ICALEPCS2017 - List of Keywords (extraction)

Paper	Title	Other Keywords	Page
TUCPA03	Experience with Machine Learning in Accelerator Controls	ion, network, controls, framework	258
	K.A. Brown, S. Binello, T. D'Ottavio, P.S. Dyer, S. Nemesure, D.J. Thomas BNL, Upton, Long Island, New York, USA
	Funding: Work supported by Brookhaven Science Associates, LLC under Contract No. DE-SC0012704 with the U.S. Department of Energy. The repository of data for the Relativistic Heavy Ion Collider and associated pre-injector accelerators consists of well over half a petabyte of uncompressed data. By todays standard, this is not a large amount of data. However, a large fraction of that data has never been analyzed and likely contains useful information. We will describe in this paper our efforts to use machine learning techniques to pull out new information from existing data. Our focus has been to look at simple problems, such as associating basic statistics on certain data sets and doing predictive analysis on single array data. The tools we have tested include unsupervised learning using Tensorflow, multimode neural networks, hierarchical temporal memory techniques using NuPic, as well as deep learning techniques using Theano and Keras.
	Slides TUCPA03 [6.658 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-TUCPA03
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

TUPHA199	Software Applications Used at the REX/HIE-ISOLDE Linac	ion, ISOL, detector, cavity	910
	E. Fadakis, N. Bidault, E.O. Gonzalez, M.L. Lozano Benito, E. Matli, J.A. Rodriguez, S. Sadovich, E. Siesling CERN, Geneva, Switzerland
	The HIE-ISOLDE Linac (High Intensity and Energy) is a recent upgrade to the ISOLDE facility of CERN, increasing the maximum beam energy and providing means to explore more scientific opportunities. The main software tools required to set up the new superconducting post-accelerator and to characterise the beam provided to the experimental stations will be presented in this paper. Emphasis will be given to the suite of applications to control all beam instrumentation equipment which are more complex compared to the ones in the low energy part of ISOLDE. A variety of devices are used (Faraday cups, collimators, scanning slits, striping foils and silicon detectors). Each serves its own purpose and provides different information concerning the beam characteristics. Every group of devices required a specific approach to be programmed.
	Poster TUPHA199 [0.940 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-TUPHA199
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

THPHA122	Optimization and Upgrade of Slow Extraction Control System for HIRFL CSR Main Ring	ion, controls, feedback, database	1663
	Y.C. Chen Chen Yucong, ChengGuan, People's Republic of China J.M. Dong, Y.C. Feng, M. Li, S. Li, W.L. Li, R.S. Mao, J. Shi, T.C. Zhao IMP/CAS, Lanzhou, People's Republic of China
	The heavy ion beam from Heavy Ion Research Facility in Lanzhou (HIRFL) CSR Main Ring (CSRm) is slowly extracted by using a third-order resonance driven by sextupole magnets and delivered to various experimental facilities. The slow extraction is driven by the transverse radio frequency knockout (RF-KO) exciter. Many physics and radiation medicine experiments require high-quality spill-structure. In other words, the extracted spill should have flat structure and low ripple noise [1]. Therefore, a novel RF-KO exciter and spill feedback control system has been implemented and tested in CSRm. [1] Onuma S, Ichikawa T, Mochiki K I, et al. DEVELOPMENT OF SPILL CONTROL SYSTEM FOR THE J-PARC SLOW EXTRACTION[J]. Proceedings of Pac, 2009.
	Poster THPHA122 [1.376 MB]
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-THPHA122
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

Paper

Title

Other Keywords

Page

TUCPA03

Experience with Machine Learning in Accelerator Controls

ion, network, controls, framework

258

K.A. Brown, S. Binello, T. D'Ottavio, P.S. Dyer, S. Nemesure, D.J. Thomas
BNL, Upton, Long Island, New York, USA

Funding: Work supported by Brookhaven Science Associates, LLC under Contract No. DE-SC0012704 with the U.S. Department of Energy.
The repository of data for the Relativistic Heavy Ion Collider and associated pre-injector accelerators consists of well over half a petabyte of uncompressed data. By todays standard, this is not a large amount of data. However, a large fraction of that data has never been analyzed and likely contains useful information. We will describe in this paper our efforts to use machine learning techniques to pull out new information from existing data. Our focus has been to look at simple problems, such as associating basic statistics on certain data sets and doing predictive analysis on single array data. The tools we have tested include unsupervised learning using Tensorflow, multimode neural networks, hierarchical temporal memory techniques using NuPic, as well as deep learning techniques using Theano and Keras.

Slides TUCPA03 [6.658 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-TUCPA03

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

TUPHA199

Software Applications Used at the REX/HIE-ISOLDE Linac

ion, ISOL, detector, cavity

910

E. Fadakis, N. Bidault, E.O. Gonzalez, M.L. Lozano Benito, E. Matli, J.A. Rodriguez, S. Sadovich, E. Siesling
CERN, Geneva, Switzerland

The HIE-ISOLDE Linac (High Intensity and Energy) is a recent upgrade to the ISOLDE facility of CERN, increasing the maximum beam energy and providing means to explore more scientific opportunities. The main software tools required to set up the new superconducting post-accelerator and to characterise the beam provided to the experimental stations will be presented in this paper. Emphasis will be given to the suite of applications to control all beam instrumentation equipment which are more complex compared to the ones in the low energy part of ISOLDE. A variety of devices are used (Faraday cups, collimators, scanning slits, striping foils and silicon detectors). Each serves its own purpose and provides different information concerning the beam characteristics. Every group of devices required a specific approach to be programmed.

Poster TUPHA199 [0.940 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-TUPHA199

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

THPHA122

Optimization and Upgrade of Slow Extraction Control System for HIRFL CSR Main Ring

ion, controls, feedback, database

1663

Y.C. Chen
Chen Yucong, ChengGuan, People's Republic of China
J.M. Dong, Y.C. Feng, M. Li, S. Li, W.L. Li, R.S. Mao, J. Shi, T.C. Zhao
IMP/CAS, Lanzhou, People's Republic of China

The heavy ion beam from Heavy Ion Research Facility in Lanzhou (HIRFL) CSR Main Ring (CSRm) is slowly extracted by using a third-order resonance driven by sextupole magnets and delivered to various experimental facilities. The slow extraction is driven by the transverse radio frequency knockout (RF-KO) exciter. Many physics and radiation medicine experiments require high-quality spill-structure. In other words, the extracted spill should have flat structure and low ripple noise [1]. Therefore, a novel RF-KO exciter and spill feedback control system has been implemented and tested in CSRm.
[1] Onuma S, Ichikawa T, Mochiki K I, et al. DEVELOPMENT OF SPILL CONTROL SYSTEM FOR THE J-PARC SLOW EXTRACTION[J]. Proceedings of Pac, 2009.

Poster THPHA122 [1.376 MB]

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-ICALEPCS2017-THPHA122

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)