Abstract
Partial discharge (PD) measurement is a diagnostic technique used for electrical insulating systems. The establishment of a highly accurate PD diagnostic technique has become necessary in recent years. Therefore, in this study, we analyzed a phase-resolved PD signal using machine learning classification for different types of experimental electrode systems. A polyethylene sheet was used as the sample, and PD was generated by applying a high AC voltage to four different types of electrodes. The number of PD pulses was counted from the raw data as preprocessing to calculate the feature value for the machine learning. The PD generation rate was defined for each phase angle section. Four types of machine learning algorithms were adopted for the classification of the electrode system: k-NN (k-nearest neighbor algorithm), logistic regression, decision tree, and random forest. The best accuracy was obtained by using the random forest algorithm (0.97), and it was found that k-NN also demonstrated good performance. The parameter dependencies were also evaluated for each algorithm. Based on the results generated by the random forest, it became clear that there were phase angle sections that were of high importance. The reason for the result was discussed from the perspective of (i) the difference due to the electrical circuit parameters (modified abc-model) and (ii) the stochastic fluctuation of PD signal.
Similar content being viewed by others
References
Bartnikas R (2002) Partial discharges their mechanism, detection and measurement. IEEE Trans Dielectr Electr Insul 9:763–808. https://doi.org/10.1109/TDEI.2002.1038663
Callender G, Lewin PL (2020) Modeling partial discharge phenomena. IEEE Electr Insul Mag 36:29–36. https://doi.org/10.1109/MEI.2020.9070114
Niemeyer L (1995) A generalized approach to partial discharge modeling. IEEE Trans Dielectr Electr Insul 2:510–528. https://doi.org/10.1109/94.407017
Crichton GC, Karlsson PW, Pedersen A (1989) Partial discharges in ellipsoidal and spheroidal voids. IEEE Trans Electr Insul 24:335–342. https://doi.org/10.1109/14.90292
Boggs SA (1990) Partial discharge. III. Cavity-induced PD in solid dielectrics. IEEE Electr Insul Mag 6:11–16. https://doi.org/10.1109/57.63094
McAllister IW, Crichton GC (2005) Influence of bulk dielectric polarization upon partial discharge transients effect of heterogeneous dielectric geometry. IEEE Trans Dielectr Electr Insul 7:124–132. https://doi.org/10.1109/94.839350
Illias H, Chen G, Lewin PL (2010) Modeling of partial discharge activity in spherical cavities within a dielectric material. IEEE Electr Insul Mag 27:38–45. https://doi.org/10.1109/MEI.2011.5699446
Gouda OE, ElFarskoury AA, Elsinnary AR, Farag AA (2018) Investigating the effect of cavity size within medium-voltage power cable on partial discharge behaviour. IET Gener Transm Distrib 12:1190–1197. https://doi.org/10.1049/iet-gtd.2017.1012
Maekawa H, Doi M, Kawamoto S (2001) Equivalent circuit model of partial discharge for needle on spacer in gas insulated switchgegrs. IEEJ Trans Power Energy 121:1169–1174. https://doi.org/10.1541/ieejpes1990.121.9_1169
Patsch R, Berton F (2002) Pulse sequence analysis: a diagnostic tool based on the physics behind partial discharges. J Phys D Appl Phys 35:25–32. https://doi.org/10.1088/0022-3727/35/1/306
Achillides Z, Georghiou GE, Kyriakides E (2008) Partial discharges and associated transients: the induced charge concept versus capacitive modeling. IEEE Trans Dielectr Electr Insul 15:1507–1516. https://doi.org/10.1109/TDEI.2008.4712652
Achillides Z, Danikas MG, Kyriakides E (2017) Partial discharge modeling and induced charge concept: comments and criticism of pedersen’s model and associated measured transients. IEEE Trans Dielectr Electr Insul 24:1118–1122. https://doi.org/10.1109/TDEI.2017.006013
Lemke E (2012) A critical review of partial-discharge models. IEEE Electr Insul Mag 28:11–16. https://doi.org/10.1109/MEI.2012.6340519
Hikita M, Yamada K, Nakamura A, Mizutani T, Oohasi A, Ieda M (1990) Measurements of partial discharges by computer and analysis of partial discharge distribution by the Monte Carlo method. IEEE Trans Electr Insul 25:453–468. https://doi.org/10.1109/14.55716
Heitz C (1999) A generalized model for partial discharge processes based on a stochastic process approach. J Phys D Appl Phys 32:1012–1023. https://doi.org/10.1088/0022-3727/32/9/312
Ovsyannikov AG, Korobeynikov SM, Vagin DV (2017) Simulation of apparent and true charges of partial discharges. IEEE Trans Dielectr Electr Insul 24:3687–3693. https://doi.org/10.1109/TDEI.2017.006635
Trotsenko Y, Brzhezitsky V, Masluchenko I (2017) Circuit simulation of electrical breakdown in air using Kind’s equal-area criterion. Technol Audit Prod Reserv 35:44–49. https://doi.org/10.15587/2312-8372.2017.102240
Karpov DI, Kupershtokh AL, Meredova MB, Zuev MV (2017) Simulation of partial discharges in cavities and streamers with high spatial resolution. J Phys: Conf Ser 899:082001. https://doi.org/10.1088/1742-6596/899/8/082001
Trotsenko Y, Brzhezitsky V, Protsenko O, Chumack V, Haran Y (2018) Simulation of partial discharges under influence of impulse voltage. Technology Audit and Production Reserves 39:36–41. https://doi.org/10.15587/2312-8372.2018.123309
Whitehead S (1951) Dielectric breakdown in solids. Clarendon Press, Oxford
Okamoto T, Tanaka T (1985) Analysis of partial discharge characteristics by an equivalent circuit with fluctuating discharge time lag. The Trans Inst Electr Eng Jpn 105:269–275. https://doi.org/10.1541/ieejfms1972.105.269
Mukherjee S, Chattopadhyay AB, Thomas S (2018) Electrostatic field theoretic approach to analyze the partial discharge phenomenon pertaining to insulation degradation. Int J Eng Technol 7:842–848. https://doi.org/10.14419/ijet.v7i2.12095
Trotsenko Y, Brzhezitsky V, Protsenko O, Mykhailenko V (2019) Application of three-capacitance models for simulation of partial discharges in solid dielectric containing several cavities. In: 2019 IEEE 2nd Ukraine conference on electrical and computer engineering, pp 279–282. DOI: https://doi.org/10.1109/UKRCON.2019.8879931
Hikita M, Kato T, Okubo H (1994) Partial discharge measurements in SF/sub 6/ and air using phase-resolved pulse-height analysis. IEEE Trans Dielectr Electr Insul 1:276–283. https://doi.org/10.1109/94.300260
Suwarno SY, Komori F, Mizutani T (1996) Partial discharges due to electrical treeing in polymers: phase-resolved and time-sequence observation and analysis. J Phys D Appl Phys 29:2922–2931. https://doi.org/10.1088/0022-3727/29/11/028
Altenburger R, Heitz C, Timmer J (2002) Analysis of phase-resolved partial discharge patterns of voids based on a stochastic process approach. J Phys D Appl Phys 35:1149–1163. https://doi.org/10.1088/0022-3727/35/11/309
Hudon C, Belec M (2005) Partial discharge signal interpretation for generator diagnostics. IEEE Trans Dielectr Electr Insul 12:297–319. https://doi.org/10.1109/TDEI.2005.1430399
Das S, Purkait P (2008) ϕ-q-n pattern analysis for understanding partial discharge phenomena in narrow voids. In: 2008 IEEE power and energy society general meeting - conversion and delivery of electrical energy in the 21st century, pp 1–7. https://doi.org/10.1109/PES.2008.4596196.
Liao R, Yan J, Yang L, Zhu M, Liu B (2011) Study on the relationship between damage of oil-impregnated insulation paper and evolution of phase-resolved partial discharge patterns. Eur Trans Electr Power 21:2112–2124. https://doi.org/10.1002/etep.546
Kasinathan E, Mahajan A, Gupta N (2017) Phase resolved PD patterns in treeing in the presence of voids. J Electrostat 87:45–50. https://doi.org/10.1016/j.elstat.2017.03.004
Kunicki M, Cichon A (2018) Application of a phase resolved partial discharge pattern analysis for acoustic emission method in high voltage insulation systems diagnostics. Arch Acoust 43:235–243. https://doi.org/10.24425/122371
Yanagizawa T, Iwamoto S, Okamoto T, Fukagawa H (1991) Recognition of the partial discharge pattern of the electrode voids by neural network theory. IEEJ Trans Power Energy 111:706–712. https://doi.org/10.1541/ieejpes1990.111.7_706
Okamoto T (1995) Recent partial discharge diagnostics. IEEJ Trans Power Energy 115:1136–1139. https://doi.org/10.1541/ieejpes1990.115.10_1136
Hara T, Hiraiwa N, Hirotsu K, Fukunage S (1996) Detection of partial discharges in power cables by neural network. EEJ Trans Electron Inf Syst 116:734–740. https://doi.org/10.1541/ieejeiss1987.116.7_734
Catterson VM, Sheng B (2015) Deep neural networks for understanding and diagnosing partial discharge data. IEEE Electr Insul Conf 2015:218–221. https://doi.org/10.1109/ICACACT.2014.7223616
Li G, Rong M, Wang X, Li X, Li Y (2016) Partial discharge patterns recognition with deep convolutional neural networks. Int Conf Cond Monit Diagn 2016:324–327. https://doi.org/10.1109/CMD.2016.7757816
Li G, Wang X, Li X, Yang A, Rong M (2018) Partial discharge recognition with a multi-resolution convolutional neural network. Sensors 18:3512. https://doi.org/10.3390/s18103512
Zhang Q, Lin J, Song H, Sheng G (2018) Fault identification based on PD ultrasonic signal using RNN, DNN and CNN. Cond Monit Diagn 2018:1–6. https://doi.org/10.1109/CMD.2018.8535878
Wang X, Huang H, Hu Y, Yang Y (2018) Partial discharge pattern recognition with data augmentation based on generative adversarial networks. Cond Monit Diagn 2018:1–4. https://doi.org/10.1109/CMD.2018.8535718
Ardila-Rey JA, Ortiz JE, Creixell W, Muhammad-Sukki F, Bani NA (2020) Artificial generation of partial discharge sources through an algorithm based on deep convolutional generative adversarial networks. IEEE Access 8:24561–24575. https://doi.org/10.1109/ACCESS.2020.2971319
Zemouri R, Lévesque M, Amyot N, Hudon C, Kokoko O, Tahan SA (2020) Deep convolutional variational autoencoder as a 2D-visualization tool for partial discharge source classification in hydrogenerators. IEEE Access 8:5438–5454. https://doi.org/10.1109/ACCESS.2019.2962775
Morette N, Ditchi T, Oussar Y (2020) Feature extraction and ageing state recognition using partial discharges in cables under HVDC. Electric Power Syst Res 178:106053. https://doi.org/10.1016/j.epsr.2019.106053
Adam B, Tenbohlen S (2021) Classification of superimposed partial discharge patterns. Energies 14:2144. https://doi.org/10.3390/en14082144
Fixt E, Hodges JL Jr (1989) Discriminatory analysis-nonparametric discrimination: consistency properties. Int Stat Rev 57:238–247. https://doi.org/10.2307/1403797
Altman NS (1992) An introduction to kernel and nearest-neighbor nonparametric regression. Am Stat. https://doi.org/10.2307/2685209
Zou X, Hu Y, Tian Z, Shen K (2019) Logistic regression model optimization and case analysis. In: 2019 IEEE 7th international conference on computer science and network technology, pp 135–139. https://doi.org/10.1109/ICCSNT47585.2019.8962457
Qin J, Lou Y (2019) L1–2 regularized logistic regression. In: 2019 53rd Asilomar conference on signals, systems, and computers, pp 779–783. https://doi.org/10.1109/IEEECONF44664.2019.9048830
Ho TK (1995) Random decision forests. In: Proceedings of 3rd international conference on document analysis and recognition, vol 1, pp 278–282. https://doi.org/10.1109/ICDAR.1995.598994
Ho TK (1998) The random subspace method for constructing decision forests. IEEE Trans Pattern Anal Mach Intell 20:832–844. https://doi.org/10.1109/34.709601
Breiman L (2001) Random forests. Mach Learn 45:5–32. https://doi.org/10.1023/A:1010933404324
Agoris DP, Hatziargyriou ND (1993) Approach to partial discharge development in closely coupled cavities embedded in solid dielectrics by the lumped capacitance model. IEE Proc A Sci Meas Technol 2:131–134. https://doi.org/10.1049/ip-a-3.1993.0021
Okamoto T, Kato T, Yokomizu Y, Suzuoki Y (2000) Integral equation represention for partial discharge fluctuation. IEEJ Trans Fundam Mater 120:490–498. https://doi.org/10.1541/ieejfms1990.120.4_490
Okamoto T, Kato T, Yokomizu Y, Suzuoki Y (2000) Fluctuation analysis of partial discharge pulse occurrence with an integral equation. IEEJ Trans Fundam Mater 120:620–630. https://doi.org/10.1541/ieejfms1990.120.5_620
Nozu D, Okamoto T (2016) Integral equation for analysis of partial discharge pulses based on residual voltage fluctuation. IEEJ Trans Fundam Mater 136:812–816. https://doi.org/10.1541/ieejfms.136.812
Nozu D, Okamoto T (2017) Integral equation for analysis of partial discharge pulses under sinusoidal voltage stress. IEEJ Trans Fundam Mater 137:529–535. https://doi.org/10.1541/ieejfms.137.529
Acknowledgements
The authors would like to thank Prof. H. Uehara and Dr. T. Okamoto for the fruitful discussions.
Funding
This work was partially supported by the Japan Society for the Promotion of Science KAKENHI (Grant Number JP20H02140).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there is no conflict of interest.
Availability of data and material
The raw/processed data required to reproduce these findings cannot be shared at this time as the data also forms part of an ongoing study.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Iwata, S., Kitani, R. Phase-resolved partial discharge analysis of different types of electrode systems using machine learning classification. Electr Eng 103, 3189–3199 (2021). https://doi.org/10.1007/s00202-021-01306-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00202-021-01306-5