Submitted by szolling on

Please note that the we kindly ask you when connecting to this seminar to mute your microphones and cameras in order to have a good connection.

Abstract:

In this seminar, the development and the implementation of a real-time measurement system starting from the system requirements defined by the final users  (i.e., low-level radio frequency, power converters, and machine operators) will be presented. To satisfy all the necessities and all the constraints for all the seven particle accelerators that will benefit from this system, it was a crucial point to have a measurement system as flexible as possible to minimize the maintenance costs and to be prone to future requests by the system's users without the necessity of massive changes. Will also be presented the possibility of using neural networks to predict the magnetic field and all its non-linearity, such as eddy currents and hysteresis inside magnets for particle accelerators.
Considering a calibration quadrupole as case study,  various neural network-based architectures were designed and implemented. The achieved result of this study is a network able to predict the magnetic field leading to a percent error below 0.02%.

Type
Meeting
Timezone
Europe/Zurich
Room
ZOOM
Category
MSC Seminars
Category ID
2265
Indico iCal
https://indico.cern.ch/export/event/1132453.ics
Room Map URL
https://cern.zoom.us/j/94326148529?pwd=azRpMFlYZ0EzdHpUR3JtSmJLZkVidz09
Start Date
End Date