Analytics of Waveform Distortion Variations in Railway Pantograph Measurements by Deep Learning

Waveform distortion in general represents a widespread problem in electrified transports due to interference, service disruption, increased losses, and aging of components. Given the multitude of moving sources and the extremely variable operating conditions, short-time records must be considered for analysis, and this increases in turn its complexity, from which the need for effective automated processing, as offered by a deep learning (DL) approach. This article proposes an application of unsupervised DL to measurements of railway pantograph quantities to identify waveform distortion patterns. Data consist of pantograph current from a Swiss 15-kV 16.7-Hz railway system. Three DL input types are considered: waveforms, harmonic spectra, and supraharmonic spectra. The applied DL method applied is the deep autoencoder (DAE) followed by feature clustering, using techniques to define a suitable number of clusters. Short-term distortion is evaluated over sub-10-min intervals of harmonic and supraharmonic spectra down to subsecond intervals. Results are explained among others by connecting the distribution of the clusters (determined by the self-supervised method) to the dynamic operating conditions of the rolling stock. The resulting DAE performance is superior in terms of accuracy and comprehensiveness of spectral components compared to a more traditional principal component analysis (PCA) that was chosen as a reference for comparison.