Reference-based degradation screening of 150-kV insulators using GWO-optimized one-class SVM under limited puncture-test data

Giovanni Dimas Prenata; Ahmad Ridhoi

doi:10.33795/eltek.v24i2.11136

Authors

Giovanni Dimas Prenata Universitas 17 Agustus 1945 Surabaya
Ahmad Ridhoi Universitas 17 Agustus 1945 Surabaya

DOI:

https://doi.org/10.33795/eltek.v24i2.11136

Keywords:

150-kV Insulator, One-class SVM, Grey Wolf Optimizer, Degradation Screening, Reference-based Learning, Anomaly Detection, Puncture-test Data

Abstract

This study proposes a reference-based degradation screening framework for 150-kV ceramic, glass, and polymer insulators using a Grey Wolf Optimizer–One-Class Support Vector Machine (GWO-OCSVM) under limited puncture-test data. The dataset comprised 72 observations, including 36 replacement samples used exclusively as reference data and 36 existing samples reserved for screening and evaluation. Input features were constructed from normalized string position and voltage ratio relative to the material-specific reference mean. Model development employed nested leave-one-position-out validation, while the OCSVM parameters ν and γ were optimized by GWO using reference data only. REF-GWO-OCSVM achieved an AUC of 0.8299, improving over REF-OCSVM at 0.7535, while increasing the mean anomaly-score gap from 0.0560 to 0.1447. The final consensus parameters were ν=0.1338 and γ=1.8257. A conservative P₉₅=0.1970 threshold reduced reference rejection to 2/36 while flagging 9/36 existing samples. The results demonstrate that the proposed method enables reference-based anomaly screening without using existing-condition data during training or hyperparameter optimization.

References

D. R. de Mello, J. A. P. Rodrigues, J. A. D’Affonseca Cardoso, and F. de A. A. F. Vieira, “The influence of a compact test circuit in the puncture test,” in Proc. 2010 Int. Conf. High Voltage Engineering and Application (ICHVE), 2010, doi: 10.1109/ICHVE.2010.5640707.

N. Tonmitr, K. Tonmitr, and E. Kaneko, “The effect of controlling stray and disc capacitance of ceramic string insulator in the case of clean and contaminated conditions,” Procedia Computer Science, vol. 86, pp. 333–336, 2016, doi: 10.1016/j.procs.2016.05.090.

L. Zheng, P. Yin, J. Li, H. Liu, T. Li, and H. Luo, “Research on diagnostic methods for zero-value insulators in 110 kV transmission lines based on spatial distribution characteristics of electric fields,” Energies, vol. 18, no. 6, Art. no. 1534, 2025, doi: 10.3390/en18061534.

J. Lu, J. Hu, Z. Fang, X. Qiao, and Z. Zhang, “Electric field distribution and AC breakdown characteristics of polluted novel lightning protection insulator under icing conditions,” Energies, vol. 14, no. 22, Art. no. 7493, 2021, doi: 10.3390/en14227493.

C. A. Badachi and P. Dixit, “Prediction of pollution flashover voltages of ceramic string insulators under uniform and non-uniform pollution conditions,” Journal of Electrical Systems and Information Technology, vol. 3, no. 2, pp. 270–281, 2016, doi: 10.1016/j.jesit.2016.01.003.

A. A. Salem et al., “Influence of contamination distribution in characterizing the flashover phenomenon on outdoor insulator,” Ain Shams Engineering Journal, vol. 14, no. 12, Art. no. 102249, 2023, doi: 10.1016/j.asej.2023.102249.

A. A. Salem et al., “Leakage current characteristics in estimating insulator reliability: Experimental investigation and analysis,” Scientific Reports, vol. 12, Art. no. 14974, 2022, doi: 10.1038/s41598-022-17792-x.

A. A. Salem et al., “Monitoring porcelain insulator condition based on leakage current characteristics,” Materials, vol. 15, no. 18, Art. no. 6370, 2022, doi: 10.3390/ma15186370.

A. A. Salem, K. Y. Lau, Z. Abdul-Malek, N. Mohammed, A. M. Al-Shaalan, A. A. Al-Shamma’a, and H. M. H. Farh, “Polymeric insulator conditions estimation by using leakage current characteristics based on simulation and experimental investigation,” Polymers, vol. 14, no. 4, Art. no. 737, 2022, doi: 10.3390/polym14040737.

U. A. Khan et al., “Experimental validation of machine learning for contamination classification of polluted high voltage insulators using leakage current,” Scientific Reports, vol. 15, Art. no. 13246, 2025, doi: 10.1038/s41598-025-97646-4.

Arshad, J. Ahmad, A. Tahir, B. G. Stewart, and A. Nekahi, “Forecasting flashover parameters of polymeric insulators under contaminated conditions using the machine learning technique,” Energies, vol. 13, no. 15, Art. no. 3889, 2020, doi: 10.3390/en13153889.

L. Song, Q. Liang, H. Chen, H. Hu, Y. Luo, and Y. Luo, “A new approach to optimize SVM for insulator state identification based on improved PSO algorithm,” Sensors, vol. 23, no. 1, Art. no. 272, 2023, doi: 10.3390/s23010272.

A. S. Haiba and A. E. Gad, “Artificial neural network analysis for classification of defected high voltage ceramic insulators,” Scientific Reports, vol. 14, Art. no. 1513, 2024, doi: 10.1038/s41598-024-51860-8.

B. Schölkopf, J. C. Platt, J. Shawe-Taylor, A. J. Smola, and R. C. Williamson, “Estimating the support of a high-dimensional distribution,” Neural Computation, vol. 13, no. 7, pp. 1443–1471, 2001, doi: 10.1162/089976601750264965.

D. M. J. Tax and R. P. W. Duin, “Uniform object generation for optimizing one-class classifiers,” Journal of Machine Learning Research, vol. 2, pp. 155–173, 2001.

A. Thomas, V. Feuillard, and A. Gramfort, “Calibration of One-Class SVM for MV set estimation,” in Proc. IEEE Int. Conf. Data Science and Advanced Analytics (DSAA), 2015, doi: 10.1109/DSAA.2015.7344789.

S. Mirjalili, S. M. Mirjalili, and A. Lewis, “Grey Wolf Optimizer,” Advances in Engineering Software, vol. 69, pp. 46–61, 2014, doi: 10.1016/j.advengsoft.2013.12.007.

S. Varma and R. Simon, “Bias in error estimation when using cross-validation for model selection,” BMC Bioinformatics, vol. 7, Art. no. 91, 2006, doi: 10.1186/1471-2105-7-91.

S. Arlot and A. Celisse, “A survey of cross-validation procedures for model selection,” Statistics Surveys, vol. 4, pp. 40–79, 2010, doi: 10.1214/09-SS054..

T. Fawcett, “An introduction to ROC analysis,” Pattern Recognition Letters, vol. 27, no. 8, pp. 861–874, 2006, doi: 10.1016/j.patrec.2005.10.010.

A. A. Salem et al., “Classification of RTV-coated porcelain insulator condition under different profiles and levels of pollution,” Scientific Reports, vol. 14, Art. no. 22759, 2024, doi: 10.1038/s41598-024-73520-7.

M. Monemi, S. M. Shahrtash, and M. Kalantar, “Failure type and failure level detection of insulators according to monitored leakage current,” Heliyon, vol. 10, no. 14, Art. no. e34143, 2024, doi: 10.1016/j.heliyon.2024.e34143.

Z.-Y. Xu and X. Tang, “Transmission line insulator defect detection algorithm based on MAP-YOLOv8,” Scientific Reports, vol. 15, Art. no. 10288, 2025, doi: 10.1038/s41598-025-92445-3.

L. Das, B. Gjorgiev, and G. Sansavini, “An improved anomaly detection model for automated inspection of power line insulators,” Engineering Applications of Artificial Intelligence, vol. 158, Part B, Art. no. 111431, 2025, doi: 10.1016/j.engappai.2025.111431.

Z. Xie, S. Wu, T. Yang, N. Zhan, et al., “Unsupervised visual anomaly detection for high voltage insulators using context aware multi scale memory networks,” Discover Applied Sciences, vol. 8, Art. no. 463, 2026, doi: 10.1007/s42452-026-08435-1.

Z. Que and C.-J. Lin, “One-Class SVM Probabilistic Outputs,” IEEE Transactions on Neural Networks and Learning Systems, vol. 36, no. 4, pp. 6244-6256, 2025, doi: 10.1109/TNNLS.2024.3395148.

G. D. Prenata, “Klasifikasi Keandalan Sistim Distribusi Tenaga Listrik di PT. PLN (Persero) UP3 Surabaya Selatan Menggunakan Support Vector Machine (SVM),” Jurnal Teknik Elektro, vol. 16, no. 2, pp. 62-70, 2023, doi: 10.9744/jte.16.2.62-70.

G. D. Prenata, “Predicting Breakdown Voltage of Transformer Oil under Copper/Iron Contamination: A Comparative Study of Gradient vs Metaheuristic Training,” ELKHA: Jurnal Teknik Elektro, vol. 18, no. 1, pp. 65-73, 2026, doi: 10.26418/elkha.v18i1.101026.

G. D. Prenata and A. Ridho’i, “Breakdown Voltage Prediction of Transformer Oil under Copper/Iron Contamination Using SVR and KNN Regression: A Baseline Study on Small Experimental Data,” El Sains: Jurnal Elektro, vol. 8, no. 1, pp. 81-87, 2026, doi: 10.30996/elsains.v8i1.133785.

G. D. Prenata and A. Ridho’i, “Thermal Behavior Clustering of High-Voltage Electrical Equipment Using K-Means and Fuzzy C-Means,” Elkom: Jurnal Elektronika dan Komputer, vol. 19, no. 1, pp. 229-238, 2026, doi: 10.51903/elkom.v19i1.3700.