Development of prediction model for mechanical properties of batch annealed thin steel strip by using artificial neural network modelling

被引:13
作者
Myllykoski, P [1 ]
Larkiola, J [1 ]
Nylander, J [1 ]
机构
[1] RAUTARUUKKI OY,THIN SHEET DIV,SF-13300 HAMEENLINNA,FINLAND
关键词
artificial neural networks; modelling; mechanical properties; thin steel strip;
D O I
10.1016/0924-0136(96)02361-8
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
It is important to predict the mechanical properties of thin steel strip when it is produced by rolling. For this purpose we have used artificial neural networks (ANN) and the data acquisition system of Rautaruukki Hameenlinna Works. This paper shows that it is possible to predict accurately the mechanical properties thin steel strip, by using ANN modelling and the measurement data of the process. The prediction model can be used in different ways. For example the effects of process parameters can be evaluated and the controllable parameters can be changed in such a way that the process yields the desired mechanical properties.
引用
收藏
页码:399 / 404
页数:6
相关论文
共 5 条
[1]  
BOGER Z, 1995, P ICANN 95 OCT 9 13
[2]  
Cybenko G., 1989, Mathematics of Control, Signals, and Systems, V2, P303, DOI 10.1007/BF02551274
[3]  
FREEMAN JA, 1991, NEURAL NETWORK ALGOR
[4]  
PARLOS A, 1994, IEEE T NEURAL NETWOR, V5
[5]  
Rumelhart D. E., 1986, PARALLEL DISTRIBUTED, V1