Time Series Anomaly Detection in Power Electronics Signals with Recurrent and Convlstm Autoencoders

Abstract

The anomalies in the high voltage converter modulator (HVCM) remain a major down time for the spallation neutron source facility, that delivers the most intense neutron beam in the world for scientific materials research. In this work, we propose neural network architectures based on Recurrent AutoEncoders (RAE) to detect anomalies ahead of time in the power signals coming from the HVCM. Bi-directional gated recurrent unit, bi-directional long-short term memory (LSTM), and convolutional LSTM (ConvLSTM) are developed, trained, and tested using real experimental signals from the HVCM module. The results show a good performance of the proposed RAE models, achieving precision up to 91\%, recall up to 88\%, false omission rate as low as 20\% (i.e. 80\% of the anomalies were detected), and area under the ROC curve up to 0.9. The three RAE models provide very comparable performance, while each model seems to slightly excel over the other two depending on the selected false positive threshold. The RAE models are benchmarked against other anomaly detection methods, including isolation forests, support vector machine, local outlier factor, and feedforward autoencoders; showing a better performance. The results of this study demonstrate the promising potential of RAE in anomaly detection for real-world power systems, and for increasing the reliability of the HVCM modules for the spallation neutron source.

Keywords: anomaly detection, Autoencoders, ConvLSTM, High Voltage Converter Modulator, Spallation Neutron Source