Beamline Steering Using Deep Learning Models

TL;DR

This paper explores the use of deep learning models to improve beam steering calibration in particle accelerators, aiming to reduce human effort and enhance accuracy compared to traditional methods.

Contribution

The study compares various neural network architectures for beam steering calibration, demonstrating that smaller models outperform larger ones under current training constraints.

Findings

Smaller neural networks with fewer inputs and outputs outperform larger models.

Limited training time and computational resources hinder larger model performance.

Proposed models could surpass SVD with more training time and computational power.

Abstract

Beam steering involves the calibration of the angle and position at which a particle accelerator's electron beam is incident upon the x-ray target with respect to the rotation axis of the collimator. Beam Steering is an essential task for light sources. The Linac To Undulator is very difficult to steer and aim due to the changes of each use of the accelerator there must be re-calibration of magnets. However with each use of the Beamline its current method of steering runs into issues when faced with calibrating angles and positions. Human operators spend a substantial amount of time and resources on the task. We developed multiple different feed-forward-neural networks with varying hyper-parameters, inputs, and outputs, seeking to compare their performance. Specifically, our smaller models with 33 inputs and 13 outputs outperformed the larger models with 73 inputs and 50 outputs. We propose the following explanations for this lack of performance in larger models. First, a lack of training time and computational power limited the ability of our models to mature. Given more time, our models would outperform SVD. Second, when the input size of the model increases the noise increases as well. In this case more inputs corresponded to a greater length upon the LINAC accelerator. Less specific and larger models that seek to make more predictions will inherently perform worse than SVD.