EARLY DETECTION OF LEAKAGES IN THE EXHAUST AND DISCHARGE SYSTEMS OF RECIPROCATING MACHINES BY VIBRATION ANALYSIS

被引：28

作者：

BARDOU, O

SIDAHMED, M

机构：

[1] CETlM-Senlis, 60304 Senlis Cedex

来源：

MECHANICAL SYSTEMS AND SIGNAL PROCESSING | 1994年 / 8卷 / 05期

关键词：

D O I：

10.1006/mssp.1994.1039

中图分类号：

TH [机械、仪表工业];

学科分类号：

0802 ;

摘要：

This paper discusses the early detection of leakages and more generally the problem of predictive diagnosis in the exhaust and discharge systems of reciprocating machines. Vibration transducers, which are easy to install on the machine, are the basic tool needed for devising a method of detection. The vibrational signals picked up on these machines are highly non-stationary. However it is possible to characterise any defect by using signal processing involving techniques that can accommodate this aspect [time-frequency analysis, non-stationary auto-regressive modeling]. Pattern recognition methods and more particularly, methods of classification, are then used, notably involving neural networks which make it possible to 'automate' the diagnosis.

引用

页码：551 / 570

页数：20

共 41 条

[1]

Batis H., Verney S., CETIM Informations, (1986)

[2]

Petit M., Pétrole Et Techniques, 356, pp. 43-46, (1990)

[3]

Johnston A.B., Stronach A.F., Proceedings of Condition Monitoring, pp. 197-205, (1986)

[4]

Chiollaz M., Flandrin P., Gache N., Proceedings of GRETSI, pp. 579-582, (1987)

[5]

Bardou O., Watremetz M., Sidahmed M., Proceedings of IMMDC, (1991)

[6]

Grivelet P., Proceedings of IMMDC, pp. 393-399, (1990)

[7]

Auger F., Don Carli C., Traitement Du Signal, 9, pp. 3-25, (1992)

[8]

Boashah B., O'shea P., IEEE Transactions on Acoustics Speech and Signal Processing, 38, pp. 1829-1841, (1990)

[9]

Bondant L., Thesis of the Institut National Polytechnique of Grenoble, (1988)

[10]

Cohen L., Proceedings of the IEEE, 11, pp. 941-981, (1989)

← 1 2 3 4 5 →