Identification of PD defect typologies using a support vector machine
Identification of PD defect typologies using a support vector machine
The Support Vector Machine (SVM) has been adopted here to identify four different Partial Discharge (PD) sources that can affect the insulation system of AC rotating machines. A number of Roebel bars were prepared to generate bar-to-finger, corona and slot PD in addition to the distributed micro-voids that are typical of this insulation type. PD measurements were performed using different set-up conditions, defect locations and voltage levels in order to produce examples of PD activity that represent the same source under a range of conditions. The SVM was trained to differentiate between the inherent features (global and derived parameters) of the phase resolved PD (PRPD) distributions produced by each discharge source. In order to achieve the optimum source classification accuracy, different combinations of distribution features were used to produce a range of SVM models to identify which parameters were influenced by the measurement conditions. A cross validation technique has been used to obtain the highest testing accuracy. Moreover, results obtained using raw data and normalized parameters, were also compared to obtain the best identification performance of the given defect typologies.
978-1-4673-4739-6
333-336
Lewin, P.L.
78b4fc49-1cb3-4db9-ba90-3ae70c0f639e
Hunter, J.A.
dae3e13b-a97e-4e81-a617-20ab6965da3c
Hao, L
e6006548-3fc1-4a7e-9df4-a4e9a9a05c45
Contin, A
9c8d180d-d037-4d75-aa8a-1dcfa558aaeb
2 June 2013
Lewin, P.L.
78b4fc49-1cb3-4db9-ba90-3ae70c0f639e
Hunter, J.A.
dae3e13b-a97e-4e81-a617-20ab6965da3c
Hao, L
e6006548-3fc1-4a7e-9df4-a4e9a9a05c45
Contin, A
9c8d180d-d037-4d75-aa8a-1dcfa558aaeb
Lewin, P.L., Hunter, J.A., Hao, L and Contin, A
(2013)
Identification of PD defect typologies using a support vector machine.
IEEE 2013 Electrical Insulation Conference, Ottawa, Canada.
02 - 05 Jun 2013.
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
The Support Vector Machine (SVM) has been adopted here to identify four different Partial Discharge (PD) sources that can affect the insulation system of AC rotating machines. A number of Roebel bars were prepared to generate bar-to-finger, corona and slot PD in addition to the distributed micro-voids that are typical of this insulation type. PD measurements were performed using different set-up conditions, defect locations and voltage levels in order to produce examples of PD activity that represent the same source under a range of conditions. The SVM was trained to differentiate between the inherent features (global and derived parameters) of the phase resolved PD (PRPD) distributions produced by each discharge source. In order to achieve the optimum source classification accuracy, different combinations of distribution features were used to produce a range of SVM models to identify which parameters were influenced by the measurement conditions. A cross validation technique has been used to obtain the highest testing accuracy. Moreover, results obtained using raw data and normalized parameters, were also compared to obtain the best identification performance of the given defect typologies.
Text
072.pdf
- Version of Record
Restricted to Registered users only
Request a copy
More information
Published date: 2 June 2013
Venue - Dates:
IEEE 2013 Electrical Insulation Conference, Ottawa, Canada, 2013-06-02 - 2013-06-05
Organisations:
EEE
Identifiers
Local EPrints ID: 353266
URI: http://eprints.soton.ac.uk/id/eprint/353266
ISBN: 978-1-4673-4739-6
PURE UUID: 0818579c-4bf7-4eb3-b3d1-84a611317d69
Catalogue record
Date deposited: 03 Jun 2013 20:12
Last modified: 15 Mar 2024 02:43
Export record
Contributors
Author:
P.L. Lewin
Author:
J.A. Hunter
Author:
L Hao
Author:
A Contin
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics