The Joint Accelerator Conferences Website (JACoW) is an international collaboration that publishes the proceedings of accelerator conferences held around the world.
TY - CONF AU - Dewitte, T. AU - Meert, W. AU - Van Trappen, P. AU - Van Wolputte, E. ED - White, Karen S. ED - Brown, Kevin A. ED - Dyer, Philip S. ED - Schaa, Volker RW TI - Anomaly Detection for CERN Beam Transfer Installations Using Machine Learning J2 - Proc. of ICALEPCS2019, New York, NY, USA, 05-11 October 2019 CY - New York, NY, USA T2 - International Conference on Accelerator and Large Experimental Physics Control Systems T3 - 17 LA - english AB - Reliability, availability and maintainability determine whether or not a large-scale accelerator system can be operated in a sustainable, cost-effective manner. Beam transfer equipment (e.g. kicker magnets) has potentially significant impact on the global performance of a machine complex. Identifying root causes of malfunctions is currently tedious, and will become infeasible in future systems due to increasing complexity. Machine Learning could automate this process. For this purpose a collaboration between CERN and KU Leuven was established. We present an anomaly detection pipeline which includes preprocessing, detection, postprocessing and evaluation. Merging data of different, asynchronous sources is one of the main challenges. Currently, Gaussian Mixture Models and Isolation Forests are used as unsupervised detectors. To validate, we compare to manual e-logbook entries, which constitute a noisy ground truth. A grid search allows for hyper-parameter optimization across the entire pipeline. Lastly, we incorporate expert knowledge by means of semi-supervised clustering with COBRAS. PB - JACoW Publishing CP - Geneva, Switzerland SP - 1066 EP - 1070 DA - 2020/08 PY - 2020 SN - 2226-0358 SN - 978-3-95450-209-7 DO - doi:10.18429/JACoW-ICALEPCS2019-WEMPR010 UR - https://jacow.org/icalepcs2019/papers/wempr010.pdf ER -