Use of Plasma Information in Machine-Learning-Based Fault Detection and Classification for Advanced Equipment Control

For advanced equipment control, two schemata of real-time fault detection were performed using machine learning algorithms in silicon etching in SF 6 /O 2 /Ar plasma. Fault detection and classification is investigated with the plasma state information with optical emission spectroscopy (OES) data to...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on semiconductor manufacturing Ročník 34; číslo 3; s. 408 - 419
Hlavní autori:	Kim, Dong Hwan, Hong, Sang Jeen
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	New York IEEE 01.08.2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Abnormalities advanced equipment control Algorithms Argon plasma Classification Classification algorithms Control equipment data mining Electron density Electron energy Emission analysis Etching Fault detection FDC Flow velocity Gas flow Machine learning Machine learning algorithms Mathematical models Optical emission spectroscopy Parameter identification Plasma plasma information (PI) Plasmas Prediction algorithms Process control Process parameters Real time Real-time systems Root cause analysis
ISSN:	0894-6507, 1558-2345
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	For advanced equipment control, two schemata of real-time fault detection were performed using machine learning algorithms in silicon etching in SF 6 /O 2 /Ar plasma. Fault detection and classification is investigated with the plasma state information with optical emission spectroscopy (OES) data to find the root cause of the anomaly in the process parameters. Fault detection and control is also demonstrated to predict the shift of the process parameter along the amount of process gas flow rate injected into the chamber, considering a fault. Especially, plasma information (PI), such as electron temperature and electron density, was derived from OES data into equation-based corona model. These were utilized to evaluate which process parameter is the most significantly affecting on the performance of the established model through Shapley value in fault detection and control. By the combination of isolation forest algorithm for finding the plasma abnormalities in real time and Adaboost algorithm for classifying root causes of faults, the suggested algorithm could accurately detect the root cause. DeepSHAP algorithm helped not only the prediction of gas flow rate, but PI was identified as critical parameter, interpreting the model through Shapley value. We propose a new multi-function integrated algorithm by the ensemble algorithms.
AbstractList	For advanced equipment control, two schemata of real-time fault detection were performed using machine learning algorithms in silicon etching in SF6/O2/Ar plasma. Fault detection and classification is investigated with the plasma state information with optical emission spectroscopy (OES) data to find the root cause of the anomaly in the process parameters. Fault detection and control is also demonstrated to predict the shift of the process parameter along the amount of process gas flow rate injected into the chamber, considering a fault. Especially, plasma information (PI), such as electron temperature and electron density, was derived from OES data into equation-based corona model. These were utilized to evaluate which process parameter is the most significantly affecting on the performance of the established model through Shapley value in fault detection and control. By the combination of isolation forest algorithm for finding the plasma abnormalities in real time and Adaboost algorithm for classifying root causes of faults, the suggested algorithm could accurately detect the root cause. DeepSHAP algorithm helped not only the prediction of gas flow rate, but PI was identified as critical parameter, interpreting the model through Shapley value. We propose a new multi-function integrated algorithm by the ensemble algorithms. For advanced equipment control, two schemata of real-time fault detection were performed using machine learning algorithms in silicon etching in SF 6 /O 2 /Ar plasma. Fault detection and classification is investigated with the plasma state information with optical emission spectroscopy (OES) data to find the root cause of the anomaly in the process parameters. Fault detection and control is also demonstrated to predict the shift of the process parameter along the amount of process gas flow rate injected into the chamber, considering a fault. Especially, plasma information (PI), such as electron temperature and electron density, was derived from OES data into equation-based corona model. These were utilized to evaluate which process parameter is the most significantly affecting on the performance of the established model through Shapley value in fault detection and control. By the combination of isolation forest algorithm for finding the plasma abnormalities in real time and Adaboost algorithm for classifying root causes of faults, the suggested algorithm could accurately detect the root cause. DeepSHAP algorithm helped not only the prediction of gas flow rate, but PI was identified as critical parameter, interpreting the model through Shapley value. We propose a new multi-function integrated algorithm by the ensemble algorithms.
Author	Hong, Sang Jeen Kim, Dong Hwan
Author_xml	– sequence: 1 givenname: Dong Hwan orcidid: 0000-0002-3023-6327 surname: Kim fullname: Kim, Dong Hwan email: vbbo7880@naver.com organization: Department of Electronics Engineering, Myongji University, Yongin, South Korea – sequence: 2 givenname: Sang Jeen orcidid: 0000-0002-6576-690X surname: Hong fullname: Hong, Sang Jeen email: samhong@mju.ac.kr organization: Department of Electronics Engineering, Myongji University, Yongin, South Korea
BookMark	eNp9kE1PGzEQhi0EEiFwR-JiqecN_tr1-pimBJCCigScV17vmDra2MH2Vuq_xxDUQw-9zFye5x3Ne4aOffCA0CUlC0qJun5-elgwwuiCE6kYpUdoRuu6rRgX9TGakVaJqqmJPEVnKW0JoUIoOUPTSwIcLH4cddppfO9tiDudXfDYefygzS_nodqAjt751-q7TjDgtZ7GjH9ABvNJaj_gVQlIzjpzkEsMXg6_tTeFv3mb3H4HPuNV8DmG8RydWD0muPjac_Syvnle3VWbn7f3q-WmMryWuRKmsZayQZG-MX0_GMbLJJKD4loyo1UvCtBY4NCKhoJmrBXM9tC2xAySz9G3Q-4-hrcJUu62YYq-nOxYXUslFReqUM2BMjGkFMF2xuXPN3LUbuwo6T4q7krF3UfF3VfFRST_iPvodjr--Z9ydVAcAPzFlWBSKcHfAYW0ioY
CODEN	ITSMED
CitedBy_id	crossref_primary_10_1109_TSM_2022_3161512 crossref_primary_10_35848_1347_4065_adc938 crossref_primary_10_1016_j_fusengdes_2024_114675 crossref_primary_10_1088_1361_6595_ad80c6 crossref_primary_10_1109_ACCESS_2024_3432174 crossref_primary_10_3390_coatings13030559 crossref_primary_10_3390_s23041889 crossref_primary_10_5757_ASCT_2024_33_6_181 crossref_primary_10_1088_1361_6463_ad2339 crossref_primary_10_1109_TSM_2023_3314431 crossref_primary_10_3390_app14010355 crossref_primary_10_1088_1361_6463_ad6ba1 crossref_primary_10_3390_electronics11020253 crossref_primary_10_1016_j_ymssp_2024_111948 crossref_primary_10_1116_6_0003434 crossref_primary_10_1088_1361_6501_acf77a crossref_primary_10_1109_TSM_2023_3248273 crossref_primary_10_1063_5_0160228 crossref_primary_10_1109_TPS_2023_3268170 crossref_primary_10_1109_TSM_2022_3170270 crossref_primary_10_1109_TSM_2023_3238555
Cites_doi	10.1080/18756891.2014.947114 10.1088/0022-3727/43/40/403001 10.1109/ASMC49169.2020.9185331 10.1016/j.vacuum.2007.07.016 10.1088/0022-3727/37/12/R01 10.1016/j.lwt.2014.02.031 10.1016/j.patcog.2012.07.027 10.1103/PhysRevE.55.3450 10.1016/j.saa.2020.118629 10.1109/TSM.2011.2175394 10.1029/2010GL044544 10.1109/ICDM.2008.17 10.1088/0963-0252/24/6/064003 10.1080/10170669.2012.702135 10.1109/TSM.2019.2931328 10.3938/jkps.65.168 10.1109/TSM.2004.831952 10.1109/TBCAS.2015.2500101 10.1109/TSM.2018.2824314 10.1103/PhysRevE.60.6016 10.1109/TIM.2011.2122430 10.1088/0022-3727/42/2/025203 10.1109/TSM.2009.2028215 10.1145/3331184.3331312 10.1016/j.engappai.2017.09.021 10.4310/SII.2009.v2.n3.a8 10.1109/TSM.2016.2602226 10.1016/j.compchemeng.2017.02.009 10.1063/1.4802252 10.1201/9781420040661-7 10.1109/ASMC.2017.7969205 10.1109/TSM.2019.2938546
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID	97E RIA RIE AAYXX CITATION 7SP 7U5 8FD L7M
DOI	10.1109/TSM.2021.3079211
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library CrossRef Electronics & Communications Abstracts Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Solid State and Superconductivity Abstracts
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Economics Engineering
EISSN	1558-2345
EndPage	419
ExternalDocumentID	10_1109_TSM_2021_3079211 9427994
Genre	orig-research
GrantInformation_xml	– fundername: Korea Semiconductor Research Consortium (KSRC) Support Program for the development of the future semiconductor device – fundername: Korean Government (MOTIE) grantid: P0008458 – fundername: Ministry of Trade, Industry and Energy (MOTIE) grantid: K_G012000649902 funderid: 10.13039/501100003052 – fundername: Korea Institute of Advanced Technology (KIAT) Grant
GroupedDBID	-~X .DC 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P RIA RIE RNS TN5 VH1 AAYXX CITATION 7SP 7U5 8FD L7M
ID	FETCH-LOGICAL-c357t-4c6ff12d90b6cbbdc23bbd073e93a72ca9b4ff16fe3e8461ea22842fbe880cd73
IEDL.DBID	RIE
ISICitedReferencesCount	23
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000681129000034&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0894-6507
IngestDate	Sun Jun 29 12:31:57 EDT 2025 Sat Nov 29 05:13:42 EST 2025 Tue Nov 18 22:27:42 EST 2025 Wed Aug 27 02:39:34 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	3
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c357t-4c6ff12d90b6cbbdc23bbd073e93a72ca9b4ff16fe3e8461ea22842fbe880cd73
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-3023-6327 0000-0002-6576-690X
PQID	2557979349
PQPubID	85442
PageCount	12
ParticipantIDs	proquest_journals_2557979349 crossref_primary_10_1109_TSM_2021_3079211 ieee_primary_9427994 crossref_citationtrail_10_1109_TSM_2021_3079211
PublicationCentury	2000
PublicationDate	2021-08-01
PublicationDateYYYYMMDD	2021-08-01
PublicationDate_xml	– month: 08 year: 2021 text: 2021-08-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on semiconductor manufacturing
PublicationTitleAbbrev	TSM
PublicationYear	2021
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref34 ref12 lundberg (ref37) 2017 ref15 ref14 ref31 ref33 ref11 ref32 ref1 ref39 rostami (ref10) 2016 ref17 chen (ref38) 2019 ref16 ref19 ref18 freund (ref30) 1996 ref24 ref23 ref26 ref25 ref20 ref41 ref22 ref21 goodfellow (ref35) 2016 matsunawa (ref29) 2015; 9427 ref28 ref27 ref8 ref7 ref9 ref3 kim (ref4) 2017; 9 ref6 ref5 ref40 shrikumar (ref36) 2016 kerdprasop (ref2) 2011; 5
References_xml	– start-page: 8 year: 2016 ident: ref10 article-title: Equipment anomaly detection and automatic fault fingerprint extraction in semiconductor manufacturing publication-title: Proc Int Symp Semicond Manuf Intell – ident: ref24 doi: 10.1080/18756891.2014.947114 – year: 2016 ident: ref35 publication-title: Deep Learning – ident: ref22 doi: 10.1088/0022-3727/43/40/403001 – ident: ref11 doi: 10.1109/ASMC49169.2020.9185331 – ident: ref12 doi: 10.1016/j.vacuum.2007.07.016 – ident: ref20 doi: 10.1088/0022-3727/37/12/R01 – start-page: 148 year: 1996 ident: ref30 article-title: Experiments with a new boosting algorithm publication-title: Proc 13th Int Conf Mach Learn – year: 2016 ident: ref36 publication-title: Not just a black box Learning important features through propagating activation differences – ident: ref28 doi: 10.1016/j.lwt.2014.02.031 – volume: 9 start-page: 20 year: 2017 ident: ref4 article-title: Real-time fault detection in semiconductor manufacturing process: Research with jade solution company publication-title: International Journal of Internet Broadcasting and Communication – ident: ref27 doi: 10.1016/j.patcog.2012.07.027 – ident: ref16 doi: 10.1103/PhysRevE.55.3450 – ident: ref13 doi: 10.1016/j.saa.2020.118629 – ident: ref34 doi: 10.1109/TSM.2011.2175394 – ident: ref17 doi: 10.1029/2010GL044544 – ident: ref40 doi: 10.1109/ICDM.2008.17 – start-page: 261 year: 2019 ident: ref38 article-title: Explaining models by propagating Shapley values of local components publication-title: Explainable AI in Healthcare and Medicine – ident: ref14 doi: 10.1088/0963-0252/24/6/064003 – ident: ref8 doi: 10.1080/10170669.2012.702135 – ident: ref9 doi: 10.1109/TSM.2019.2931328 – ident: ref23 doi: 10.3938/jkps.65.168 – ident: ref33 doi: 10.1109/TSM.2004.831952 – ident: ref31 doi: 10.1109/TBCAS.2015.2500101 – ident: ref15 doi: 10.1109/TSM.2018.2824314 – volume: 9427 year: 2015 ident: ref29 article-title: A new lithography Hotspot detection framework based on AdaBoost classifier and simplified feature extraction publication-title: Proc Design Process Technol Co-Optim Manuf – ident: ref19 doi: 10.1103/PhysRevE.60.6016 – volume: 5 start-page: 336 year: 2011 ident: ref2 article-title: A data mining approach to automate fault detection model development in the semiconductor manufacturing process publication-title: Int J Mech – start-page: 4765 year: 2017 ident: ref37 article-title: A unified approach to interpreting model predictions publication-title: Proc Adv Neural Inf Process Syst – ident: ref25 doi: 10.1109/TIM.2011.2122430 – ident: ref21 doi: 10.1088/0022-3727/42/2/025203 – ident: ref7 doi: 10.1109/TSM.2009.2028215 – ident: ref26 doi: 10.1145/3331184.3331312 – ident: ref41 doi: 10.1016/j.engappai.2017.09.021 – ident: ref32 doi: 10.4310/SII.2009.v2.n3.a8 – ident: ref3 doi: 10.1109/TSM.2016.2602226 – ident: ref6 doi: 10.1016/j.compchemeng.2017.02.009 – ident: ref18 doi: 10.1063/1.4802252 – ident: ref1 doi: 10.1201/9781420040661-7 – ident: ref39 doi: 10.1109/ASMC.2017.7969205 – ident: ref5 doi: 10.1109/TSM.2019.2938546
SSID	ssj0014497
Score	2.3982084
Snippet	For advanced equipment control, two schemata of real-time fault detection were performed using machine learning algorithms in silicon etching in SF 6 /O 2 /Ar... For advanced equipment control, two schemata of real-time fault detection were performed using machine learning algorithms in silicon etching in SF6/O2/Ar...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	408
SubjectTerms	Abnormalities advanced equipment control Algorithms Argon plasma Classification Classification algorithms Control equipment data mining Electron density Electron energy Emission analysis Etching Fault detection FDC Flow velocity Gas flow Machine learning Machine learning algorithms Mathematical models Optical emission spectroscopy Parameter identification Plasma plasma information (PI) Plasmas Prediction algorithms Process control Process parameters Real time Real-time systems Root cause analysis
Title	Use of Plasma Information in Machine-Learning-Based Fault Detection and Classification for Advanced Equipment Control
URI	https://ieeexplore.ieee.org/document/9427994 https://www.proquest.com/docview/2557979349
Volume	34
WOSCitedRecordID	wos000681129000034&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-2345 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014497 issn: 0894-6507 databaseCode: RIE dateStart: 19880101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB5UBPXgW1xf5OBFMO42TZvN0dfiRRFU8FbaZCoL2lW39fc7SbOLogheSg-TUPiSmUnzzTcAh4mwtl84VqNUyCWlALxAVXLjxKZQxSU5Zt9sQt3c9B8f9e0MHE9rYRDRk8_wxL36u3w7Mo37VdbVUiit5SzMKpW2tVrTGwMpdavqqSWnrENNriR7unt_d00HQRGd0HrWIoq-hSDfU-WHI_bRZbDyv-9aheWQRbLTFvY1mMFqHRYmRcbjdVj6ojO4Ac3DGNmoZLeUKr_kLJQgOUjYsGLXnk-JPEitPvEzimyWDfLmuWYXWHuyVsXyyjLfQtORi9rBNA07DSQCdvnWDD35iJ239PdNeBhc3p9f8dBvgZs4UTWXJi3LSFjdK1JTFNaImJ7kA1DHuRIm14Ukg7TEGCltiTAXFNxEWSA5AWNVvAVz1ajCbWBJmos-Ya2tKmWinQZ8WkhrMCXjXCYd6E4gyEwQI3c9MZ4zfyjp6YxAyxxoWQCtA0fTEa-tEMcfthsOpKldwKcDexOUs7BTxxkdqZQmJyX1zu-jdmHRzd2S_vZgrn5vcB_mzUc9HL8f-EX4CQLS22A
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT9wwEB3xUYlyKBRadVs-fOgFCbMbx4nXRwqsQLArpC4StyixJ2glmm3ZpL-fseNdgUBIXKIcxkmkZ8-M4zdvAH4mwtp-4ViNUiGXlALwAlXJjRObQhWX5Jh9swk1GvVvb_X1EhwuamEQ0ZPP8Mjd-rN8OzWN-1XW1VIoreUyrLrOWUlbrbU4M5BSt7qeWnLKO9T8ULKnu-PfQ9oKiuiIZrQWUfQsCPmuKi9csY8vg433fdkmfAp5JDtugf8MS1htwdq8zHi2BetPlAa3obmZIZuW7JqS5T85C0VIDhQ2qdjQMyqRB7HVO_6LYptlg7y5r9kp1p6uVbG8ssw30XT0onYwPYYdBxoBO_vXTDz9iJ20BPgvcDM4G5-c89BxgZs4UTWXJi3LSFjdK1JTFNaImK7kBVDHuRIm14Ukg7TEGClxiTAXFN5EWSC5AWNV_BVWqmmF34AlaS76hLa2qpSJdirwaSGtwZSMc5l0oDuHIDNBjtx1xbjP_LakpzMCLXOgZQG0DhwsRvxtpTjesN12IC3sAj4d2JmjnIW1OstoU6U0uSmpv78-ah_WzsfDq-zqYnT5Az6697QUwB1YqR8a3IUP5n89mT3s-Qn5CJtn3qs
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Use+of+Plasma+Information+in+Machine-Learning-Based+Fault+Detection+and+Classification+for+Advanced+Equipment+Control&rft.jtitle=IEEE+transactions+on+semiconductor+manufacturing&rft.au=Kim%2C+Dong+Hwan&rft.au=Hong%2C+Sang+Jeen&rft.date=2021-08-01&rft.issn=0894-6507&rft.eissn=1558-2345&rft.volume=34&rft.issue=3&rft.spage=408&rft.epage=419&rft_id=info:doi/10.1109%2FTSM.2021.3079211&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TSM_2021_3079211
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0894-6507&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0894-6507&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0894-6507&client=summon