Work

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

Year: 2026
Type: preprint
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
Language: English
Open Access status: green
OpenAlex ID: W7233549554
Cites:
Cited by:
Related to: