Data-Driven Deep Reinforcement Learning Control: Application to New Energy Aircraft PMSM

As the power of the new energy aircraft, the performance of permanent magnet synchronous motor (PMSM) directly determines the reliability and stability of the flight state. The complex coupling characteristics (strong nonlinearity, time-varying parameters, multiple working modes) essentially exist i...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Chinese Automation Congress (Online) s. 7127 - 7132
Hlavní autoři: Li, Xin, Qi, Yiwen, Zhao, Tienan, Liu, Yuanqiang, Zhang, Lei, Xu, Hai, Yu, Wenke, Zhao, Xiujuan, Zhang, Chi
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 22.10.2021
Témata:
ISSN:2688-0938
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract As the power of the new energy aircraft, the performance of permanent magnet synchronous motor (PMSM) directly determines the reliability and stability of the flight state. The complex coupling characteristics (strong nonlinearity, time-varying parameters, multiple working modes) essentially exist in the PMSM speed control system, which makes it difficult for traditional control methods to meet application requirements. Aiming at the PMSM speed control, this paper proposes a novel data-driven deep reinforcement learning method. The system operating data is utilized, and a deep deterministic policy gradient (DDPG) agent is established to fully characterize the system data relationship. Instead of the speed loop and current loop in traditional PID control, DDPG intelligent controller directly outputs the quadrature axis voltage. The problem of poor torque dynamic performance caused by the slow response speed of the current loop in the traditional speed control system is effectively solved. Simulation results demonstrate that, under three different typical operating conditions, the proposed method can meet high requirements of PMSM control system. Compared with the traditional PID controller, the DDPG controller shows excellent dynamic and steady-state characteristics, and has stronger robustness and stability.
AbstractList As the power of the new energy aircraft, the performance of permanent magnet synchronous motor (PMSM) directly determines the reliability and stability of the flight state. The complex coupling characteristics (strong nonlinearity, time-varying parameters, multiple working modes) essentially exist in the PMSM speed control system, which makes it difficult for traditional control methods to meet application requirements. Aiming at the PMSM speed control, this paper proposes a novel data-driven deep reinforcement learning method. The system operating data is utilized, and a deep deterministic policy gradient (DDPG) agent is established to fully characterize the system data relationship. Instead of the speed loop and current loop in traditional PID control, DDPG intelligent controller directly outputs the quadrature axis voltage. The problem of poor torque dynamic performance caused by the slow response speed of the current loop in the traditional speed control system is effectively solved. Simulation results demonstrate that, under three different typical operating conditions, the proposed method can meet high requirements of PMSM control system. Compared with the traditional PID controller, the DDPG controller shows excellent dynamic and steady-state characteristics, and has stronger robustness and stability.
Author Yu, Wenke
Qi, Yiwen
Xu, Hai
Zhang, Chi
Zhao, Xiujuan
Zhao, Tienan
Zhang, Lei
Li, Xin
Liu, Yuanqiang
Author_xml – sequence: 1
  givenname: Xin
  surname: Li
  fullname: Li, Xin
  organization: Rhyxeon General Aircraft Co., Ltd.,Shenyang,China,110132
– sequence: 2
  givenname: Yiwen
  surname: Qi
  fullname: Qi, Yiwen
  email: qiyiwen@sau.edu.cn
  organization: Rhyxeon General Aircraft Co., Ltd.,Shenyang,China,110132
– sequence: 3
  givenname: Tienan
  surname: Zhao
  fullname: Zhao, Tienan
  organization: Rhyxeon General Aircraft Co., Ltd.,Shenyang,China,110132
– sequence: 4
  givenname: Yuanqiang
  surname: Liu
  fullname: Liu, Yuanqiang
  organization: Rhyxeon General Aircraft Co., Ltd.,Shenyang,China,110132
– sequence: 5
  givenname: Lei
  surname: Zhang
  fullname: Zhang, Lei
  organization: Shenyang Aircraft Airworthiness Certification Center of CAAC,Shenyang,China,110043
– sequence: 6
  givenname: Hai
  surname: Xu
  fullname: Xu, Hai
  organization: Shenyang Aircraft Airworthiness Certification Center of CAAC,Shenyang,China,110043
– sequence: 7
  givenname: Wenke
  surname: Yu
  fullname: Yu, Wenke
  organization: Shenyang Aerospace University,School of Automation,Shenyang,China,110136
– sequence: 8
  givenname: Xiujuan
  surname: Zhao
  fullname: Zhao, Xiujuan
  organization: Shenyang Aerospace University,School of Automation,Shenyang,China,110136
– sequence: 9
  givenname: Chi
  surname: Zhang
  fullname: Zhang, Chi
  organization: Shenyang Aerospace University,School of Automation,Shenyang,China,110136
BookMark eNot0MtKAzEUgOEoCra1TyBCXmDqyWWSjLthWi8wVfEC7komPSmRNjOkodK3d2FX_-5b_GNyEfuIhNwymDEG1V1TN6UAEDMOnM0qzQ2r2BkZM6VKyZXUcE5GXBlTQCXMFZnu9z8AwAWTpYQR-Z7bbIt5CgeMdI440HcM0ffJ4Q5jpi3aFEPc0KaPOfXbe1oPwzY4m0Mfae7pC_7SRcS0OdI6JJesz_Rt-bG8Jpfebvc4PXVCvh4Wn81T0b4-Pjd1WwTGTC7W3GpvwJlSaS9EpUzHrdK26oQHFKWSaLyznYXOc614B2bNpGOOg5ZCWzEhN_9uQMTVkMLOpuPqNEL8AXXJU5g
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/CAC53003.2021.9728191
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 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 1665426470
9781665426473
EISSN 2688-0938
EndPage 7132
ExternalDocumentID 9728191
Genre orig-research
GrantInformation_xml – fundername: Technology Development
  funderid: 10.13039/100006180
– fundername: Liaoning Revitalization Talents Program
  funderid: 10.13039/501100018617
– fundername: National Natural Science Foundation of China
  funderid: 10.13039/501100001809
– fundername: Scientific Research Fund of Liaoning Provincial Education Department
  funderid: 10.13039/501100013099
GroupedDBID 6IE
6IF
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
OCL
RIE
RIL
ID FETCH-LOGICAL-i118t-d2a7f80c8567f33968b2a67a9b3f0e3564e8fcaba0bf2762b08d14c1c207437a3
IEDL.DBID RIE
IngestDate Wed Aug 27 02:37:27 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i118t-d2a7f80c8567f33968b2a67a9b3f0e3564e8fcaba0bf2762b08d14c1c207437a3
PageCount 6
ParticipantIDs ieee_primary_9728191
PublicationCentury 2000
PublicationDate 2021-Oct.-22
PublicationDateYYYYMMDD 2021-10-22
PublicationDate_xml – month: 10
  year: 2021
  text: 2021-Oct.-22
  day: 22
PublicationDecade 2020
PublicationTitle Chinese Automation Congress (Online)
PublicationTitleAbbrev CAC
PublicationYear 2021
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0002314540
Score 1.7952431
Snippet As the power of the new energy aircraft, the performance of permanent magnet synchronous motor (PMSM) directly determines the reliability and stability of the...
SourceID ieee
SourceType Publisher
StartPage 7127
SubjectTerms Aircraft
Atmospheric modeling
Data driven control
Data models
DDPG
New energy aircraft
PMSM
Reinforcement learning
Steady-state
Torque
Velocity control
Title Data-Driven Deep Reinforcement Learning Control: Application to New Energy Aircraft PMSM
URI https://ieeexplore.ieee.org/document/9728191
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JawIxFA5WeuipLVq6k0OPjWYyk2V6k1HpoYp0AW-SSV6KF5Xp2N_fJA5KoZfeQiAEXsLbv-8h9KA1FdYGotuElyRz3BJtXUKkgIwxwxm1kcT1RU6naj7PZy30uMfCAEBsPoNeWMZavl2bbUiV9XMZyj4-1jmSUuywWvt8ivdTAplcA9JJaN4vBgVP_af1QSBLes3ZX0NUog0Zn_7v9jPUPYDx8GxvZs5RC1YdNB_qWpNhFXQVHgJs8CtEDlQT0324oU39xMWuFf0JDw6ValyvsVdueBRxf3iwrEylXY1nk7dJF32MR-_FM2mGJJCljw1qYpmWTlGjuJAuTXOhSqaF1HmZOgopFxkoZ3SpaemY13wlVTbJTGJYcB6kTi9Qe7VewSXCPAHm_T1tjLGZMjLnytrA35WDDjzzV6gTpLLY7HgwFo1Arv_evkEnQfBBzzN2i9p1tYU7dGy-6-VXdR8f7wf2kZpc
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3Na8IwFA_iBttpGzo295XDjqumadOku0lVHFORzYE3SZOX4UWlq_v7l8SiDHbZLQRC4L3wPvP7PYQepSSJ1o7oNmR5EBumA6lNGPAEYkoVo0R7EtcRn0zEfJ5Oa-hpj4UBAP_5DNpu6Xv5eq22rlTWSblr-9hc54jFMSU7tNa-omIjFUcnV8F0QpJ2sm7GIvtsbRpIw3Z1-tcYFe9FBmf_u_8cNQ9wPDzdO5oLVINVA817spRBr3DWCvcANvgNPAuq8gU_XBGnfuJs9xn9GXcPvWpcrrE1b7jvkX-4uyxUIU2Jp-P3cRN9DPqzbBhUYxKCpc0OykBTyY0gSrCEmyhKE5FTmXCZ5pEhELEkBmGUzCXJDbW2LydCh7EKFXXhA5fRJaqv1iu4QpiFQG3EJ5VSOhaKp0xo7Ri8UpCOaf4aNZxUFpsdE8aiEkjr7-0HdDKcjUeL0cvk9QadOiU4q0_pLaqXxRbu0LH6Lpdfxb1X5A8vwZ2j
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=proceeding&rft.title=Chinese+Automation+Congress+%28Online%29&rft.atitle=Data-Driven+Deep+Reinforcement+Learning+Control%3A+Application+to+New+Energy+Aircraft+PMSM&rft.au=Li%2C+Xin&rft.au=Qi%2C+Yiwen&rft.au=Zhao%2C+Tienan&rft.au=Liu%2C+Yuanqiang&rft.date=2021-10-22&rft.pub=IEEE&rft.eissn=2688-0938&rft.spage=7127&rft.epage=7132&rft_id=info:doi/10.1109%2FCAC53003.2021.9728191&rft.externalDocID=9728191