We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
FAULT CLASSIFICATION OF INDUCTION MOTOR BEARING USING STATISTICAL FEATURES AND ARTIFICIAL NEURAL NETWORK.
- Authors
PATEL, RAJ KUMAR; GIRI, V. K.
- Abstract
Bearings are one of the critical components in rotating machines and the majority of failure arises from the defective bearings. Bearing failure leads to failure of a machine and unpredicted productivity loss for production facilities. Hence, bearing fault detection and diagnosis is an integral part of the preventive maintenance procedures. In this paper, vibration signals for four conditions of a deep groove ball bearing Normal (N), fault on Inner Race (IR), fault on ball and fault on Outer Race (OR) were acquired from a customized bearing test rig, under no load and full load condition and each load condition with two fault size 0.007 inch and 0.021 inch has been taken. Statistical parameter from the time domain has been used as a feature of vibration signal for the classification purpose. Sensitivity analysis is performed to understand the significance of each input feature on the ANN (Artificial Neural Network) output. The ANN performance has been found to be comparatively higher to those feature which are highly sensitive.
- Subjects
ROTATING machinery; FAILURE analysis; VIBRATION (Mechanics); FAULT tolerance (Engineering); INDUCTION motors; BEARINGS (Machinery); ARTIFICIAL neural networks
- Publication
i-Manager's Journal on Electrical Engineering, 2015, Vol 9, Issue 2, p41
- ISSN
0973-8835
- Publication type
Article
- DOI
10.26634/jee.9.2.3718