Spectrogram-Based Joint Detection, Localization, and Classification of Events in Continuously Recorded IBR Waveforms
Continuously recorded high-resolution power system waveforms capture fast dynamics and transient events. However, extracting actionable insights from these large volumes of data requires automated event detection, temporal localization, and classification. This paper proposes a spectrogram-based framework that jointly detects, localizes, and classifies events in voltage and current waveforms at the terminal of an inverter-based resource (IBR). We recast this problem as a temporal object detection problem using time-frequency representations that explicitly reveal transient and harmonic signatures. The short-time Fourier transform is applied to each waveform channel, and the resulting log-spectrograms are stacked into a multi-channel tensor and processed by a U-Net architecture to jointly estimate event occurrence, temporal boundaries, and event type. A network of the same depth and width operating on raw waveform samples serves as a baseline. Experiments on synthetic single-phase disturbances and three-phase faults in IBR terminal recordings demonstrate that the proposed approach substantially improves event detection and temporal localization compared with the raw-waveform baseline, particularly at finer time-frequency resolutions, while also improving classification accuracy.