Skip to main content

Machine Learning for Improved Availability of the SNS Klystron High Voltage Converter Modulators...

by George C Pappas, Dan Lu, M Schram, Draguna Vrabie
Publication Type
Conference Paper
Journal Name
Proceedings of 2021 Particle Accelerator Conference,
Book Title
International Particle Accelerator Conference (12th)
Publication Date
Page Numbers
4303 to 4306
Publisher Location
Geneva, Switzerland
Conference Name
12th International Particle Accelerator Conference (IPAC)
Conference Location
Campinas, Brazil
Conference Sponsor
Conference Date

Beam availability has increased at the SNS, however, the targeted availability is greater than 95 %, while the SNS has failed to meet lower targets in the past. The HVCM used to power the linac klystrons have been one source of lost beam time and was chosen to explore using AI/ML techniques to improve reliability. Among the possibilities being explored are automating the tuning of HVCMs and predicting component failures such as capacitor aging, rectifier assemblies containing hundreds of diodes, and insulating oil degradation. The methodology pursued includes data cleaning, de-noising, post-analysis data labeling, and machine learning model development. We explore using Long Short-Term Memory and autoencoders for anomaly detection and prognostication used to schedule maintenance. We evaluate the use of model regularizers and constraints to improve the performance of the model and investigate methods to estimate the uncertainty of the models to provide a robust prediction with statistical interoperability. This paper describes the operational experience and known failures of the HVCMs and the proposed ML methodology and the preliminary results of training the AI/ML algorithms.