Document Type : Research Articles
Authors
Department of electrical and computer Engineering, Qom university of Technology, Qom, Iran
Abstract
Insulator pollution levels are critical for ensuring the operational stability and safety of power transmission systems. Traditional methods for detecting pollution are often invasive, inaccurate, and time-consuming. To address these issues, this study investigates the application of Artificial Intelligence (AI), specifically Gradient Boosting Machines (GBM), to classify insulator pollution levels based on Partial Discharge (PD) characteristics. We utilize a combination of time-domain and frequency-domain features extracted from PD signals to train a predictive model. The results indicate that the proposed model achieves a high classification accuracy, averaging between 92% and 95% across various contamination levels. Furthermore, the study analyzes the model's sensitivity to environmental factors, including humidity and Hydrophobicity Class (HC), revealing important insights that could influence classification performance. By employing this AI-driven approach, we aim to significantly enhance the efficiency of power grid maintenance, ultimately contributing to the long-term stability and reliability of transmission systems. The findings from this research underscore the potential of AI in revolutionizing pollution assessment methods and optimizing maintenance practices in power infrastructure.
Keywords
- Artificial Intelligence
- Composite Insulators
- Gradient Boosting Machines
- Partial Discharge
- Pollution Assessment
Main Subjects
[1] A. Ghaedi, R. Sedaghati, M. Mahmoudian, and S. Bazyari, “De-Noising of Partial Discharge Signals in HV XLPE Cables by Reference Noise based on the Wavelet Transform,” International Journal of Industrial Electronics Control and Optimization, vol. 6, no. 4, pp. 291-306, 2023, doi: 10.22111/ieco.2023.46346.1498
[2] T. Kim and J. Yi, “Application of hydrophobic coating to reduce leakage current through surface energy control of high voltage insulator,” Applied Surface Science, vol. 578, p. 151820, 2022, doi: 10.1016/j.apsusc.2021.151820
[3] S. N. Razavinia et al., “Numerical Simulation of Electron Cyclotron Resonance Discharge Generated by Permanent Magnets,” Power, Control, and Data Processing Systems, vol. 2, no. 1, 2025, doi: 10.30511/pcdp.2025.718447
[4] M. E. Ibrahim and A. M. Abd-Elhady, “Rogowski coil transducer-based condition monitoring of high voltage insulators,” IEEE Sensors Journal, vol. 20, no. 22, pp. 13694-13703, 2020, doi: 10.1109/jsen.2020.3005223
[5] S. Deb, R. Ghosh, S. Dutta, S. Dalai, and B. Chatterjee, “Effect of humidity on leakage current of a contaminated 11 kV Porcelain Pin Insulator,” in 2017 6th International Conference on Computer Applications In Electrical Engineering-Recent Advances (CERA), 2017, pp. 215-219: IEEE, doi: 10.1109/CERA.2017.8343329
[6] L. Jin, Z. Xu and S. Zhang, “A pre-warning method of contamination flashover based on the leakage current of insulators in dry condition,” 2017 International Symposium on Electrical Insulating Materials (ISEIM), Toyohashi, Japan, 2017, pp. 757-760, doi: 10.23919/ISEIM.2017.8166599.
[7] U. Benisheikh, Z. Abdul-Malek, and A. Sahito, “Classification of leakage current odd harmonic component of aged insulator surface condition under different relative humidity using crest factor,” Archives of Electrical Engineering, pp. 1069-1085, 2024, doi:10.24425/aee.2024.152111
[8] L. Zhengfa et al., “Study on leakage current characteristics and influence factors of 110kV polluted composite insulators,” 2018 12th International Conference on the Properties and Applications of Dielectric Materials (ICPADM), Xi'an, China, 2018, pp. 896-900, doi: 10.1109/ICPADM.2018.8401173.
[9] M. A. Amini and A. R. Sedighi, “A new procedure for determination of insulators contamination in electrical distribution networks,” International Journal of Electrical Power & Energy Systems, vol. 61, pp. 380-385, 2014, doi: 10.1016/j.ijepes.2014.03.034.
[10] M. Amini, A. S. Anaraki and M. Sadeghi, “High frequency components of feeder current as diagnostic tool to study contamination conditions of outdoor insulators in power distribution networks,” 2013 21st Iranian Conference on Electrical Engineering (ICEE), Mashhad, Iran, 2013, pp. 1-6, doi: 10.1109/IranianCEE.2013.6599890.
[11] S. Ahmad, R. Ahmed, R. Abd Rahman, A. Ullah, A. Jamal, and R. Akram, “A comprehensive study of nano/micro fillers on silicone rubber insulators: Electrical, mechanical, and thermal characterization,” Results in Engineering, vol. 25, p. 103654, 2025, doi: 10.1016/j.rineng.2024.103654.
[12] B. Cao, Y. Liu, Z. Li, S. Shen, L. Wang and Z. Wang, “Assessment of Insulator Pollution Degree Based on Contamination Moisture With Temperature Change,” in IEEE Sensors Journal, vol. 22, no. 21, pp. 21172-21178, 1 Nov.1, 2022, doi: 10.1109/JSEN.2022.3206215.
[13] Y.-T. Lin and C.-C. Kuo, “Real-time salt contamination monitoring system and method for transmission line insulator based on artificial intelligence,” Applied Sciences, vol. 14, no. 4, p. 1506, 2024, doi: 10.3390/app14041506.
[14] S. Gao et al., “Prediction method of leakage current of insulators on the transmission line based on BP neural network,” 2018 IEEE 2nd International Electrical and Energy Conference (CIEEC), Beijing, China, 2018, pp. 569-572, doi: 10.1109/CIEEC.2018.8745839.
[15] Z. Fei, Y. Li, and S. Yang, “Partial Discharge Pattern Recognition Based on an Ensembled Simple Convolutional Neural Network and a Quadratic Support Vector Machine,” Energies, vol. 17, no. 11, p. 2443, 2024, doi:10.3390/en17112443
[16] Q. Zhu et al., “Research on partial discharge pattern recognition of transformer based on KPCA and JS-SVM algorithm,” in Journal of Physics: Conference Series, 2025, vol. 2963, no. 1, p. 012013: IOP Publishing, doi:10.1088/1742-6596/2963/1/012013
[17] H. Jung, Y.-T. Kim, S.-K. Lee, and J.-h. Ahn, “Study on Deep-Learning Model for Phase Resolved Partial Discharge Pattern Classification Based on Convolutional Neural Network Algorithm,” Journal of Electrical Engineering & Technology, vol. 20, no. 1, pp. 873-878, 2025, doi: 10.1007/s42835-024-01967-9
[18] C. W. Priananda, H. A. Illias, W. J. K. Raymond and I. M. Y. Negara, “Hybrid Deep Learning Models for Enhanced Classification of Phase-Resolved Partial Discharge Patterns from High-Voltage Rotating Machine Insulation,” in IEEE Transactions on Dielectrics and Electrical Insulation, doi: 10.1109/TDEI.2025.3542343.
[19] H. Shadfar and H. R. Izadfar, “Frequency Response Analysis: An Overview of the Measurement Process and Interpretation of Results for Fault Diagnosis and Location in Power Transformers,” International Journal of Industrial Electronics Control and Optimization, vol. 8, no. 2, pp. 149-163, 2025, doi: 10.22111/ieco.2024.49470.1603
[20] M. M. Mohsenzadeh, S. Hasanzadeh, H. R. Sezavar, and M. H. Samimi, “Flashover voltage and time prediction of polluted silicone rubber insulator based on artificial neural networks,” Electric Power Systems Research, vol. 221, p. 109456, 2023, doi: 10.1016/j.epsr.2023.109456
[21] H. Sezavar, N. Fahimi, S. Hasanzadeh, and A. S. Akmal, “Risk assessment of contaminated composite insulators in pre-flashover conditions,” Electric Power Systems Research, vol. 230, p. 110256, 2024, doi:10.1016/j.epsr.2024.110256
[22] A. H. Alshalawi and F. S. Al-Ismail, “Partial Discharge Detection Based on Ultrasound Using Optimized Deep Learning Approach,” in IEEE Access, vol. 12, pp. 5151-5162, 2024, doi: 10.1109/ACCESS.2024.3350555.
[23] S. Li et al., “Partial Discharge Data Enhancement and Pattern Recognition Method Based on a CAE-ACGAN and ResNet,” Symmetry, vol. 17, no. 1, p. 55, 2024, doi: 10.3390/sym17010055.
[24] M. Messaoudi, S. M. Kameli, S. S. Refaat, H. Abu-Rub and M. Trabelsi, “Deep Learning Based Corona Discharge Severity Classification for High Voltage Equipment,” IECON 2024 - 50th Annual Conference of the IEEE Industrial Electronics Society, Chicago, IL, USA, 2024, pp. 1-5, doi: 10.1109/IECON55916.2024.10905579.
[25] H. R. Sezavar, N. Fahimi and A. A. Shayegani-Akmal, “An Improved Dynamic Multi-Arcs Modeling Approach for Pollution Flashover of Silicone Rubber Insulator,” in IEEE Transactions on Dielectrics and Electrical Insulation, vol. 29, no. 1, pp. 77-85, Feb. 2022, doi: 10.1109/TDEI.2022.3146531.
[26] H. R. Sezavar and S. Hasanzadeh, “Integrating Weibull analysis and KAN-ODEs for enhanced flashover prediction in contaminated composite insulators,” Electric Power Systems Research, vol. 244, p. 111584, 2025, doi: 10.1016/j.epsr.2025.111584
[27] S. F. Stefenon et al., “Wavelet group method of data handling for fault prediction in electrical power insulators,” International Journal of Electrical Power & Energy Systems, vol. 123, p. 106269, 2020, doi:10.1016/j.ijepes.2020.106269.
[28] Z. Zhang, F. Yang, H. Zhang, C. Zhou, Y. Li, and H. Liu, “A probabilistic neural network assessment method for insulator pollution level based on discharge noise,” Measurement, vol. 242, p. 115869, 2025, doi: 10.1016/j.measurement.2024.115869.
[29] Y. I. Jang, J. Y. Sim, J.-R. Yang, and N. K. Kwon, “The optimal selection of mother wavelet function and decomposition level for denoising of DCG signal,” Sensors, vol. 21, no. 5, p. 1851, 2021, doi:10.3390/s21051851.
[30] H. Farajpanah, A. Adib, M. Lotfirad, H. EsmaeiliGisavandani, M. M. Riyahi, and A. Zaerpour, “A novel application of waveform matching algorithm for improving monthly runoff forecasting using wavelet–ML models,” Journal of Hydroinformatics, vol. 26, no. 7, pp. 1771-1789, 2024, doi: 10.2166/hydro.2024.128
[31] C. Bentéjac, A. CsörgÅ‘, and G. Martínez-Muñoz, “A comparative analysis of gradient boosting algorithms,” Artificial Intelligence Review, vol. 54, pp. 1937-1967, 2021, doi: 10.1007/s10462-020-09896-5.
[32] A. A. Salem et al., “Classification of RTV-coated porcelain insulator condition under different profiles and levels of pollution,” Scientific Reports, vol. 14, no. 1, p. 22759, 2024, doi: 10.1038/s41598-024-73520-7
[33] N. Fahimi, H. R. Sezavar and A. A. Shayegani-Akmal, “Flashover Prediction of Polymer Insulators Based on Dynamic Modeling of Pollution Layer Resistance Using ANN,” in IEEE Transactions on Dielectrics and Electrical Insulation, vol. 30, no. 1, pp. 122-130, Feb. 2023, doi:10.1109/TDEI.2022.3207452.
)