A supervisory fuzzy neural network control system for tracking periodic inputs

被引:135
作者
Lin, FJ [1 ]
Hwang, WJ [1 ]
Wai, RJ [1 ]
机构
[1] Chung Yuan Christian Univ, Dept Elect Engn, Chungli 32023, Taiwan
关键词
fuzzy neural network; periodic inputs; PM synchronous servo motor; supervisory control;
D O I
10.1109/91.746304
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A supervisory fuzzy neural network (FNN) control system is designed to track periodic reference inputs in this study, The control system is composed of a permanent magnet CPM) synchronous servo motor drive with a supervisory FNN position controller, The supervisory FNN controller comprises a supervisory controller, which is designed to stabilize the system states around a defined bound region and an FNN sliding-mode controller, which combines the advantages of the sliding-mode control with robust characteristics and the FNN with on-line learning ability. The theoretical and stability analyses of the supervisory FNN controller are discussed in detail. Simulation and experimental results show that the proposed control system is robust with regard to plant parameter variations and external load disturbance. Moreover, the advantages of the proposed control system are indicated in comparison with the sliding-mode control system.
引用
收藏
页码:41 / 52
页数:12
相关论文
共 20 条
  • [1] IMPLEMENTATION OF A FUZZY INFERENCE SYSTEM USING A NORMALIZED FUZZY NEURAL-NETWORK
    CHAO, CT
    TENG, CC
    [J]. FUZZY SETS AND SYSTEMS, 1995, 75 (01) : 17 - 31
  • [2] A MODEL-REFERENCE CONTROL-STRUCTURE USING A FUZZY NEURAL-NETWORK
    CHEN, YC
    TENG, CC
    [J]. FUZZY SETS AND SYSTEMS, 1995, 73 (03) : 291 - 312
  • [3] THEORY AND APPLICATIONS OF NEURAL NETWORKS FOR INDUSTRIAL CONTROL-SYSTEMS
    FUKUDA, T
    SHIBATA, T
    [J]. IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 1992, 39 (06) : 472 - 489
  • [4] REPETITIVE CONTROL-SYSTEM - A NEW TYPE SERVO SYSTEM FOR PERIODIC EXOGENOUS SIGNALS
    HARA, S
    YAMAMOTO, Y
    OMATA, T
    NAKANO, M
    [J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1988, 33 (07) : 659 - 668
  • [5] ON FUZZY MODELING USING FUZZY NEURAL NETWORKS WITH THE BACKPROPAGATION ALGORITHM
    HORIKAWA, S
    FURUHASHI, T
    UCHIKAWA, Y
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (05): : 801 - 806
  • [6] NEURAL NETWORKS FOR CONTROL-SYSTEMS - A SURVEY
    HUNT, KJ
    SBARBARO, D
    ZBIKOWSKI, R
    GAWTHROP, PJ
    [J]. AUTOMATICA, 1992, 28 (06) : 1083 - 1112
  • [7] NEURO-FUZZY MODELING AND CONTROL
    JANG, JSR
    SUN, CT
    [J]. PROCEEDINGS OF THE IEEE, 1995, 83 (03) : 378 - 406
  • [8] A RECURRENT NEURAL-NETWORK-BASED ADAPTIVE VARIABLE-STRUCTURE MODEL-FOLLOWING CONTROL OF ROBOTIC MANIPULATORS
    KARAKASOGLU, A
    SUNDARESHAN, MK
    [J]. AUTOMATICA, 1995, 31 (10) : 1495 - 1507
  • [9] DIAGONAL RECURRENT NEURAL NETWORKS FOR DYNAMIC-SYSTEMS CONTROL
    KU, CC
    LEE, KY
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1995, 6 (01): : 144 - 156
  • [10] TRACKING PERIODIC INPUTS USING SAMPLED COMPENSATORS
    LEDWICH, GF
    BOLTON, AG
    [J]. IEE PROCEEDINGS-D CONTROL THEORY AND APPLICATIONS, 1991, 138 (03): : 242 - 248