Skip to content
2000
Volume 18, Issue 5
  • ISSN: 2352-0965
  • E-ISSN: 2352-0973

Abstract

Background

Feature extraction methods such as statistical features and image features based on traditional partial discharge spectrograms require the support of expert experience and prior knowledge, making their engineering applications have significant limitations. Currently, electrical equipment fault diagnosis is moving towards intelligent and scientific directions, and how to apply deep learning methods for more accurate, intelligent, and autonomous diagnosis has become a hot issue in the current field.

Methods

The construction and optimal selection of high-voltage cable partial discharge feature space is an important means to improve recognition accuracy. This paper proposes a new method that can independently and deeply mine partial discharge image features to quickly identify partial discharge types. Firstly, a self encoder is used to encode and decode partial discharge images, and a multi-level stack structure is used to achieve the goal of deep feature mining; then, the partial discharge data features decoded based on a stack self encoder are imported into a random forest network for type recognition; Finally, based on the random forest algorithm, the redundant feature space is optimized and compared with other traditional recognition methods.

Results

The recognition accuracy of the proposed method is about 10% higher than that of traditional methods.

Conclusion

The optimized feature parameters can maintain more than 90% recognition accuracy in both random forest algorithms, common support vector machines, and BP neural networks, proving the feasibility and effectiveness of the method in this paper.

© 2025 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/raeeng/10.2174/0123520965269613231127081659
2025-06-01
2025-09-02

  • From This Site

    /content/journals/raeeng/10.2174/0123520965269613231127081659
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. HaiboS. ManchengY. ChunhuaF. Influence factors analysis and optimization of forces on t-type cable joint in ring main unit.2018 China International Conference on Electricity Distribution (CICED)Tianjin, China201826692673
     [Google Scholar]
  2. WangW. ChengX. LiuC. ZongF. ShenX. Detection method of partial discharge in XLPE Cable accessories based on the method of VHF combined with acoustic emission. 2008 International Symposium on Electrical Insulating Materials (ISEIM 2008)Yokkaichi, Japan200847147410.1109/ISEIM.2008.4664589
     [Google Scholar]
  3. ZhangS. LiC. WangK. LiJ. LiaoR. ZhouT. ZhangY. Improving recognition accuracy of partial discharge patterns by image-oriented feature extraction and selection technique.IEEE Trans. Dielectr. Electr. Insul.20162321076108710.1109/TDEI.2015.005226
     [Google Scholar]
  4. ZhouL. YangH. LiuC. WangD. XiangE. Research on the electrical-thermal field characteristics of XLPE cable terminal under damp defects. 2021 IEEE 2nd China International Youth Conference on Electrical Engineering (CIYCEE)15-17 December 2021, Chengdu, China202110.1109/CIYCEE53554.2021.9676988
     [Google Scholar]
  5. YinJ. ZhouX. MaY. WuY. XuX. Power transformer fault diagnosis based on multi-class multi-kernel learning relevance vector machine. 2015 IEEE International Conference on Mechatronics and Automation (ICMA)Beijing, China201521722110.1109/ICMA.2015.7237485
     [Google Scholar]
  6. LiuQ. HuangG. MaoC. ShangY. WangF. Recognition of dissolved gas in transformer oil by ant colony optimization support vector machine. 2016 IEEE International Conference on High Voltage Engineering and Application (ICHVE)Chengdu, China20161410.1109/ICHVE.2016.7800837
     [Google Scholar]
  7. GuoL. Fault diagnosis based on multiscale texture features of cable terminal on EMU of high-speed railway.IEEE Trans Instrum Meas2021PP991110.1109/TIM.2020.3025375
     [Google Scholar]
  8. BaiL. ZhouL. LiL. ChenY. CheY. YuY. GuoL. Partial discharge of cable termination on electric multiple unit of China high‐speed railway below zero‐degree centigrade.IET Sci. Measur. Technol.201913691292110.1049/iet‑smt.2018.5277
     [Google Scholar]
  9. FangY. SunT. CuiJ. LeiX. YangY. Partial discharge pattern recognition for XLPE cables based on autonomous feature extraction of CNN. 2022 IEEE International Conference on Power Systems and Electrical Technology (PSET)13-15 October 2022, Aalborg, Denmark5863202210.1109/PSET56192.2022.10100378
     [Google Scholar]
  10. HuangX. HabetlerT.G. HarleyR.G. Detection of rotor eccentricity faults in a closed-loop drive-connected induction motor using an artificial neural network.IEEE Trans. Power Electron.20072241552155910.1109/TPEL.2007.900607
     [Google Scholar]
  11. RaoS. MunirajuG. TepedelenliogluC. SrinivasanD. TamizhmaniG. SpaniasA. Dropout and pruned neural networks for fault classification in photovoltaic arrays.IEEE Access2021912003412004210.1109/ACCESS.2021.3108684
     [Google Scholar]
  12. BindiM. CortiF. GrassoF. LuchettaA. ManettiS. PiccirilliM.C. ReattiA. Failure prevention in DC–DC converters: Theoretical approach and experimental application on a zeta converter.IEEE Trans. Ind. Electron.202370193093910.1109/TIE.2022.3153827
     [Google Scholar]
  13. UckolH.I. IlhanS. OzdemirA. Partial discharge pattern classification based on deep learning for defect identification in MV cable terminations. 2020 IEEE International Conference on High Voltage Engineering and Application (ICHVE)Beijing, China20201410.1109/ICHVE49031.2020.9279399
     [Google Scholar]
  14. LiangY. XuY-Y. WanX-S. LiY. LiuN. ZhangG-J. Dissolved gas analysis of transformer oil based on deep belief networks. 2018 12th International Conference on the Properties and Applications of Dielectric Materials (ICPADM)20-24 May 2018, Xi'an, China201810.1109/ICPADM.2018.8401156
     [Google Scholar]
  15. MajidiM. FadaliM.S. Etezadi-AmoliM. OskuoeeM. Partial discharge pattern recognition via sparse representation and ANN.IEEE Trans. Dielectr. Electr. Insul.20152221061107010.1109/TDEI.2015.7076807
     [Google Scholar]
  16. DuanY. ZhangH. HuX. JinA. SunX. PD pattern recognition of XLPE cable based on parameter optimal support vector machine algorithm. 2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA)Xi'an, China201935535910.1109/ICIEA.2019.8833737
     [Google Scholar]
  17. Hoo-Chang Shin OrtonM.R. CollinsD.J. DoranS.J. LeachM.O. Stacked autoencoders for unsupervised feature learning and multiple organ detection in a pilot study using 4D patient data.IEEE Trans. Pattern Anal. Mach. Intell.20133581930194310.1109/TPAMI.2012.27723787345
     [Google Scholar]
  18. GlorotX. BordesA. BengioY. Deep sparse rectifier neural networks.J. Mach. Learn. Res.201115315323
     [Google Scholar]
  19. XuZ. MoW. WangY. LuoS. LiuT. Transformer fault diagnosis based on deep brief sparse autoencoder. 2019 Chinese Control Conference (CCC)Guangzhou, China20197432743510.23919/ChiCC.2019.8866347
     [Google Scholar]
  20. BreimanL. Random forests.Mach. Learn.200145153210.1023/A:1010933404324
     [Google Scholar]
  21. MenzeB.H. KelmB.M. MasuchR. HimmelreichU. BachertP. PetrichW. HamprechtF.A. A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data.BMC Bioinformatics200910121310.1186/1471‑2105‑10‑21319591666
     [Google Scholar]
  22. PillalaP. BhansaliP.K. ReddyM.A.E. RojamaniG. Random forest model for intrusion detection in crowd-sourced reviews. 2020 International Conference on Smart Electronics and Communication (ICOSEC)Trichy, India202032532910.1109/ICOSEC49089.2020.9215423
     [Google Scholar]
  23. ZhangY. WuZ. LiuG. ZhangD. TanX. ZhouX. Research on partial discharge characteristics and type identification of typical insulation defects of 10kV XLPE cables.2021 IEEE Sustainable Power and Energy Conference (iSPEC) 23-25 December 2021, Nanjing, China202110.1109/iSPEC53008.2021.9735803
     [Google Scholar]
  24. XuY. QianY. YangF. LiZ. ShengG. JiangX. DC cable feature extraction based on the PD image in the non-subsampled contourlet transform domain.IEEE Trans. Dielectr. Electr. Insul.201825253354010.1109/TDEI.2018.006919
     [Google Scholar]
  25. ChenX. LuoG. PanX. JiangT. BiM. Study on development characteristics of cavity discharge in composite insulation of superconducting cable. 2020 IEEE International Conference on High Voltage Engineering and Application (ICHVE)Beijing, China20201410.1109/ICHVE49031.2020.9279575
     [Google Scholar]
  26. ChenZ. WuC. FangR. LiZ. ShengG. JiangX. Research on leakage current analysis of DC cable based on wavelet packet multi - scale decompositionCondition Monitoring and Diagnosis.Perth, WA, AustraliaCMD201816
     [Google Scholar]
/content/journals/raeeng/10.2174/0123520965269613231127081659
Loading
Fault Feature Mining and Identification Method of 10kV XLPE Cable Combining SAE and RF
Recent Advances in Electrical & Electronic Engineering 18, 589 (2025); https://doi.org/10.2174/0123520965269613231127081659
/content/journals/raeeng/10.2174/0123520965269613231127081659
/content/journals/raeeng/10.2174/0123520965269613231127081659
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): auto-encoder; machines; partial discharge; pattern recognition; random forest; XLPE cable

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test