Input Beam Matching and Beam Dynamics Design Optimizations of the IsoDAR RFQ Using Statistical and Machine Learning Techniques

Koser, Daniel; Waites, Loyd; Winklehner, Daniel; Frey, Matthias; Adelmann, Andreas; Conrad, J. M.

doi:10.3389/fphy.2022.875889

Cited by 8 publications

(21 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Statistical [218] or machine learning techniques are used [219]. These models can for example replace a computationally expensive simulation in a multi-objective optimization [220][221][222] or become an online tuning tool.…”

Section: Surrogate Model Constructionmentioning

confidence: 99%

High-power Fixed-Field Accelerators

et al. 2023

View full text Add to dashboard Cite

We report the state of the field of High-Power Fixed-Field Accelerators (with an emphasis on cyclotrons) as discussed by international experts during a three-day workshop of the same name in 2021. The workshop was part of the Snowmass'21 Community Planning Exercise. Here, we take stock of the world inventory of high-power fixed-field accelerators, assess available beam currents and beam powers, and investigate limitations. Furthermore, we evaluate the role of these machines in particle physics, directly used or as injectors to other machines, and in industry, as drivers for (medical) isotope production and, potentially, for accelerator-driven systems and sub-critical reactors. Finally, we discuss novel concepts and cutting-edge developments to push the available current higher at several energy scales, thereby increasing relative power. Highlights include new spiral inflector types, direct RFQ injection, H2 + acceleration, utilizing vortex motion, and self-extraction schemes. We also discuss modern computational frameworks to optimize accelerators more efficiently, and better describe the relevant physical processes in simulations.

show abstract

Section: Surrogate Model Constructionmentioning

confidence: 99%

High-power Fixed-Field Accelerators

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The IsoDAR particle accelerator comprises an ion source, radio-frequency quadrupole (RFQ), and a cyclotron [16,17]. Surrogate modeling has proven invaluable to IsoDAR's development, allowing us to demonstrate the robustness of IsoDAR's cyclotron design [17] through uncertainty quantification [2], and to perform a small pilot study to investigate the use of surrogate models for RFQs [18].…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we expand upon work presented in [18] to build a NN-based surrogate model of an RFQ, but rethink the RFQ parametrization to account for collinear effects in the feature space, physical RFQ design constraints, and incorporate variables previously hidden from trained surrogate models. We use these insights to generate an accurate surrogate model for a 32.8 MHz RFQ covering a wide design parameter space (subject to physical design constraints).…”

Section: Introductionmentioning

confidence: 99%

Neural networks as effective surrogate models of radio-frequency quadrupole particle accelerator simulations

Villarreal,

Winklehner,

Koser

et al. 2024

Mach. Learn.: Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Radio-Frequency Quadrupoles (RFQs) are multi-purpose linear particle accelerators that simultaneously bunch and accelerate charged particle beams. They are ubiquitous in accelerator physics, especially as injectors to higher-energy machines, owing to their impressive efficiency. The design and optimization of these devices can be lengthy due to the need to repeatedly perform high-fidelity simulations. Several recent papers have demonstrated that machine learning can be used to build surrogate models (fast-executing replacements of computationally costly beam simulations) for order-of-magnitude computing time speedups. However, while these pilot studies are encouraging, there is room to improve their predictive accuracy. Particularly, beam summary statistics such as emittances (an important figure of merit in particle accelerator physics) have historically been challenging to predict. For the first time, we present a surrogate model trained on of 200,000 samples that yields <6% mean average percent error for the predictions of all relevant beam output parameters from defining RFQ design parameters, solving the problem of poor emittance predictions by identifying and including hidden variables which were not accounted for previously. These surrogate models were made possible by using the Julia language and GPU computing; we briefly discuss both. We demonstrate the utility of surrogate modeling by performing a multi-objective optimization using our best model as a callback in the objective function to select an optimal RFQ design. We consider trade-offs in RFQ performance for various choices of Pareto-optimal design variables—common issues for any multi-objective optimization scheme. Lastly, we make recommendations for input data preparation, selection, and neural network architectures that pave the way for future development of production-capable surrogate models for RFQs and other particle accelerators.

show abstract

“…During the LHC run, the machine operators may change several parameters of the system, such as currents in the quadrupole, sextupole, and octupole magnets, in order to maximize the beam intensity and thus minimize the particle loss. Machine learning and statistical methods have been extensively used to analyze the data from accelerators and to improve operations [4][5][6][7][8][9]. It is possible to construct predictive models of the losses from the control parameters using standard ML techniques [1] based on LHC beam loss data within the same year, but the generalization of such approaches to the data of the next year was found to be challenging.…”

Section: Introductionmentioning

confidence: 99%

Data-driven modeling of beam loss in the LHC

et al. 2023

View full text Add to dashboard Cite

In the Large Hadron Collider, the beam losses are continuously measured for machine protection. By design, most of the particle losses occur in the collimation system, where the particles with high oscilla-tion amplitudes or large momentum error are scraped from the beams. The particle loss level is typically optimized manually by changing control parameters, among which are currents in the focusing and defocusing magnets. It is generally challenging to model and predict losses based only on the control parameters, due to the presence of various (non-linear) effects in the system, such as electron clouds, resonance effects, etc., and multiple sources of uncertainty. At the same time understanding the influence of control parameters on the losses is extremely important in order to improve the operation and performance, and future design of accelerators. Prior work [1] showed that modeling the losses as an instantaneous function of the control parameters does not generalize well to data from a different year, which is an indication that the leveraged statistical associations are not capturing the actual mechanisms which should be invariant from 1 year to the next. Given that this is most likely due to lagged effects, we propose to model the losses as a function of not only instantaneous but also previously observed control parameters as well as previous loss values. Using a standard reparameterization, we reformulate the model as a Kalman Filter (KF) which allows for a flexible and efficient estimation procedure. We consider two main variants: one with a scalar loss output, and a second one with a 4D output with loss, horizontal and vertical emittances, and aggregated heatload as components. The two models once learned can be run for a number of steps in the future, and the second model can forecast the evolution of quantities that are relevant to predicting the loss itself. Our results show that the proposed models trained on the beam loss data from 2017 are able to predict the losses on a time horizon of several minutes for the data of 2018 as well and successfully identify both local and global trends in the losses.

show abstract

Input Beam Matching and Beam Dynamics Design Optimizations of the IsoDAR RFQ Using Statistical and Machine Learning Techniques

Cited by 8 publications

References 31 publications

High-power Fixed-Field Accelerators

High-power Fixed-Field Accelerators

Neural networks as effective surrogate models of radio-frequency quadrupole particle accelerator simulations

Data-driven modeling of beam loss in the LHC

Contact Info

Product

Resources

About