Abstract

In this study, a method for the detection of high impedance faults (HIF) in distribution systems is developed. The method uses three-phase current measurements from a 900 meter long low voltage line. For feature extraction, the current signals are processed using the Discrete Wavelet Transform (DWT) method using basic features including root mean square (RMS), mean, standard deviation, maximum value, energy and entropy. Artificial Neural Network (ANN) and Support Vector Machine (SVM) classifier models are used for fault detection. An accuracy of over 99% was achieved with the DWT+ANN approach. Approximately 98% accuracy was achieved with the DWT+SVM approach. It is demonstrated that DWT-based feature extraction combined with machine learning classifiers achieves successful results for HIF detection in low voltage networks.

References

[1] Chen, J., Phung, T., Blackburn, T., Ambikairajah, E., & Zhang, D. (2016). Detection of high impedance faults using current transformers for sensing and identification based on features extracted using wavelet transform. IET Generation, Transmission and Distribution, 10(12), 2990–2998. https://doi.org/10.1049/iet-gtd.2016.0021

[2] Lavanya, S., Prabakaran, S., & Kumar, N. A. (2022). Behavioral dynamics of high impedance fault under different line parameters. energy, 9, 12.

[3] Wang, S., & Dehghanian, P. (2020). On the Use of Artificial Intelligence for High Impedance Fault Detection and Electrical Safety. IEEE Transactions on Industry Applications, 56(6), 7208–7216. https://doi.org/10.1109/TIA.2020.3017698

[4] Mahanty, R., & Gupta, P. (2004). Voltage stability analysis in unbalanced power systems by optimal power flow. IEE Proceedings-Generation, Transmission and …, 151(3), 201–212. https://doi.org/10.1049/ip-gtd

[5] Güllüdereli, M. (2007). Enerji iletim sistemlerinde arıza analizinin otomasyonel çözümleri. Sakarya Üniversitesi.

[6] Mondal, S., & Pradhan, R. (2024, November). Fault Classification for High Impedance Faults Using Back Propagation Based Artificial Neural Network Technique. In 2024 International Conference on Sustainable Power & Energy (ICSPE) (pp. 1-6). IEEE

[7] Attar, M. S., & Miveh, M. R. (2025). High‐Impedance Fault Detection in Distribution Networks Based on Support Vector Machine and Wavelet Transform Approach (Case Study: Markazi Province of Iran). Energy Science & Engineering, 13(3), 1171-1183.

[8] Cano, A., Arévalo, P., Benavides, D., & Jurado, F. (2024). Integrating discrete wavelet transform with neural networks and machine learning for fault detection in microgrids. International Journal of Electrical Power & Energy Systems, 155, 109616.

[9] Mahzan, N. N., Othman, M. L., Wahab, N. I. A., Veerasamy, V., Salim, N. A., Abidin, A. A. Z., & Islam, S. Z. (2025). Performance Analysis of Intelligent Classifiers for High Impedance Fault Detection in a PV-Integrated IEEE-13 Bus System Analyse des performances des classificateurs intelligents pour la détection des défauts à haute impédance dans un système de bus IEEE-13 intégré au système PV. IEEE Canadian Journal of Electrical and Computer Engineering.

[10] Guttimari, T. Y. (2024, August). K-Nearest Neighbor Based High Impedance Fault Detection for Radial Feeder. In 2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems (IACIS) (pp. 1-8). IEEE.

[11] Farkhani, J. S., Çelik, Ö., Ma, K., Bak, C. L., & Chen, Z. (2024). Fault Detection, Classification, and Location Based on Empirical Wavelet Transform-Teager Energy Operator and ANN for Hybrid Transmission Lines in VSC-HVDC Systems. Journal of Modern Power Systems and Clean Energy.

[12] Nayak, P., Das, S. R., Mallick, R. K., Mishra, S., Althobaiti, A., Mohammad, A., & Aymen, F. (2024). 2D-convolutional neural network based fault detection and classification of transmission lines using scalogram images. Heliyon, 10(19).

[13] Sakovich, N., Aksenov, D., Pleshakova, E., & Gataullin, S. (2025). Wavelet-Based Optimization and Numerical Computing for Fault Detection Method—Signal Fault Localization and Classification Algorithm. Algorithms, 18(4), 217.

[14] Kurmaiah, A., & Vaithilingam, C. (2025). Optimization of Fault Identification and Location Using Adaptive Neuro-Fuzzy Inference System and Support Vector Machine for an AC Microgrid. IEEE Access.

[15] Kumar, V. R., & Jeyanthy, P. A. (2025). Fault Classification and Detection in Transmission Lines by Hybrid Algorithm Associated Support Vector Machine. Transactions on Emerging Telecommunications Technologies, 36(3), e70034.

[16] Villarreal, R., Chamorro-Solano, S., Vega-Sampayo, Y., Espejo, C. A., Cantillo, S., Gaviria, L., ... & Montoya, C. (2025). A New Approach to Electrical Fault Detection in Urban Structures Using Dynamic Programming and Optimized Support Vector Machines. Sensors, 25(7), 2215.

[17] Samal, S., Samantaray, S. R., & Sharma, N. K. (2025). A New Differential Index-Based Fault Detection Scheme for Microgrids. IEEE Transactions on Industry Applications.

[18] Shalby, E. M., Abdelaziz, A. Y., Ahmed, E. S., & Abd-Elhamed Rashad, B. (2025). A comprehensive guide to selecting suitable wavelet decomposition level and functions in discrete wavelet transform for fault detection in distribution networks. Scientific Reports, 15(1), 1160.

[19] Janiabadi, A. A., & Hasheminejad, S. (2025). A new algorithm for the identification of high impedance faults in distribution systems utilizing S transform. Ain Shams Engineering Journal, 16(4), 103334.