A recurrent neural network for N-stage optimal control problems

被引：6
|
作者：
Liao, LZ [1 ]
机构：
[1] Hong Kong Baptist Univ, Dept Math, Kowloon, Peoples R China
来源：
NEURAL PROCESSING LETTERS | 1999年 / 10卷 / 03期
关键词：
recurrent neural network; optimal control; gradient method;
D O I：
10.1023/A:1018776323513
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A recurrent neural network is introduced for the N-stage optimal control problem. The new neural network is based on a reformulation of the original optimal control problem and the gradient method. The simulation results on two examples indicate that the new neural network is quite effective.
引用
收藏
页码：195 / 200
页数：6
相关论文
共 50 条
  • [21] The simplification of neural network for quadratic programming problems and its applications in optimal control
    Tao, Q
    Sun, DM
    PROCEEDINGS OF THE 3RD WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION, VOLS 1-5, 2000, : 3504 - 3508
  • [22] On Infinite Horizon Optimal Control Problems with a Feed Forward Neural Network Scheme
    Marziyeh Mortezaee
    Alireza Nazemi
    Neural Processing Letters, 2020, 51 : 449 - 471
  • [23] Nonlinear fractional optimal control problems with neural network and dynamic optimization schemes
    Ghasemi, Safiye
    Nazemi, Alireza
    Hosseinpour, Soleiman
    NONLINEAR DYNAMICS, 2017, 89 (04) : 2669 - 2682
  • [24] A recurrent neural network applied to optimal motion control of mobile robots with physical constraints
    Chen, Dechao
    Li, Shuai
    Liao, Liefa
    APPLIED SOFT COMPUTING, 2019, 85
  • [25] Time-optimal constrained kinematic control of robotic manipulators by recurrent neural network
    Li, Zhan
    Li, Shuai
    EXPERT SYSTEMS WITH APPLICATIONS, 2024, 257
  • [26] Optimal control of a batch emulsion copolymerisation reactor based on recurrent neural network models
    Tian, Y
    Zhang, J
    Morris, J
    CHEMICAL ENGINEERING AND PROCESSING-PROCESS INTENSIFICATION, 2002, 41 (06) : 531 - 538
  • [27] Simple recurrent neural network:: A neural network structure for control systems
    Hernández, RP
    Gallegos, JA
    Reyes, JAH
    NEUROCOMPUTING, 1998, 23 (1-3) : 277 - 289
  • [28] N-stage splitting for maximum penalized likelihood estimation
    Latham, GA
    Yu, S
    JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION, 1996, 55 (1-2) : 159 - 168
  • [29] Approximate dynamic programming for stochastic N-stage optimization with application to optimal consumption under uncertainty
    Mauro Gaggero
    Giorgio Gnecco
    Marcello Sanguineti
    Computational Optimization and Applications, 2014, 58 : 31 - 85
  • [30] A genetic algorithm to obtain the optimal recurrent neural network
    Blanco, A
    Delgado, M
    Pegalajar, MC
    INTERNATIONAL JOURNAL OF APPROXIMATE REASONING, 2000, 23 (01) : 67 - 83
12345