APPLICATION OF MACHINE LEARNING MODELS FOR FAULT CLASSIFICATION AND LOCATION IN POWER TRANSMISSION LINES

Nguyễn Quốc Minh; Trần Văn Tiến; Bùi Thị Phương Thảo; Nguyễn Minh Hoàng; Phạm Thị Kim Hương

doi:10.34238/tnu-jst.11857

APPLICATION OF MACHINE LEARNING MODELS FOR FAULT CLASSIFICATION AND LOCATION IN POWER TRANSMISSION LINES

About this article

Received: 10/01/25 Revised: 27/02/25 Published: 27/02/25

Authors

1. Nguyen Quoc Minh , School of Electrical and Electronic Engineering - Hanoi University of Science and Technology
2. Tran Van Tien, School of Electrical and Electronic Engineering - Hanoi University of Science and Technology
3. Bui Thi Phuong Thao, School of Electrical and Electronic Engineering - Hanoi University of Science and Technology
4. Nguyen Minh Hoang, School of Electrical and Electronic Engineering - Hanoi University of Science and Technology
5. Pham Thi Kim Huong, School of Electrical and Electronic Engineering - Hanoi University of Science and Technology

Abstract

This paper presents a method for fault classification and localization on transmission lines using machine learning models. The training data for these models were derived from simulations of the IEEE 9-bus power system in MATLAB Simulink software, with faults generated under various conditions. The study employed machine learning models such as Decision Tree, Logistic Regression, XGBoost and Artificial Neural Networks for fault classification, and recurrent neural network such as Convolutional Neural Network, Long Short-Term Memory, Gated Recurrent Unit, as well as hybrid models like CNN-LSTM and CNN-GRU for fault localization. By utilizing these machine learning models, the research focused on evaluating the accuracy of fault classification and localization on transmission lines with the goal of enhancing the stability and reliability of the power system while reducing fault recovery time. The results demonstrate the effectiveness of the machine learning models, with ANN achieving a fault classification accuracy of up to 99.974%, while CNN-GRU can localize faults with a mean absolute error of less than 0.029 km.

Keywords

Fault analysis; Fault localization; Fault classification; Power transmission line; Machine learning

Full Text:

PDF (Tiếng Việt)

References

[1] N. D. Tleis, “1 - Introduction to power system faults,” in Power Systems Modelling and Fault Analysis, in Newnes Power Engineering Series. Oxford: Newnes, 2008, pp. 1-27, doi: 10.1016/B978-075068074-5.50005-9.

[2] M. S. Uddin et al., “On the protection of power system: Transmission line fault analysis based on an optimal machine learning approach,” Energy Rep., vol. 8, pp. 10168–10182, Nov. 2022, doi: 10.1016/j.egyr.2022.07.163.

[3] M. Bhatnagar and A. Yadav, “Fault Detection and Classification in Transmission Line Using Fuzzy Inference System,” in 2020 5th IEEE International Conference on Recent Advances and Innovations in Engineering (ICRAIE), Dec. 2020, pp. 1-6, doi: 10.1109/ICRAIE51050.2020.9358386.

[4] L. Hulka, U. Klapper, M. Putter, and W. Wurzer, “Measurement of line impedance and mutual coupling of parallel lines to improve the protection system,” in CIRED 2009 - 20th International Conference and Exhibition on Electricity Distribution - Part 1, Jun. 2009, pp. 1-4, doi: 10.1049/cp.2009.0800.

[5] T.-C. Lin, B. Simachew, and M.-Y. Cho, “A Novel Single-Ended Fault Location Algorithm for Digital Distance Relays Based on A New FPGA Design,” in 2023 IEEE Power & Energy Society General Meeting (PESGM), Jul. 2023, pp. 1–5, doi: 10.1109/PESGM52003.2023.10253255.

[6] W. Chen, D. Wang, D. Cheng, F. Qiao, X. Liu, and M. Hou, “Novel travelling wave fault location principle based on frequency modification algorithm,” Int. J. Electr. Power Energy Syst., vol. 141, Oct. 2022, Art. no. 108155, doi: 10.1016/j.ijepes.2022.108155.

[7] I. A. França, C. W. Vieira, D. C. Ramos, L. H. Sathler, and E. G. Carrano, “A machine learning-based approach for comprehensive fault diagnosis in transmission lines,” Comput. Electr. Eng., vol. 101, Jul. 2022, Art. no. 108107, doi: 10.1016/j.compeleceng.2022.108107.

[8] S. Banerjee, P. S. Bhowmik, and A. K. Bohre, “Detection and Location of Fault in Microgrid using Discrete Wavelet Transform based Technique,” in 2022 IEEE 6th International Conference on Condition Assessment Techniques in Electrical Systems (CATCON), Dec. 2022, pp. 417-421, doi: 10.1109/CATCON56237.2022.10077697.

[9] S. Vieira, W. H. Lopez Pinaya, and A. Mechelli, “Chapter 1 - Introduction to machine learning,” in Machine Learning, A. Mechelli and S. Vieira, Eds., Academic Press, 2020, pp. 1-20, doi: 10.1016/B978-0-12-815739-8.00001-8.

[10] A. Géron, Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems. O’Reilly Media, Incorporated, 2019.

[11] W. H. L. Pinaya, S. Vieira, R. Garcia-Dias, and A. Mechelli, “Chapter 10 - Convolutional neural networks,” in Machine Learning, A. Mechelli and S. Vieira, Eds., Academic Press, 2020, pp. 173-191, doi: 10.1016/B978-0-12-815739-8.00010-9.

[12] C. H. Pham, Q. M. Nguyen, D. T. Nguyen, and T. Q. A. Tao, “Short-Term Electricity Load Forecasting Based on Temporal Fusion Transformer Model,” IEEE Access, vol. 10, pp. 106296-106304, 2022, doi: 10.1109/ACCESS.2022.3211941.

[13] K. Cho et al., “Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation,” in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), A. Moschitti, B. Pang, and W. Daelemans, Eds., Doha, Qatar: Association for Computational Linguistics, Oct. 2014, pp. 1724-1734, doi: 10.3115/v1/D14-1179.

[14] M. Abumohsen, A. Y. Owda, M. Owda, and A. Abumihsan, “Hybrid machine learning model combining of CNN-LSTM-RF for time series forecasting of Solar Power Generation,” E-Prime - Adv. Electr. Eng. Electron. Energy, vol. 9, Sep. 2024, Art. no. 100636, doi: 10.1016/j.prime.2024.100636.

[15] M.-C. Chiu, H.-W. Hsu, K.-S. Chen, and C.-Y. Wen, “A hybrid CNN-GRU based probabilistic model for load forecasting from individual household to commercial building,” Energy Rep., vol. 9, pp. 94-105, Oct. 2023, doi: 10.1016/j.egyr.2023.05.090.

DOI: https://doi.org/10.34238/tnu-jst.11857

Refbacks

There are currently no refbacks.



Remember me