Fault Classification in Cylinders Using Multilayer Perceptrons, Support Vector Machines and Guassian Mixture Models
Artificial Intelligence
2007-05-23 v1
Abstract
Gaussian mixture models (GMM) and support vector machines (SVM) are introduced to classify faults in a population of cylindrical shells. The proposed procedures are tested on a population of 20 cylindrical shells and their performance is compared to the procedure, which uses multi-layer perceptrons (MLP). The modal properties extracted from vibration data are used to train the GMM, SVM and MLP. It is observed that the GMM produces 98%, SVM produces 94% classification accuracy while the MLP produces 88% classification rates.
Keywords
Cite
@article{arxiv.0705.0197,
title = {Fault Classification in Cylinders Using Multilayer Perceptrons, Support Vector Machines and Guassian Mixture Models},
author = {Tshilidzi Marwala and Unathi Mahola and Snehashish Chakraverty},
journal= {arXiv preprint arXiv:0705.0197},
year = {2007}
}