Time series anomaly detection in power electronics signals with recurrent and ConvLSTM autoencoders

Radaideh, Majdi I.; Pappas, Chris; Walden, Jared; Lu, Dan; Vidyaratne, Lasitha; Britton, Thomas; Rajput, Kishansingh; Schram, Malachi; Cousineau, Sarah

doi:10.1016/j.dsp.2022.103704

Title: Time series anomaly detection in power electronics signals with recurrent and ConvLSTM autoencoders

Journal Article · Wed Aug 31 00:00:00 EDT 2022 · Digital Signal Processing

DOI:https://doi.org/10.1016/j.dsp.2022.103704· OSTI ID:1897003

^[1]; Pappas, Chris ^[1];

^[1];

^[1]; Vidyaratne, Lasitha ^[2]; Britton, Thomas ^[2];

^[2]; Schram, Malachi ^[2];

^[1]

Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Thomas Jefferson National Accelerator Facility (TJNAF), Newport News, VA (United States)

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, with LSTM showing slightly better performance than GRU and ConvLSTM. The RAE models are benchmarked against other anomaly detection methods, including isolation forest, support vector machine, local outlier factor, feedforward and convolutional autoencoders, and others; showing a better performance. Here, 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 in the spallation neutron source.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Sponsoring Organization:: USDOE Office of Science (SC), Basic Energy Sciences (BES). Scientific User Facilities Division

Grant/Contract Number:: AC05-00OR22725; SC0009915

OSTI ID:: 1897003

Journal Information:: Digital Signal Processing, Vol. 130; ISSN 1051-2004

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (21)

Temporal convolutional autoencoder for unsupervised anomaly detection in time series Thill, Markus; Konen, Wolfgang; Wang, Hao Applied Soft Computing, Vol. 112 https://doi.org/10.1016/j.asoc.2021.107751	journal	November 2021
Unsupervised anomaly detection with LSTM autoencoders using statistical data-filtering Maleki, Sepehr; Maleki, Sasan; Jennings, Nicholas R. Applied Soft Computing, Vol. 108 https://doi.org/10.1016/j.asoc.2021.107443	journal	September 2021
Bidirectional recurrent neural networks Schuster, M.; Paliwal, K. K. IEEE Transactions on Signal Processing, Vol. 45, Issue 11 https://doi.org/10.1109/78.650093	journal	January 1997
Neural-based time series forecasting of loss of coolant accidents in nuclear power plants Radaideh, Majdi I.; Pigg, Connor; Kozlowski, Tomasz Expert Systems with Applications, Vol. 160 https://doi.org/10.1016/j.eswa.2020.113699	journal	December 2020
Auto-encoder based dimensionality reduction Wang, Yasi; Yao, Hongxun; Zhao, Sicheng Neurocomputing, Vol. 184 https://doi.org/10.1016/j.neucom.2015.08.104	journal	April 2016
The Spallation Neutron Source in Oak Ridge: A powerful tool for materials research Mason, T. E.; Abernathy, D.; Anderson, I. Physica B: Condensed Matter, Vol. 385-386 https://doi.org/10.1016/j.physb.2006.05.281	journal	November 2006
Multivariate time series anomaly detection: A framework of Hidden Markov Models Li, Jinbo; Pedrycz, Witold; Jamal, Iqbal Applied Soft Computing, Vol. 60 https://doi.org/10.1016/j.asoc.2017.06.035	journal	November 2017
Detecting cyberattacks using anomaly detection in industrial control systems: A Federated Learning approach Huong, Truong Thu; Bac, Ta Phuong; Long, Dao Minh Computers in Industry, Vol. 132 https://doi.org/10.1016/j.compind.2021.103509	journal	November 2021
Neural Networks for Modeling and Control of Particle Accelerators Edelen, A. L.; Biedron, S. G.; Chase, B. E. IEEE Transactions on Nuclear Science, Vol. 63, Issue 2 https://doi.org/10.1109/TNS.2016.2543203	journal	April 2016
Analyzing nuclear reactor simulation data and uncertainty with the group method of data handling Radaideh, Majdi I.; Kozlowski, Tomasz Nuclear Engineering and Technology, Vol. 52, Issue 2 https://doi.org/10.1016/j.net.2019.07.023	journal	February 2020
Discriminative Autoencoder for Feature Extraction: Application to Character Recognition Gogna, Anupriya; Majumdar, Angshul Neural Processing Letters, Vol. 49, Issue 3 https://doi.org/10.1007/s11063-018-9894-5	journal	July 2018
Anomaly Detection Based on Convolutional Recurrent Autoencoder for IoT Time Series Yin, Chunyong; Zhang, Sun; Wang, Jin IEEE Transactions on Systems, Man, and Cybernetics: Systems, Vol. 52, Issue 1 https://doi.org/10.1109/TSMC.2020.2968516	journal	January 2022
Analytical investigation of autoencoder-based methods for unsupervised anomaly detection in building energy data Fan, Cheng; Xiao, Fu; Zhao, Yang Applied Energy, Vol. 211 https://doi.org/10.1016/j.apenergy.2017.12.005	journal	February 2018
Long Short-Term Memory Hochreiter, Sepp; Schmidhuber, Jürgen Neural Computation, Vol. 9, Issue 8 https://doi.org/10.1162/neco.1997.9.8.1735	journal	November 1997
Digital Twin-driven online anomaly detection for an automation system based on edge intelligence Huang, Huiyue; Yang, Lei; Wang, Yuanbin Journal of Manufacturing Systems, Vol. 59 https://doi.org/10.1016/j.jmsy.2021.02.010	journal	April 2021
Real electronic signal data from particle accelerator power systems for machine learning anomaly detection Radaideh, Majdi I.; Pappas, Chris; Cousineau, Sarah Data in Brief, Vol. 43 https://doi.org/10.1016/j.dib.2022.108473	journal	August 2022
Forecasting and Anomaly Detection approaches using LSTM and LSTM Autoencoder techniques with the applications in supply chain management Nguyen, H. D.; Tran, K. P.; Thomassey, S. International Journal of Information Management, Vol. 57 https://doi.org/10.1016/j.ijinfomgt.2020.102282	journal	April 2021
A machine-learning phase classification scheme for anomaly detection in signals with periodic characteristics Ahrens, Lia; Ahrens, Julian; Schotten, Hans D. EURASIP Journal on Advances in Signal Processing, Vol. 2019, Issue 1 https://doi.org/10.1186/s13634-019-0619-3	journal	May 2019
An introduction to ROC analysis Fawcett, Tom Pattern Recognition Letters, Vol. 27, Issue 8 https://doi.org/10.1016/j.patrec.2005.10.010	journal	June 2006
A survey on anomaly detection for technical systems using LSTM networks Lindemann, Benjamin; Maschler, Benjamin; Sahlab, Nada Computers in Industry, Vol. 131 https://doi.org/10.1016/j.compind.2021.103498	journal	October 2021
Predicting particle accelerator failures using binary classifiers Rescic, Miha; Seviour, Rebecca; Blokland, Willem Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 955 https://doi.org/10.1016/j.nima.2019.163240	journal	March 2020

Similar Records

Application of Convolutional and Feedforward Neural Networks for Fault Detection in Particle Accelerator Power Systems

Conference · Sat Oct 01 00:00:00 EDT 2022 · OSTI ID:1897003

Radaideh, Majdi; Pappas, Chris; Ramuhalli, Pradeep; +1 more

Multi-module-based CVAE to predict HVCM faults in the SNS accelerator

Journal Article · Thu Jul 20 00:00:00 EDT 2023 · Machine Learning with Applications · OSTI ID:1897003

Alanazi, Yasir; Schram, Malachi; Rajput, Kishansingh; +7 more

Progress on Machine Learning for the SNS High Voltage Converter Modulators

Conference · Mon Aug 01 00:00:00 EDT 2022 · OSTI ID:1897003

Pappas, Chris; Lu, Dan; Walden, Jared; +6 more

Related Subjects

42 ENGINEERING
Signal processing
Anomaly detection
Autoencoders
ConvLSTM
High voltage converter modulator
Spallation neutron source

Title: Time series anomaly detection in power electronics signals with recurrent and ConvLSTM autoencoders

Citation Formats

References (21)

Similar Records

Related Subjects