Superconducting radio-frequency cavity fault classification using machine learning at Jefferson Laboratory

TL;DR

This paper presents machine learning models developed to classify faults in superconducting RF cavities at Jefferson Lab, enabling near real-time fault detection with high accuracy, improving maintenance efficiency and operational reliability.

Contribution

The study introduces ML models for real-time classification of SRF cavity faults, reducing manual analysis and enhancing fault detection speed and accuracy.

Findings

Cavity identification accuracy of 84.9%

Fault classification accuracy of 78.2%

Models perform effectively during physics runs

Abstract

We report on the development of machine learning models for classifying C100 superconducting radio-frequency (SRF) cavity faults in the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab. CEBAF is a continuous-wave recirculating linac utilizing 418 SRF cavities to accelerate electrons up to 12 GeV through 5-passes. Of these, 96 cavities (12 cryomodules) are designed with a digital low-level RF system configured such that a cavity fault triggers waveform recordings of 17 RF signals for each of the 8 cavities in the cryomodule. Subject matter experts (SME) are able to analyze the collected time-series data and identify which of the eight cavities faulted first and classify the type of fault. This information is used to find trends and strategically deploy mitigations to problematic cryomodules. However manually labeling the data is laborious and time-consuming. By leveraging machine learning, near real-time (rather than post-mortem) identification of the offending cavity and classification of the fault type has been implemented. We discuss performance of the ML models during a recent physics run. Results show the cavity identification and fault classification models have accuracies of 84.9% and 78.2%, respectively.