Abstract
Partial discharge (PD) recognition using neural networks is studied. The paper offers a description of the main neural networks used, their recognition rate as well as comments on the variety of PD parameters fed to neural networks. Problems regarding the stochastic nature of PD, the multiple defects and the influence of the voltage level on the recognition rate are discussed. Proposals for future work are made.
Similar content being viewed by others
References
Kelen A (1967) Studies on partial discharges on solid dielectrics: a contribution to the discharge resistance testing of insulating materials. Acta Polyt Scand 16:138
Kreuger FH (1964) Discharge detection in HV equipment. Heywood, London
Kuffel E, Zaengl WS, Kuffel J (2000) High voltage engineering: fundamentals. Newnes, Oxford
Devins JC (1984) The physics of partial discharges in solid dielectrics. IEEE Trans. Electr. Insul 19:475–495
Van Brunt RJ (1991) Stochastic properties of partial discharge phenomena. IEEE Trans. Electr Insul 26:902–948
Megahed IY (1975) The discharge-repetition rate in cavities in epoxy resin, polyethylene and mica under alternative voltage conditions. IEEE Trans Electr Insul 10:69–74
Koenig D, Rao YN (1993) Partial discharges in electrical power apparatus. VDE, Berlin
IEEE Trans Electr Insul (1995) 2:October
Gassaway JD, Jacob PB, Vassiliadis CA, Reynolds PH (1987) Computer-aided partial discharge measurement and recognition. Paper presented at the 5th International Symposium on High Voltage Engineering, Braunschweig, Germany, 24–28 August, paper 41.03
Satish L, Zaengl WS (1994) Artificial neural networks for recognition of 3-d partial discharge patterns. IEEE Trans Diel Electr Insul 1:265–274
Gulski E, Kreuger FH (1991) Computer-aided recognition of discharge patterns. Paper presented at the 7th International Symposium on High Voltage Engineering, Dresden, Germany, 26–30 August, paper 71.01
Kranz HG, Krump R (1992) Partial discharge diagnosis using statistical optimization on a PC-based system. IEEE Trans Electr Insul 27:93–98
Werle P, Akbari A, Borsi H, Gockenbach E (2001) Partial discharge localisation on power transformers using neural networks combined wirh sectional winding transfer functions as knowledge base. Paper presented at the 3rd International Symposium on Electrical Insulation Material (ISEIM), Himeji, Japan, 19–22 November
Cachin Ch, Wiesmann HJ (1995) PD recognition with knowledge-based preprocessing and neural networks. IEEE Trans Electr Insul 2:578–589
Tu YM, Huang JM, Gao N, Yan Z (1997) Transformer insulation diagnosis based on improved NN analysis. In: Proceedings of the 5th International Conference on Prop. and Appl Diel Mat, Seoul, Korea. IEEE, New York, pp 263–266
Gao W, Gao N, Yan Z (1998) Application of adaptive wavelet classification network for fault diagnosis in oil-immersed power equipment. Trans China Electrotechnol Soc 6:33–38 (in Chinese)
Hong T, Fang MTC, Hilder D (1996) PD classification by a modular neural network based on task decomposition. IEEE Trans Diel Electr Insul 3:207–212
Kohonen T (1990) The self-organizing map. Proc IEEE 78:1464–1480
Gulski E, Krivda A (1993) Neural networks as a tool for recognition of partial discharges. IEEE Trans Electr Insul 28:984–1001
Yang HT, Liao CC, Chou JH (2001) Fuzzy learning vector quantization networks for power transformer condition assessment. IEEE Trans Diel Electr Insul 8:143–149
Borsi H, Gockenbach E, Wenzel, D (1995) Separation of partial discharge from pulse-shaped noise signals with the help of neural networks. IEE Proc Sci Meas Technol 142:69–74
Gao N, Zhang GJ, Yan Z (1998) Diagnosis of DGA based on fuzzy and ANN methods. Proceedings of the International Symposiumon Electrical Insulating Materials, Toyohashi, Japan. IEEE Japan, Toyohashi, Japan, pp 40–43
Mazroua AA, Salama MMA, Bartnikas R (1993) PD pattern recognition with neural networks using the multilayer perceptron technique. IEEE Trans Electr Insul 28:1082–1089
Mazroua AA, Bartnikas R, Salama MMA (1995) Neural network system using the multilayer perceptron technique for recognition of PD pulse shapes due to cavities and electrical trees. IEEE Trans Power Deliv 10:92–96
Mazroua AA, Bartnikas R, Salama MMA (1994) Discrimination between PD pulse shapes using different neural network paradigms. IEEE Trans Diel Electr Insul 1:1119–1131
Salama MMA, Bartnikas R (2002) Determination of neural-network topology for partial discharge pulse pattern recognition. IEEE Trans Neur Netw 13:446–456
Mason JH (1978) Discharges. IEEE Trans Electr Insul 13:211–238
Gulski E (1991) Computer-aided recognition of partial discharge using statistical tools. PhD Dissertation, Delft University of Technology, The Netherlands
Suzuki H, Endoh T (1992) Pattern recognition of partial discharge in XLPE cables using a neural network. IEEE Trans Electr Insul 27:543–549
Satish L, Gururaj BI (1993) Partial discharge pattern classification using multilayer neural network. Proc. IEE A July:323–330
Kolcunova I, Haluska R (1997) Partial discharge recognition in XPE cables using articial neural networks. J Electr Eng 48:316–319
Amini MR, Gallinari P, d'Alche-Buc F, Bonnard F, Fernandez E (1998) Automated statistical recognition of partial discharge in insulation systems. In: Proceedings of the 8th International Conference on Artificial Neural Networks, Skövde, Sweden, 2–4 September
Hamilton DJ, Pearson JS (1997) Classification of partial discharge sources in gas-insulated substations using novel preprocessing strategies. IEE Proc Sci Meas Technol 144:17–23
Candela R, Mirelli G, Schifani R (2000) PD recognition by means of statistical and fractal parameters and a neural network. IEEE Trans Diel Electr Insul 7:87–94
Happe S, Kranz HG (1999) Practical applications for the machine intelligent partial discharge disturbing pulse suppression system Neurotek II. In: Proceedings of the International Symposium on High Voltage Engineering, IEEE, New York
Kranz HG (2000) Fundamentals in computer aided PD processing, PD pattern recognition and automated diagnosis in GIS. IEEE Trans Diel Electr Insul 7:12–20
Gao K, Tang K, Li F, Wu C (2002) PD pattern recognition for stator bar models with six kinds of characteristic vectors using BP network. IEEE Trans Diel Electr Insul 9:381–389
Satish L, Zaengl WS (1995) Can fractal features be used for recognizing 3-d partial discharge patterns? IEEE Trans Diel Electr Insul 2:352–359
Hoof M, Freisleben B, Patsch R (1997) PD source identification with novel discharge parameters using counterpropagation neural networks. IEEE Trans Diel Electr Insul 4:17–32
Sletbak J (1995) The influence of cavity shape and sample geometry on partial discharge behavior. IEEE Trans Diel Electr Insul 3:126–130
Zingales G (2000) The requirements of a PD measuring system analyzed in the time domain. IEEE Trans Diel Electr Insul 7:2–5
Tanaka T (1993) Partial discharge pulse distribution pattern analysis. International Conference Partial Discharge, Canterbury, England. IEE Conf Publ 378:31–35
Gulski E (1995) Discharge pattern recognition in high voltage equipment. IEE Proc Sci Meas Technol 142:51–61
Zalis K, Beranova L, Prskavec L, Teminova R (2002) Some problems with partial discharge measurements in on-line mode. In: Proceedings of the International Conference on Optimization of Electrical and Electronic Equipment, Brasov, Romania, 16–18 May. Faculty of Electrical Engineering,Transilvania University of Brasov
Hoof M, Patsch R (1994) Analyzing partial discharge pulse sequences—a new approach to investigate degradation phenomena. IEEE International Symposium on Electrical Insulation, Pittsburgh. IEEE, Piscataway, N.J., pp 327–331
Hucker T (1995) Computergestuetzte Teilentladungsdiagnostik unter Beruecksichtigung praxisrelevanter Randbedingungen. PhD Dissertation, Bergische Universitaet Wuppertal, Germany
Kuebler B (1978) Investigations of partial discharge measuring techniques using epoxy resin samples with several voids. Conference Record of the International Symposium Electrical Insulation, Montreal, Canada. IEEE, New York, pp 82–85
Agoris DP, Hatziargyriou ND (1993) Approach to partial discharges development in closely coupled cavities embedded in solid dielectrics by the lumped capacitance model. IEE Proc A 140:131–134
Danikas MG (2001) Partial discharge behaviour of two (or more) adjacent cavities in polyethylene samples. J Electr Eng 52:36–39
Bruning AM, Kasture DG, Campbell FJ, Turner NH (1991) Effect of cavity sub-corona current on polymer insulation life. IEEE Trans Electr Insul 26:826–836
Brancato EL (1990) Electrical aging—a new insight. IEEE Electr Insul 6:50–51
Wahidahanu RSD, Paneer Selvam MA (1996) NDE of electrical insulation using genetic algorithm based artificial neural nets. In: Proceedings of the 14th World Conference on Non-Destructive Testing, New Delhi, India, 8–13 December. Indian Institute of Science, Bangalore, India, pp 1863–1866
Kelen A (1994) EI aging:development of concepts and approaches. In: Proceedings of Nordic Insulation Symposium, Vaasa, Finland, June, paper 3.0, pp 1–13
Kelen A (1995) Trends in PD diagnostics: when new options proliferate, so do old and new problems. IEEE Trans Diel Electr Insul 2:529–534
Kelen A, Danikas MG (1995) Evidence and presumption in PD diagnostics. IEEE Trans Diel Electr Insul 2:780–795
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Danikas, M.G., Gao, N. & Aro, M. Partial discharge recognition using neural networks: a review. Electr Eng 85, 87–93 (2003). https://doi.org/10.1007/s00202-002-0151-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00202-002-0151-5