Aachen 2019 – wissenschaftliches Programm

Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

T: Fachverband Teilchenphysik

T 42: Experimentelle Methoden I

T 42.10: Vortrag

Dienstag, 26. März 2019, 18:20–18:35, ST 1

Data Quality Monitoring for the Neural Network z-Trigger in the Drift Chamber at the Belle-II Experiment — •Felix Meggendorfer, Sebastian Skambraks, Sara McCarney, and Christian Kiesling for the Belle 2 collaboration — MPI for Physics

For the drift chamber of the Belle-II experiment located in Tsukuba, Japan, a first level hardware neural network z-trigger is added to the standard 2D track trigger, which is used to identify tracks coming from outside of the interaction region. With this additional condition, a dominating portion of the background is efficiently suppressed and pure 2-track triggers become possible. Since changing background conditions during the first years of SuperKEKB operation are expected, the neural network weightsets will be adapted accordingly. In order to ensure optimal trigger efficiency and background rejection it is important to monitor the performance of the networks over time and retrain and update their weightsets with data from the experiment. An overview of the data quality monitoring system for the neural z-trigger is presented.