SIMULATION OF STEEL TRANSFORMATION CURVES WITH A NEURAL NETWORK

被引：0

作者：

DEPEYRE, D ^{[1
]}

ISAMBERT, A ^{[1
]}

PREVOST, PH ^{[1
]}

DONADILLE, C ^{[1
]}

PERISSE, R ^{[1
]}

机构：

[1] IRSID,F-78105 ST GERMAIN LAYE,FRANCE

来源：

COMPUTERS & CHEMICAL ENGINEERING | 1993年 / 17卷

关键词：

NEURAL NETWORKS; MULTILAYERS NETWORKS; DATABASE LEARNING; BACKPROPAGATION; STEEL GRADE; HOLDING TEMPERATURE; FRACTAL; PHASE TRANSFORMATION;

D O I：

暂无

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

We have carried out simulations of steel transformation curves with Neural Networks. For this purpose, it was necessary to use special learning techniques because of the non-ideal nature of the industrial experimental results (insufficient in precision and quantity) that we used. The consideration of examples not used in the learning process led us to introduce knowledge of various types and sources in the Neural Network. It was noted that knowledge that an ''expert'' might use was particularly helpful for a Neural Network.

引用

页码：S417 / S422

页数：6

共 13 条

[1]

CONSTANT A, 1986, PRINCIPES BASE TRAIT

[2]

DAVALO E, 1989, RESEAUX NEURONES

[3]

GHABOUSSI J, 1990, NUMERICAL METHODS EN, P703

[4] ARTIFICIAL NEURAL NETWORK MODELS OF KNOWLEDGE REPRESENTATION IN CHEMICAL-ENGINEERING [J].