• DocumentCode
    85079
  • Title

    Position-Offset-Based Parameter Estimation Using the Adaline NN for Condition Monitoring of Permanent-Magnet Synchronous Machines

  • Author

    Kan Liu ; Zhu, Z.Q.

  • Author_Institution
    Dept. of Electron. & Electr. Eng., Univ. of Sheffield, Sheffield, UK
  • Volume
    62
  • Issue
    4
  • fYear
    2015
  • fDate
    Apr-15
  • Firstpage
    2372
  • Lastpage
    2383
  • Abstract
    This paper proposes how to use the addition of rotor position offsets as perturbation signals for the parameter estimation of permanent-magnet synchronous machines (PMSMs), which can be used for the condition monitoring of rotor permanent magnet and stator winding. During the proposed estimation, two small position offsets are intentionally added into the drive system, and the resulting voltage variation will be recorded for the estimation of rotor flux linkage. With the aid from estimated rotor flux linkage, the stator winding resistance can be subsequently estimated at steady state. This method is experimentally verified on two prototype PMSMs (150 W and 3 kW, respectively) and shows good performance in monitoring the variation of rotor flux linkage and winding resistance.
  • Keywords
    condition monitoring; neural nets; parameter estimation; permanent magnet machines; rotors; stators; synchronous machines; Adaline NN; condition monitoring; permanent-magnet synchronous machines; position-offset-based parameter estimation; power 150 W; power 3 kW; rotor flux linkage; rotor permanent magnet; rotor position; stator winding; voltage variation; winding resistance; Couplings; Estimation; Parameter estimation; Resistance; Rotors; Stator windings; Windings; Adaline neural network; Adaline neural network (NN); condition monitoring; parameter estimation; parameter identification; permanent magnet synchronous machine; permanent-magnet synchronous machine (PMSM); position offset; rotor flux linkage; stator winding resistance;
  • fLanguage
    English
  • Journal_Title
    Industrial Electronics, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    0278-0046
  • Type

    jour

  • DOI
    10.1109/TIE.2014.2360145
  • Filename
    6909071