Electric railway systems (ERS) are characterized by several particularities regarding the return current circuits, moving loads, multiple sources of waveform distortion, and extensive deployment of static converters from various manufacturers, topologies, and solutions. This work presents a methodology for application of load monitoring to classify rolling stock (RS) waveform distortion signatures. The proposed methodology combines the benefits and advantages of unsupervised deep learning and reconstruction error performance classification for performing non-intrusive load monitoring (NILM) in ERS. It consists of adapting autoencoder-based novelty detection for load classification problems. The method is applied to pantograph measurements from four rolling stock items using two types of data input (harmonic spectra up to kHz and VI diagram images), which are compared in binary classifications of the same kind of railway electrification. The methodology shows suitable classification performance with high accuracy, scoring an average of 98.81 % for spectrum input and 97.77 % for VI diagram input. It has also been validated with a NILM dataset (LIT) for multi-class applications showing 99.13 % for spectrum input and 94.28 % for VI diagram input. The proposed method has suitable computational times and scalability, allowing application to a wide range of NILM and classification problems using distortion signatures.

Assessing harmonic distortion measurements in the electric railway power systems (ERPS) requires evaluating the time-varying behavior, interactions, and performance in different time scales. This paper aims to map and assess harmonic voltage levels in 13 traction converter stations for the Swedish railway power supply system, with findings that have direct practical implications. For that, measurements from the public and railway grid sides for 69 weeks are analyzed. Statistical values are explored for the harmonic voltage spectra and total harmonic distortion (THD) variation. The public grid side measurements are investigated using 95th percentile weekly values, and performance is evaluated by comparing the recommended planning levels of IEC 61,000–3–6. The intraweek variation complements the information about the time-varying behavior of the THD. The 95th percentile, minimum daily values, and intraday variation are explored to understand the time-based behavior since there are no reference limits from standards for comparison, looking to the railway grid side. Extended analysis is placed on the railway grid side to highlight some aspects of measurement time-aggregation based on 10-min values, and time-series trend analysis is used to confirm traffic planning impact. Discussion and findings regarding railway operation, the technology deployed at the traction converter station, time-varying behavior, traffic planning impact, measurement time-aggregation, and spectra patterns were presented.

This work addresses the imbalance in the literature regarding the modeling of waveform distortion resonance and propagation in low-frequency railway electrification systems, focusing on the Swedish Electric Railway Power Supply (ERPS). A framework is proposed for modeling synchronous components of waveform distortion up to 25 kHz, incorporating local interactions between traction converter stations (TCSs) and rolling stock. The nodal admittance matrix is developed for an autotransformer-fed circuit with three railway sections and four TCSs. Rolling stock is represented through a measurement-based Norton model capturing high-order components and probabilistic harmonic emissions. Monte Carlo (MC) simulations assess resonance and propagation uncertainties under variable operating conditions. Results reveal key influences of railway section lengths, filters, and stochastic emission models on impedance characteristics, offering ERPS tools for future assessment.

This work proposes an application of unsupervised deep learning (DL) on 2-D images containing VI diagrams of measured railway pantograph quantities to find patterns in operating conditions (OCs) and waveform distortion. Measurement data consist of pantograph voltage and current measurements from a Swiss 15 kV 16.7 Hz commercial locomotive and a French 2x25 kV 50 Hz test-dedicated locomotive, containing more than 4000 records of 5-cycle snippets for each system. The variational autoencoder (VAE), followed by feature clustering, finds patterns in the input data. Each cluster captures patterns from the VI diagrams, which contain information from current and voltage waveshapes and sub-second variations. The time-domain admittance allows inference about the rolling stock (RS) operation and the waveform distortion spectra, including harmonics and supraharmonics characteristics from both RS and traction supply. The VAE successfully performs data embedding using only 16 channels in the latent space. The effectiveness of the method is quantified by means of the mean square reconstruction error (never larger than 1.5% and equal to 0.31% and 0.33% on average for the Swiss and French case, respectively). The t-SNE visualization confirms that overlapping of clusters is negligible, with a percentage of “misplaced” cluster points of 2.18% and 2.50%, again for the Swiss and French case, respectively. The computation time for the VAE prediction could be brought to some tens of ms representing a performance reference for future implementations. The proposed VI diagram assessment covers emissions for different OCs, rapid changes in power supply conditions, and background distortion caused by other trains on the same line, including line and impedance changes due to the moving load. In this perspective physical justification is found by domain knowledge integration for the identified clusters. A concluding discussion regarding advantages, limitations, and potential improvements or diversification is also included.

Waveform distortion in general represent a widespread problem in electrified transports due to interference, service disruption, increased losses and ageing 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 paper proposes an application of unsupervised DL to measurements of railway pantograph quantities to identify waveform distortion patterns. Data consists 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 sub-second intervals. Results are explained among others by connecting the distribution of the clusters (determined by self-supervised method) to the dynamic operating conditions of the rolling stock. Resulting DAE performance are superior in terms of accuracy and comprehensiveness of spectral components compared to a more traditional principal component analysis (PCA) that was chosen as reference for comparison.

This paper addresses the accelerated aging of medium-voltage (MV) cable terminations with resistive stress-grading due to supraharmonics. The paper introduces a simple and quick way to relate the risk of cable termination failure to the characteristics of supraharmonic distortion in the system. The motivation is to give practical recommendations and guidelines to evaluate the risk of failure of cable terminations under the presence of supraharmonics in MV networks. The underlying model relates the heating in the cable termination linearly with the frequency of the voltage applied and proportionally with the square of the magnitude of the voltage. The indicator can be used to decide whether given levels and frequencies of supraharmonics in the MV network represent a risk to cable terminations. The parameters of the cable termination design are not needed for that decision. However, the decision criterion is based on one sample data (Eagle Pass) and more field information is crucial to improve the approach.