Fermilab, Batavia, Illinois, USA
RRCAT, Indore (M.P.), India
VECC, Kolkata, India
BARC, Mumbai, India
STFC/DL/ASTeC, Daresbury, Warrington, Cheshire, United Kingdom
INFN/LASA, Segrate (MI), Italy
Università degli Studi di Milano & INFN, Segrate, Italy
ANL, Lemont, Illinois, USA
STFC/DL, Daresbury, Warrington, Cheshire, United Kingdom
Low-beta and high-beta sections of PIP-II linac will use nine low-beta cryomodules with four cavities each and four high-beta cryomodules with six cavities each. These cavities will be produced and qualified in collaboration between Fermilab and the international partner labs. Prior to their installation into prototype cryomodules, several dressed cavities, which include jacketed cavities, high power couplers, and tuners, will be qualified in STC horizontal test bed at Fermilab. After qualification of bare β = 0.9 cavities at Fermilab, several pre-production β = 0.92 and β = 0.61 cavities have been and are being fabricated and qualified. Procurements have also been started for high power couplers and tuners. In this contribution we present the current status of prototype dressed cavity qualification for PIP-II.
JLab, Newport News, Virginia, USA
ODU, Norfolk, Virginia, USA
STFC/DL, Daresbury, Warrington, Cheshire, United Kingdom
We report on the development of machine learning models for classifying C100 superconducting radiofrequency (SRF) cavity faults in the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab. Of the 418 SRF cavities in CEBAF, 96 are designed with a digital low-level RF system configured such that a cavity fault triggers recordings of RF signals for each of eight cavities in the cryomodule. Subject matter experts 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 postmortem - identification of the offending cavity and classification of the fault type has been implemented. We discuss the performance of the machine learning models during a recent physics run. We also discuss efforts for further insights into fault types through unsupervised learning techniques and present preliminary work on cavity and fault prediction using data collected prior to a failure event.