The Joint Accelerator Conferences Website (JACoW) is an international collaboration that publishes the proceedings of accelerator conferences held around the world.
TY - CONF AU - Li, Y. AU - Cheng, W.X. AU - Rainer, R.S. AU - Yu, L. ED - Schaa, Volker RW ED - Makino, Kyoko ED - Snopok, Pavel ED - Berz, Martin TI - Genetic Algorithm Enhanced by Machine Learning in Dynamic Aperture Optimization J2 - Proc. of ICAP2018, Key West, FL, USA, 20-24 October 2018 CY - Key West, FL, USA T2 - International Computational Accelerator Physics Conference T3 - 13 LA - english AB - 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 NSLS-II Ring. During the evolution employed by the genetic algorithm, the population is classified into different clusters. The clusters with top average fitness are given elite status. Intervention is implemented by repopulating some potentially competitive candidates based on the accumulated data. These candidates replace randomly selected candidates among the original data pool. The average fitness of the population is improved while diversity is not lost. 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. The machine learning techniques that exploit the genetic algorithm can also be used in other population-based optimization problems such as particle swarm algorithm. PB - JACoW Publishing CP - Geneva, Switzerland SP - 8 EP - 14 KW - dynamic-aperture KW - lattice KW - sextupole KW - storage-ring KW - resonance DA - 2019/01 PY - 2019 SN - 978-3-95450-200-4 DO - DOI: 10.18429/JACoW-ICAP2018-SAPAF01 UR - http://jacow.org/icap2018/papers/sapaf01.pdf ER -