Dynamic weight estimation using an artificial neural network

被引：27
作者：
Bahar, HB
Horrocks, DH
机构：
[1] Cardiff Univ Wales, Sch Engn, Cardiff CF2 3TF, S Glam, Wales
[2] Tabriz Univ, Fac Engn, Tabriz, Iran
来源：
ARTIFICIAL INTELLIGENCE IN ENGINEERING | 1998年 / 12卷 / 1-2期
关键词：
Artificial Neural Networks; dynamic weight estimation; Multi-Layer Perceptron; platform model parameters; real-time system;
D O I：
10.1016/S0954-1810(97)00017-4
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A Multi-Layer Perceptron Artificial Neural Network is employed to enable the mass that is applied to a weighing platform to be rapidly and accurately estimated before the platform has settled to the steady state. This is achieved through training the network on a set of waveforms resulting from applied masses over the operating range of the weighing platform. Results are given for both simulated and experimental data that confirm the success of the method. (C) 1997 Elsevier Science Limited.
引用
收藏
页码：135 / 139
页数：5
相关论文
共 20 条
  • [1] TRAINING BACKPROPAGATION AND CMAC NEURAL NETWORKS FOR CONTROL OF A SCARA ROBOT
    ANANTHRAMAN, S
    GARG, DP
    [J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 1993, 6 (02) : 105 - 115
  • [2] [Anonymous], PATTERN RECOGNITION
  • [3] Cybenko G., 1989, Mathematics of Control, Signals, and Systems, V2, P303, DOI 10.1007/BF02551274
  • [4] DANACI M, 1995, P EUR C CIRC THEOR D, P507
  • [5] DANACI M, 1996, THESIS CARDIFF U WAL
  • [6] FERGUSON AC, 1974, ENGINEERING-LONDON, V214, P202
  • [7] Layered Neural Networks with Gaussian Hidden Units as Universal Approximations
    Hartman, Eric J.
    Keeler, James D.
    Kowalski, Jacek M.
    [J]. NEURAL COMPUTATION, 1990, 2 (02) : 210 - 215
  • [8] Haykin S., 1994, NEURAL NETWORKS COMP
  • [9] MULTILAYER FEEDFORWARD NETWORKS ARE UNIVERSAL APPROXIMATORS
    HORNIK, K
    STINCHCOMBE, M
    WHITE, H
    [J]. NEURAL NETWORKS, 1989, 2 (05) : 359 - 366
  • [10] KERSTEN J, 1995, CONTROL INSTRUM, V27, P23
12