Machine-learning approach for operating electron beam at KEK $e^-/e^+$ injector Linac

In current accelerators, numerous parameters and monitored values are to be adjusted and evaluated, respectively. In addition, fine adjustments are required to achieve the target performance. Therefore, the conventional accelerator-operation method, in which experts manually adjust the parameters, i...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mitsuka, Gaku, Kato, Shinnosuke, Iida, Naoko, Natsui, Takuya, Satoh, Masanori
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Mitsuka, Gaku
Kato, Shinnosuke
Iida, Naoko
Natsui, Takuya
Satoh, Masanori
description In current accelerators, numerous parameters and monitored values are to be adjusted and evaluated, respectively. In addition, fine adjustments are required to achieve the target performance. Therefore, the conventional accelerator-operation method, in which experts manually adjust the parameters, is reaching its limits. We are currently investigating the use of machine learning for accelerator tuning as an alternative to expert-based tuning. In recent years, machine-learning algorithms have progressed significantly in terms of speed, sensitivity, and application range. In addition, various libraries are available from different vendors and are relatively easy to use. Herein, we report the results of electron-beam tuning experiments using Bayesian optimization, a tree-structured Parzen estimator, and a covariance matrix-adaptation evolution strategy. Beam-tuning experiments are performed at the KEK $e^-$/$e^+$ injector Linac to maximize the electron-beam charge and reduce the energy-dispersion function. In each case, the performance achieved is comparable to that of a skilled expert.
doi_str_mv 10.48550/arxiv.2401.14739
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2401_14739</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2401_14739</sourcerecordid><originalsourceid>FETCH-LOGICAL-a679-b3f69aa92c7f4d973cb4d6a396dc072dc0ed7ddc4bf5855324246b545ce918d83</originalsourceid><addsrcrecordid>eNotjz1PwzAQhr0woMIPYMJDN-Q0iR07HlFVPtQglrI2OttnMEqdyEQI_j1uy3InPa_e0z2E3FRlIdqmKVeQfsJ3UYuyKiqhuL4kby9gP0JENiCkGOI7hWlKY4bUj4mOEyaYjxgHtHMaIzUIBwoz3W62dIl7tsL93ZKG-Jnz3OhCBHtFLjwMX3j9vxdk97DZrZ9Y9_r4vL7vGEilmeFeagBdW-WF04pbI5wErqWzparzQKecs8L4Jr_Pa1ELaRrRWNRV61q-ILfnsyevfkrhAOm3P_r1Jz_-B04wSmA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Machine-learning approach for operating electron beam at KEK $e^-/e^+$ injector Linac</title><source>arXiv.org</source><creator>Mitsuka, Gaku ; Kato, Shinnosuke ; Iida, Naoko ; Natsui, Takuya ; Satoh, Masanori</creator><creatorcontrib>Mitsuka, Gaku ; Kato, Shinnosuke ; Iida, Naoko ; Natsui, Takuya ; Satoh, Masanori</creatorcontrib><description>In current accelerators, numerous parameters and monitored values are to be adjusted and evaluated, respectively. In addition, fine adjustments are required to achieve the target performance. Therefore, the conventional accelerator-operation method, in which experts manually adjust the parameters, is reaching its limits. We are currently investigating the use of machine learning for accelerator tuning as an alternative to expert-based tuning. In recent years, machine-learning algorithms have progressed significantly in terms of speed, sensitivity, and application range. In addition, various libraries are available from different vendors and are relatively easy to use. Herein, we report the results of electron-beam tuning experiments using Bayesian optimization, a tree-structured Parzen estimator, and a covariance matrix-adaptation evolution strategy. Beam-tuning experiments are performed at the KEK $e^-$/$e^+$ injector Linac to maximize the electron-beam charge and reduce the energy-dispersion function. In each case, the performance achieved is comparable to that of a skilled expert.</description><identifier>DOI: 10.48550/arxiv.2401.14739</identifier><language>eng</language><subject>Physics - Accelerator Physics</subject><creationdate>2024-01</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2401.14739$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2401.14739$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Mitsuka, Gaku</creatorcontrib><creatorcontrib>Kato, Shinnosuke</creatorcontrib><creatorcontrib>Iida, Naoko</creatorcontrib><creatorcontrib>Natsui, Takuya</creatorcontrib><creatorcontrib>Satoh, Masanori</creatorcontrib><title>Machine-learning approach for operating electron beam at KEK $e^-/e^+$ injector Linac</title><description>In current accelerators, numerous parameters and monitored values are to be adjusted and evaluated, respectively. In addition, fine adjustments are required to achieve the target performance. Therefore, the conventional accelerator-operation method, in which experts manually adjust the parameters, is reaching its limits. We are currently investigating the use of machine learning for accelerator tuning as an alternative to expert-based tuning. In recent years, machine-learning algorithms have progressed significantly in terms of speed, sensitivity, and application range. In addition, various libraries are available from different vendors and are relatively easy to use. Herein, we report the results of electron-beam tuning experiments using Bayesian optimization, a tree-structured Parzen estimator, and a covariance matrix-adaptation evolution strategy. Beam-tuning experiments are performed at the KEK $e^-$/$e^+$ injector Linac to maximize the electron-beam charge and reduce the energy-dispersion function. In each case, the performance achieved is comparable to that of a skilled expert.</description><subject>Physics - Accelerator Physics</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotjz1PwzAQhr0woMIPYMJDN-Q0iR07HlFVPtQglrI2OttnMEqdyEQI_j1uy3InPa_e0z2E3FRlIdqmKVeQfsJ3UYuyKiqhuL4kby9gP0JENiCkGOI7hWlKY4bUj4mOEyaYjxgHtHMaIzUIBwoz3W62dIl7tsL93ZKG-Jnz3OhCBHtFLjwMX3j9vxdk97DZrZ9Y9_r4vL7vGEilmeFeagBdW-WF04pbI5wErqWzparzQKecs8L4Jr_Pa1ELaRrRWNRV61q-ILfnsyevfkrhAOm3P_r1Jz_-B04wSmA</recordid><startdate>20240126</startdate><enddate>20240126</enddate><creator>Mitsuka, Gaku</creator><creator>Kato, Shinnosuke</creator><creator>Iida, Naoko</creator><creator>Natsui, Takuya</creator><creator>Satoh, Masanori</creator><scope>GOX</scope></search><sort><creationdate>20240126</creationdate><title>Machine-learning approach for operating electron beam at KEK $e^-/e^+$ injector Linac</title><author>Mitsuka, Gaku ; Kato, Shinnosuke ; Iida, Naoko ; Natsui, Takuya ; Satoh, Masanori</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a679-b3f69aa92c7f4d973cb4d6a396dc072dc0ed7ddc4bf5855324246b545ce918d83</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Physics - Accelerator Physics</topic><toplevel>online_resources</toplevel><creatorcontrib>Mitsuka, Gaku</creatorcontrib><creatorcontrib>Kato, Shinnosuke</creatorcontrib><creatorcontrib>Iida, Naoko</creatorcontrib><creatorcontrib>Natsui, Takuya</creatorcontrib><creatorcontrib>Satoh, Masanori</creatorcontrib><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Mitsuka, Gaku</au><au>Kato, Shinnosuke</au><au>Iida, Naoko</au><au>Natsui, Takuya</au><au>Satoh, Masanori</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Machine-learning approach for operating electron beam at KEK $e^-/e^+$ injector Linac</atitle><date>2024-01-26</date><risdate>2024</risdate><abstract>In current accelerators, numerous parameters and monitored values are to be adjusted and evaluated, respectively. In addition, fine adjustments are required to achieve the target performance. Therefore, the conventional accelerator-operation method, in which experts manually adjust the parameters, is reaching its limits. We are currently investigating the use of machine learning for accelerator tuning as an alternative to expert-based tuning. In recent years, machine-learning algorithms have progressed significantly in terms of speed, sensitivity, and application range. In addition, various libraries are available from different vendors and are relatively easy to use. Herein, we report the results of electron-beam tuning experiments using Bayesian optimization, a tree-structured Parzen estimator, and a covariance matrix-adaptation evolution strategy. Beam-tuning experiments are performed at the KEK $e^-$/$e^+$ injector Linac to maximize the electron-beam charge and reduce the energy-dispersion function. In each case, the performance achieved is comparable to that of a skilled expert.</abstract><doi>10.48550/arxiv.2401.14739</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2401.14739
ispartof
issn
language eng
recordid cdi_arxiv_primary_2401_14739
source arXiv.org
subjects Physics - Accelerator Physics
title Machine-learning approach for operating electron beam at KEK $e^-/e^+$ injector Linac
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T12%3A51%3A06IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Machine-learning%20approach%20for%20operating%20electron%20beam%20at%20KEK%20$e%5E-/e%5E+$%20injector%20Linac&rft.au=Mitsuka,%20Gaku&rft.date=2024-01-26&rft_id=info:doi/10.48550/arxiv.2401.14739&rft_dat=%3Carxiv_GOX%3E2401_14739%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true