Bearing Fault Diagnosis in Mechanical Gearbox, Based on Time and Frequency - Domain Parameters with MLP-ARD

Özet

Gearboxes are one of the most important parts of the rotating machinery employed inindustries. Their function is to transfer torque and power from one shaft to another. If faults occurin any component (bearings) of these machines during operating conditions, serious consequencesmay occur. Consequently, condinuous monitoring of such subsystems could increase reliability ofmachines carrying out field operations. Recently, research has been focused on the implementationof vibration signals analysis for the health status diagnosis in gearboxes having as a base the useof acceleration measurements. Informative features sensitive to specific bearing faults and faultlocations were constructed by using advanced signal processing enabling the accuratediscrimination of faults based on their location.This work presents a fault diagnosis method for a mechanical gearbox with time and frequency -domain features by using a Multilayer Perceptron with Bayesian Automatic Relevance (MLP-ARD)Neural Network.The time and frequency-domain vibration signals of normal and faulty bearings are processed forfeature extraction. These features from all the signals are used as input to the MLP-ARD. Theexperimental results show that the proposed approach (MLP-ARD) presents very high accuracy indifferent bearing fault detection. This approach will be extended as regards real-time faultdetection of rotating parts in agricultural vehicles where the anticipation of detection of incipientfailure can lead to reduced downtime.