Extracting symptoms of bearing faults from noise using a non-linear neural filter

Abstract

Improving the signal-to-noise ratio is an important feature for the early detection of faults in bearings subject to large amounts of environmental noises. A method is proposed for improving the signal-to-noise ratio by adaptive neural filtering (ANF). A comparison of failure detection capabilities of a linear adaptive filter using the least mean square (LMS) algorithm and a non-linear adaptive filter using the ANF algorithm in conditions of large amounts of environmental noise is made. Experimental results show that an adaptive filter using a neural filtering algorithm is an effective means for extracting the symptoms of a bearing fault under such conditions.

Keywords

early symptoms bearing fault adaptive filter neural filtering algorithm

Get full access to this article

View all access options for this article.

References

Dyer

Stewart

R. M.

Detection of rolling element bearing damage by statistical vibration analysis. Trans. ASME, J. Mech. Des., April 1978, 100, 229–235.

Braun

Datner

Analysis of roller/ball bearing vibrations. Trans. ASME, J. Mech. Des., January 1979, 101, 118–125.

Taylor

J. I.

Identification of bearing defects by spectra analysis. Trans. ASME, J. Mech. Des., April 1980, 102, 198–204.

Matthew

Alfredson

R. J.

The condition monitoring of rolling element bearings using vibration analysis. J. Vibr., Acoust., Stress, and Reliability in Des., July 1984, 106, 447–453.

Sandy

Monitoring and diagnostic for rolling element bearings. Sound Vibr., June 1988, 16–22.

Braun

S. G.

The signature analysis of sonic bearing vibration. IEEE Trans. on Sonic and Ultrasonic, November 1980, Su-27 (6).

Chaturvedi

G. K.

Thomas

D. W.

Bearing fault detection using adaptive noise cancelling. Trans. ASME, J. Mech. Des., 1982, 104, 280–289.

Shao

Nezu

Detection of self-aligning roller bearing fault using asynchronous adaptive noise cancelling technology. JSME Int. J., March 1999, 42 (1), 33–43.

C. J.

S. M.

On-line detection of localized defects in bearings by pattern recognition analysis. Trans. ASME, J. Engng for Industry, November 1989, 111, 331–336.

10.

Peeken

Failure diagnosis system using fuzzy logic. In The 1989 ASME Design Technical Conference-12th Biennial Conference on

Mechanical Vibration and Noise, Montreal, Quebec, Canada, 1989, De-Vols 18–3, 18–4, 18–5, pp. 93–99.

11.

Alguindigue

I. E.

Buczak

A. L.

Uhrig

R. E.

Monitoring and diagnosis of rolling element bearings using artificial neural networks. IEEE Trans. Ind. Electronics, April 1993, 40 (2).

12.

Shao

Nezu

Feature extraction of machinery diagnosis using neural network. In Proceedings of IEEE International Conference on Neural Networks, Perth, Australia, November 1995, Vol. 1, pp. 459–464.

13.

Shao

Nezu

An on-line monitoring and diagnostic method of rolling element bearing with AI. Trans. Soc. Instrum. Control Engrs, 1996, 32 (8), 1287–1293.

14.

Shensa

M. J.

Non-Wiener solutions of the adaptive noise canceller with a noise reference. IEEE Trans. Acoust., Speech, and Signal Processing, August 1980, ASSP-28 (4).

15.

Bershad

N. J.

L. Z.

LMS adaptation with correlated data-A scalar example. IEEE Trans. Acoust., Speech, and Signal Processing, August 1984, ASSP-32 (4).

16.

Widrow

Stearns

S. D.

Adaptive Signal Processing, 1985 (Prentice-Hall, Englewood Cliffs, New Jersey).

17.

Haykin

Adaptive Filter Theory, 1996 (Prentice-Hall, A Simon and Schuster Company, Upper Saddle River, New Jersey).

18.

Van Hulle

M. M.

Learning rate adaptive achieved in unsupervised competitive learning: An application to noise cancelling. In Proceedings of IEEE International Conference on Neural Networks, Perth, Australia, November 1995, Vol. 2, pp. 860–864.

19.

Hummels

D. M.

Ahmed

Musavi

M. T.

Adaptive detection of small sinusoidal signals in non-Gaussian noise using an RBF neural network. IEEE Trans. Neural Networks, 1995, 6 (1).

20.

Training neural networks with additive noise in the desired signal. IEEE Trans. Neural Networks, 1999, 10 (6).

21.

Ngia

L. S.H.

Sjoberg

Efficient training of neural nets for nonlinear adaptive filtering using a recursive Levenberg-Marquardt algorithm. IEEE Trans. Signal Processing, 2000, 48 (7).

22.

Williamson

G. A.

Clarkson

P. M.

Adaptive algorithms for non-Gaussian noise environments: The order statistic least mean squares algorithms. IEEE Trans. Signal Processing, November 1994, 42 (11).

23.

Neural Network Toolbox User's Guide (Math Works Inc., Natick, Massachusetts).