Neural Networks based Speed-Torque Estimators for Induction Motors and Performance Metrics

This paper focuses on the quantitative analysis of deep neural networks used in data-driven modeling of induction motor dynamics. With the availability of a large amount of data generated by industrial sensor networks, it is now possible to train deep neural networks. Recently researchers have start...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society s. 495 - 500
Hlavní autori: Verma, Sagar, Henwood, Nicolas, Castella, Marc, Jebai, Al Kassem, Pesquet, Jean-Christophe
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 18.10.2020
Predmet:
deep learning
induction motor
Induction motors
Mathematical model
Measurement
Neural networks
time series
Torque
Training
Trajectory
ISSN:2577-1647
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract This paper focuses on the quantitative analysis of deep neural networks used in data-driven modeling of induction motor dynamics. With the availability of a large amount of data generated by industrial sensor networks, it is now possible to train deep neural networks. Recently researchers have started exploring the usage of such networks for physics modeling, online control, monitoring, and fault prediction in induction motor operations. We consider the problem of estimating speed and torque from currents and voltages of an induction motor. Neural networks provide quite good performance for this task when analysed from a machine learning perspective using standard metrics. We show, however, that there are some caveats in using machine learning metrics to analyze a neural network model when applied to induction motor problems. Given the mission- critical nature of induction motor operations, the performance of neural networks has to be validated from an electrical engineering point of view. To this end, we evaluate several traditional neural network architectures and recent state of the art architectures on dynamic and quasi-static benchmarks using electrical engineering metrics.
AbstractList This paper focuses on the quantitative analysis of deep neural networks used in data-driven modeling of induction motor dynamics. With the availability of a large amount of data generated by industrial sensor networks, it is now possible to train deep neural networks. Recently researchers have started exploring the usage of such networks for physics modeling, online control, monitoring, and fault prediction in induction motor operations. We consider the problem of estimating speed and torque from currents and voltages of an induction motor. Neural networks provide quite good performance for this task when analysed from a machine learning perspective using standard metrics. We show, however, that there are some caveats in using machine learning metrics to analyze a neural network model when applied to induction motor problems. Given the mission- critical nature of induction motor operations, the performance of neural networks has to be validated from an electrical engineering point of view. To this end, we evaluate several traditional neural network architectures and recent state of the art architectures on dynamic and quasi-static benchmarks using electrical engineering metrics.
Author Jebai, Al Kassem
Verma, Sagar
Henwood, Nicolas
Castella, Marc
Pesquet, Jean-Christophe
Author_xml – sequence: 1
  givenname: Sagar
  surname: Verma
  fullname: Verma, Sagar
  organization: Université Paris-Saclay, CentraleSupelec, Inria,Centre de Vision Numérique
– sequence: 2
  givenname: Nicolas
  surname: Henwood
  fullname: Henwood, Nicolas
  organization: Schneider Toshiba Inverter Europe
– sequence: 3
  givenname: Marc
  surname: Castella
  fullname: Castella, Marc
  organization: Institut Polytechnique de Paris,SAMOVAR, Télécom SudParis
– sequence: 4
  givenname: Al Kassem
  surname: Jebai
  fullname: Jebai, Al Kassem
  organization: Schneider Toshiba Inverter Europe
– sequence: 5
  givenname: Jean-Christophe
  surname: Pesquet
  fullname: Pesquet, Jean-Christophe
  organization: Université Paris-Saclay, CentraleSupelec, Inria,Centre de Vision Numérique
BookMark eNotkM1KAzEUhaMoWOs8gQvzAlOT3GSSWUqpOtAfwbpxU-5k7uBgO6nJFPHtLdrVgfPB4eNcs4s-9MTYnRQTKUV5X82mq6UGKGGihBKTUhmjoDhjWWmdtMpJo6U252ykjLW5LLS9YllKXS200lYIU4zY-5IOEbd8ScN3iJ-J15io4a97oiZfh_h1ID5LQ7fDIcTE2xB51TcHP3Sh54vwV2Lf8BeKR7bD3hNf0BA7n27YZYvbRNkpx-ztcbaePufz1VM1fZjnH-DkkHvwNbpSa0FWOvSNQOkJgJpaO-uxrY2urdMotTCuMKYEU5i2BSQQrUAYs9v_3Y6INvt4dI0_m9Mb8AvyS1d9
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/IECON43393.2020.9255236
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9781728154145
1728154146
EISSN 2577-1647
EndPage 500
ExternalDocumentID 9255236
Genre orig-research
GroupedDBID 6IE
6IH
ALMA_UNASSIGNED_HOLDINGS
CBEJK
M43
RIE
RIO
ID FETCH-LOGICAL-h381t-c3cba89440e718acd0a1ce33edb487cafb54b784a1405865593565ff3ae30f0a3
IEDL.DBID RIE
ISICitedReferencesCount 5
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000637323700078&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:28:31 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-h381t-c3cba89440e718acd0a1ce33edb487cafb54b784a1405865593565ff3ae30f0a3
OpenAccessLink https://cir.nii.ac.jp/crid/1873679867809482496
PageCount 6
ParticipantIDs ieee_primary_9255236
PublicationCentury 2000
PublicationDate 2020-10-18
PublicationDateYYYYMMDD 2020-10-18
PublicationDate_xml – month: 10
  year: 2020
  text: 2020-10-18
  day: 18
PublicationDecade 2020
PublicationTitle IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society
PublicationTitleAbbrev IECON
PublicationYear 2020
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssib042470056
Score 2.1782932
Snippet This paper focuses on the quantitative analysis of deep neural networks used in data-driven modeling of induction motor dynamics. With the availability of a...
SourceID ieee
SourceType Publisher
StartPage 495
SubjectTerms deep learning
induction motor
Induction motors
Mathematical model
Measurement
Neural networks
time series
Torque
Training
Trajectory
Title Neural Networks based Speed-Torque Estimators for Induction Motors and Performance Metrics
URI https://ieeexplore.ieee.org/document/9255236
WOSCitedRecordID wos000637323700078&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
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA7b8OBJZRN_k4NHs6VJ2jRn2VBwY-CU4WW8Jq8oaDvWzb_fpKsTwYu3EloCL-n73kve9z5CrkUCHoVEzCInLFNgIpYKG7MEMs2VdXlcy7c9P-jJJJ3PzbRFbnZcGESsi8-wHx7ru3xX2k04KhsYH_8KmbRJW2u95Wp97x0llA5tLZsSroibwX2QAlRSGunTQMH7zde_ZFRqFBkd_G_-Q9L7oePR6Q5ojkgLiy55CW014J1OtnXcFQ145Ojj0r_FZuXK-3s69P_vR8iqK-pjUxpkOmoaAx2X9SAUjk5_mAN0HOS1bNUjT6Ph7PaONUIJ7NUD7ppZaTNIjVIcPdSAdRwii1Kiy3w-YiHPYpXpVIHPpuLARDXSx3F5LgElzznIY9IpygJPCI3Bh9yoBYcclXJoEDIrRJ5YSEMfoFPSDXZZLLe9MBaNSc7-Hj4n-8H0wddH6QXprFcbvCR79nP9Vq2u6gX8AomLnYs
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA61CnpSacW3OXg0bTbJPnKWSovtUrBK8VJmkywKulu6rb_fJF1bBC_eQkgg5PXNJPPNh9Ati8CiEAtJoJkiAmRAEqZCEkEWU6F0Hnr5tpdhnKbJdCrHDXS34cIYY3zwmem4ov_L16VauaeyrrT2L-PRDtoNhWDBmq31s3sEE7FLbFkHcQVUdgdODFBwLrl1BBnt1P1_Cal4HHk4_N8IjlB7S8jD4w3UHKOGKVro1SXWgA-criO5K-wQSeOnuW1FJuXC3vi4Z0_wp_OrK2ytU-yEOjyRAY9KXwmFxuMtdwCPnMCWqtro-aE3ue-TWiqBvFnIXRLFVQaJFIIaCzagNIVAGc6NzqxHoiDPQpHFiQDrT4WOiyq5teTynIPhNKfAT1CzKAtzinAI1ug2MaOQGyG0kQYyxVgeKUhcJqAz1HLzMpuvs2HM6ik5_7v6Bu33J6PhbDhIHy_QgVsGd_MHySVqLhcrc4X21NfyvVpc-8X8BukEoNI
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%3Abook&rft.genre=proceeding&rft.title=IECON+2020+The+46th+Annual+Conference+of+the+IEEE+Industrial+Electronics+Society&rft.atitle=Neural+Networks+based+Speed-Torque+Estimators+for+Induction+Motors+and+Performance+Metrics&rft.au=Verma%2C+Sagar&rft.au=Henwood%2C+Nicolas&rft.au=Castella%2C+Marc&rft.au=Jebai%2C+Al+Kassem&rft.date=2020-10-18&rft.pub=IEEE&rft.eissn=2577-1647&rft.spage=495&rft.epage=500&rft_id=info:doi/10.1109%2FIECON43393.2020.9255236&rft.externalDocID=9255236