Discrete-Time Recurrent Neural DC Motor Control using Kalman Learning

被引:4
|
作者
Castaneda, Carlos E. [1 ]
Sanchez, Edgar N. [1 ]
Loukianov, Alexander G. [1 ]
Castillo-Toledo, Bernardino [1 ]
机构
[1] CINVESTAV, Unidad Guadalajara, Guadalajara 45090, Jalisco, Mexico
来源
2008 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-8 | 2008年
关键词
D O I
10.1109/IJCNN.2008.4634062
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
An adaptive tracking controller for a discrete-time direct current (DC) motor model in presence of bounded disturbances is presented. A high order neural network is used to identify the plant model; this network is trained with an extended Kalman filter. Then, the discrete-time block control and sliding modes techniques are used to develop the reference tracking control. This paper includes also the respective stability analysis and a strategy to avoid specific adaptive weights zero-crossing. The scheme is illustrated via simulations for a discrete-time nonlinear model of an electric DC motor.
引用
收藏
页码:1930 / 1937
页数:8
相关论文
共 50 条
  • [41] Approximation to Nonlinear Discrete-Time Systems by Recurrent Neural Networks
    Li, Fengjun
    SIXTH INTERNATIONAL SYMPOSIUM ON NEURAL NETWORKS (ISNN 2009), 2009, 56 : 527 - 534
  • [42] Robust global stability of discrete-time recurrent neural networks
    Mahmoud, M. S.
    PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART I-JOURNAL OF SYSTEMS AND CONTROL ENGINEERING, 2009, 223 (I8) : 1045 - 1053
  • [43] Global asymptotic stability of discrete-time recurrent neural networks
    Hu, SQ
    Wang, J
    PROCEEDINGS OF THE 39TH IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-5, 2000, : 877 - 882
  • [44] A Class of Discrete-Time Recurrent Neural Networks with Multivalued Neurons
    Zhou, Wei
    Zurada, Jacek M.
    IJCNN: 2009 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1- 6, 2009, : 981 - +
  • [45] Global stability analysis of discrete-time recurrent neural networks
    Barabanov, NE
    Prokhorov, DV
    PROCEEDINGS OF THE 2001 AMERICAN CONTROL CONFERENCE, VOLS 1-6, 2001, : 4550 - 4555
  • [46] Bounds of the incremental gain for discrete-time recurrent neural networks
    Chu, YC
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2002, 13 (05): : 1087 - 1098
  • [47] Extraction of rules from discrete-time recurrent neural networks
    Omlin, CW
    Giles, CL
    NEURAL NETWORKS, 1996, 9 (01) : 41 - 52
  • [48] ABSOLUTE STABILITY CONDITIONS FOR DISCRETE-TIME RECURRENT NEURAL NETWORKS
    JIN, L
    NIKIFORUK, PN
    GUPTA, MM
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (06): : 954 - 964
  • [49] ROBUST KALMAN FILTER IN DISCRETE-TIME
    ERSHOV, AA
    LIPTSER, RS
    AUTOMATION AND REMOTE CONTROL, 1978, 39 (03) : 359 - 367
  • [50] Predictive control of linear discrete-time Markovian jump systems by learning recurrent patterns
    Han, SooJean
    Chung, Soon -Jo
    Doyle, John C.
    AUTOMATICA, 2023, 156