UNM-ECE, Albuquerque, USA
Argonne National Laboratory, Office of Naval Research Project, Argonne, Illinois, USA
Element Aero, Chicago, USA
UNM-ME, Albuquerque, New Mexico, USA
NERS-UM, Ann Arbor, Michigan, USA
University of Michigan, Ann Arbor, Michigan, USA
IHEP, Beijing, People’s Republic of China
Michigan University, Ann Arbor, Michigan, USA
The applications of machine learning in today’s world encompass all fields of life and physical sciences. In this paper, we implement a machine learning based algorithm in the context of laser physics and particle accelerators. Specifically, a neural network-based optimisation algorithm has been developed that offers enhanced control over an ultrafast femtosecond laser in comparison to the traditional Proportional Integral and derivative (PID) controls. This research opens a new potential of utilising machine learning and even deep learning techniques to improve the performance of several different lasers and accelerators systems.
UNM-ECE, Albuquerque, USA
BNL, Upton, New York, USA
UNM-ME, Albuquerque, New Mexico, USA
LANL, Los Alamos, New Mexico, USA
ANL, Lemont, Illinois, USA
A MeV ultrafast electron diffraction (MUED) instrument is a unique characterization technique to study ultrafast processes in materials by a pump-probe technique. This relatively young technology can be advanced further into a turn-key instrument by using data science and artificial intelligence (AI) mechanisms in conjunctions with high-performance computing. This can facilitate automated operation, data acquisition and real time or near- real time processing. AI based system controls can provide real time feedback on the electron beam which is currently not possible due to the use of destructive diagnostics. Deep learning can be applied to the MUED diffraction patterns to recover valuable information on subtle lattice variations that can lead to a greater understanding of a wide range of material systems. A data science enabled MUED facility will also facilitate the application of this technique, expand its user base, and provide a fully automated state-of-the-art instrument. We will discuss the progress made on the MUED instrument in the Accelerator Test Facility of Brookhaven National Laboratory.
UNM-ECE, Albuquerque, USA
SLAC, Menlo Park, California, USA
UNM-ME, Albuquerque, New Mexico, USA
ODU, Norfolk, Virginia, USA
Superconducting radio frequency (SRF) cavities with high loaded quality factors that operate in continuous wave (CW) and low beam loading are sensitive to microphonics-induced detuning. Cavity detuning can result in an increase of operational power and/or in a cavity quench. Such SRF cavities have bandwidths on the order of 10 Hz and detuning requirements can be as tight as 10 Hz. Passive methods to mitigate vibration sources and their impact in the cryomodule/cavity environment are widely used. Active resonance control techniques that use stepper motors and piezoelectric actuators to tune the cavity resonance frequency by compensating for microphonics detuning have been investigated. These control techniques could be further improved by applying Machine Learning (ML), which has shown promising results in other particle accelerator control systems. In this paper, we describe a Low-level RF (LLRF) and resonance control system based on ML methods that optimally and adaptively tunes the control parameters. We present simulations and test results obtained using a low power test bench with a cavity emulator.
UNM-ECE, Albuquerque, USA
BNL, Upton, New York, USA
ANL, Lemont, Illinois, USA
UNM-ME, Albuquerque, New Mexico, USA
UNM-ECE, Albuquerque, USA
Tech-X, Boulder, Colorado, USA
Ion Linac Systems, Inc., Albuquerque, USA
We discuss electromagnetic simulations of accelerating structures in a high performance computing (HPC) system. Our overarching goal is to resolve the linac operation in a large ensemble of initial beam conditions. This requires a symbiotic relation between the electromagnetic solver and HPC. The linac is being developed by Ion Linac Systems to produce a low-energy, high-current, proton beam. We use VSim, an electromagnetic solver and PIC software developed by Tech-X to determine the electromagnetic fundamental mode of operation of the accelerating structures and discuss its implementation at the THETA supercomputer in the Argonne Leadership Computing Facility.
LANL, Los Alamos, New Mexico, USA
UNM-ECE, Albuquerque, USA
The goal of this work was to develop a solution to the problem of longitudinal beam instability. Beam instability has been a significant problem with storage rings’ performance for many decades. The proton storage ring (PSR) at the Los Alamos Neutron Science Center (LANCE) is no exception. To mitigate the instability, it was found that ferrite inductive inserts can be used to bunch the protons that are diverging due to the electron background. The PSR was the first storage ring to successfully use inductive inserts to mitigate the longitudinal instability with normal production beams. However, years later new machine upgrades facilitate shorter, more intense beams to meet the needs of researchers. The ferrite inserts used to reduce the transverse instabilities induce a microwave instability with the shorter more intense proton beam. This study investigates alternative magnetic materials for inductive inserts in particle beam storage rings, including the necessary engineering for maintaining the ideal temperature during operation.
’ tjschaub@unm.edu
BNL, Upton, New York, USA
UNM-ECE, Albuquerque, USA
Stony Brook University, Stony Brook, New York, USA
SBU, Stony Brook, USA
We discuss the possible use of crystalline beams in storage rings for applications in quantum information science (QIS). Crystalline beams have been created in ion trap systems and proven to be useful as a computational basis for QIS applications. The same structures can be created in a storage ring, but the ions necessarily have a constant velocity and are rotating in a circular trap. The basic structures that are needed are ultracold crystalline beams, called ion Coulomb crystals (ICC’s). We will describe different applications of ICC’s for QIS, how QIS information is obtained and can be used for quantum computing, and some of the challenges that need to be resolved to realize practical QIS applications in storage rings.
UNM-ME, Albuquerque, New Mexico, USA
UNM-ECE, Albuquerque, USA
SLAC, Menlo Park, California, USA
Machine learning (ML) has recently been applied to Low-level RF (LLRF) control systems to keep the voltage and phase of Superconducting Radiofrequency (SRF) cavities stable within 0.01 degree in phase and 0.01% amplitude as constraints. Model predictive control (MPC) uses an optimization algorithm offline to minimize a cost function with constraints on the states and control input. The surrogate model optimally controls the cavities online. Time series deep ML structures including recurrent neural network (RNN) and long short-term memory (LSTM) can model the control input of MPC and dynamics of LLRF as a surrogate model. When the predicted states diverge from the measured states more than a threshold at each time step, the states’ measurements from the cavity fine-tune the surrogate model with transfer learning. MPC does the optimization offline again with the updated surrogate model, and, next, transfer learning fine-tunes the surrogate model with the new data from the optimal control inputs. The surrogate model provides us with a computationally faster and accurate modeling of MPC and LLRF, which in turn results in a more stable control system.
Machine learning, Surrogate model, control, LLRF, MPC, Transfer learning
UNM-ECE, Albuquerque, USA
UNM-ME, Albuquerque, New Mexico, USA
Tech-X, Boulder, Colorado, USA
SLAC, Menlo Park, California, USA
During the last decade, the production of soft to hard x-rays (up to 25 keV) at XFEL facilities has enabled new developments in a broad range of disciplines. One caveat is that these instruments can require a large amount of real estate. For example, the XFEL driver is typically an electron beam linear accelerator (LINAC) and the need for higher electron beam energies capable of generating higher energy X-rays can require longer linacs; costs quickly become prohibitive, requiring state of art methods. One cost-saving measure is to produce a high accelerating gradient while reducing cavity size. Compact accelerating structures are also high-frequency. Here, we describe design concepts for a high-gradient, cryo-cooled LINAC for XFEL facilities in the C-band regime (~4-8 GHz). We are also exploring C-band for different applications including drivers for security applications. We investigate 2 different traveling wave (TW) geometries optimized for high-gradient operation as modeled with VSim software.