A neural-network method for the nonlinear servomechanism problem

被引：26
|
作者：
Chu, YC [1 ]
Huang, J
机构：
[1] Nanyang Technol Univ, Sch Elect & Elect Engn, Singapore 639798, Singapore
[2] Chinese Univ Hong Kong, Dept Mech & Automat Engn, Shatin, New Territories, Peoples R China
来源：
IEEE TRANSACTIONS ON NEURAL NETWORKS | 1999年 / 10卷 / 06期
关键词：
cellular neural networks; gradient descent; intelligent computation; Levenberg-Marquardt method; nonlinear servomechanism problem; numerical mathematics; partial differential equations; recurrent neural networks; regulator equations;
D O I：
10.1109/72.809086
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
The solution of the nonlinear servomechanism problem relies on the solvability of a set of mixed nonlinear partial differential and algebraic equations known as the regulator equations. Due to the nonlinear nature, it is difficult to obtain the exact solution of the regulator equations. This paper proposes to solve the regulator equations based on a class of recurrent neural network, which has the features of a cellular neural network. This research not only represents a novel application of the neural networks to numerical mathematics, but also leads to an effective approach to approximately solving nonlinear servomechanism problem. The resulting design method is illustrated by application to the well-known ball and beam system.
引用
收藏
页码：1412 / 1423
页数：12
相关论文
共 50 条
  • [21] A neural-network algorithm for solving systems of nonlinear equations
    Wen Hui
    Zeng Zhe-zhao
    [J]. 2008 INTERNATIONAL WORKSHOP ON EDUCATION TECHNOLOGY AND TRAINING AND 2008 INTERNATIONAL WORKSHOP ON GEOSCIENCE AND REMOTE SENSING, VOL 1, PROCEEDINGS, 2009, : 734 - 737
  • [22] THE HOPFIELD NEURAL-NETWORK APPLIED TO THE QUADRATIC ASSIGNMENT PROBLEM
    BOUSONOCALZON, C
    MANNING, MRW
    [J]. NEURAL COMPUTING & APPLICATIONS, 1995, 3 (02): : 64 - 72
  • [23] A neural-network algorithm for solving nonlinear equation systems
    Li, Guimei
    Zeng, Zhezhao
    [J]. 2008 INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND SECURITY, VOLS 1 AND 2, PROCEEDINGS, 2008, : 20 - +
  • [24] COMMENTS ON A NEURAL-NETWORK APPROACH TO MVDR BEAMFORMING PROBLEM
    LO, KW
    [J]. IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION, 1993, 41 (09) : 1344 - 1345
  • [25] An adaptive neural-network control of discrete nonlinear systems
    Yamamoto, Y
    Yoshimura, H
    [J]. 7TH WORLD MULTICONFERENCE ON SYSTEMICS, CYBERNETICS AND INFORMATICS, VOL XI, PROCEEDINGS: COMMUNICATION, NETWORK AND CONTROL SYSTEMS, TECHNOLOGIES AND APPLICATIONS: II, 2003, : 205 - 209
  • [26] Robust stability of nonlinear neural-network modeled systems
    Lee, Jong-Bae
    Park, Chang-Woo
    Sung, Ha-Gyeong
    [J]. ADVANCES IN NATURAL COMPUTATION, PT 1, 2006, 4221 : 427 - 436
  • [27] NEURAL-NETWORK SYSTEM FOR FORECASTING METHOD SELECTION
    CHU, CH
    WIDJAJA, D
    [J]. DECISION SUPPORT SYSTEMS, 1994, 12 (01) : 13 - 24
  • [28] On robust VSS Nonlinear servomechanism problem
    Utkin, V
    Castillo-Toledo, B
    Loukianov, A
    Espinosa-Guerra, O
    [J]. VARIABLE STRUCTURE SYSTEMS: TOWARDS THE 21ST CENTURY, 2002, 274 : 343 - 363
  • [29] A BOOLEAN NEURAL-NETWORK APPROACH FOR THE TRAVELING SALESMAN PROBLEM
    BHIDE, S
    JOHN, N
    KABUKA, MR
    [J]. IEEE TRANSACTIONS ON COMPUTERS, 1993, 42 (10) : 1271 - 1278
  • [30] AN ANALOG NEURAL-NETWORK TO SOLVE THE HAMILTONIAN CYCLE PROBLEM
    MEHTA, S
    FULOP, L
    [J]. NEURAL NETWORKS, 1993, 6 (06) : 869 - 881
12345