Skip to main content
SpringerLink
Log in

Investigation on machine learning algorithms to support transformer dissolved gas analysis fault identification

  • Original Paper
  • Published:
Electrical Engineering Aims and scope Submit manuscript

Abstract

Dissolved gas analysis (DGA) is a powerful tool to monitor the condition of a power transformer. Several interpretation methods have been proposed, one of the most reliable of which is the graphical Duval triangle method (DTM). The method consists of several triangles, which still requires expertise for fault identification. The use of computer-based technology has been implemented in recent years to support transformer fault identification. However, no study has done thorough investigation on the use of suitable machine learning algorithm for the ML-based implementation of this matter. This study examines six commonly used machine learning algorithms to support DGA fault identification of power transformer: decision tree, support vector machine, random forest (RF), neural network, Naïve Bayes, and AdaBoost. Three DGA fault identification methods for mineral oil insulated transformer were studied, namely DTM1, DTM4, and DTM5. The training and testing datasets were generated for each DGA method, and trained to each ML algorithm. The tenfold cross validation was used to evaluate the results using five criteria, namely classification accuracy, area under curve, F1, Precision, and Recall. RF models demonstrated the best performance in classifying fault codes of most DGA methods. A validation was carried out using the validation dataset, comparing the selected RF-based models to the graphical DGA fault identification. The combination method was also implemented in the developed model. The results show that the proposed model is reliable, and especially useful to be used for fault identification of a large number of transformer populations.

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

Similar content being viewed by others

References

  1. Abu-Siada A (2019) Improved consistent interpretation approach of fault type within power transformers using dissolved gas analysis and gene expression programming. Energies 12:730. https://doi.org/10.3390/en12040730

    Article  Google Scholar 

  2. Bakar NA, Abu-Siada A, Cui H, Li S (2017) Improvement of DGA interpretation using scoring index method. In: ICEMPE 2017—1st international conference on electrical materials and power equipment. https://doi.org/10.1109/ICEMPE.2017.7982139

  3. Pattanadech N, Sasomponsawatline K, Siriworachanyadee J, Angsusatra W (2019) The conformity of DGA interpretation techniques: experience from transformer 132 units. In: 2019 IEEE 20th international conference on dielectric liquids, pp 1–4. https://doi.org/10.1109/icdl.2019.8796588

  4. Faiz J, Soleimani M (2017) Dissolved gas analysis evaluation in electric power transformers using conventional methods a review. IEEE Trans Dielectr Electr Insul 24:1239–1248. https://doi.org/10.1109/TDEI.2017.005959

    Article  Google Scholar 

  5. Abu-Siada A, Hmood S, Islam S (2013) A new fuzzy logic approach for consistent interpretation of dissolved gas-in-oil analysis. IEEE Trans Dielectr Electr Insul 20:2343–2349. https://doi.org/10.1109/TDEI.2013.6678888

    Article  Google Scholar 

  6. Shang H, Xu J, Zheng Z et al (2019) A novel fault diagnosis method for power transformer based on dissolved gas analysis using hypersphere multiclass support vector machine and improved D-S evidence theory. Energies. https://doi.org/10.3390/en12204017

    Article  Google Scholar 

  7. Zeng B, Guo J, Zhu W et al (2019) A transformer fault diagnosis model based on hybrid grey wolf optimizer and LS-SVM. Energies. https://doi.org/10.3390/en12214170

    Article  Google Scholar 

  8. Prasojo RA, Suwarno, Abu-Siada A (2021) Dealing with data uncertainty for transformer insulation system health index. IEEE Access 9:1–1. https://doi.org/10.1109/access.2021.3081699

    Article  Google Scholar 

  9. Ghoneim SSM, Taha IB (2015) Artificial neural networks for power transformers fault diagnosis based on iec code using dissolved gas analysis. Int J Control Autom Syst 4:18–21

    Google Scholar 

  10. Rediansyah D, Prasojo RA, Suwarno, Abu-Siada A (2021) Artificial intelligence-based power transformer health index for handling data uncertainty. IEEE Access 9:150637–150648. https://doi.org/10.1109/access.2021.3125379

    Article  Google Scholar 

  11. IEEE Std C57.104–2019 (2019) IEEE guide for the interpretation of gases generated in mineral oil-immersed transformers

  12. Irungu GK, Akumu AO, Munda JL (2016) A new fault diagnostic technique in oil-filled electrical equipment; the dual of Duval triangle. IEEE Trans Dielectr Electr Insul 23:3405–3410. https://doi.org/10.1109/TDEI.2016.005927

    Article  Google Scholar 

  13. Akbari A, Setayeshmehr A, Borsi H, Gockenbach E (2008) A software implementation of the Duval triangle method. In: Conference record of the 2008 IEEE international symposium on electrical insulation, pp 124–127.https://doi.org/10.1109/ELINSL.2008.4570294

  14. Geetha R (2016) Fault diagnosis of power transformer using duval triangle based artificial intelligence techniques, pp 78–88

  15. Duval M (2008) The Duval triangle for load tap changers, non-mineral oils and low. IEEE Electr Insul Mag 24:22–29

    Article  Google Scholar 

  16. Aciu AM, Nicola CI, Nicola M, Nițu MC (2021) Complementary analysis for DGA based on Duval methods and furan compounds using artificial neural networks. Energies 14:1–22. https://doi.org/10.3390/en14030588

    Article  Google Scholar 

  17. Prasojo RA, Diwyacitta K, Suwarno, Gumilang H (2017) Transformer paper expected life estimation using ANFIS based on oil characteristics and dissolved gases (Case study: Indonesian transformers). Energies. https://doi.org/10.3390/en10081135

    Article  Google Scholar 

  18. Ghoneim SSM, Taha IBM, Elkalashy NI (2016) Integrated ANN-based proactive fault diagnostic scheme for power transformers using dissolved gas analysis. IEEE Trans Dielectr Electr Insul 23:1838–1845. https://doi.org/10.1109/TDEI.2016.005301

    Article  Google Scholar 

  19. Forouhari S, Abu-Siada A (2018) Application of adaptive neuro fuzzy inference system to support power transformer life estimation and asset management decision. IEEE Trans Dielectr Electr Insul 25:845–852. https://doi.org/10.1109/TDEI.2018.006392

    Article  Google Scholar 

  20. Nasution EF, Prasojo RA, et al (2018) Estimation of the degree of polymerization (DP) in oil-paper insulation system based on dielectric and DGA data using fuzzy logic algorithm. In: 4th IEEE conference on power engineering and renewable energy, ICPERE 2018—proceedings, pp 1–6. https://doi.org/10.1109/ICPERE.2018.8739284

  21. Basuki A (2018) Online dissolved gas analysis of power transformers based on decision tree model. In: 4th IEEE conference on power engineering and renewable energy, ICPERE 2018—proceedings

  22. Li Z, Zhang Y, Abu-Siada A et al (2021) Fault diagnosis of transformer windings based on decision tree and fully connected neural network. Energies. https://doi.org/10.3390/en14061531

    Article  Google Scholar 

  23. Ashkezari AD, Ma H, Saha T, Ekanayake C (2013) Application of fuzzy support vector machine for determining the health index of the insulation system of in-service power transformers. IEEE Trans Dielectr Electr Insul 20:965–973. https://doi.org/10.1109/TDEI.2013.6518966

    Article  Google Scholar 

  24. Liu J, Zhao Z, Tang C et al (2019) Classifying transformer winding deformation fault types and degrees using FRA based on support vector machine. IEEE Access 7:112494–112504. https://doi.org/10.1109/access.2019.2932497

    Article  Google Scholar 

  25. Prasojo RA, Suwarno (2018) Power transformer paper insulation assessment based on oil measurement data using SVM-classifier. Int J Electr Eng Informatics 10:661–673. https://doi.org/10.15676/ijeei.2018.10.4.4

    Article  Google Scholar 

  26. Bigdeli M, Vakilian M, Rahimpour E (2012) Transformer winding faults classification based on transfer function analysis by support vector machine. IET Electr Power Appl 6:268–276. https://doi.org/10.1049/iet-epa.2011.0232

    Article  Google Scholar 

  27. Breiman L (1999) Random forests—random features, Tecnical Report 567, Statistic Department, University of California, Berkeley, (https://www.stat.berkeley.edu/~breiman/random-forests.pdf, 08.10.2018’de erişildi), pp 1–29

  28. Kartojo IH, Wang Y-B, Zhang G-J (2019) Partial discharge defect recognition in power transformer using random forest. In: 2019 IEEE 20th international conference on dielectric liquids (ICDL). IEEE, pp 1–4

  29. Shah AM, Bhalja BR (2016) Fault discrimination scheme for power transformer using random forest technique. IET Gener Transm Distrib 10:1431–1439. https://doi.org/10.1049/iet-gtd.2015.0955

    Article  Google Scholar 

  30. Wang S-C (2003) Artificial neural network. In: Interdisciplinary computing in java programming. In: The Springer international series in engineering and computer science

  31. Wang Z, Liu Y, Griffin PJ (2000) Neural net and expert system diagnose transformer faults. IEEE Comput Appl Power 13:50–55. https://doi.org/10.1109/67.814667

    Article  Google Scholar 

  32. Webb GI (2017) Naive Bayes. In: Encyclopedia of machine learning and data mining

  33. Schapire RE (2013) Explaining adaboost. Empir Inference

  34. Zhang C, Hu C, Zhang Z, Cao S (2020) Research on main transformer defect detection methods based on Conditional Inference Tree and AdaBoost Algorithm. In: The 2nd international seminar on computer science and engineering technology (SCSET)

  35. Yan C, Li M, Liu W (2019) Transformer fault diagnosis based on BP-Adaboost and PNN series connection. Math Probl Eng

  36. Kim SW, Kim SJ, Seo HD et al (2013) New methods of DGA diagnosis using IEC TC 10 and related databases Part 1: application of gas-ratio combinations. IEEE Trans Dielectr Electr Insul 20:685–690. https://doi.org/10.1109/TDEI.2013.6508773

    Article  Google Scholar 

  37. Ibrahim K, Sharkawy RM, Temraz HK, Salama MMA (2016) Selection criteria for oil transformer measurements to calculate the Health Index. IEEE Trans Dielectr Electr Insul 23:3397–3404. https://doi.org/10.1109/TDEI.2016.006058

    Article  Google Scholar 

  38. Mharakurwa ET, Nyakoe GN, Akumu AO (2019) Power transformer fault severity estimation based on dissolved gas analysis and energy of fault formation technique. J Electr Comput Eng. https://doi.org/10.1155/2019/9674054

    Article  Google Scholar 

  39. Abu-Siada A, Islam S (2012) A new approach to identify power transformer criticality and asset management decision based on dissolved gas-in-oil analysis. IEEE Trans Dielectr Electr Insul 19:1007–1012. https://doi.org/10.1109/TDEI.2012.6215106

    Article  Google Scholar 

  40. Ranga C, Chandel AK (2017) Expert system for health index assessment of power transformers. Int J Electr Eng Inform 9:850–865. https://doi.org/10.15676/ijeei.2017.9.4.16

    Article  Google Scholar 

  41. Prasojo RA, Gumilang H et al (2020) A fuzzy logic model for power transformer faults’ severity determination based on gas level, gas rate, and dissolved gas analysis interpretation. Energies 13:1009

    Article  Google Scholar 

  42. Ranga C, Chandel AK, Chandel R (2017) Expert system for condition monitoring of power transformer using fuzzy logic. J Renew Sustain Energy. https://doi.org/10.1063/1.4995648

    Article  Google Scholar 

  43. Kadim EJ, Azis N, Jasni J et al (2018) Transformers health index assessment based on neural-fuzzy network. Energies. https://doi.org/10.3390/en11040710

    Article  Google Scholar 

  44. Ranga C, Chandel AK, Chandel R (2017) Condition assessment of power transformers based on multi-attributes using fuzzy logic. IET Sci Meas Technol 11:983–990. https://doi.org/10.1049/iet-smt.2016.0497

    Article  Google Scholar 

  45. Bacha K, Souahlia S, Gossa M (2012) Power transformer fault diagnosis based on dissolved gas analysis by support vector machine. Electr Power Syst Res 83:73–79. https://doi.org/10.1016/j.epsr.2011.09.012

    Article  Google Scholar 

  46. Ghoneim S, Ward S (2012) Dissolved gas analysis as a diagnostic tools for early detection of transformer faults. Adv Electr 1:152–156

    Google Scholar 

  47. Mansour DEA (2015) Development of a new graphical technique for dissolved gas analysis in power transformers based on the five combustible gases. IEEE Trans Dielectr Electr Insul 22:2507–2512. https://doi.org/10.1109/TDEI.2015.004999

    Article  Google Scholar 

  48. Mehta AK, Sharma RN, Chauhan S, Saho S (2013) Transformer diagnostics under dissolved gas analysis using Support vector machine. In: Proceedings 2013 international conference on power, energy and control (ICPEC), pp 181–186.https://doi.org/10.1109/ICPEC.2013.6527647

  49. Tang WH, Goulermas JY, Wu QH et al (2008) A probabilistic classifier for transformer dissolved gas analysis with a particle swarm optimizer. IEEE Trans Power Deliv 23:751–759. https://doi.org/10.1109/TPWRD.2008.915812

    Article  Google Scholar 

  50. Su Q, Lai LL, Austin P (2001) A fuzzy dissolved gas analysis method for the diagnosis of multiple incipient faults in a transformer. IEE Conf Publ 15:344–348. https://doi.org/10.1049/cp:20000420

    Article  Google Scholar 

  51. Forouhari M (2017) Remnant life estimation of power transformers based on chemical diagnostic parameters using adaptive neuro- fuzzy inference system

  52. Duval M (2002) A review of faults detectable by gas-in-oil analysis in transformers. IEEE Electr Insul Mag 18:8–17

    Article  Google Scholar 

  53. Duval M, DePablo A (2001) Interpretation of gas-in-oil analysis using new IEC publication 60599 and IEC TC 10 databases. IEEE Electr Insul Mag 17:31–41. https://doi.org/10.1109/57.917529

    Article  Google Scholar 

  54. Gouda OE, El-Hoshy SH, Tamaly HHEL (2019) Condition assessment of power transformers based on dissolved gas analysis. IET Gener Transm Distrib 13:2299–2310. https://doi.org/10.1049/iet-gtd.2018.6168

    Article  Google Scholar 

  55. Gouda OE, El-Hoshy SH, El-Tamaly HH (2018) Proposed three ratios technique for the interpretation of mineral oil transformers based dissolved gas analysis. IET Gener Transm Distrib 12:2650–2661. https://doi.org/10.1049/iet-gtd.2017.1927

    Article  Google Scholar 

  56. Scatiggio F, Fraioli A, Iuliani V, Pompili M (2014) Health index: the TERNA’s practical approach for transformers fleet management. In: CIGRE Session 45—45th international conference on large high voltage electric systems, pp 178–182

  57. Ma C, Xie R, Zhang L et al (2018) A novel condition assessment method based on dissolved gas in transformer oil. IEEE Electr Insul Conf EIC 2018:232–235. https://doi.org/10.1109/EIC.2018.8481079

    Article  Google Scholar 

  58. Ghoneim SSM (2018) Intelligent prediction of transformer faults and severities based on dissolved gas analysis integrated with thermodynamics theory. IET Sci Meas Technol 12:388–394. https://doi.org/10.1049/iet-smt.2017.0450

    Article  Google Scholar 

  59. Prasojo RA, Gumilang H et al (2020) A fuzzy logic model for power transformer faults’ severity determination based on gas level, gas rate, and dissolved gas analysis interpretation. Energies. https://doi.org/10.3390/en13041009

    Article  Google Scholar 

  60. Taecharoen P, Kunagonniyomrattana P, Chotigo S (2019) Development of Dissolved gas analysis analyzing program using visual studio program. In: 2019 IEEE PES GTD Gd International Conference Expo Asia, GTD Asia 2019, pp 785–790. https://doi.org/10.1109/GTDAsia.2019.8715892

  61. Mansour DEA (2012) A new graphical technique for the interpretation of dissolved gas analysis in power transformers. In: Annual report—conference on electrical insulation and dielectric phenomena, CEIDP, pp 195–198.https://doi.org/10.1109/CEIDP.2012.6378754

  62. Li E, Wang L, Song B, Jian S (2018) Improved fuzzy C-means clustering for transformer fault diagnosis using dissolved gas analysis data. Energies. https://doi.org/10.3390/en11092344

    Article  Google Scholar 

  63. Abu-Siada A (2019) Improved consistent interpretation approach of fault type within power transformers using dissolved gas analysis and gene expression programming. Energies. https://doi.org/10.3390/en12040730

    Article  Google Scholar 

  64. Abu-Siada A, Arshad M, Islam S (2010) Fuzzy logic approach to identify transformer criticality using dissolved gas analysis. IEEE PES Gen Meet PES 2010:1–5. https://doi.org/10.1109/PES.2010.5589789

    Article  Google Scholar 

  65. Ahmed MR, Geliel MA, Khalil A (2013) Power transformer fault diagnosis using fuzzy logic technique based on dissolved gas analysis. In: 21st Mediterranean conference on control and automation, pp 584–589. https://doi.org/10.1109/MED.2013.6608781

  66. Tamma WR, Prasojo RA (2021) High voltage power transformer condition assessment considering the health index value and its decreasing rate. High Volt. https://doi.org/10.1049/hve2.12074

    Article  Google Scholar 

  67. Taha IBM, Mansour DEA, Ghoneim SSM, Elkalashy NI (2017) Conditional probability-based interpretation of dissolved gas analysis for transformer incipient faults. IET Gener Transm Distrib 11:943–951. https://doi.org/10.1049/iet-gtd.2016.0886

    Article  Google Scholar 

  68. Farooque MU, Wani SA, Khan SA (2016) Artificial neural network (ANN) based implementation of Duval pentagon. In: 2015 International conference on condition assessment techniques in electrical systems CATCON 2015—Proceedings, pp 46–50. https://doi.org/10.1109/CATCON.2015.7449506

  69. Hongzhong M, Zheng L, Ju P, et al (2008) Diagnosis of power transformer faults on fuzzy three-ratio method, pp 1–456. https://doi.org/10.1109/ipec.2005.206897

  70. Poiss G (2016) Development of DGA indicator for estimating risk level of power transformers. In: Proc—2016 17th international scientific conference on electric power engineering, EPE 2016, pp 4–7. https://doi.org/10.1109/EPE.2016.7521813

  71. Mendes Barbosa T, Goncalves Ferreira J, Antonio Ferreira Finocchio M, Endo W (2017) Development of an application based on the Duval triangle method. IEEE Lat Am Trans 15:1439–1446. https://doi.org/10.1109/TLA.2017.7994790

    Article  Google Scholar 

  72. Benmahamed Y, Teguar M, Boubakeur A (2017) Application of SVM and KNN to Duval Pentagon 1 for transformer oil diagnosis. IEEE Trans Dielectr Electr Insul 24:3443–3451. https://doi.org/10.1109/TDEI.2017.006841

    Article  Google Scholar 

Download references

Funding

Funding was provided by Politeknik Negeri Malang (Grant No. SP DIPA 023.18.2.677606/2021).

Author information

Authors and Affiliations

  1. Information Technology Department, Politeknik Negeri Malang, Malang, 65141, Indonesia

    Ekojono, Meyti Eka Apriyani & Anugrah Nur Rahmanto

  2. Electrical Engineering Department, Politeknik Negeri Malang, Malang, 65141, Indonesia

    Rahman Azis Prasojo

Authors
  1. Ekojono
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Rahman Azis Prasojo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Meyti Eka Apriyani
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Anugrah Nur Rahmanto
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Rahman Azis Prasojo.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ekojono, Prasojo, R.A., Apriyani, M.E. et al. Investigation on machine learning algorithms to support transformer dissolved gas analysis fault identification. Electr Eng 104, 3037–3047 (2022). https://doi.org/10.1007/s00202-022-01532-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00202-022-01532-5

Keywords

Search

Navigation