View in EDS HTML Full Text PDF Full Text

Predefined-Time Performance-Guaranteed Control of Permanent Magnet Synchronous Motors (PMSMs) Based on Reinforcement Learning.

Saved in:
Bibliographic Details
Title: Predefined-Time Performance-Guaranteed Control of Permanent Magnet Synchronous Motors (PMSMs) Based on Reinforcement Learning.
Authors: Jin, Yuliang1 (AUTHOR), Yin, Chunwu2 (AUTHOR), Li, Duanyang3 (AUTHOR), Li, Zhiwu1 (AUTHOR), Wu, Naiqi1,2 (AUTHOR) nqwu@must.edu.mo
Source: Energies (19961073). Jun2026, Vol. 19 Issue 11, p2645. 19p.
Subject Terms: *Reinforcement learning, *Tracking control systems, *Energy consumption, *Dynamic loads, *Perturbation theory, *Permanent magnet motors
Abstract: Against the background that efficient energy utilization has become a global focus and the demand for energy conservation and consumption reduction of industrial equipment is increasingly urgent, aiming at the problems of permanent magnet synchronous motors (PMSMs) in actual operation, such as parameter perturbation, time-varying load and control saturation constraints, which lead to decreased operation efficiency, insufficient energy utilization, low trajectory tracking accuracy, slow convergence speed, weak anti-interference ability and poor engineering applicability, this paper proposes a predefined-time convergent guaranteed-performance control strategy to provide technical support for the efficient and stable operation of PMSMs. Firstly, a prescribed performance control structure independent of the initial value is designed, which breaks through the dependence of traditional Prescribed Performance Control (PPC) on initial states and lays a control foundation for efficient energy utilization. Secondly, the traditional reinforcement learning algorithm is improved to overcome its randomness defect, which is used to accurately online estimate the composite time-varying disturbances (including parameter perturbation and time-varying load) during the operation of PMSMs. Furthermore, the predefined-time convergence control mechanism is integrated to design a prescribed performance control law for PMSMs, which ensures that the angular velocity tracking error converges to zero within a pre-specified time, realizes time-optimal control, effectively suppresses the adverse effects caused by various disturbances and control saturation, and improves the motor operation efficiency and energy utilization efficiency. Finally, the effectiveness is verified by simulation. The results show that the strategy can effectively improve the trajectory tracking accuracy of PMSMs, achieve fast convergence within the predefined time, enhance the adaptability of the motor to complex working conditions, and further improve the energy utilization efficiency. [ABSTRACT FROM AUTHOR]
Database: Energy & Power Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: enr
DbLabel: Energy & Power Source
An: 194588033
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Predefined-Time Performance-Guaranteed Control of Permanent Magnet Synchronous Motors (PMSMs) Based on Reinforcement Learning.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Jin%2C+Yuliang%22">Jin, Yuliang</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Yin%2C+Chunwu%22">Yin, Chunwu</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Duanyang%22">Li, Duanyang</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Zhiwu%22">Li, Zhiwu</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wu%2C+Naiqi%22">Wu, Naiqi</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> nqwu@must.edu.mo</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Energies+%2819961073%29%22">Energies (19961073)</searchLink>. Jun2026, Vol. 19 Issue 11, p2645. 19p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Reinforcement+learning%22">Reinforcement learning</searchLink><br />*<searchLink fieldCode="DE" term="%22Tracking+control+systems%22">Tracking control systems</searchLink><br />*<searchLink fieldCode="DE" term="%22Energy+consumption%22">Energy consumption</searchLink><br />*<searchLink fieldCode="DE" term="%22Dynamic+loads%22">Dynamic loads</searchLink><br />*<searchLink fieldCode="DE" term="%22Perturbation+theory%22">Perturbation theory</searchLink><br />*<searchLink fieldCode="DE" term="%22Permanent+magnet+motors%22">Permanent magnet motors</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Against the background that efficient energy utilization has become a global focus and the demand for energy conservation and consumption reduction of industrial equipment is increasingly urgent, aiming at the problems of permanent magnet synchronous motors (PMSMs) in actual operation, such as parameter perturbation, time-varying load and control saturation constraints, which lead to decreased operation efficiency, insufficient energy utilization, low trajectory tracking accuracy, slow convergence speed, weak anti-interference ability and poor engineering applicability, this paper proposes a predefined-time convergent guaranteed-performance control strategy to provide technical support for the efficient and stable operation of PMSMs. Firstly, a prescribed performance control structure independent of the initial value is designed, which breaks through the dependence of traditional Prescribed Performance Control (PPC) on initial states and lays a control foundation for efficient energy utilization. Secondly, the traditional reinforcement learning algorithm is improved to overcome its randomness defect, which is used to accurately online estimate the composite time-varying disturbances (including parameter perturbation and time-varying load) during the operation of PMSMs. Furthermore, the predefined-time convergence control mechanism is integrated to design a prescribed performance control law for PMSMs, which ensures that the angular velocity tracking error converges to zero within a pre-specified time, realizes time-optimal control, effectively suppresses the adverse effects caused by various disturbances and control saturation, and improves the motor operation efficiency and energy utilization efficiency. Finally, the effectiveness is verified by simulation. The results show that the strategy can effectively improve the trajectory tracking accuracy of PMSMs, achieve fast convergence within the predefined time, enhance the adaptability of the motor to complex working conditions, and further improve the energy utilization efficiency. [ABSTRACT FROM AUTHOR]
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=enr&AN=194588033
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/en19112645
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 19
        StartPage: 2645
    Subjects:
      – SubjectFull: Reinforcement learning
        Type: general
      – SubjectFull: Tracking control systems
        Type: general
      – SubjectFull: Energy consumption
        Type: general
      – SubjectFull: Dynamic loads
        Type: general
      – SubjectFull: Perturbation theory
        Type: general
      – SubjectFull: Permanent magnet motors
        Type: general
    Titles:
      – TitleFull: Predefined-Time Performance-Guaranteed Control of Permanent Magnet Synchronous Motors (PMSMs) Based on Reinforcement Learning.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Jin, Yuliang
      – PersonEntity:
          Name:
            NameFull: Yin, Chunwu
      – PersonEntity:
          Name:
            NameFull: Li, Duanyang
      – PersonEntity:
          Name:
            NameFull: Li, Zhiwu
      – PersonEntity:
          Name:
            NameFull: Wu, Naiqi
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 19961073
          Numbering:
            – Type: volume
              Value: 19
            – Type: issue
              Value: 11
          Titles:
            – TitleFull: Energies (19961073)
              Type: main
ResultId 1