A Comparative Study of Soft Computing Techniques for Rolling Element Bearing Condition Monitoring using Vibration Signal Analysis

Vijay, G S and Pai, Srinivasa P and Sriram, N S (2010) A Comparative Study of Soft Computing Techniques for Rolling Element Bearing Condition Monitoring using Vibration Signal Analysis. In: International Conference ICETMCA 2010 (International Conference on Emerging Trends in Mathematics and Computer Applications 2010, December 16th to 18th, Mepco Schlenk Engineering College, Sivakasi, .

[img] PDF
paper_3.pdf - Published Version
Restricted to Registered users only

Download (288kB) | Request a copy

Abstract

– Comparison of two classifiers – Artificial Neural Network (ANN) and Support Vector Machine (SVM) for condition monitoring of rolling element bearings (REB) is presented in this paper. Performance of Multi Layer Perceptron (MLP) neural network and Radial Basis Function (RBF) neural network are compared with that of SVM classifier. Features are extracted from the raw vibration signals (acceleration) acquired from normal and used REB. Various dimensional and non-dimensional statistical features (like Mean, Variance, Standard deviation, Skewness, Kurtosis, Crest factor, Shape factor, Impulse factor, Normal negative log likelihood, Weibull negative log likelihood, etc.) of the non-overlapping time-domain vibration signal segments are extracted and used as input to the ANN and SVM classifiers. A Separation Index (SI) is used to select the predominantly sensitive features. A comparison between the performances of two ANN classifiers (MLP & RBF) and SVM with respect to all the features and selected features is made. ANN and SVM perform better with lesser number of sensitive features. SVM classifier performs better than ANN classifier.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Neural Networks, Support vector machines, Bearing condition monitoring, Vibration signal analysis
Subjects: Engineering > MIT Manipal > Mechanical and Manufacturing
Depositing User: MIT Library
Date Deposited: 25 Mar 2013 04:51
Last Modified: 25 Mar 2013 04:51
URI: http://eprints.manipal.edu/id/eprint/79252

Actions (login required)

View Item View Item