Search Menu
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information
Search Scholarly Publications

Title: Real-time artificial intelligence for accelerator control: A study at the Fermilab Booster

Journal Article · · Physical Review Accelerators and Beams
ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [2]; ORCiD logo [3]; ORCiD logo [2];  [4]
  1. Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)
  2. Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
  3. Univ. of California, San Diego, CA (United States)
  4. Columbia Univ., New York, NY (United States)
+ Show Author Affiliations

We describe a method for precisely regulating the gradient magnet power supply (GMPS) at the Fermilab Booster accelerator complex using a neural network trained via reinforcement learning. We demonstrate preliminary results by training a surrogate machine-learning model on real accelerator data to emulate the GMPS, and using this surrogate model in turn to train the neural network for its regulation task. We additionally show how the neural networks to be deployed for control purposes may be compiled to execute on field-programmable gate arrays (FPGAs), and show the first machine-learning based control algorithm implemented on an FPGA for controls at the Fermilab accelerator complex. As there are no surprise latencies on an FPGA, this capability is important for operational stability in complicated environments such as an accelerator facility.

Research Organization:
Pacific Northwest National Laboratory (PNNL), Richland, WA (United States); Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States); Thomas Jefferson National Accelerator Facility (TJNAF), Newport News, VA (United States)
Sponsoring Organization:
USDOE Office of Science (SC), High Energy Physics (HEP); USDOE Laboratory Directed Research and Development (LDRD) Program; National Science Foundation (NSF)
Grant/Contract Number:
AC02-07CH11359; FNAL-LDRD-2019-027; AC05-76RL01830; SC0021187; DGE-1644869
OSTI ID:
1826394
Alternate ID(s):
OSTI ID: 1826740; OSTI ID: 1828840; OSTI ID: 1886597
Report Number(s):
PNNL-SA-157642; FERMILAB-PUB-20-565-AD-E-QIS-SCD; arXiv:2011.07371; JLAB-CST-21-3606; DOE/OR/23177-5611; TRN: US2216330
Journal Information:
Physical Review Accelerators and Beams, Vol. 24, Issue 10; ISSN 2469-9888
Publisher:
American Physical Society (APS)Copyright Statement
Country of Publication:
United States
Language:
English

References (48)

Machine learning for orders of magnitude speedup in multiobjective optimization of particle accelerator systems journal April 2020
Fast inference of Boosted Decision Trees in FPGAs for particle physics journal May 2020
Learning long-term dependencies with gradient descent is difficult journal March 1994
Deep learning journal May 2015
Sample-efficient reinforcement learning for CERN accelerator control journal December 2020
Policy gradient methods for free-electron laser and terahertz source optimization and stabilization at the FERMI free-electron laser at Elettra journal December 2020
Neuronlike adaptive elements that can solve difficult learning control problems journal September 1983
Human-level control through deep reinforcement learning journal February 2015
Machine learning-based surrogate modeling for data-driven optimization: a comparison of subset selection for regression techniques journal May 2019
Fast inference of deep neural networks in FPGAs for particle physics journal July 2018
Investigating Causal Relations by Econometric Models and Cross-spectral Methods journal August 1969
Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors journal June 2021
Toolflows for Mapping Convolutional Neural Networks on FPGAs: A Survey and Future Directions journal July 2018
Compressing deep neural networks on FPGAs to binary and ternary precision with hls4ml journal December 2020
Fast convolutional neural networks on FPGAs with hls4ml journal July 2021
Directional Stability of Automatically Steered Bodies journal May 1922
Bayesian Optimization of a Free-Electron Laser journal March 2020
BOOSTR: A Dataset for Accelerator Control Systems journal April 2021
Demonstration of Model-Independent Control of the Longitudinal Phase Space of Electron Beams in the Linac-Coherent Light Source with Femtosecond Resolution journal July 2018
Physics model-informed Gaussian process for online optimization of particle accelerators journal July 2021
Adaptive method for electron bunch profile prediction journal October 2015
Machine learning and the physical sciences journal December 2019
Optimum Settings for Automatic Controllers journal June 1993
The Fermilab ACNET upgrade
  • Briegel, Charlie; Johnson, Glenn; Winterowd, Lin
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 293, Issue 1-2 https://doi.org/10.1016/0168-9002(90)91434-D
journal August 1990
On the Theory of Dynamic Programming journal August 1952
Neural Networks for Modeling and Control of Particle Accelerators journal April 2016
Basic Reinforcement Learning Techniques to Control the Intensity of a Seeded Free-Electron Laser journal May 2020
An Introduction to Deep Reinforcement Learning journal January 2018
Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics journal January 2021
Superconducting radio-frequency cavity fault classification using machine learning at Jefferson Laboratory journal November 2020
Long Short-Term Memory journal November 1997
[DL] A Survey of FPGA-based Neural Network Inference Accelerators journal April 2019
Apache Spark: a unified engine for big data processing journal October 2016
Machine learning for beam dynamics studies at the CERN Large Hadron Collider
  • Arpaia, P.; Azzopardi, G.; Blanc, F.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 985 https://doi.org/10.1016/j.nima.2020.164652
journal January 2021
FINN- R: An End-to-End Deep-Learning Framework for Fast Exploration of Quantized Neural Networks
  • Blott, Michaela; Preußer, Thomas B.; Fraser, Nicholas J.
  • ACM Transactions on Reconfigurable Technology and Systems, Vol. 11, Issue 3 https://doi.org/10.1145/3242897
journal December 2018
Machine learning-based longitudinal phase space prediction of particle accelerators journal November 2018
FPGA-Based Accelerators of Deep Learning Networks for Learning and Classification: A Review journal January 2019
On the Theory of Dynamic Programming journal August 1952
Surrogate modeling of the CLIC final-focus system using artificial neural networks journal May 2021
Overview and Approach journal November 2018
Playing Atari with Deep Reinforcement Learning preprint January 2013
Resonant Frequency Control For the PIP-II Injector Test RFQ: Control Framework and Initial Results preprint January 2016
First Steps Toward Incorporating Image Based Diagnostics Into Particle Accelerator Control Systems Using Convolutional Neural Networks preprint January 2016
Neural Network Model Of The PXIE RFQ Cooling System and Resonant Frequency Response preprint January 2016
Hindsight Experience Replay preprint January 2017
Bayesian optimization of a free-electron laser text January 2019
Accelerating Machine Learning for Machine Physics (an AMALEA-project at KIT) text January 2020
BOOSTR: A Dataset for Accelerator Control Systems (Partial Release 2020) dataset January 2020

Similar Records

Related Subjects

43 PARTICLE ACCELERATORS
artification intelligence
accelerator control
reinforcement learning
surrogate model
LSTM
DQN
machine learning
neural network
FPGA
artificial intelligence