Reconstruction of offsets of an electron gun using deep learning and an optimization algorithm

David Meier; Gregor Hartmann; Jens Völker; Jens Viefhaus; Bernhard Sick

doi:10.1117/12.2568001

21 August 2020 Reconstruction of offsets of an electron gun using deep learning and an optimization algorithm

David Meier, Gregor Hartmann, Jens Völker, Jens Viefhaus, Bernhard Sick

Proceedings Volume 11493, Advances in Computational Methods for X-Ray Optics V; 114930E (2020) https://doi.org/10.1117/12.2568001
Event: SPIE Optical Engineering + Applications, 2020, Online Only

Abstract

A photoelectron gun cavity is an electron source that every Energy Recovery Linac (ERL) requires. Its characteristics and precision determine the capabilities and performance of the ERL. Calibration of the electron gun is a crucial part of its initial setup, which requires a lot of time and experience. We present the first steps towards a tool that guides the electron gun operator, which knobs to turn in which position to achieve the desired properties. In this report, we determine the - typically difficult to identify - offsets between the simulation and the real-world device. We accomplish this by using machine learning and a global optimization algorithm.

Conference Presentation

Citation Download Citation

David Meier, Gregor Hartmann, Jens Völker, Jens Viefhaus, and Bernhard Sick "Reconstruction of offsets of an electron gun using deep learning and an optimization algorithm", Proc. SPIE 11493, Advances in Computational Methods for X-Ray Optics V, 114930E (21 August 2020); https://doi.org/10.1117/12.2568001

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available