Detection and Classification of High-Impedance Faults in 25 kV Distribution Networks Using a Hybrid DWT-ANN Approach

Abstract ⁠High-Impedance Faults (HIFs) pose a critical safety and operational challenge in medium-voltage distribution networks because their low fault current magnitudes often fail to trigger conventional overcurrent protection relays. This paper presents an intelligent hybrid protection scheme combining Discrete Wavelet Transform (DWT) and Artificial Neural Networks (ANN) for the accurate detection and classification of HIFs in a 25 kV distribution system modeled in MATLAB/Simulink. The proposed methodology extracts the Zero-Sequence Current (I0) at the substation bus and decomposes it using the Daubechies-4 (db4) mother wavelet to isolate high-frequency transient components within the first-level detail coefficients (D1). Three statistical features—Wavelet Energy, Standard Deviation (STD), and Peak Amplitude—are computed across normal operating conditions and varying fault resistances (50 Ohm, 100 Ohm, and 200 Ohm). These features are utilized to train a Pattern Recognition ANN classifier. Simulation results demonstrate a sharp contrast between normal states and HIF events, enabling the proposed DWT-ANN model to achieve a 100% classification accuracy with

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-15
DOI
https://doi.org/10.5281/zenodo.24253741
Primary Topic
Power Systems Fault Detection
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Detection and Classification of High-Impedance Faults in 25 kV Distribution Networks Using a Hybrid DWT-ANN Approach

Sajad Ali Essa Al-Bahadli
Zenodo (CERN European Organization for Nuclear Research)
Power Systems Fault Detection
preprint

Detection and Classification of High-Impedance Faults in 25 kV Distribution Networks Using a Hybrid DWT-ANN Approach

Sajad Ali Essa Al-Bahadli
preprint en

Abstract

Abstract ⁠High-Impedance Faults (HIFs) pose a critical safety and operational challenge in medium-voltage distribution networks because their low fault current magnitudes often fail to trigger conventional overcurrent protection relays. This paper presents an intelligent hybrid protection scheme combining Discrete Wavelet Transform (DWT) and Artificial Neural Networks (ANN) for the accurate detection and classification of HIFs in a 25 kV distribution system modeled in MATLAB/Simulink. The proposed methodology extracts the Zero-Sequence Current (I0) at the substation bus and decomposes it using the Daubechies-4 (db4) mother wavelet to isolate high-frequency transient components within the first-level detail coefficients (D1). Three statistical features—Wavelet Energy, Standard Deviation (STD), and Peak Amplitude—are computed across normal operating conditions and varying fault resistances (50 Ohm, 100 Ohm, and 200 Ohm). These features are utilized to train a Pattern Recognition ANN classifier. Simulation results demonstrate a sharp contrast between normal states and HIF events, enabling the proposed DWT-ANN model to achieve a 100% classification accuracy with

Zenodo (CERN European Organization for Nuclear Research)
Power Systems Fault Detection
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon