Artificial Neural Network based Condition Monitoring of Rolling Element Bearing using Vibration Signals

Vijay, G S and Pai, Srinivasa P and Sriram, N S (2010) Artificial Neural Network based Condition Monitoring of Rolling Element Bearing using Vibration Signals. In: Proceedings of NAME 2010, November 12th to 13th, JNN College of Engineering, Shimoga.

[img] PDF
paper_2.pdf - Published Version
Restricted to Registered users only

Download (236kB) | Request a copy

Abstract

Vibration signal analysis is a commonly used technique for monitoring the condition of rolling element bearings (REB). Artificial Neural Networks (ANN) is one of the widely used artificial intelligence technique for condition monitoring of REB. This helps in replacing human expert in diagnosing the condition of REB. In this paper, vibration signal has been used to monitor the condition of deep groove ball bearings in an indigenously designed and fabricated bearing test rig. The vibration signal has been collected using an external accelerometer mounted on the bearing housing vertically. The experiments were carried out on a normal and used bearing at different speeds and loads. The vibration parameters considered for analysis included RMS, zero-to-peak (0-P), load and speed which were used as input features to train and test multilayer perceptron (MLP) Neural Networks. The neural network was able to classify the good bearings from the used bearings. The MLP classifier was found to classify the bearing condition with a success rate of about 95%.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Proceedings of the National Conference on Advances in Mechanical Engineering
Uncontrolled Keywords: Rolling element bearing, Condition Monitoring, Vibration Signals, Neural Networks
Subjects: Engineering > MIT Manipal > Mechanical and Manufacturing
Depositing User: MIT Library
Date Deposited: 25 Mar 2013 04:50
Last Modified: 25 Mar 2013 04:50
URI: http://eprints.manipal.edu/id/eprint/79251

Actions (login required)

View Item View Item