The Joint Accelerator Conferences Website (JACoW) is an international collaboration that publishes the proceedings of accelerator conferences held around the world.
TY - CONF AU - Wang, F.Y. AU - Huang, X. AU - Zhang, Z. ED - Yamazaki, Yoshishige ED - Raubenheimer, Tor ED - McCausey, Amy ED - Schaa, Volker RW TI - Analyzing Accelerator Operation Data with Neural Networks J2 - Proc. of NAPAC2019, Lansing, MI, USA, 01-06 September 2019 CY - Lansing, MI, USA T2 - North American Particle Accelerator Conference T3 - 4 LA - english AB - Accelerator operation history data are used to train neural networks in an attempt to understand the underly-ing causes of performance drifts. In the study, injection efficiency of SPEAR3 [1] over two runs is modelled with a neural network (NN) to map the relationship of the injection efficiency with the injected beam trajectory and environment variables. The NN model can accurately predict the injection performance for the test data. With the model, we discovered that an environment parameter, the ground temperature, has a big impact to the injection performance. The ideal trajectory as a function of the ground temperature can be extracted from the model. The method has the potential for even larger scale application for the discovery of deep connections between machine performance and environment parameters. PB - JACoW Publishing CP - Geneva, Switzerland SP - 487 EP - 489 KW - injection KW - operation KW - storage-ring KW - network KW - booster DA - 2019/10 PY - 2019 SN - 2673-7000 SN - 978-3-95450-223-3 DO - doi:10.18429/JACoW-NAPAC2019-TUPLS14 UR - http://jacow.org/napac2019/papers/tupls14.pdf ER -