Radio location of partial discharge sources: a support vector regression approach

Partial discharge (PD) can provide a useful forewarning of asset failure in electricity substations. A significant proportion of assets are susceptible to PD due to incipient weakness in their dielectrics. This study examines a low cost approach for uninterrupted monitoring of PD using a network of...

Full description

Saved in:
Bibliographic Details
Published in:IET science, measurement & technology measurement & technology, 2018-03, Vol.12 (2), p.230-236
Main Authors: Iorkyase, Ephraim T, Tachtatzis, Christos, Lazaridis, Pavlos, Glover, Ian A, Atkinson, Robert C
Format: Article
Language:English
Subjects:
ANN model
artificial neural network model
computerised instrumentation
dielectric material
electricity substation
explicit regression surface
failure analysis
failure assessment
function estimation
high‐dimensional feature space
learning (artificial intelligence)
least squares approximations
least‐squares support vector regression
LSSVR approach
machine learning technique
partial discharge measurement
partial discharge source
PD received signal strength
PD source localisation
radio direction‐finding
radio location
radio sensor
regression analysis
Research Article
support vector machine
support vector machines
uninterrupted PD monitoring
wireless sensor networks
Citations: Items that this one cites
Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Partial discharge (PD) can provide a useful forewarning of asset failure in electricity substations. A significant proportion of assets are susceptible to PD due to incipient weakness in their dielectrics. This study examines a low cost approach for uninterrupted monitoring of PD using a network of inexpensive radio sensors to sample the spatial patterns of PD received signal strength. Machine learning techniques are proposed for localisation of PD sources. Specifically, two models based on support vector machines are developed: support vector regression (SVR) and least-squares support vector regression (LSSVR). These models construct an explicit regression surface in a high-dimensional feature space for function estimation. Their performance is compared with that of artificial neural network (ANN) models. The results show that both SVR and LSSVR methods are superior to ANNs in accuracy. LSSVR approach is particularly recommended as practical alternative for PD source localisation due to its low complexity.
ISSN:1751-8822
1751-8830
1751-8830
DOI:10.1049/iet-smt.2017.0175