High-fidelity physics simulations are powerful tools in the design and optimization of charged particle accelerators. However, the computational burden of these simulations often limits their use in practice for design optimization and experiment planning. It also precludes their use as on-line models tied directly to accelerator operation. We introduce an approach based on machine learning to create nonlinear, fastexecuting surrogate models that are informed by a sparse sampling of the physics simulation. The models are Oð10 6 Þ-Oð10 7 Þ times more computationally efficient to execute. We also demonstrate that these models can be reliably used with multiobjective optimization to obtain orders-of-magnitude speedup in initial design studies and experiment planning. For example, we required 132 times fewer simulation evaluations to obtain an equivalent solution for our main test case, and initial studies suggest that between 330-550 times fewer simulation evaluations are needed when using an iterative retraining process. Our approach enables new ways for high-fidelity particle accelerator simulations to be used, at comparatively little computational cost.

No abstract

During the conceptual design of an accelerator or beamline, first-order beam dynamics models are essential for studying beam properties. However, they can only produce approximate results. During commissioning, these approximate results are compared to measurements, which will rarely coincide if the model does not include the relevant physics. It is therefore essential that this linear model is extended to include higher-order effects. In this paper, the effects of particle-matter interaction have been included in the model of the transport lines in the proton therapy facility at the Paul Scherrer Institut (PSI) in Switzerland. The first-order models of these beamlines provide an approximated estimation of beam size, energy loss and transmission. To improve the performance of the facility, a more precise model was required and has been developed with OPAL (Object oriented Particle Accelerator Library), a multi-particle open source beam dynamics code. In OPAL, the Monte Carlo simulations of Coulomb scattering and energy loss are performed seamless with the particle tracking. Beside the linear optics, the influence of the passive elements (e.g. degrader, collimators, scattering foils and air gaps) on the beam emittance and energy spread can be analysed in the new model. This allows for a significantly improved precision in the prediction of beam transmission and beam properties. The accuracy of the OPAL model has been confirmed by numerous measurements.

We present a novel machine learning-based approach to generate fast-executing virtual radiofrequency quadrupole (RFQ) particle accelerators using surrogate modelling. These could potentially be used as on-line feedback tools during beam commissioning and operation, and to optimize the RFQ beam dynamics design prior to construction. Since surrogate models execute orders of magnitude faster than corresponding physics beam dynamics simulations using standard tools like PARMTEQM and RFQGen, the computational complexity of the multi-objective optimization problem reduces significantly. Ultimately, this presents a computationally inexpensive and time efficient method to perform sensitivity studies and an optimization of the crucial RFQ beam output parameters like transmission and emittances. Two different methods of surrogate model creation (polynomial chaos expansion and neural networks) are discussed and the achieved model accuracy is evaluated for different study cases with gradually increasing complexity, ranging from a simple FODO cell example to the full RFQ optimization. We find that variations of the beam input Twiss parameters can be reproduced well. The prediction of the beam with respect to hardware changes, e.g., the electrode modulation, are challenging on the other hand. We discuss possible reasons for that and elucidate nevertheless existing benefits of the applied method to RFQ beam dynamics design.