Application of ACF-wavelet feature extraction for classification of some artificial PD models of power transformer

In this paper, 7 different artificial partial discharge (PD) models of power transformer defect types arebuilt in a high voltage laboratory, and then PD signals are recorded in the whole power frequency cycle to develop apreliminary PD knowledge base. A specific technique is used to extract single PD events from the recorded knowledgebase. By application of wavelet transform, different decomposition levels of extracted PD signals are investigated. Featureextraction is performed by application of statistic moments on the autocorrelation function of PD signal decompositions.“Best” features are selected based on the F-test. To evaluate the performance of features, a naive Bayes classifier is appliedto selected features. Results show that nearly 100 percent accuracy in PD discrimination is achieved using multivariatemultinomial distribution estimation of the feature space. A case study is carried out to show the contribution of theproposed approach. The combined PD detection-classification system proposed in this paper can serve as a complementto conventional PD monitoring systems.

PDF

___

Jain MB, Srinivas MB, Jain A. A novel web based expert system architecture for on-line and off-line fault diagnosis and control (FDC) of transformers. In: TENCON 2008 IEEE Region 10 Conference; 2008. pp. 1–5.
Rusov V, Zhivodernikov S. Transformer condition monitoring. In: International Conference on Condition Monitoring and Diagnosis (CMD); 2008. pp. 1012-1014.
Arshad M, Islam SM. Power Transformer Condition Monitoring and Assessment for Strategic Benefits. Perth, Australia: Curtin University of Technology, Department of Electrical and Computer Engineering, 2003.
Özgönenel O, Thomas D. Modeling and simulation of 2.5MVA SF6-gas insulated transformer. Turk J Elec Eng & Comp Sci 2017; 25: 3475-3485.
Akbari A, Werle P, Borsi H, Gockenbach E. Transfer function-based partial discharge localization in power transformers: a feasibility study. IEEE Electr Insul Mag 2002; 18: 22-32.
Stone G. Partial discharge diagnostics and electrical equipment insulation condition assessment. IEEE T Dielectr Electr Insul 2005; 12: 891-904.
Li J, Jiang T, Wang C, Cheng C. Optimization of UHF Hilbert antenna for partial discharge detection of transformers. IEEE T Antenn Propag 2012; 60: 2536-2540.
Gulski E, Kreuger FH. Determination of discharge sources by analysis of discharge quantities as a function of time. In: IEEE International Symposium on Electrical Insulation Conference; 1992. pp. 397-400.
Gulski E, Kreuger FH. Computer-aided recognition of discharge sources. IEEE T Electr Insul 1992; 27: 82-92.
Kreuger FH, Gulski E, Krivda A. Classification of partial discharges IEEE T Electr Insul 1993; 28: 917-931.
Strachan SM, Rudd S, McArthur SD, Judd MD, Meijer S, Gulski E. Knowledge-based diagnosis of partial discharges in power transformers. IEEE T Dielectr Electr Insul 2008; 15: 259-268.
Lai KX, Phung BT, Blackburn TR. Application of data mining on partial discharge part I: Predictive modelling classification. IEEE T Dielectr Electr Insul 2010; 17: 846-854.
Babnik T, Aggarwal R, Moore P. Data mining on a transformer partial discharge data using the self-organizing map. IEEE T Dielectr Electr Insul 2007; 14: 444-452.
Sahoo NC, Salama MM, Bartnikas R. Trends in partial discharge pattern classification: a survey. IEEE T Dielectr Electr Insul 2005; 12: 248-264.
Darabad VP, Vakilian M, Phung BT, Blackburn TR. An efficient diagnosis method for data mining on single PD pulses of transformer insulation defect models. IEEE T Dielectr Electr Insul 2013; 20: 2061-2072.
Evagorou D, Kyprianou A, Lewin PL, Stavrou A, Efthymiou V, Metaxas AC, Georghiou GE. Feature extraction of partial discharge signals using the wavelet packet transform and classification with a probabilistic neural network. IET Sci Measur Tech 2010; 4: 177-192.
Dey D, Chatterjee B, Chakravorti S, Munshi S. Cross-wavelet transform as a new paradigm for feature extraction from noisy partial discharge pulses. IEEE T Dielectr Electr Insul 2010; 17: 157-166.
Masud AA, Stewart BG, McMeekin SG. An investigative study into the sensitivity of different partial discharge ϕ-q-n pattern resolution sizes on statistical neural network pattern classification. Measurement 2016; 92: 497-507.
Al-Geelani NA, Piah MAM, Bashir N. A review on hybrid wavelet regrouping particle swarm optimization neural networks for characterization of partial discharge acoustic signals. Renew Sustain Energy Rev 2015; 45: 20-35.
Robles G, Parrado-Hernández E, Ardila-Rey J, Martínez-Tarifa J. Multiple partial discharge source discrimination with multiclass support vector machines. Expert Syst Appl 2016; 55: 417-428.
Sharkawy RM, Ibrahim K, Salama MMA, Bartnikas R. Particle swarm optimization feature selection for the classification of conducting particles in transformer oil. IEEE T Dielectr Electr Insul 2011; 18: 1897-1907.
Jahangir H, Hajipour E, Vakilian M, Akbari A, Blackburn TR, Phung BT. A method to capture and de-noise partial discharge pulses using discrete wavelet transform and ANFIS. Int Trans Electr Energy Syst 2015: 25: 2696-2712.
Rizzi A, Mascioli FMF, Baldini F, Mazzetti C, Bartnikas R. Genetic optimization of a PD diagnostic system for cable accessories. IEEE T Power Deliv 2009; 24: 1728-1738.
Darabad VP, Vakilian M, Blackburn TR, Phung BT. An efficient PD data mining method for power transformer defect models using SOM technique. Int J Electr Power Energy Syst 2015; 71: 373-382.
Chang CS, Jin J, Chang C, Hoshino T, Hanai M, Kobayashi N. Separation of corona using wavelet packet transform and neural network for detection of partial discharge in gas-insulated substations. IEEE T Power Deliv 2005; 20: 1363-1369.
Pittner S, Kamarthi SV. Feature extraction from wavelet coefficients for pattern recognition tasks. IEEE T Pattern Anal Mach Intell 1999; 21: 83-88.
Avci E, Avci D. A novel approach for digital radio signal classification: Wavelet packet energy–multiclass support vector machine (WPE–MSVM). Expert Syst Appl 2008; 34: 2140-2147.
Ghunem RA, Shatshat RE, Ozgonenel O. A novel selection algorithm of a wavelet based transformer differential current features. IEEE T Pow Deliv 2014; 29: 1120-1126.
Khan A, Ozgonenel O, Rahman MA. Wavelet transform based on-line protection of synchronous generators. Elect Pow Comp Syst 2007; 35: 625-637.
Ozgonenel O, Khan A, Rahman MA. Wavelet power based transformer internal fault protection algorithm. In: 9th International Conference on Developments in Power System Protection (DPSP); 17–20 March 2008; Glasgow, UK.
Lomax RG, Hahs-Vaughn DL. Statistical Concepts: A Second Course. New York, NY, USA: Routledge, 2013.
Kantardzic M. Data Mining: Concepts, Models, Methods, and Algorithms. New York, NY, USA: John Wiley & Sons, 2011.
Darabad VP, Vakilian M, Blackburn T, Phung BT. Data mining on partial discharge signals of power transformer’s defect models. Int Trans Electr Energ Syst 2013; 3: 423-437.