Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Graph learning for particle accelerator operations

Journal Article · · Frontiers in Big Data
 [1];  [2];  [2];  [2];  [1]
  1. University of Virginia, Charlottesville, VA (United States)
  2. Thomas Jefferson National Accelerator Facility (TJNAF), Newport News, VA (United States)
+ Show Author Affiliations
Particle accelerators play a crucial role in scientific research, enabling the study of fundamental physics and materials science, as well as having important medical applications. This study proposes a novel graph learning approach to classify operational beamline configurations as good or bad. By considering the relationships among beamline elements, we transform data from components into a heterogeneous graph. We propose to learn from historical, unlabeled data via our self-supervised training strategy along with fine-tuning on a smaller, labeled dataset. Additionally, we extract a low-dimensional representation from each configuration that can be visualized in two dimensions. Leveraging our ability for classification, we map out regions of the low-dimensional latent space characterized by good and bad configurations, which in turn can provide valuable feedback to operators. This research demonstrates a paradigm shift in how complex, many-dimensional data from beamlines can be analyzed and leveraged for accelerator operations.
Research Organization:
Thomas Jefferson National Accelerator Facility, Newport News, VA (United States)
Sponsoring Organization:
USDOE Office of Science (SC), Nuclear Physics (NP); USDOE Laboratory Directed Research and Development (LDRD) Program
Grant/Contract Number:
AC05-06OR23177
OSTI ID:
2336694
Report Number(s):
JLAB-ACP--24-3904; DOE/OR/23177--7248; 2022—LDRD-1
Journal Information:
Frontiers in Big Data, Journal Name: Frontiers in Big Data Vol. 7; ISSN 2624-909X
Publisher:
FrontiersCopyright Statement
Country of Publication:
United States
Language:
English

References (9)

Supervised principal component analysis: Visualization, classification and regression on subspaces and submanifolds journal July 2011
1D convolutional neural networks and applications: A survey journal April 2021
Continuous wave superconducting radio frequency electron linac for nuclear physics research journal December 2016
Challenges and Goals for Accelerators in the XXI Century book September 2012
JGCL: Joint Self-Supervised and Supervised Graph Contrastive Learning conference April 2022
UMAP: Uniform Manifold Approximation and Projection journal September 2018
Representation Learning with Contrastive Predictive Coding preprint January 2018
Adversarial Graph Augmentation to Improve Graph Contrastive Learning preprint January 2021
G-Mixup: Graph Data Augmentation for Graph Classification preprint January 2022

Similar Records

Graph Embeddings for CEBAF Operations: Progress and Future Plans
Conference · Tue Nov 01 00:00:00 EDT 2022 · OSTI ID:1963703
Graph Analytics for CEBAF Operations
Technical Report · Tue Mar 26 00:00:00 EDT 2024 · OSTI ID:2331262
Error-Bounded Graph Construction for Semi-supervised Manifold Learning
Conference · Wed Aug 01 00:00:00 EDT 2018 · OSTI ID:1470850

Related Subjects

43 PARTICLE ACCELERATORS
SSL
graph learning algorithm
graph neural network
particle accelerator
self-supervised learning
supervised training