Using genetic algorithms to design a control strategy of an industrial process

被引:21
作者
Sette, S
Boullart, L
Van Langenhove, L
机构
[1] State Univ Ghent, Dept Text, B-9052 Zwijnaarde, Belgium
[2] State Univ Ghent, Dept Control Engn & Automat, B-9052 Zwijnaarde, Belgium
关键词
optimisation; modelling; neural networks; genetic algorithms; textiles; production systems;
D O I
10.1016/S0967-0661(98)00046-X
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In this paper a methodology is presented to design a control strategy to optimise a complex spinning (fibre-yarn) production process, using a neural network combined with genetic algorithms. The neural network is used to model the process, with the machine setpoints and raw fibre quality parameters as input, and with the yarn tenacity and elongation as output. Genetic algorithms are used in two ways: to optimise the architecture and the underlying parameters of the neural network, in order to achieve the most effective model of the production process; to obtain setpoint values and raw material characteristics for an optimal quality of the spinned yarns. (C) 1998 Elsevier Science Ltd. All rights reserved.
引用
收藏
页码:523 / 527
页数:5
相关论文
共 15 条
[1]  
Boullart L., 1997, Journal A, V38, P13
[2]  
Goldberg D., 1989, GENETIC ALGORITHMS S
[3]  
Holland J. H., 1973, SIAM Journal on Computing, V2, P88, DOI 10.1137/0202009
[4]  
POHLEIM H, 1995, AUTOMATISIERUNGSTECH, V43, P110
[5]   USE OF NEURAL NETS FOR DETERMINING THE SPINNABILITY OF FIBERS [J].
PYNCKELS, F ;
KIEKENS, P ;
SETTE, S ;
VANLANGENHOVE, L ;
IMPE, K .
JOURNAL OF THE TEXTILE INSTITUTE, 1995, 86 (03) :425-437
[6]  
PYNCKELS F, 1997, J TEXTILE I
[7]   Optimizing the fiber-to-yarn production process with a combined neural network genetic algorithm approach [J].
Sette, S ;
Boullart, L ;
VanLangenhove, L ;
Kiekens, P .
TEXTILE RESEARCH JOURNAL, 1997, 67 (02) :84-92
[8]  
Sette S, 1996, 23 INT COTT C BREM M, P233
[9]  
SETTE S, 1995, P TEXTILE PROCESS CO
[10]  
Sprave J., 1995, Automatisierungstechnik, V43, P110