Поиск :
Личный кабинет :
Электронный каталог: Lyapin, I. D. - Machine Learning for Cyclotron Magnetic Field Isochronization
Lyapin, I. D. - Machine Learning for Cyclotron Magnetic Field Isochronization

Статья
Автор: Lyapin, I. D.
Физика элементарных частиц и атомного ядра: Machine Learning for Cyclotron Magnetic Field Isochronization : Abstract
б.г.
ISBN отсутствует
Автор: Lyapin, I. D.
Физика элементарных частиц и атомного ядра: Machine Learning for Cyclotron Magnetic Field Isochronization : Abstract
б.г.
ISBN отсутствует
Статья
Lyapin, I.D.
Machine Learning for Cyclotron Magnetic Field Isochronization : Abstract / I.D.Lyapin, O.V.Karamyshev // Физика элементарных частиц и атомного ядра : пер. с англ. – 2025. – Т. 56, № 6. – P. 1973. – URL: https://www1.jinr.ru/Pepan/v-56-6/Lyapin.pdf. – We explore the application of machine learning techniques to the isochronization of the magnetic field in the MSC-230 isochronous cyclotron. The primary objective is to reduce the computational effort typically required for adjusting the magnet’s geometry in order to achieve isochronicity. By predicting the necessary modifications to the magnet’s geometry, our approach aims to streamline the iterative process. We compare several machine learning models against traditional methods, demonstrating their potential to reduce the number of iterations needed.
Спец.(статьи,препринты) = С 345 а - Общие сведения о проектируемых и действующих ускорителях
ОИЯИ = ОИЯИ (JINR)2025
Lyapin, I.D.
Machine Learning for Cyclotron Magnetic Field Isochronization : Abstract / I.D.Lyapin, O.V.Karamyshev // Физика элементарных частиц и атомного ядра : пер. с англ. – 2025. – Т. 56, № 6. – P. 1973. – URL: https://www1.jinr.ru/Pepan/v-56-6/Lyapin.pdf. – We explore the application of machine learning techniques to the isochronization of the magnetic field in the MSC-230 isochronous cyclotron. The primary objective is to reduce the computational effort typically required for adjusting the magnet’s geometry in order to achieve isochronicity. By predicting the necessary modifications to the magnet’s geometry, our approach aims to streamline the iterative process. We compare several machine learning models against traditional methods, demonstrating their potential to reduce the number of iterations needed.
Спец.(статьи,препринты) = С 345 а - Общие сведения о проектируемых и действующих ускорителях
ОИЯИ = ОИЯИ (JINR)2025
На полку