Giovanni Dimas Prenata
Universitas 17 Agustus 1945
Ahmad Ridho’i
Universitas 17 Agustus 1945
ABSTRAK
Penelitian ini mengusulkan kerangka Position-Aware Physics-Guided Grey Wolf Optimizer–Support Vector Regression (PG-GWO-SVR) untuk estimasi profil referensi dan penyaringan degradasi isolator 150 kV pada data terbatas. Dataset berisi 72 observasi keramik, kaca, dan polimer pada 12 posisi fisik untuk kondisi existing dan replacement; hanya 36 observasi replacement digunakan untuk pemodelan referensi. Posisi dinormalisasi melalui basis nonlinear [s,s2,s3,s4], sedangkan tegangan dinormalisasi terhadap rata-rata spesifik material. Hyperparameter RBF least-squares SVR dioptimasi dengan GWO menggunakan nested leave-one-position-out dan grouped three-fold position validation. PG-GWO-SVR menghasilkan RMSE 0,3513 kV, MAE 0,2815 kV, MAPE 0,1299, dan R2 0,7667, dengan kinerja keseluruhan terbaik dibanding RAW-SVR, PG-SVR, dan RAW-GWO-SVR. Korelasi profil replacement ternormalisasi sebesar 0,9630, 0,9125, dan 0,9773 mendukung formulasi profil bersama. Ambang ketidakpastian P95 sebesar 30,53% kemudian digunakan untuk menyaring kondisi existing, menghasilkan deviasi rata-rata 36,51%, 32,97%, dan 39,11% untuk keramik, kaca, dan polimer, dengan 10/12, 8/12, dan 10/12 posisi terflag. Kerangka ini ditujukan sebagai alat penyaringan berbantuan referensi untuk prioritas pemeriksaan, bukan klasifikasi kegagalan berbasis ground truth.
Kata Kunci: Isolator 150 kV, Pemodelan Berbasis Posisi, Pembelajaran Berbasis Fisika, Grey Wolf Optimizer, Support Vector Regression, Estimasi Profil Referensi, Penyaringan Degradasi.
REFERENSI
[1] A. Al-Gheilani, W. Rowe, Y. Li, and K. L. Wong, “Stress control methods on a high voltage insulator: A review,” Energy Procedia, vol. 110, pp. 95–100, 2017, doi: 10.1016/j.egypro.2017.03.112.
[2] 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.
[3] 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.
[4] 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.
[5] 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.
[6] A. A. Salem, R. Abd-Rahman, M. T. B. Ishak, K. Y. Lau, Z. Abdul- Malek, S. Al-Ameri, S. A. Al-Gailani, and S. S. M. Ghoneim, “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.
[7] A. A. Salem, K. Y. Lau, W. Rahiman, 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.
[8] A. A. Salem, K. Y. Lau, M. T. Ishak, Z. Abdul-Malek, S. A. Al-Gailani, S. M. Al-Ameri, A. Mohammed, A. A. S. Alashbi, and S. S. M. Ghoneim, “Monitoring porcelain insulator condition based on leakage current characteristics,” Materials, vol. 15, no. 18, Art. no. 6370, 2022.
[9] 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.
[10] U. A. Khan, M. Asif, M. H. Zafar, 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.
[11] 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.
[12] 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.
[13] 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.
[14] A. Karpatne, G. Atluri, J. H. Faghmous, et al., “Theory-guided data science: A new paradigm for scientific discovery from data,” IEEE Transactions on Knowledge and Data Engineering, vol. 29, no. 10, pp. 2318–2331, Oct. 2017, doi: 10.1109/TKDE.2017.2720168.
[15] X. Jia, J. Willard, A. Karpatne, J. Read, J. A. Zwart, M. Steinbach, and V. Kumar, “Physics-guided machine learning for scientific discovery: An application in simulating lake temperature profiles,” ACM/IMS Transactions on Data Science, vol. 2, no. 3, Art. no. 20, 2021, doi: 10.1145/3447814.
[16] M. Ezzat, M. Ramadan, M. A. Abd-Allah, S. M. A. El-Gamal, et al., “Cross-material physics-informed machine learning framework for optimizing nanofiller loading in epoxy nanocomposites for high-voltage insulation,” Scientific Reports, vol. 16, Art. no. 22515, 2026, doi: 10.1038/s41598-026-61831-w.
[17] K. Pelckmans, I. Goethals, J. De Brabanter, J. A. K. Suykens, and B. De Moor, “Componentwise least squares support vector machines,” arXiv:cs/0504086, 2005.
[18] 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.
[19] 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.
[20] 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.
[21] 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.
[22] 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.
[23] G. D. Prenata and A. Ridho’i, “Analisis Perbandingan Kinerja KNN Regression dan Support Vector Regression dalam Prediksi Kehandalan Sistem Tenaga Listrik Berdasarkan Indeks SAIDI–SAIFI,” Jurnal Teknik Elektro dan Komputasi (ELKOM), vol. 8, no. 1, pp. 139–150, 2026, doi: 10.32528/elkom.v8i1.5213.
[24] G. D. Prenata, “Analisis Perbandingan Kinerja Jaringan Saraf Tiruan (JST) yang Dioptimalkan Metaheuristik dan Regresi Vektor Pendukung untuk Prediksi Konsumsi Energi Listrik,” CYCLOTRON, vol. 9, no. 2, pp. 32–37, 2026, doi: 10.30651/ct.v9i02.30809.
PUBLISHED
30-9-2026
ISSUE
Vol. 12 No. 3 (2026)
SECTION
Articles