DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Genetic algorithm enhanced by machine learning in dynamic aperture optimization

Abstract

With the aid of machine learning techniques, the genetic algorithm has been enhanced and applied to the multi-objective optimization problem presented by the dynamic aperture of the National Synchrotron Light Source II (NSLS-II) Storage Ring. During the evolution processes employed by the genetic algorithm, the population is classified into different clusters in the search space. The clusters with top average fitness are given “elite” status. Intervention on the population is implemented by repopulating some potentially competitive candidates based on the experience learned from the accumulated data. These candidates replace randomly selected candidates among the original data pool. The average fitness of the population is therefore improved while diversity is not lost. Maintaining diversity ensures that the optimization is global rather than local. The quality of the population increases and produces more competitive descendants accelerating the evolution process significantly. When identifying the distribution of optimal candidates, they appear to be located in isolated islands within the search space. Some of these optimal candidates have been experimentally confirmed at the NSLS-II storage ring. Furthermore, the machine learning techniques that exploit the genetic algorithm can also be used in other population-based optimization problems such as particle swarm algorithm.

Authors:
; ; ;
Publication Date:
Research Org.:
Brookhaven National Lab. (BNL), Upton, NY (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES)
OSTI Identifier:
1439379
Alternate Identifier(s):
OSTI ID: 1439451
Report Number(s):
BNL-205720-2018-JAAM
Journal ID: ISSN 2469-9888; PRABCJ; 054601
Grant/Contract Number:  
SC0012704
Resource Type:
Published Article
Journal Name:
Physical Review Accelerators and Beams
Additional Journal Information:
Journal Name: Physical Review Accelerators and Beams Journal Volume: 21 Journal Issue: 5; Journal ID: ISSN 2469-9888
Publisher:
American Physical Society
Country of Publication:
United States
Language:
English
Subject:
43 PARTICLE ACCELERATORS

Citation Formats

Li, Yongjun, Cheng, Weixing, Yu, Li Hua, and Rainer, Robert. Genetic algorithm enhanced by machine learning in dynamic aperture optimization. United States: N. p., 2018. Web. doi:10.1103/PhysRevAccelBeams.21.054601.
Li, Yongjun, Cheng, Weixing, Yu, Li Hua, & Rainer, Robert. Genetic algorithm enhanced by machine learning in dynamic aperture optimization. United States. https://doi.org/10.1103/PhysRevAccelBeams.21.054601
Li, Yongjun, Cheng, Weixing, Yu, Li Hua, and Rainer, Robert. Tue . "Genetic algorithm enhanced by machine learning in dynamic aperture optimization". United States. https://doi.org/10.1103/PhysRevAccelBeams.21.054601.
@article{osti_1439379,
title = {Genetic algorithm enhanced by machine learning in dynamic aperture optimization},
author = {Li, Yongjun and Cheng, Weixing and Yu, Li Hua and Rainer, Robert},
abstractNote = {With the aid of machine learning techniques, the genetic algorithm has been enhanced and applied to the multi-objective optimization problem presented by the dynamic aperture of the National Synchrotron Light Source II (NSLS-II) Storage Ring. During the evolution processes employed by the genetic algorithm, the population is classified into different clusters in the search space. The clusters with top average fitness are given “elite” status. Intervention on the population is implemented by repopulating some potentially competitive candidates based on the experience learned from the accumulated data. These candidates replace randomly selected candidates among the original data pool. The average fitness of the population is therefore improved while diversity is not lost. Maintaining diversity ensures that the optimization is global rather than local. The quality of the population increases and produces more competitive descendants accelerating the evolution process significantly. When identifying the distribution of optimal candidates, they appear to be located in isolated islands within the search space. Some of these optimal candidates have been experimentally confirmed at the NSLS-II storage ring. Furthermore, the machine learning techniques that exploit the genetic algorithm can also be used in other population-based optimization problems such as particle swarm algorithm.},
doi = {10.1103/PhysRevAccelBeams.21.054601},
journal = {Physical Review Accelerators and Beams},
number = 5,
volume = 21,
place = {United States},
year = {Tue May 29 00:00:00 EDT 2018},
month = {Tue May 29 00:00:00 EDT 2018}
}

Journal Article:
Free Publicly Available Full Text

Citation Metrics:
Cited by: 24 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Nonlinear dynamics optimization with particle swarm and genetic algorithms for SPEAR3 emittance upgrade
journal, September 2014

  • Huang, Xiaobiao; Safranek, James
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 757
  • DOI: 10.1016/j.nima.2014.04.078

Simultaneous optimization of the cavity heat load and trip rates in linacs using a genetic algorithm
journal, October 2014

  • Terzić, Balša; Hofler, Alicia S.; Reeves, Cody J.
  • Physical Review Special Topics - Accelerators and Beams, Vol. 17, Issue 10
  • DOI: 10.1103/PhysRevSTAB.17.101003

Transverse beam splitting made operational: Key features of the multiturn extraction at the CERN Proton Synchrotron
journal, June 2017


Online optimization of storage ring nonlinear beam dynamics
journal, August 2015


Multiobjective optimization of dynamic aperture
journal, May 2011

  • Yang, Lingyun; Li, Yongjun; Guo, Weiming
  • Physical Review Special Topics - Accelerators and Beams, Vol. 14, Issue 5
  • DOI: 10.1103/PhysRevSTAB.14.054001

Simultaneous optimization of beam emittance and dynamic aperture for electron storage ring using genetic algorithm
journal, September 2011

  • Gao, Weiwei; Wang, Lin; Li, Weimin
  • Physical Review Special Topics - Accelerators and Beams, Vol. 14, Issue 9
  • DOI: 10.1103/PhysRevSTAB.14.094001

Small-emittance and low-beta lattice designs and optimizations
journal, May 2012

  • Sun, C.; Robin, D. S.; Nishimura, H.
  • Physical Review Special Topics - Accelerators and Beams, Vol. 15, Issue 5
  • DOI: 10.1103/PhysRevSTAB.15.054001

Multiobjective optimization design of an rf gun based electron diffraction beam line
journal, March 2017


Multivariate optimization of a high brightness dc gun photoinjector
journal, March 2005

  • Bazarov, Ivan V.; Sinclair, Charles K.
  • Physical Review Special Topics - Accelerators and Beams, Vol. 8, Issue 3
  • DOI: 10.1103/PhysRevSTAB.8.034202

Transparent lattice characterization with gated turn-by-turn data of diagnostic bunch train
journal, November 2017


Innovative applications of genetic algorithms to problems in accelerator physics
journal, January 2013

  • Hofler, Alicia; Terzić, Balša; Kramer, Matthew
  • Physical Review Special Topics - Accelerators and Beams, Vol. 16, Issue 1
  • DOI: 10.1103/PhysRevSTAB.16.010101

Multi-objective dynamic aperture optimization for storage rings
journal, November 2016


Particle trapping during passage through a high-order nonlinear resonance
journal, October 1974


Global optimization of an accelerator lattice using multiobjective genetic algorithms
journal, October 2009

  • Yang, Lingyun; Robin, David; Sannibale, Fernando
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 609, Issue 1
  • DOI: 10.1016/j.nima.2009.08.027

Design of low energy bunch compressors with space charge effects
journal, January 2015


Construction of higher order symplectic integrators
journal, November 1990


Pseudo-Single-Bunch with Adjustable Frequency: A New Operation Mode for Synchrotron Light Sources
journal, December 2012


Multiobjective genetic algorithm optimization of the beam dynamics in linac drivers for free electron lasers
journal, March 2012

  • Bartolini, R.; Apollonio, M.; Martin, I. P. S.
  • Physical Review Special Topics - Accelerators and Beams, Vol. 15, Issue 3
  • DOI: 10.1103/PhysRevSTAB.15.030701

Techniques for transparent lattice measurement and correction
journal, July 2017


Analysis of nonlinear dynamics by square matrix method
journal, March 2017


Global Dynamics of the Advanced Light Source Revealed through Experimental Frequency Map Analysis
journal, July 2000


Multiobjective optimizations of a novel cryocooled dc gun based ultrafast electron diffraction beam line
journal, September 2016


Genetic algorithm for chromaticity correction in diffraction limited storage rings
journal, April 2016


A fast and elitist multiobjective genetic algorithm: NSGA-II
journal, April 2002

  • Deb, K.; Pratap, A.; Agarwal, S.
  • IEEE Transactions on Evolutionary Computation, Vol. 6, Issue 2
  • DOI: 10.1109/4235.996017

Machine based optimization using genetic algorithms in a storage ring
journal, February 2014


Works referencing / citing this record:

FCC-ee: The Lepton Collider: Future Circular Collider Conceptual Design Report Volume 2
journal, June 2019

  • Abada, A.; Abbrescia, M.; AbdusSalam, S. S.
  • The European Physical Journal Special Topics, Vol. 228, Issue 2
  • DOI: 10.1140/epjst/e2019-900045-4

FCC-ee: The Lepton Collider
text, January 2019

  • Abada, A.; Abbrescia, M.; AbdusSalam, S. S.
  • Deutsches Elektronen-Synchrotron, DESY, Hamburg
  • DOI: 10.3204/pubdb-2019-02730

FCC-ee: The Lepton Collider: Future Circular Collider Conceptual Design Report Volume 2
journal, June 2019

  • Abada, A.; Abbrescia, M.; AbdusSalam, S. S.
  • The European Physical Journal Special Topics, Vol. 228, Issue 2
  • DOI: 10.1140/epjst/e2019-900045-4

Convolutional neural networks for grazing incidence x-ray scattering patterns: thin film structure identification
journal, March 2019

  • Liu, Shuai; Melton, Charles N.; Venkatakrishnan, Singanallur
  • MRS Communications, Vol. 9, Issue 02
  • DOI: 10.1557/mrc.2019.26