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.
Highlights
The Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Laboratory is a continuous-wave recirculating linac [1,2]
In order to better understand the nature and frequency of these faults, we developed a new data acquisition system (DAQ)—by taking advantage of the digital level rf system (LLRF) system of the C100s—that simultaneously records waveforms of 17 different rf signals for each of eight cavities in a cryomodule
The data acquisition system is comprised of two primary components, the LLRF and experimental physics and industrial control systems (EPICS), along with a collection of highlevel applications
Summary
The Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Laboratory is a continuous-wave recirculating linac (see Fig. 1) [1,2]. Each cryomodule (comprised of eight seven-cell cavities) is capable of 100 MV energy gain and is regulated with an associated digital low-level rf system (LLRF). In order to better understand the nature and frequency of these faults, we developed a new data acquisition system (DAQ)—by taking advantage of the digital LLRF system of the C100s—that simultaneously records waveforms of 17 different rf signals for each of eight cavities in a cryomodule. This process is triggered when the LLRF system for any cavity in the cryomodule detects a fault condition. We conclude with results from the winter 2020 physics run and discuss future work
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have