JACoW is a publisher in Geneva, Switzerland that publishes the proceedings of accelerator conferences held around the world by an international collaboration of editors.
TY - CONF AU - Abell, D.T. AU - Edelen, J.P. AU - Freeman, B.G. AU - Kazimi, R. AU - Moser, D.G. AU - Tennant, C. ED - Furukawa, Kazuro ED - Yan, Yingbing ED - Leng, Yongbin ED - Chen, Zhichu ED - Schaa, Volker R.W. TI - Development of a Smart Alarm System for the CEBAF Injector J2 - Proc. of ICALEPCS2021, Shanghai, China, 14-22 October 2021 CY - Shanghai, China T2 - International Conference on Accelerator and Large Experimental Physics Control Systems T3 - 18 LA - english AB - RadiaSoft and Jefferson Laboratory are working together to develop a machine-learning-based smart alarm system for the CEBAF injector. Because of the injector’s large number of parameters and possible fault scenarios, it is highly desirable to have an autonomous alarm system that can quickly identify and diagnose unusual machine states. We present our work on artificial neural networks designed to identify such undesirable machine states. In particular, we test both auto-encoders and inverse models as possible tools for differentiating between normal and abnormal states. These models are being developed using both supervised and unsupervised learning techniques, and are being trained using CEBAF injector data collected during dedicated machine studies as well as during regular operations. Lastly, we discuss tradeoffs between the two types of models. PB - JACoW Publishing CP - Geneva, Switzerland SP - 691 EP - 694 KW - operation KW - network KW - vacuum KW - solenoid KW - quadrupole DA - 2022/03 PY - 2022 SN - 2226-0358 SN - 978-3-95450-221-9 DO - doi:10.18429/JACoW-ICALEPCS2021-WEPV023 UR - https://jacow.org/icalepcs2021/papers/wepv023.pdf ER -