Adaptive Backstepping Control for a PMSM Drive Using RFNN Uncertainty Observer

被引:0
作者
Lin, Chih-Hong [1 ]
Wu, Ren-Cheng [1 ]
Chong, Chong-Chi [1 ]
机构
[1] Natl United Univ, Dept Elect Engn, Miaoli 360, Taiwan
来源
2011 6TH IEEE CONFERENCE ON INDUSTRIAL ELECTRONICS AND APPLICATIONS (ICIEA) | 2011年
关键词
permanent magnet synchronous motor; recurrent fuzzy neural network; digital signal processor; FUZZY-NEURAL-NETWORK; SLIDING MODE CONTROL; POSITION CONTROLLER; MOTOR DRIVE; SYSTEMS; DESIGN;
D O I
暂无
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
In this paper an adaptive backstepping control system is proposed to control the rotor position of a permanent magnet synchronous motor (PMSM) drive using recurrent fuzzy neural network (RFNN). First, the field-oriented mechanism is applied to formulate the dynamic equation of the PMSM servo drive. Then, an adaptive backstepping approach is proposed to compensate the uncertainties in the motion control system. With the proposed adaptive backstepping control system, the rotor position of the PMSM drive possesses the advantages of good transient control performance and robustness to uncertainties for the tracking of periodic reference trajectories. Moreover, to further increase the robustness of the PMSM drive, a RFNN uncertainty observer is proposed to estimate the required lumped uncertainty in the adaptive backstepping control system. In addition, an on-line parameter training methodology, which is derived using the gradient descent method, is proposed to increase the learning capability of the RFNN. The effectiveness of the proposed control scheme is verified by experimental results.
引用
收藏
页码:62 / 67
页数:6
相关论文
共 18 条
[1]  
[Anonymous], 1995, NONLINEAR ADAPTIVE C
[2]  
[Anonymous], 1996, CONTROL ELECT DRIVES
[3]  
[Anonymous], 1996, Neural fuzzy systems
[4]  
Astrom K.J., 1995, ADAPTIVE CONTROL
[5]   Properties of a combined adaptive/second-order sliding mode control algorithm for some classes of uncertain nonlinear systems [J].
Bartolini, G ;
Ferrara, A ;
Giacomini, L ;
Usai, E .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2000, 45 (07) :1334-1341
[6]   A recurrent self-organizing neural fuzzy inference network [J].
Juang, CF ;
Lin, CT .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (04) :828-845
[7]   SYSTEMATIC DESIGN OF ADAPTIVE CONTROLLERS FOR FEEDBACK LINEARIZABLE SYSTEMS [J].
KANELLAKOPOULOS, I ;
KOKOTOVIC, PV ;
MORSE, AS .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1991, 36 (11) :1241-1253
[8]   ADAPTIVE NONLINEAR DESIGN WITH CONTROLLER-IDENTIFIER SEPARATION AND SWAPPING [J].
KRSTIC, M ;
KOKOTOVIC, PV .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1995, 40 (03) :426-440
[9]   ADAPTIVE NONLINEAR CONTROL WITHOUT OVERPARAMETRIZATION [J].
KRSTIC, M ;
KANELLAKOPOULOS, I ;
KOKOTOVIC, PV .
SYSTEMS & CONTROL LETTERS, 1992, 19 (03) :177-185
[10]   On-line tuning of fuzzy-neural network for adaptive control of nonlinear dynamical systems [J].
Leu, YG ;
Lee, TT ;
Wang, WY .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 1997, 27 (06) :1034-1043