JACoW logo

Joint Accelerator Conferences Website

The Joint Accelerator Conferences Website (JACoW) is an international collaboration that publishes the proceedings of accelerator conferences held around the world.

RIS citation export for SUSPFO053: Operational Results of LHC Collimator Alignment Using Machine Learning

AU  - Azzopardi, G.
AU  - Muscat, A.
AU  - Redaelli, S.
AU  - Salvachua, B.
AU  - Valentino, G.
ED  - Boland, Mark
ED  - Tanaka, Hitoshi
ED  - Button, David
ED  - Dowd, Rohan
ED  - Schaa, Volker RW
ED  - Tan, Eugene
TI  - Operational Results of LHC Collimator Alignment Using Machine Learning
J2  - Proc. of IPAC2019, Melbourne, Australia, 19-24 May 2019
CY  - Melbourne, Australia
T2  - International Particle Accelerator Conference
T3  - 10
LA  - english
AB  - A complex collimation system is installed in the Large Hadron Collider to protect sensitive equipment from unavoidable beam losses. The collimators are positioned close to the beam in the form of a hierarchy, which is guaranteed by precisely aligning each collimator with a precision of a few tens of micrometers. During past years, collimator alignments were performed semi-automatically*, such that collimation experts had to be present to oversee and control the alignment. In 2018, machine learning was introduced to develop a new fully-automatic alignment tool, which was used for collimator alignments throughout the year. This paper discusses how machine learning was used to automate the alignment, whilst focusing on the operational results obtained when testing the new software in the LHC. Automatically aligning the collimators decreased the alignment time at injection by a factor of three whilst maintaining the accuracy of the results.
PB  - JACoW Publishing
CP  - Geneva, Switzerland
SP  - 1208
EP  - 1211
DA  - 2019/06
PY  - 2019
SN  - 978-3-95450-208-0
DO  - DOI: 10.18429/JACoW-IPAC2019-TUZZPLM1
UR  - http://jacow.org/ipac2019/papers/tuzzplm1.pdf
ER  -