An Intelligent Framework for Multiscale Detection of Power System Events Using Hilbert–Huang Decomposition and Neural Classifiers

This article proposes a multiscale classification framework for detecting voltage disturbances in electrical distribution systems using artificial neural networks (ANNs) combined with the Hilbert–Huang transform (HHT). The framework targets four core power quality (PQ) events defined in the IEEE 1159-2019 standard: normal operation and voltage sag, swell, and interruption. Unlike traditional methods that operate on a fixed disturbance duration, our approach incorporates multiple time scales (0.2 s, 0.4 s, and 0.8 s) to improve detection robustness across varied event lengths, a critical factor in real-world scenarios where disturbance durations are unpredictable. Features are extracted using empirical mode decomposition (EMD) and Hilbert spectral analysis, enabling accurate representation of the signals’ non-stationary and nonlinear characteristics. The ANN is trained using statistical descriptors derived from the first two intrinsic mode functions (IMFs), capturing both amplitude and frequency content. The method was validated in MATLAB on the IEEE 33-bus radial distribution test system using simulated disturbances. The proposed model achieved a classification accuracy of 94.09% and demonstrated consistent performance across all time windows, supporting its suitability for real-time monitoring in smart distribution networks. This study contributes a scalable and adaptable solution for automated PQ event classification under variable conditions.