NEURAL-NETWORK-BASED ADAPTIVE OBSERVER OF POSITION AND SPEED OF PMSM
LI Hong-ru, GU Shu-sheng (Northeastern University, Shenyang 110006,China)
A neural network-based nonlinear adaptive observer is designed through a nonlinear transformation of mathematical model of permanent magnet synchronous motor (PMSM) in a stationary ba- reference frame. Furthermore, the Lyapunov function is created, and on-line learning rules are given for the network weight matrix, such that the stability of observer is proved. Theoretical analysis and simulation results show that the proposed strategy has stronger robustness and satisfactory performance.
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.