Early Anomaly-Onset Detection based on Wigner--Ville Distribution Slice Spectra: A Transmission-Grid Test Case

2026-06-14

AI Summary

This study addresses the challenge of online early detection of abnormal voltage waveform onsets in high-voltage transmission networks by proposing a real-time method that eliminates the need for manual selection of fault-related frequency features. The approach constructs a 128-dimensional sequential representation based on slices of the Wigner–Ville distribution (WVDS), preserving its bilinear midpoint interaction structure to exploit cross-term information and enhance representational selectivity. High-precision discrimination is achieved through a combination of baseline-normalized deviation (BND) scoring and a three-window persistence rule. Experimental results demonstrate that the WVDS-BND method reduces the record-level false alarm rate prior to anomaly onset to 0.69%, significantly outperforming existing techniques and achieving optimal performance in false-alarm-cost-sensitive scenarios.

Abstract

Operational disturbance monitoring in power networks requires decisions to be made from waveform windows as they arrive, rather than from completed records after the event. This study evaluates full-vector Wigner--Ville Distribution Slice (WVDS) spectra for sequential anomaly-onset detection in high-voltage grid-voltage waveforms. The approach keeps the bilinear midpoint interaction structure of the Wigner--Ville distribution and represents each 128-sample voltage window by a 128-dimensional slice spectrum, avoiding manually selected fault-frequency markers. WVDS is used with a baseline-normalized deviation (BND) score and is compared against the BND of Fast Fourier Transform (FFT-BND), raw-window autoencoders, FFT autoencoders, and WVDS autoencoders under the same thresholding and three-window persistence rule. A synthetic autoencoder--clustering teacher is used to select RTE fault records that start from an initially normal region and then transition to anomalous behavior. On the filtered test set, FFT-BND achieves the highest sensitivity, whereas WVDS-BND provides the lowest false-alarm operating point, reducing record-level pre-onset false alarms to 0.69%. The autoencoder comparison follows the same selectivity pattern: WVDS reconstruction decreases false alarms relative to FFT reconstruction but misses more examples. The results indicate that preserved WVD cross-term information can form a selective representation for online grid-waveform anomaly monitoring when false alarms are costly.

Problem

• anomaly-onset detection
• power grid monitoring
• Wigner-Ville distribution
• false alarm reduction
• real-time waveform analysis

Innovation

• Wigner–Ville Distribution Slice
• anomaly-onset detection
• baseline-normalized deviation
• false-alarm reduction
• online grid monitoring