Multiclass Electrical Fault Classification in Three-Phase Power Systems Using Random Forest, Support Vector Machine, and XGBoost
DOI:
https://doi.org/10.35870/ijsecs.v6i3.8397Keywords:
Electrical Fault Classification, Three-Phase Power System, Machine Learning, Random Forest, Multiclass ClassificationAbstract
Electrical fault classification in three-phase power systems remains challenging because different fault conditions can exhibit similar current and voltage characteristics, limiting the diagnostic capability of conventional binary fault detection. This study aimed to compare the performance of Random Forest, Support Vector Machine, and Extreme Gradient Boosting (XGBoost) for multiclass electrical fault classification and to identify the most effective and stable model. The publicly available Electrical Fault Detection and Classification dataset obtained from the Kaggle repository was used in this study. The dataset contains 7,861 observations with six electrical features comprising three-phase currents (Ia, Ib, and Ic) and voltages (Va, Vb, and Vc), which were used to classify six operating conditions: Normal, Line-to-Ground, Line-to-Line, Double Line-to-Ground, Three-Phase, and Three-Phase-to-Ground faults. The models were evaluated using accuracy, precision, recall, F1-score, and five-fold stratified cross-validation, complemented by confusion-matrix and feature-importance analyses. Random Forest achieved the best test performance with an accuracy of 86.78% and an F1-score of 86.76%, while cross-validation produced a mean accuracy of 87.55% and a mean F1-score of 87.53%. Class-level analysis revealed that Three-Phase and Three-Phase-to-Ground faults were the most difficult conditions to distinguish because of substantial overlap in their electrical characteristics. The findings demonstrated that Random Forest provided the most effective and stable classification performance and that combining performance, stability, and class-level analyses provided deeper insight into multiclass electrical fault diagnosis.
Downloads
References
Abro, S. A., Memon, S. A., Khan, T. A., Memon, I., Nasir, H., & Fatima, K. (2025). Non-technical loss detection in power distribution networks using machine learning. Dental Science Reports, 15(1), 36189. https://doi.org/10.1038/s41598-025-20048-z
Agarwal, M., Gill, K. S., Malhotra, S., & Devliyal, S. (2024). Logistic regression utilization for electrical fault identification and classification using machine learning. 2024 International Conference on Applied and Practical Computing and Information Technology (APCIT), 1–5. https://doi.org/10.1109/apcit62007.2024.10673522
Alaca, O., Piesciorovsky, E. C., Ekti, A. R., Stenvig, N., Gui, Y., Olama, M. M., Bhusal, N., & Yadav, A. P. (2024). Assessment of envelope- and machine learning-based electrical fault type detection algorithms for electrical distribution grids. Electronics, 13(18), 3663. https://doi.org/10.3390/electronics13183663
Almagrahi, N. A. (2025). Protecting electrical power systems from malfunctions and disturbances. International Journal of Advances in Engineering and Management (IJAEM), 7(6), 294–298. https://doi.org/10.35629/5252-0706294298
Alvarez-Alvarado, M. S., Donaldson, D. L., Recalde, A. A., Noriega, H. H., Khan, Z. A., Velasquez, W., & Rodriguez-Gallegos, C. D. (2024). Power system reliability and maintenance evolution: A critical review and future perspectives. Journal of Power and Energy Engineering, 12(3), 45-60. https://doi.org/10.60692/y0zb4-x6n29
Anwar, T., Mu, C., Yousaf, M. Z., Khan, W., Khalid, S., Hourani, A. O., & Зайцев, Є. (2025). Robust fault detection and classification in power transmission lines via ensemble machine learning models. Dental Science Reports, 15(1). https://doi.org/10.1038/s41598-025-86554-2
Assadi, K., & Salhi, S. (2023). Shunt faults detection and classification in electrical power transmission line systems based on artificial neural networks. COMPEL-The International Journal for Computation and Mathematics in Electrical and Electronic Engineering. https://doi.org/10.1108/compel-10-2022-0371
Awalin, L. J., Mubarok, M. A., Mokhlis, H. M., Ali, M. S., Halim, S. A., Mohammad, H., Baihaqi, M. F., Taufiqurrahman, M. R., & Sari, F. A. (2025). Fault type detection and classification using rule-based approach. 2025 Innovations in Power and Advanced Computing Technologies (i-PACT), 1–8. https://doi.org/10.1109/i-pact65952.2025.11307821
Basnet, B., & Sen, V. I. (2025). Robust fault detection and classification in power systems via physics-informed and data-driven learning. Journal of Electrical Engineering and Automation, 7(3), 241–259. https://doi.org/10.36548/jeea.2025.3.004
Briza, A. C., Piedad, E., & Peramo, E. C. (2024). Simpler machine learning methods outperform deep learning in motor fault detection. 2024 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), 675–680. https://doi.org/10.1109/icaiic60209.2024.10463445
Daang, J. A. M., Omas-as, A. M., & Arboleda, E. R. (2024). Advancements in fault detection techniques for transmission lines: A literature review. Preprints. https://doi.org/10.20944/preprints202405.0662.v2
Ghaly, A. El. (2025). Hybrid ML algorithm for fault classification in transmission lines using multi-target ensemble classifier with limited data. Eng, 6(1), 4. https://doi.org/10.3390/eng6010004
Goyal, H. R., Habelalmateen, M. I., Badhoutiya, A., Deepak, A., Pushkarna, G., & Harikrishna, M. (2024). Support vector machines for fault detection and classification in electrical systems. 2024 International Conference on Computer, Communication, and Signal Engineering (IC3SE), 1-6. https://doi.org/10.1109/ic3se62002.2024.10592853
Liu, H., & Liu, X. (2024). Electrical fault detection and classification based on multiple machine learning algorithms. Applied and Computational Engineering, 74(1), 245–250. https://doi.org/10.54254/2755-2721/74/20240484
Malla, P., Coburn, W., Keegan, K. G., & Yu, X.-H. (2019). Power system fault detection and classification using wavelet transform and artificial neural networks. In International Conference on Artificial Intelligence and Soft Computing (pp. 266–272). Springer, Cham. https://doi.org/10.1007/978-3-030-22808-8_27
Mandal, S., & Bohre, A. K. (2022). Fault classification in electrical systems using machine learning algorithms. 2022 International Conference on Inventions in Communication and Computational Technologies (ICICICT), 1412–1416. https://doi.org/10.1109/ICICICT54557.2022.9917976
MeenaPrakash, R., Krishnaleela, P., Sambooranalaxmi, S., Srivathsan, V., SivaBala, I., & Bose, K. S. C. (2025). IoT-enabled machine learning framework for fault detection and classification in electrical transmission lines. 2025 International Conference on Artificial Intelligence and Information Communication (ICAAIC), 1966–1971. https://doi.org/10.1109/icaaic64647.2025.11331157
Mukherjee, M., Batabyal, S., Roy, S. D., Koley, B. L., Debroy, S., & Ray, S. (2025). Deep learning-based fault detection and classification in power distribution networks. Lex Localis, 23(S6), 1915–1928. https://doi.org/10.52152/vdwhe059
Nandhini, K., & Prajith, C. A. (2023). Review on fault detection and classification in transmission line using machine learning methods. 2023 International Conference on Innovative Computing and Cloud Computing (ICCC), 1–6. https://doi.org/10.1109/ICCC57789.2023.10164876
Nolasco, J. F. E., Coit, D. W., Prakash, U., & Ramirez-Marquez, J. E. (2005). Reliability modeling of electricity transmission systems: An adaptation of traditional reliability methods. Proceedings of the Annual Reliability and Maintainability Symposium (RAMS), 1-7.
Nurul’aini, A. R., Alam, M. M., Aprilianto, R. A., Sutikno, T., Wahono, T., & Facta, M. (2025). Electrical generator fault detection using artificial intelligence approaches. 2025 International Conference on Electrical Engineering, Computer Science and Informatics (EECSI), 469–475. https://doi.org/10.1109/eecsi67060.2025.11290121
Oishi, J., Hossain, Md. M., Nahid, E., & Siddique, Md. A. I. (2023). Comparative analysis of machine learning algorithms for transmission line fault detection. 2023 International Conference on Power Systems (ICPS), 1–6. https://doi.org/10.1109/icps60393.2023.10428812
Otudi, H., Dokic, T., Mohamed, T., Kezunovic, M., Hu, Y., & Obradovic, Z. (2022). Line faults classification using machine learning on three phase voltages extracted from large dataset of PMU measurements. Proceedings of the 55th Hawaii International Conference on System Sciences, 1–10. https://doi.org/10.24251/hicss.2022.425
Palomares-Salas, J.-C., Aguado-González, S., & Fernández, J. M. S. (2025). Robustness of machine learning and deep learning models for power quality disturbance classification: A cross-platform analysis. Applied Sciences, 15(19), 10602. https://doi.org/10.3390/app151910602
Pillai, A. G., Biradar, V., Mohanty, S. C., Jana, A. K., Verma, A., & Gupta, R. (2024). Power quality issues in power system & load voltage compensation for boosting performance. 2024 World Conference on Communication and Computing (WCONF), 1–7. https://doi.org/10.1109/wconf61366.2024.10692269
Ponukumati, B. K., Sinha, P., Maharana, M., Kumar, A., & Karthik, A. (2022). An intelligent fault detection and classification scheme for distribution lines using machine learning. Engineering, Technology & Applied Science Research, 12(4), 8972–8977. https://doi.org/10.48084/etasr.5107
Rafi, M. A. I., Sohan, M. R., Nadid, M. H., Rafa, T. S., & Jawad, A. (2024). Enhancing power transmission line fault detection with a hybrid ANN-SVM machine learning model: A comparative study. 2024 International Conference on Advances in Computing, Communication and Embedded Systems (ICACCESS), 1–6. https://doi.org/10.1109/icaccess61735.2024.10499518
Sarmiento, J. L. P., Delfino, J. C. D. V., & Arboleda, E. R. (2024). Machine learning advances in transmission line fault detection: A literature review. International Journal of Science and Research Archive, 12(1), 2880–2887. https://doi.org/10.30574/ijsra.2024.12.1.1150
Singla, M., Chauhan, R., Gill, K. S., & Kapruwan, A. (2024). Usage of a support vector machine learning classifier to identify and sort electrical faults. 2024 International Conference on Optimization Techniques (OTCON), 1–5. https://doi.org/10.1109/otcon60325.2024.10688000
Soundharya, B., Das, S., & Vijayapriya, R. (2025). Classification of power quality disturbances in EV application and classifier accuracy analysis. 2025 Innovations in Power and Advanced Computing Technologies (i-PACT), 1–8. https://doi.org/10.1109/i-pact65952.2025.11308024
Sridevi, S., Pidatala, R., & Janaki, N. (2023). Detection of intelligent machine fault using deep learning classification. International Journal of Advanced Trends in Engineering and Management, 2(12). https://doi.org/10.59544/rpwh8660/ijatemv02i12p4
Tshodi, M. E., Kasoro, N., Keredjim, F., Nkongolo, Al. N., Matondo, J.-J. K., Balowe, P. M., & Kitoko, L. (2024). Application of machine learning in fault detection and classification in power transmission lines. Journal of Innovation Information Technology and Application, 6(2), 118–129. https://doi.org/10.35970/jinita.v6i2.2424
Uzel, H., Özüpak, Y., Alpsalaz, F., & Aslan, E. (2025). Optimized ANN–RF hybrid model with optuna for fault detection and classification in power transmission systems. Dental Science Reports, 16. https://doi.org/10.1038/s41598-025-31008-y
Xin, M., Wang, Y., Zhang, R., Zhang, J., & Li, J. (2025). Improving electrical fault detection: A two-stage prediction hybrid model aided by feature engineering. Journal of Physics: Conference Series, 3079(1), 12018. https://doi.org/10.1088/1742-6596/3079/1/012018
Yasin, V., Mardiyati, S., Junaedi, I., Hartawan, R., Immasari, I. R., & Siagian, R. C. (2026). Leakage-aware fault detection in three-phase power systems using an artificial neural network and scenario-based data splitting. Jurnal Teknik Elektro, 18(1), 19–33. https://doi.org/10.15294/jte.v18i1.40675
Yu, J., Yu, Z., & Wen-zhen, Y. E. (2024). Enhanced recognition of power quality disturbances through an augmented S-transform and XGBoost algorithm. 2024 International Conference on Electrical, Power and Energy Technologies (ICEPET), 1052–1056. https://doi.org/10.1109/icepet61938.2024.10626274
Zhou, K., Fang, L., Zhang, J., & Wang, Y. (2024). Classification and prediction of faults in power grids using machine learning algorithms. 2024 International Conference on Electronics, Computing and Information Engineering (ECIE), 273–277. https://doi.org/10.1109/ecie61885.2024.10626809
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Sri Mardiyati, Pandhu Pramarta
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
1. Copyright Retention and Open Access License
Authors retain copyright of their work and grant the journal non-exclusive right of first publication under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
This license allows unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
2. Rights Granted Under CC BY 4.0
Under this license, readers are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, including commercial use
- No additional restrictions — the licensor cannot revoke these freedoms as long as license terms are followed
3. Attribution Requirements
All uses must include:
- Proper citation of the original work
- Link to the Creative Commons license
- Indication if changes were made to the original work
- No suggestion that the licensor endorses the user or their use
4. Additional Distribution Rights
Authors may:
- Deposit the published version in institutional repositories
- Share through academic social networks
- Include in books, monographs, or other publications
- Post on personal or institutional websites
Requirement: All additional distributions must maintain the CC BY 4.0 license and proper attribution.
5. Self-Archiving and Pre-Print Sharing
Authors are encouraged to:
- Share pre-prints and post-prints online
- Deposit in subject-specific repositories (e.g., arXiv, bioRxiv)
- Engage in scholarly communication throughout the publication process
6. Open Access Commitment
This journal provides immediate open access to all content, supporting the global exchange of knowledge without financial, legal, or technical barriers.
