Towards automatic setup of 18 MeV electron beamline using machine learning

To improve the performance-critical stability and brightness of the electron bunch at injection into the proton-driven plasma wakefield at the AWAKE CERN experiment, automation approaches based on unsupervised machine learning (ML) were developed and deployed. Numerical optimisers were tested togeth...

Szczegółowa specyfikacja

Opis bibliograficzny

Główni autorzy:	Francesco Maria Velotti, Brennan Goddard, Verena Kain, Rebecca Ramjiawan, Giovanni Zevi Della Porta, Simon Hirlaender
Format:	Artigo
Język:	Inglês
Wydane:	IOP Publishing 2023-01-01
Seria:	Machine Learning: Science and Technology
Hasła przedmiotowe:	automatic electron beamline reinforcement learning reward dangling
Dostęp online:	https://doi.org/10.1088/2632-2153/acce21
Etykiety:	Dodaj etykietę Nie ma etykietki, Dołącz pierwszą etykiete!