Skip to main content

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

by Majdi I Radaideh, George C Pappas, Pradeep Ramuhalli, Sarah Mariehelen Cousineau
Publication Type
Conference Paper
Book Title
Proceedings of the Annual Conference of the PHM Society 2022
Publication Date
Page Numbers
1 to 8
Publisher Location
Nashville, Tennessee, United States of America
Conference Name
14th Annual Conference of the Prognostics and Health Management Society (PHM 2022)
Conference Location
Nashville, Tennessee, United States of America
Conference Sponsor
PHM Society
Conference Date

High voltage converter modulators (HVCM) provide power to the accelerating cavities of the spallation neutron source (SNS) facility. HVCM experience catastrophic failures, which increase the downtime of the SNS and reduce beam time. The faults may occur due to different reasons including failures of the resonant capacitor, core saturation due to the magnetic flux, insulated-gate bipolar transistor (IGBT) failures, and others. We recently have setup a HVCM test stand to develop and test machine learning models for anomaly detection and fault prognostics. In this work, we propose binary classifiers and autoencoder architectures based on convolutional (CNN) and feedforward neural networks (FNN) to facilitate distinguishing normal from faulty waveforms coming from the HVCM during operation. The results indicate that the CNN binary classifier is the best model among the four showing very stable performance in the training and testing sets with impressive metrics of precision and recall reaching up to 99\% with a very small uncertainty. The FNN classifier shows the least performance with a large uncertainty in its metrics. The performances of the two autoencoders based on CNN and FNN were in between, showing very good performance nonetheless.