Skip to main content
SpringerLink
Log in

An interpretable CNN model for classification of partial discharge waveforms in 3D-printed dielectric samples with different void sizes

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Regular maintenance of power equipment in high voltage power systems is essential for avoiding outages. An effective way to maintain such systems is the measurement of partial discharges in the insulation material. Voids in solid dielectrics may result from many causes including defects taking place during the manufacturing of the dielectric. These voids induce PDs. Classifying different void sizes is challenging since traditional classification tools used for partial discharge (PD) classification do not work properly. For instance, phase resolved partial discharge (PRPD) patterns resulting from different void sizes will be roughly the same since the source of the partial discharge is the same. Using existing clustering techniques such as Time–Frequency (T–F) map or analysis of statistical features extracted from the PRPD patterns presents their own limitations. T–F map restricts the use of Fast Fourier Transform, while working with PRPDs is only applicable for AC measurements. In this paper, a convolutional neural network (CNN) attention-based model has shown superior capability over traditional classification technique (T–F map) to classify partial discharge (PD) waveforms resulting from different voids in PLA 3D-printed samples. 1D-CNN has classification accuracy of 98.7% with an increase of 21.42% compared to the T–F map technique. Extensive investigation of the learned model has been conducted in order to interpret the decisions made by the proposed neural network. In particular, adding an interpretable attention model such as GRAD-CAM to our CNN shows that while making the decision the neural network learns to focus more on the regions of the waveform corresponding to the rise of the pulse.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

References

  1. Satish L, Zaengl WS (1994) Artificial neural networks for recognition of 3-d partial discharge patterns. IEEE Trans Dielectr Electr Insul 1(2):265–275

    Article  Google Scholar 

  2. Whitehead S (1951) Dielectric breakdown of solids. Clarendon Press, London

    MATH  Google Scholar 

  3. Crichton GC, Karlsson P, Pedersen A (1989) Partial discharges in ellipsoidal and spheroidal voids. IEEE Trans Electr Insul 24(2):335–342

    Article  Google Scholar 

  4. Fothergill JC (2007) Ageing, space charge and nanodielectrics: ten things we don’t know about dielectrics. In: 2007 IEEE international conference on solid dielectrics. IEEE, pp 1–10

  5. Zhang Y, He L, Zhu H (2017) Influencing factors of partial discharge of needle-plate based on acoustic emission detection. In: World conference on acoustic emission. Springer, pp 389–397

  6. Krivda A (1995) Automated recognition of partial discharges. IEEE Trans Dielectr Electr Insul 2(5):796–821

    Article  Google Scholar 

  7. Sahoo N, Salama M, Bartnikas R (2005) Trends in partial discharge pattern classification: a survey. IEEE Trans Dielectr Electr Insul 12(2):248–264

    Article  Google Scholar 

  8. Lin C-F, Wang S-D (2002) Fuzzy support vector machines. IEEE Trans Neural Netw 13(2):464–471

    Article  Google Scholar 

  9. Duda RO, Hart PE, Stork DG (2001) Pattern classification, vol 58, 2nd edn. Wiley, New York, p 16

    MATH  Google Scholar 

  10. Specht DF (1990) Probabilistic neural networks. Neural Netw 3(1):109–118

    Article  Google Scholar 

  11. Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55(1):119–139

    Article  MathSciNet  Google Scholar 

  12. Wu M, Cao H, Cao J, Nguyen H-L, Gomes JB, Krishnaswamy SP (2015) An overview of state-of-the-art partial discharge analysis techniques for condition monitoring. IEEE Electr Insul Mag 31(6):22–35

    Article  Google Scholar 

  13. Catterson V, Sheng B (2015) Deep neural networks for understanding and diagnosing partial discharge data. In: 2015 IEEE electrical insulation conference (EIC). IEEE, pp 218–221

  14. Lu S, Chai H, Sahoo A, Phung B (2020) Condition monitoring based on partial discharge diagnostics using machine learning methods: a comprehensive state-of-the-art review. IEEE Trans Dielectr Electr Insul 27(6):1861–1888

    Article  Google Scholar 

  15. Wang Y, Yan J, Yang Z, Liu T, Zhao Y, Li J (2019) Partial discharge pattern recognition of gas-insulated switchgear via a light-scale convolutional neural network. Energies 12(24):4674

    Article  Google Scholar 

  16. Barrios S, Buldain D, Comech MP, Gilbert I, Orue I (2019) Partial discharge classification using deep learning methods-survey of recent progress. Energies 12(13):2485

    Article  Google Scholar 

  17. Fawaz HI, Forestier G, Weber J, Idoumghar L, Muller P-A (2019) Deep learning for time series classification: a review. Data Min Knowl Discov 33(4):917–963

    Article  MathSciNet  Google Scholar 

  18. Ibrahim A, Zhou Y, Jenkins ME, Trejos AL, Naish MD (2020) The design of a parkinson’s tremor predictor and estimator using a hybrid convolutional-multilayer perceptron neural network. In: 2020 42nd annual international conference of the ieee engineering in medicine & biology society (EMBC). IEEE, pp 5996–6000

  19. Khan MA, Choo J, Kim Y-H (2019) End-to-end partial discharge detection in power cables via time-domain convolutional neural networks. J Electr Eng Technol 14(3):1299–1309

    Article  Google Scholar 

  20. Wang W, Yu N (2020) Partial discharge detection with convolutional neural networks. In: 2020 international conference on probabilistic methods applied to power systems (PMAPS). IEEE, pp 1–6

  21. Peng X, Yang F, Wang G, Wu Y, Li L, Li Z, Bhatti AA, Zhou C, Hepburn DM, Reid AJ et al (2019) A convolutional neural network-based deep learning methodology for recognition of partial discharge patterns from high-voltage cables. IEEE Trans Power Deliv 34(4):1460–1469

    Article  Google Scholar 

  22. Borghei M, Ghassemi M, Kordi B, Gill P, Oliver D (2021) A finite element analysis model for internal partial discharges in an air-filled cylindrical cavity inside solid dielectric. In: IEEE electrical insulation conference (EIC), pp 7–21

  23. Contin A, Cavallini A, Montanari G, Pasini G, Puletti F (2002) Digital detection and fuzzy classification of partial discharge signals. IEEE Trans Dielectr Electr Insul 9(3):335–348

    Article  Google Scholar 

  24. Cavallini A, Montanari G, Contin A, Pulletti F (2003) A new approach to the diagnosis of solid insulation systems based on pd signal inference. IEEE Electr Insul Mag 19(2):23–30

    Article  Google Scholar 

  25. Cavallini A, Montanari G, Puletti F, Contin A (2005) A new methodology for the identification of pd in electrical apparatus: properties and applications. IEEE Trans Dielectr Electr Insul 12(2):203–215

    Article  Google Scholar 

  26. Janani H (2016) Partial discharge source classification using pattern recognition algorithms. PhD thesis, University of Manitoba

  27. Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097–1105

    Google Scholar 

  28. Shen X, Ni Z, Liu L, Yang J, Ahmed K (2021) Wipass: 1d-cnn-based smartphone keystroke recognition using wifi signals. Pervasive Mob Comput 73:101393

    Article  Google Scholar 

  29. Chen W, Shi K (2019) A deep learning framework for time series classification using relative position matrix and convolutional neural network. Neurocomputing 359:384–394

    Article  Google Scholar 

  30. Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines. In: Icml

  31. Goodfellow I, Lee H, Le Q, Saxe A, Ng A (2009) Measuring invariances in deep networks. Adv Neural Inf Process Syst 22:646–654

    Google Scholar 

  32. Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2014) Semantic image segmentation with deep convolutional nets and fully connected crfs. Preprint arXiv:1412.7062

  33. Yi-de M, Qing L, Zhi-Bai Q (2004) Automated image segmentation using improved pcnn model based on cross-entropy. In: Proceedings of 2004 international symposium on intelligent multimedia, video and speech processing. IEEE, pp 743–746

  34. Zhang Z (2018) Improved adam optimizer for deep neural networks. In: 2018 IEEE/ACM 26th international symposium on quality of service (IWQoS). IEEE, pp 1–2

  35. Burman P (1989) A comparative study of ordinary cross-validation, v-fold cross-validation and the repeated learning-testing methods. Biometrika 76(3):503–514

    Article  MathSciNet  Google Scholar 

  36. Bengio Y, Courville A, Vincent P (2013) Representation learning: a review and new perspectives. IEEE Trans Pattern Anal Mach Intell 35(8):1798–1828

    Article  Google Scholar 

  37. Jetley S, Lord NA, Lee N, Torr PH (2018) Learn to pay attention. Preprint arXiv:1804.02391

  38. Du M, Liu N, Hu X (2019) Techniques for interpretable machine learning. Commun ACM 63(1):68–77

    Article  Google Scholar 

  39. Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision, pp 618–626

  40. He T, Guo J, Chen N, Xu X, Wang Z, Fu K, Liu L, Yi Z (2019) Medimlp: using grad-cam to extract crucial variables for lung cancer postoperative complication prediction. IEEE J Biomed Health Inform 24(6):1762–1771

    Article  Google Scholar 

  41. Panwar H, Gupta P, Siddiqui MK, Morales-Menendez R, Bhardwaj P, Singh V (2020) A deep learning and grad-cam based color visualization approach for fast detection of covid-19 cases using chest x-ray and ct-scan images. Chaos Solitons Fractals 140:110190

    Article  MathSciNet  Google Scholar 

  42. Cian D, van Gemert J, Lengyel A (2020) Evaluating the performance of the lime and grad-cam explanation methods on a lego multi-label image classification task. Preprint arXiv:2008.01584

  43. Feng F, Wu C, Zhu J, Wu S, Tian Q, Jiang P (2020) Research on multitask fault diagnosis and weight visualization of rotating machinery based on convolutional neural network. J Braz Soc Mech Sci Eng 42(11):1–14

    Article  Google Scholar 

Download references

Acknowledgements

The authors are thankful to Dr. Hamed Janani for his useful comments and discussion.

Funding

Financial support from Natural Sciences and Engineering Research Council of Canada (NSERC) and the Faculty of Graduate Studies, University of Manitoba is acknowledged.

Author information

Authors and Affiliations

  1. Department of Electrical and Computer Engineering, University of Manitoba, Winnipeg, MB, Canada

    Sara Mantach, Puneet Gill, Derek R. Oliver, Ahmed Ashraf & Behzad Kordi

  2. Manitoba Institute for Materials, University of Manitoba, Winnipeg, MB, Canada

    Derek R. Oliver

Authors
  1. Sara Mantach
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Puneet Gill
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Derek R. Oliver
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ahmed Ashraf
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Behzad Kordi
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conceptualization was contributed by SM, PG, DO, AA, BK; methodology was contributed by SM, PG, DO, AA, BK; software was contributed by SM; formal analysis was contributed by SM, AA, BK; investigation was contributed by SM, PG, DO, AA, BK; original draft preparation was contributed by SM; writing was contributed by SM; review and editing was contributed by SM, DO, AA, BK. All authors have read and agreed to the published version of the manuscript.

Corresponding author

Correspondence to Behzad Kordi.

Ethics declarations

Conflict of interest

The authors declare no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendix 1

Appendix 1

The appendix includes the PRPD pattern (Fig. 13) and samples of the PD waveforms corresponding to class 2 (Fig. 14).

Fig. 13
figure 13

PRPD pattern of class 2 sample

Full size image
Fig. 14
figure 14

Two examples time series waveforms from class 2: the left one shows a positive pulse and the right one shows a negative pulse. Both pulses belong to void size class 2

Full size image

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Mantach, S., Gill, P., Oliver, D.R. et al. An interpretable CNN model for classification of partial discharge waveforms in 3D-printed dielectric samples with different void sizes. Neural Comput & Applic 34, 11739–11750 (2022). https://doi.org/10.1007/s00521-022-07066-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-022-07066-y

Keywords

Search

Navigation