Design and simulation of an AI-based DWT-ANN model for high impedance fault detection and classification in nigeria distribution

Main Article Content

Yusuf Mohammed
Babalola Wasiu Lasun
Muhammad Usman Iliyasu

Abstract

High Impedance Faults (HIFs) challenge conventional protection because their low, nonlinear currents stay below overcurrent relay thresholds, causing fire hazards, equipment damage, and reliability risks. This study presents an artificial intelligence framework for HIF detection and classification in a Nigerian distribution network, integrating discrete wavelet transform feature extraction with an artificial neural network classifier. A 35-bus, 11 kV Kano Electricity Distribution Company system was modeled in MATLAB/Simulink under three load levels (100%, 70%, 45%), eight fault resistances (100–1000 Ω), eight inception angles (0°–180°), and five fault types: no fault, single-, double-, and three-phase HIF, and three-phase short circuit. Transient currents were decomposed using the Daubechies-4 (DB4) wavelet at level 4, chosen from eight wavelet families. Twelve features, including energy coefficients, statistical measures, and signal energy ratios, trained a 12-64-32-16-5 ANN with dropout and Adam optimization. It achieved 81.60% accuracy, outperforming K-Nearest Neighbors (77.87%), Naïve Bayes (61.07%), Support Vector Machine (79.23%), XGBoost (79.87%), and Long Short-Term Memory (80.12%). Precision (81.49%), recall (81.89%), F1-score (81.43%), ROC-AUC above 0.95 for all classes, and computational efficiency confirm robustness. DWT-ANN offers an effective, reliable HIF detection solution for networks modeled with actual utility parameters, sensitive to nonlinear arc signatures and resilient to noise and variability.

Article Details

How to Cite
Design and simulation of an AI-based DWT-ANN model for high impedance fault detection and classification in nigeria distribution. (2026). Journal of Emerging Innovations in Engineering , 2(03), 110-134. https://doi.org/10.65664/jeie.v2i03.21
Section
Articles
Author Biographies

Yusuf Mohammed, Department of Electrical & Electronics Engineering Technology, Federal Polytechnic, Bali, Nigeria

Lecturer II

 

Electrical and Electronics Engineering Technology.

Babalola Wasiu Lasun, Department of Technical Education, Federal College of Education, Gidan Madi, Sokoto State, Nigeria

Electrical and Electronics Engineering Technology 

Muhammad Usman Iliyasu, Department of Electrical & Electronics Engineering Technology, Federal Polytechnic, Bali, Nigeria

Department of Electrical and Electronics Engineering Technology.

 

Lecturer II

How to Cite

Design and simulation of an AI-based DWT-ANN model for high impedance fault detection and classification in nigeria distribution. (2026). Journal of Emerging Innovations in Engineering , 2(03), 110-134. https://doi.org/10.65664/jeie.v2i03.21

References

Abasi-obot, I. E., Kunya, A. B., Shehu, G. S., and Jibril, Y. (2023). High Impedance Fault Detection and Localization Using Fully-Connected Convolutional Neural Network: A Deep Learning Approach. Nigerian Journal of Technological Development, 20(4), 62-71.

Abasi-obot, I., Shehu, G., Kunya, A., and Jibril, Y. (2022). High impedance fault modelling and simulation of 33kV/11kV distribution network using MATLAB. In 2022 IEEE Nigeria 4th International Conference on Disruptive Technologies for Sustainable Development (NIGERCON), IEEE. (pp. 1-4).

Adoghe, A. U., Adeyemi-Kayode, T. M., Oguntosin, V., and Amahia, I. I. (2023). Performance evaluation of the prospects and challenges of effective power generation and distribution in Nigeria. Heliyon, 9(3).

Ahmadi, A., Aghajari, E., and Zangeneh, M. (2022). High-impedance fault detection in power distribution grid systems based on support vector machine approach. Electrical Engineering, 104(5), 3659-3672.

Aljohani, A., and Habiballah, I. (2020). High-impedance fault diagnosis: A review. Energies, 13(23), 6447.

Allawi, M. N., Hussain, A. N., Wali, M. K., and Augusto Pereira, D. (2024). High Impedance Fault Detection in Distribution Feeder Based on Spectrum Analysis and ANN with Non-Linear Load. Journal of Techniques, 6(2).

Asman, S. H., Ab Aziz, N. F., Ungku Amirulddin, U. A., and Ab Kadir, M. Z. A. (2021). Decision tree method for fault causes classification based on rms-dwt analysis in 275 kV transmission lines network. Applied Sciences, 11(9), 4031.

Ayamolowo, O. J., Buraimoh, E., Salau, A. O., and Dada, J. O. (2019). Nigeria Electricity Power Supply System: The Past, Present and the Future. 2019 IEEE PES/IAS PowerAfrica. doi:10.1109/powerafrica.2019.8928767

Attar, M. S., and 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.

Bhandia, R., de Jesus Chavez, J., Cvetković, M., and Palensky, P. (2020). High impedance fault detection using advanced distortion detection technique. IEEE Transactions on Power Delivery, 35(6), 2598-2611.

Cano, A., Ar´evalo, P., Benavides, D. and Jurado, F. (2024). Integrating discrete wavelet transform with neural networks and machine learning for fault detection in microgrids. International Journal of Electrical Power and Energy Systems. 155(109616):1-14

Cui, Q., and Weng, Y. (2019). Enhance high impedance fault detection and location accuracy via u-PMUs. IEEE Transactions on Smart Grid, 11(1), 797-809.

Dasco, A., Marguet, R., and Raison, B. (2015). Fault distance estimation in distribution network for high impedance faults. In 2015 IEEE Eindhoven PowerTech (pp. 1-6).

Dashtdar, M., Hussain, A., Al Garni, H. Z., Mas’ud, A. A., Haider, W., AboRas, K. M., and Kotb, H. (2023). Fault location in distribution network by solving the optimization problem based on power system status estimation using the PMU. Machines, 11(1), 109.

F. Fan, J. Xiong, M. Li, and G. Wang, "On interpretability of artificial neural networks: A survey," IEEE Transactions on Radiation and Plasma Medical Sciences, vol. 5, no. 6, 2021, pp. 741-760

Ferdowsi, F., Vahedi, H., and Edrington, C. S. (2017, February). High impedance fault detection utilizing real-time complexity measurement. In 2017 IEEE Texas Power and Energy Conference (TPEC) (pp. 1-5).

Ghaderi, A., Ginn III, H. L., and Mohammadpour, H. A. (2017). High impedance fault detection: A review. Electric power systems research, 143, 376-388.

Ghaderi, A., Mohammadpour, H. A., and Ginn, H. (2015). Active fault location in distribution network using time-frequency reflectometry. In 2015 IEEE Power and Energy Conference at Illinois (PECI) (pp. 1-7).

Gungor, V. C., Sahin, D., Kocak, T., Ergut, S., Buccella, C., Cecati, C., and Hancke, G. P. (2013). Smart grid technologies: Communication technologies and standards. IEEE Transactions on Industrial Informatics, 7(4), 529–539. https://doi.org/10.1109/TII.2011.2166794

Gururajapathy, S. S., Mokhlis, H., and Illias, H. A. (2017). Fault location and detection techniques in power distribution systems with distributed generation: A review. Renewable and sustainable energy reviews, 74, 949-958.

Hong, Y. Y., and Huang, W. S. (2015). Locating High‐Impedance Fault Section in Electric Power Systems Using Wavelet Transform, k‐Means, Genetic Algorithms, and Support Vector Machine. Mathematical Problems in Engineering, 2015(1), 823720.

Iurinic, L. U., Herrera-Orozco, A. R., Ferraz, R. G., and Bretas, A. S. (2015). Distribution systems high-impedance fault location: A parameter estimation approach. IEEE Transactions on Power Delivery, 31(4), 1806-1814.

Karimi, M., and Ghaffarzadeh, N. (2022). High impedance fault detection based on current harmonic analysis using Chirp Z transform. Energy Systems, 13(3), 813-833.

Kirtley, J. L. (2020). Electric power principles: sources, conversion, distribution and use. John Wiley and Sons.