Fast, efficient and flexible particle accelerator optimisation using densely connected and invertible neural networks

2021/06/30 by Bellotti, Renato, Boiger, Romana, Adelmann, Andreas
#Accelerator Physics (physics.acc-ph) #FOS: Physical sciences

paper · doi:10.48550/arxiv.2107.00060

Abstract

Particle accelerators are enabling tools for scientific exploration and discovery in various disciplines. Finding optimized operation points for these complex machines is a challenging task, however, due to the large number of parameters involved and the underlying non-linear dynamics. Here, we introduce two families of data-driven surrogate models, based on deep and invertible neural networks, that can replace the expensive physics computer models. These models are employed in multi-objective optimisations to find Pareto optimal operation points for two fundamentally different types of particle accelerators. Our approach reduces the time-to-solution for a multi-objective accelerator optimisation up to a factor of 640 and the computational cost up to 98%. The framework established here should pave the way for future on-line and real-time multi-objective optimisation of particle accelerators.

Related

• Neural Networks as Effective Surrogate Models of Radio-Frequency Quadrupole Particle Accelerator Simulations
• Large Language Models for Human-Machine Collaborative Particle Accelerator Tuning through Natural Language
• Neural Network Prior Mean for Particle Accelerator Injector Tuning
• Multi-Objective Hardware-Mapping Co-Optimisation for Multi-DNN Workloads on Chiplet-based Accelerators
• Bridging the gap between machine learning and particle accelerator physics with high-speed, differentiable simulations