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 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.

[1]  Moein Parastegari,et al.  Simultaneous location of two partial discharge sources in power transformers based on acoustic emission using the modified binary partial swarm optimisation algorithm , 2013 .

[2]  Gehao Sheng,et al.  Localization Algorithm for the PD Source in Substation Based on L-Shaped Antenna Array Signal Processing , 2015, IEEE Transactions on Power Delivery.

[3]  Kota Solomon Raju,et al.  Adaptive fault identification of bearing using empirical mode decomposition–principal component analysis-based average kurtosis technique , 2017 .

[4]  Christoforos Panayiotou,et al.  Localization Using Radial Basis Function Networks and Signal Strength Fingerprints in WLAN , 2009, GLOBECOM 2009 - 2009 IEEE Global Telecommunications Conference.

[5]  Charles L. Despins,et al.  Indoor Geolocation with Received Signal Strength Fingerprinting Technique and Neural Networks , 2004, ICT.

[6]  P.J. Moore,et al.  Partial discharge investigation of a power transformer using wireless wideband radio-frequency measurements , 2006, IEEE Transactions on Power Delivery.

[7]  A. A. Al-Arainy,et al.  Partial discharge pattern analysis using support vector machine to estimate size and position of metallic particle adhering to spacer in GIS , 2014 .

[8]  Venizelos Efthymiou,et al.  Feature extraction of partial discharge signals using the wavelet packet transform and classification with a probabilistic neural network , 2010 .

[9]  Xiaodong Wang,et al.  Robust identification of non-linear dynamic systems using support vector machine , 2006 .

[10]  P.J. Moore,et al.  RF-Based Partial Discharge Early Warning System for Air-Insulated Substations , 2009, IEEE Transactions on Power Delivery.

[11]  B. T. Phung,et al.  Partial discharge localization in transformers using UHF detection method , 2012, IEEE Transactions on Dielectrics and Electrical Insulation.

[12]  Timothy W. Simpson,et al.  Analysis of support vector regression for approximation of complex engineering analyses , 2003, DAC 2003.

[13]  Jinbao Zhang,et al.  Overview of received signal strength based fingerprinting localization in indoor wireless LAN environments , 2013, 2013 5th IEEE International Symposium on Microwave, Antenna, Propagation and EMC Technologies for Wireless Communications.

[14]  John J. Soraghan,et al.  Remote monitoring of partial discharge data from insulated power cables , 2014 .

[15]  M. V. Rojas-Moreno,et al.  Location of partial discharges sources by means of blind source separation of UHF signals , 2015, IEEE Transactions on Dielectrics and Electrical Insulation.

[16]  Jiang Xiuchen,et al.  Partial Discharge Location Based on Radio Frequency Antenna Array in Substation , 2012 .

[17]  H. Mokhlis,et al.  Partial discharge phenomena within an artificial void in cable insulation geometry: experimental validation and simulation , 2016, IEEE Transactions on Dielectrics and Electrical Insulation.

[18]  Ping Wang,et al.  Research on tourists' positioning technology based on LSSVR , 2015, 2015 IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC).

[19]  Sid Ahmed Bessedik,et al.  Prediction of flashover voltage of insulators using least squares support vector machine with particle swarm optimisation , 2013 .

[20]  Xiaojin Zhu,et al.  Rectal sensation function rebuilding based on optimal wavelet packet and support vector machine , 2013 .

[21]  Iliana E PORTUGUES,et al.  The use of radiometric partial discharge location equipment in distribution substations , 2005 .

[22]  M.D. Judd.  Radiometric partial discharge detection , 2008, 2008 International Conference on Condition Monitoring and Diagnosis.

[23]  Pengfei Li,et al.  Method for partial discharge localisation in air-insulated substations , 2017 .

[24]  Hongsheng Chen,et al.  Support Vector Regression Based Indoor Location in IEEE 802.11 Environments , 2015, Mob. Inf. Syst..

[25]  James Theiler,et al.  Accurate On-line Support Vector Regression , 2003, Neural Computation.

[26]  J Tang,et al.  Partial discharge location based on time difference of energy accumulation curve of multiple signals , 2011 .

[27]  J. Roj,et al.  Estimation of the artificial neural network uncertainty used for measurand reconstruction in a sampling transducer , 2014 .

[28]  John J. Soraghan,et al.  Online partial discharge detection in medium voltage cables using protection/instrument current transformers , 2009 .

[29]  Mehdi Vakilian,et al.  Accurate power transformer PD pattern recognition via its model , 2016 .

[30]  Y. Lu,et al.  PD detection and localisation by acoustic measurements in an oil-filled transformer , 2000 .

[31]  Yan-Bo Wang,et al.  Localization of multiple partial discharge sources in air-insulated substation using probability-based algorithm , 2017, IEEE Transactions on Dielectrics and Electrical Insulation.

[32]  I. A. Glover,et al.  Localisation of partial discharge sources using radio fingerprinting technique , 2015, 2015 Loughborough Antennas & Propagation Conference (LAPC).

[33]  D. Basak,et al.  Support Vector Regression , 2008 .

[34]  Kristin P. Bennett,et al.  Support vector machines: hype or hallelujah? , 2000, SKDD.

[35]  Gehao Sheng,et al.  Robust Time Delay Estimation Method for Locating UHF Signals of Partial Discharge in Substation , 2013, IEEE Transactions on Power Delivery.

[36]  D. Thukaram,et al.  Application of support vector machines for fault diagnosis in power transmission system , 2008 .

[37]  Saradindu Ghosh,et al.  Artificial neural networks modelling of breakdown voltage of solid insulating materials in the presence of void , 2010 .

[38]  Po-Jen Chuang,et al.  Effective neural network-based node localisation scheme for wireless sensor networks , 2014, IET Wirel. Sens. Syst..

[39]  L. Hao,et al.  Partial discharge source discrimination using a support vector machine , 2010, IEEE Transactions on Dielectrics and Electrical Insulation.

[40]  Hava T. Siegelmann,et al.  Support Vector Clustering , 2002, J. Mach. Learn. Res..