PT  - JOURNAL ARTICLE
AU  - Menasri, N.
AU  - Bouchoucha, A.
AU  - Khoja, D.
AU  - Zaoui, M.
TI  - Automation of Isolated Diagnosis Faults by Coupling Vibration Analysis- Artificial neural networks.
DP  - 2013 Mar 31
TA  - Acta Mechanica Slovaca
PG  - 38--45
VI  - 17
IP  - 1
AID - 10.21496/ams.2013.006
IS  - 13352393
AB  - 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.