform with neural network in fault diagnosis for rotating machinery. In Proceedings of the IEEE Conference on International Industrial Technology, 1996, pp. 450–454 (IEEE, New York).

Javed

Hope

Littlefair

On-line tool condition monitoring using artificial neural networks. Non-destructive Test. Condition Monitoring, 1996, 38 (5), 351–354.

Subrahmanyam

Sujatha

Using neural networks for the diagnosis of localized defects in ball bearings. Tribology Int. 1997, 30 (10), 739–752.

Wang

Propes

Khiripet

An integrated approach to machine fault diagnosis. Technical Report, Georgia Institute of Technology, Atlanta, Georgia, USA, 1999.

Nalinaksh

S. V.

Satishkumar

Artificial neural network design for fault identification in a rotor-bearing system. Mechanism Mach. Theory, 2001, 36 157–175.

10.

Bloch

H. P.

Geitner

F. K.

Practical Machinery Management for Process Plant, Vol. 2, Machinery Failure Analysis and Troubleshooting, 1990 (Gulf Publishing Company, Houston, Texas).

11.

Bishop

C. M.

Neural Networks for Pattern Recognition, 1995 (Clarendon, Oxford).

12.

Hagan

M. T.

Menhaj

Training feed-forward networks with the Marquardt algorithm. IEEE Trans. Neural Networks, 1994, 5 (6), 989–993.

13.

Rao

S. S.

Engineering Optimization, Theory and Practice, 3rd edition, 1996 (John Wiley, New York).