Detection of Combined Gear-Bearing Fault in Single Stage Spur Gear Box Using Artificial Neural Network

摘要

Gears and bearings are important components of almost every machines used in industrial environment. Hence detection of defect in any of these must be detected in advance to avoid catastrophic failure. This paper aims to address the effect of bearing defect on gear vibration signature and effect gear defect on bearing vibration signature. Also its purpose is to make vibration analysis of single stage spur gear box, when both gear and bearing are defective. A condition monitoring set up is designed for analyzing the defect in outer race of bearing and damaged tooth of gear. MATLAB is used for feature extraction and neural network is used for diagnosis. In the literature, many authors have analyzed defects in bearings and gears separately. But it is found that the real situation may be more complex. The work presents a laboratory investigation carried out through an experimental set-up for the study of combined gear-bearing fault. This paper proposes a novel approach of damage detection in which defects in multiple components are analyzed using vibration signal.