About Us

KEY WORDS

Wear, bearings, gear, vibration analysis, artificial neural networks and diagnosis.

ABSTRACT

Rotating machines play a strategic role in a manufacturing process; it is the case of a cement mill. These machines are made of fragile organs (bearings and gears, etc.) subjected to significant mechanical stresses and harsh industrial environments. Improving productivity through better control of the production tool through its automation, although by controlling its availability; automation must be associated with a maintenance strategy that will ensure a more availability. However, many techniques available currently require much expertise to successfully implement; it requires new techniques that allow relatively unskilled operators to make reliable decisions without knowing the mechanism of system and analyzing the data. The artificial neural networks (ANN) are suitable for this type of problem diagnosis using the classification method. This article discusses the automation of isolated diagnosis faults of bearings and gears in a gear unit DMGH25.4 of cement mill by coupling spectral analysis vibration-neural networks.

CITATION INFORMATION

Acta Mechanica Slovaca. Volume 17, Issue 1, Pages 38 – 45, ISSN 1335-2393

DOWNLOAD

  Automation of Isolated Diagnosis Faults by Coupling Vibration Analysis- Artificial neural networks.

REFERENCES

[1] Ahmadi H., Mollazada.K., Bearing fault diagnosis of a mine stone crasher by vibration condition monitoring technique, Res.J.Appl.Sci.Eng.Technol, vol 1(3), ,2009, p. 112-115.

[2] Dyer D., Stewart R.M., Detection of rolling element bearing damage by statistical analysis, ASME journal of mechanical design, n° 100, 1978, p. 229-235.
[3] Garreau D., Monitoring of the bearing by vibration analysis, cetim information, n°115, 1990.
[4] Khodja DJ., Chetate B., Development of Neural Network module for fault identification in Asynchronous machine using various types of reference signals, 2nd International Conference Physics and Control, August 24-26 2006, St Petersburg, Russia, p. 537-542.
[5] Kolodziejczyk T., al., Artificial intelligence as efficient technique for ball bearing fretting wear damage prediction, Wear, vol 268, 2010, p. 309-315.
[6] Manual cement mill Flender.
[7] McFadden P.D., Detection fatigue cracks in gears by amplitude and phase demodulation of Meshing vibration, ASME Transaction Journal of Vibration Acoustics and Reliability in Design, vol 108, 1986 p. 165-170.
[8] Mol H.A., Rolling bearing localized defect detection through vibration envelope analysis, SKF Engineering and Research centre BV, 2000, Sweden.
[9] Monk R., Vibration measurement gives early warning of mechanical faults, processing engineering, 1997.
[10] Patrick H., Simpson K., Foundations of neural network, Technology Update series, IEEE, 1996, p. 1-20.
[11] Randall R.B, Antoni J., Rolling element bearing diagnostics-A tutorial, Mechanical systems and signal processing 25, 2011, p. 485-520.
[12] Trajin B., Automatic detection and diagnosis of bearing defects in an asynchronous machine by spectral analysis of stator currents, JCGE’08 Lyon, 16-17 December 2008.
[13] Wang H., Chen P., Intelligent diagnosis method for rolling element bearing faults using possibility theory and neural network, Computers & industrial engineering, vol 60, 2011, p. 511-518.

[14] Yang D.M., Stronach A.F., P. MacConnell., Third order spectral techniques for the diagnosis of motor bearing condition using artificial neural networks, Mechanical Systems and Signal Processing 16(2–3), 2002, p. 391–411.

Latest Issue

ams 2 2016

Download

Guests Online

We have 13 guests and no members online