Open Access Repository

Sensitivity analysis of SVM kernel functions in machinery condition classification

Rajapaksha, N, Jayasinghe, S ORCID: 0000-0002-3304-9455, Enshaei, H ORCID: 0000-0002-5649-7015 and Jayarathne, N 2021 , 'Sensitivity analysis of SVM kernel functions in machinery condition classification', in Proceedings of the 2021 IEEE Annual Southern Power Electronics Conference (SPEC) , Institute of Electrical and Electronics Engineers, United States, pp. 1-10 , doi: 10.1109/SPEC52827.2021.9709458.

Full text not available from this repository.

Abstract

The excellent generalisation ability of the Support Vector Machine (SVM) algorithm has made it one of the most popular statistical learning theories in supervised machine learning. The classification accuracy and effectiveness of SVM is highly sensitive to the kernel function used during the training process. This paper compares linear, polynomial, and Gaussian kernel functions for evaluating their contribution to SVM for accurately and effectively classifying healthy and faulty status of rotating machinery. A three-phase induction motor and a four-stroke diesel engine were considered as the machinery for this study. Acoustic signals coming from these machines were collected using microphones and Fast Fourier Transform (FFT) was used to extract the magnitudes of the dominant frequency components of the signals. The extracted ominant frequency components are considered as acoustic signatures and their variations are taken as condition monitoring parameters. The results show that with the second-order polynomial kernel function, SVM achieved an accuracy of at least 2.4% greater than the other kernel functions with 1.2% less training time. Furthermore, the third-order polynomial kernel function found to be the second best choice.

Item Type: Conference Publication
Authors/Creators:Rajapaksha, N and Jayasinghe, S and Enshaei, H and Jayarathne, N
Keywords: support vector machines, kernel functions, condition monitoring
Journal or Publication Title: Proceedings of the 2021 IEEE Annual Southern Power Electronics Conference (SPEC)
Publisher: Institute of Electrical and Electronics Engineers
DOI / ID Number: 10.1109/SPEC52827.2021.9709458
Copyright Information:

Copyright 2021 IEEE

Related URLs:
Item Statistics: View statistics for this item

Actions (login required)

Item Control Page Item Control Page
TOP