End-to-End Partial Discharge Detection in Power Cables via Time-Domain Convolutional Neural Networks

  • Mohammad Azam Khan
  • Jaegul Choo
  • Yong-Hwa KimEmail author
Original Article


The analysis of partial discharge (PD) signals has been identified as a standardized diagnostic tool in monitoring the condition of different electrical apparatus nowadays. In this paper, we propose a novel data-driven approach to detect PD pulses in power cables using one-dimensional convolutional neural networks (CNNs), a successful deep neural network approach. Applying this deep learning method, an end-to-end framework has been proposed considering the propagations of PD signals and noises in power cables. The proposed method uses PD pulses as input, automatically extracts meaningful features for waveforms of PD pulses, and finally detects PD. Most of the existing methods, which use traditional classifiers, such as support vector machines (SVMs) and multi-layer perceptron (MLP) have mainly focused on improving feature representation and extraction manually for this task. However, the proposed CNN-based detection algorithm captures important latent features for waveforms of PD pulses with the help of its automatic feature extraction capability from raw inputs. Our experimental results show that the proposed method is better than conventional SVMs and achieves 97.38% and 93.23% detection accuracies in end-to-end settings based on our theoretical model-generated and empirical real-world PD signals, respectively.


Partial discharges Fault detection Power cable Deep neural networks Convolutional neural networks 



This research was supported by Korea Electric Power Corporation (Grant Nos: R17XA05-22 and R18XA01).


  1. 1.
    Ahmed N, Srinivas N (2001) Can the operating conditions of the cable system effect the data of the field PD testing? In: 2001 Annual Report Conference on Electrical Insulation and Dielectric Phenomena (Cat. No.01CH37225)Google Scholar
  2. 2.
    Zhou Y, Qin Y, Chappell P (2006) Cost-effective on-line partial discharge of measurements for cables. Electr Insul Mag 22:31–38CrossRefGoogle Scholar
  3. 3.
    Wielen PCJM, Steennis EF, Wouters PAAF (2003) Fundamental aspects of excitation and propagation of on-line partial discharge signals in three-phase medium voltage cable systems. Trans Dielectr Electr Insul 10:678–688CrossRefGoogle Scholar
  4. 4.
    Zhang H, Blackburn TR, Phung B, Liu Z (2006) Load and other effects on measuring partial discharge in power cables. In 2006 {IEEE} 8th International conference on properties and applications of dielectric materialsGoogle Scholar
  5. 5.
    Stone GC (2005) Partial discharge diagnostics and electrical equipment insulation condition assessment. Trans Dielectr Electr Insul 12:891–903CrossRefGoogle Scholar
  6. 6.
    Wu M, Cao H, Cao J, Nguyen HL, Gomes JB, Krishnaswamy SP (2015) An overview of state-of-the-art partial discharge analysis techniques for condition monitoring. Electr Insul Mag 31:22–35CrossRefGoogle Scholar
  7. 7.
    Lai K, Phung B, Blackburn T (2010) Application of data mining on partial discharge part I: predictive modelling classification. IEEE Trans Dielectr Electr Insul 17:846–854CrossRefGoogle Scholar
  8. 8.
    Ma H, Chan JC, Saha TK, Ekanayake C (2013) Pattern recognition techniques and their applications for automatic classification of artificial partial discharge sources. IEEE Trans Dielectr Electr Insul 20:468–478CrossRefGoogle Scholar
  9. 9.
    Lin Y-H (2011) Using K-means clustering and parameter weighting for partial-discharge noise suppression. IEEE Trans Power Deliv 26:2380–2390CrossRefGoogle Scholar
  10. 10.
    Abdel-Galil TK, Sharkawy RM, Salama MMA, Bartnikas R (2005) Partial discharge pulse pattern recognition using an inductive inference algorithm. IEEE Trans Dielectr Electr Insul 12:320–327CrossRefGoogle Scholar
  11. 11.
    Abdel-Galil TK, Sharkawy RM, Salama MMA, Bartnikas R (2005) Partial discharge pattern classification using the fuzzy decision tree approach. IEEE Trans Instrum Meas 54:2258–2263CrossRefGoogle Scholar
  12. 12.
    Hao L, Lewin P, Hunter J, Swaffield D, Contin A, Walton C, Michel M (2011) Discrimination of multiple PD sources using wavelet decomposition and principal component analysis. IEEE Trans Dielectr Electr Insul 18:1702–1711CrossRefGoogle Scholar
  13. 13.
    Chang CS, Jin J, Chang C, Hoshino T, Hanai M, Kobayashi N (2005) Separation of corona using wavelet packet transform and neural network for detection of partial discharge in gas-insulated substations. IEEE Trans Power Deliv 20:1363–1369CrossRefGoogle Scholar
  14. 14.
    Shim I, Soraghan JJ, Siew WH (2000) Digital signal processing applied to the detection of partial discharge: an overview. IEEE Electr Insul Mag 16:6–12CrossRefGoogle Scholar
  15. 15.
    Zhou C, Michel M, Hepburn DM, Song X (2009) On-line partial discharge monitoring in medium voltage underground cables. IET Sci Meas Technol 3:354–363CrossRefGoogle Scholar
  16. 16.
    Zhang H, Blackburn TR, Phung B, Sen D (2007) A novel wavelet transform technique for on-line partial discharge measurements. 2. On-site noise rejection application. IEEE Trans Dielectr Electr Insul 14:15–22CrossRefGoogle Scholar
  17. 17.
    Liao R, Fernandess Y, Tavernier K, Irving MR (2012) Recognition of partial discharge patterns. In 2012 IEEE power and energy society general meetingGoogle Scholar
  18. 18.
    Hao L, Lewin P (2010) Partial discharge source discrimination using a support vector machine. IEEE Trans Dielectr Electr Insul 17:189–197CrossRefGoogle Scholar
  19. 19.
    Hunter J, Lewin P, Hao L, Walton C, Michel M (2013) Autonomous classification of PD sources within three-phase 11 kV PILC cables. IEEE Trans Dielectr Electr Insul 20:2117–2124CrossRefGoogle Scholar
  20. 20.
    LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444CrossRefGoogle Scholar
  21. 21.
    Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85–117CrossRefGoogle Scholar
  22. 22.
    Bengio Y (2009) Learning deep architectures for AI. Found Trends Mach Learn 2:1–127CrossRefzbMATHGoogle Scholar
  23. 23.
    Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In Proceedings of the 25th International conference on neural information processing systems 1Google Scholar
  24. 24.
    Zhou K, Greenspan H, Shen D (2017) Deep learning for medical image analysis. Elsevier Science Publishing Co Inc, AmsterdamGoogle Scholar
  25. 25.
    Graves A, Jaitly N (2014) Towards end-to-end speech recognition with recurrent neural networks. In Proceedings of the 31st International conference on machine learning, BejingGoogle Scholar
  26. 26.
    Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In 2014 {IEEE} conference on computer vision and pattern recognitionGoogle Scholar
  27. 27.
    Aphex34, Own work, WikipediaGoogle Scholar
  28. 28.
    Ashtiani M, Shahrtash S (2014) Partial discharge de-noising employing adaptive singular value decomposition. IEEE Trans Dielectr Electr Insul 21:775–782CrossRefGoogle Scholar
  29. 29.
    Álvarez F, Garnacho F, Ortego J, Sánchez-Urán MÁ (2015) Application of HFCT and UHF sensors in on-line partial discharge measurements for insulation diagnosis of high voltage equipment. Sensors 15:7360–7387CrossRefGoogle Scholar
  30. 30.
    Bhattacharyya S, Chakraborty A, Saha B, Chatterjee S (2016) Electric stress analysis of a medium voltage cable termination subjected to standard and non-standard lightning impulse voltages. In 2016 International Conference on Intelligent Control Power and Instrumentation (ICICPI), Kolkata, IndiaGoogle Scholar
  31. 31.
    Kim KH, Yi SH, Lee HJ, Kang DS (2011) Setup of standard PD calibrator and its uncertainties. J Electr Eng TechnolGoogle Scholar
  32. 32.
    Gu X, Xu Y, Xia R, Meng S, Wang Y (2016) On-line calibration of partial discharge monitoring for power cable by HFCT method. In 2016 IEEE electrical insulation conference (EIC)Google Scholar
  33. 33.
    Mugala G, Eriksson R, Pettersson P (2007) Dependence of XLPE insulated power cable wave propagation characteristics on design parameters. IEEE Trans Dielectr Electr Insul 14:393–399CrossRefGoogle Scholar
  34. 34.
    Papazyan R, Eriksson R (2003) Calibration for time domain propagation constant measurements on power cables. IEEE Trans Instrum Meas 52:415–418CrossRefGoogle Scholar
  35. 35.
    Duchi J, Hazan E, Singer Y (2011) Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res 12:2121–2159MathSciNetzbMATHGoogle Scholar
  36. 36.
    Zeiler MD (2012) ADADELTA: an adaptive learning rate method. CoRRGoogle Scholar
  37. 37.
    Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. CoRRGoogle Scholar
  38. 38.
    Chollet F and others, Keras, GitHub, 2015Google Scholar
  39. 39.
    Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M, Ghemawat S, Goodfellow I, Harp A, Irving G, Isard M, Jia Y, Jozefowicz R, Kaiser L, Kudlur M, Levenberg J, Man\’{e} D, Monga R, Moore S, Murray D, Olah C, Schuster M, Shlens J, Steiner B, Sutskever I, Talwar K, Tucker P, Vanhoucke V, Vasudevan V, Vi\’{e}gas F, Vinyals O, Warden P, Wattenberg M, Wicke M, Yu Y, Zheng X (2015) TensorFlow: large-scale machine learning on heterogeneous systemsGoogle Scholar

Copyright information

© The Korean Institute of Electrical Engineers 2019

Authors and Affiliations

  • Mohammad Azam Khan
    • 1
  • Jaegul Choo
    • 1
  • Yong-Hwa Kim
    • 2
    Email author
  1. 1.Department of Computer Science and EngineeringKorea UniversitySeoulSouth Korea
  2. 2.Department of Electronic EngineeringMyongji UniversityYonginSouth Korea

Personalised recommendations