Radio location of partial discharge sources: a support vector regression approach. Issue 2 (1st March 2018)

• Record Type: Journal Article
• Authors: Iorkyase, Ephraim T.; Tachtatzis, Christos; Lazaridis, Pavlos; Glover, Ian A.; Atkinson, Robert C.
• Is Part Of: IET science, measurement & technology. Volume 12:Issue 2(2018)
• Page Start: 230
• Page End: 236
• Publication Date: 2018-03-01
• Subjects: radio direction‐finding -- support vector machines -- regression analysis -- failure analysis -- wireless sensor networks -- learning (artificial intelligence) -- least squares approximations -- partial discharge measurement -- computerised instrumentation; radio location -- partial discharge source -- electricity substation -- failure assessment -- uninterrupted PD monitoring -- radio sensor -- PD received signal strength -- machine learning technique -- PD source localisation -- support vector machine -- least‐squares support vector regression -- explicit regression surface -- high‐dimensional feature space -- function estimation -- artificial neural network model -- ANN model -- LSSVR approach -- dielectric material; Measurement -- Periodicals; Electrical engineering -- Periodicals; Electronics -- Periodicals; Nanotechnology -- Periodicals; Electromagnetism -- Periodicals; Medical instruments and apparatus -- Periodicals; 621.3
• DOI: 10.1049/iet-smt.2017.0175
• Languages: English
• ISSNs: 1751-8822

Abstract

Abstract : 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.