Classification of load waveform distortion signature based on novelty detection for electric railway systems

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 application of load monitoring to classify rolling stocks (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 diagrams 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 been also 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. • A load classification method is proposed based on novelty detection applicable to distortion signatures of connected loads. • A deep autoencoder (DAE) for each class learns own features and confronts with the other classes DAE, having optimized recall and precision performance during the training phase. • Accuracy is very high (often 99 %) for both the target problem (rolling stock in electrified railways) and for a reference benchmark dataset with home appliances.