Document Type

Conference Paper

Publication Date

2022

DOI

10.2172/1963601

Publication Title

3rd ICFA Beam Dynamics Mini-Workshop on Machine Learning Applications for Particle Accelerators

Pages

1-48

Conference Name

3rd ICFA Beam Dynamics Mini-Workshop on Machine Learning Applications for Particle Accelerators, 1-4 November 2022, Chicago, Illinois

Abstract

Over the last few years several machine learning projects at Jefferson Lab have had a common focus to optimize operation of superconducting RF (SRF) cavities in the Continuous Electron Beam Accelerator Facility (CEBAF). In this talk we highlight work to identify and classify types of faults from C100-type cavities and then to extend those capabilities to provide real-time fault prediction. Early prediction may enable mitigation strategies to prevent some types of faults. In our approach we apply a two-step fault prediction pipeline. In the first step, a model distinguishes between faulty and normal signals. In the second step, signals flagged as faulty by the first model are classified into one of seven fault types based on learned signatures in the data. Initial results show that our model can successfully predict most fault types 200 ms before onset. In additional to model performance, we also highlight challenges in working with real-world data and challenges for deploying models.

Comments

Jefferson Lab report numbers: JLAB-ACP-22-3781; DOE/OR/23177-5874

Rights

© 2022 Jefferson Lab. All rights reserved.

Included in accordance with publisher policy.

Original Publication Citation

Tennant, C., Carpenter, A., Vidyaratne, L., Monibor, R., Md, & Iftekharuddin, K. (2022). SRF cavity fault classification and prediction at Jefferson Lab [Paper presentation]. 3rd ICFA Beam Dynamics Mini Workshop on Machine Learning for Particle Accelerators, Chicago, Illinois. https://doi.org/10.2172/1963601

ORCID

0000-0003-1794-916X (Rahman), 0000-0001-8316-4163 (Iftekharuddin)

Download

Share

COinS