转炉炼钢过程人工智能静态控制模型

被引:30
作者
丁容
刘浏
机构
[1] 钢铁研究总院,钢铁研究总院,
关键词
转炉炼钢; 人工智能; 神经网络; 静态模型;
D O I
10.13228/j.boyuan.issn0449-749x.1997.01.009
中图分类号
TF713 [熔炼过程及操作];
学科分类号
080602 ;
摘要
将人工神经网络技术应用到转炉炼钢过程控制,与增量模型结合,开发出转炉炼钢人工智能静态控制模型。通过在武钢80 t转炉上的生产试验证明,转炉人工智能静态控制模型比传统的静态控制模型提高了模型对炼钢过程各因素之间复杂非线性关系的处理能力及对系统随机因素变化的反应能力和适应能力,因而提高了静态模型的控制精度和终点命中率。
引用
收藏
页码:22 / 26
页数:5
相关论文
共 7 条
[1]  
Snowbirds. Proc. Conf. on Neural Networks for Computing, AIP Conf, Proc . 1986
[2]  
Automatic Blowing Process in BOF and Direct Tapping Using the Suhlanee System. Erich Friedl. Metallurgical Plant and Technology International . 1990
[3]  
A learning algorithm for Boltzmann machines. Ackley D H,Hinton G E,Sejnowski T J. Cognitive Science . 1985
[4]  
Computing with Neural Circuits: a Model. Hopfield J J.,Tank D W. Science . 1986
[5]  
End-point Temperature Control in. LD Steelmaking. Slatosky W J. Journal of Metals . 1960
[6]  
Parallel Distributed Processing: Explorations in the Microstrueture of Cognition. Rumelhart D E,Mcclland J L. . 1986
[7]  
End-Point Temperature Control of the Basic Oxygen Furnace. Slatosky W. J. Transactions of the Metallurgical Society of AIME . 1961