JACoW logo

Journals of Accelerator Conferences Website (JACoW)

JACoW is a publisher in Geneva, Switzerland that publishes the proceedings of accelerator conferences held around the world by an international collaboration of editors.


RIS citation export for TUYE4: Machine Learning for Anomaly Detection and Classification in Particle Accelerators

TY  - CONF
AU  - Lobach, I.
AU  - Borland, M.
AU  - Harkay, K.C.
AU  - Kuklev, N.
AU  - Sannibale, A.
AU  - Sun, Y.
ED  - Biedron, Sandra
ED  - Simakov, Evgenya
ED  - Milton, Stephen
ED  - Anisimov, Petr M.
ED  - Schaa, Volker R.W.
TI  - Machine Learning for Anomaly Detection and Classification in Particle Accelerators
J2  - Proc. of NAPAC2022, Albuquerque, NM, USA, 07-12 August 2022
CY  - Albuquerque, NM, USA
T2  - International Particle Accelerator Conference
T3  - 5
LA  - english
AB  - We explore the possibility of using a Machine Learning (ML) algorithm to identify the source of occasional poor performance of the Particle Accumulator Ring (PAR) and the Linac-To-PAR (LTP) transport line, which are parts of the injector complex of the Advanced Photon Source (APS) at Argonne National Lab. The cause of reduced injection or extraction efficiencies may be as simple as one parameter being out of range. Still, it may take an expert considerable time to notice it, whereas a well-trained ML model can point at it instantly. In addition, a machine expert might not be immediately available when a problem occurs. Therefore, we began by focusing on such single-parameter anomalies. The training data were generated by creating controlled perturbations of several parameters of PAR and LTP one-by-one, while continuously logging all available process variables. Then, several ML classifiers were trained to recognize certain signatures in the logged data and link them to the sources of poor machine performance. Possible applications of autoencoders and variational autoencoders for unsupervised anomaly detection and for anomaly clustering were considered as well.
PB  - JACoW Publishing
CP  - Geneva, Switzerland
SP  - 311
EP  - 314
KW  - network
KW  - injection
KW  - linac
KW  - operation
KW  - controls
DA  - 2022/10
PY  - 2022
SN  - 2673-7000
SN  - 978-3-95450-232-5
DO  - doi:10.18429/JACoW-NAPAC2022-TUYE4
UR  - https://jacow.org/napac2022/papers/tuye4.pdf
ER  -