引用本文:谢书明,陶 钧,柴天佑.基于神经网络的转炉炼钢终点控制[J].控制理论与应用,2003,20(6):903~907.[点击复制]
XIE Shu-ming,TAO Jun,CHAI Tian-you.BOF steelmaking endpoint control based on neural network[J].Control Theory and Technology,2003,20(6):903~907.[点击复制]
基于神经网络的转炉炼钢终点控制
BOF steelmaking endpoint control based on neural network
摘要点击 2266  全文点击 1770  投稿时间:2001-12-17  修订日期:2002-10-08
查看全文  查看/发表评论  下载PDF阅读器
DOI编号  
  2003,20(6):903-907
中文关键词  神经网络  转炉炼钢  终点控制
英文关键词  neural network  BOF steelmaking  endpoint control
基金项目  国家自然科学基金项目(69674018); 辽宁省教育厅基金项目(202063296).
作者单位E-mail
谢书明 沈阳工业大学 电气工程学院, 辽宁 沈阳 110023 xiesm-wy@hotmail.com 
陶 钧 上海宝信软件股份公司, 上海 201900 shtaojun@etang.com 
柴天佑 东北大学 自动化研究中心, 辽宁 沈阳 110004 tychai@mail.neu.edu.cn 
中文摘要
      转炉炼钢是一种非常重要的炼钢方法,终点控制是转炉炼钢后期的重要操作.由于冶炼过程温度极高,很难进行准确及时地测量,无法形成通常意义下的反馈控制.采用RBF神经网络预报转炉炼钢终点温度和碳含量,在此基础上提出了基于神经网络的动态终点控制方法来确定在补吹阶段需要的吹氧量和加入的冷却剂量,克服了传统控制方法中基于热平衡和氧平衡控制模型不准确的缺点,提高了终点命中率.
英文摘要
       BOF steelmaking is a kind of paramount steelmaking method. The endpoint control is an important operation in the later period of BOF steelmaking. Because the temperature is very high in the smelting, it is very difficult to take measurement accurately and timely. There is not method to form common feedback control. The BOF endpoint temperature and carbon content were predicted by means of RBF neural network. On the basis of this, the dynamic endpoint control method based on neural network was proposed so as to determine the blown oxygen and the added coolant during the reblowing. The shortcoming that the control model based on the heat balance and the oxygen balance was not accurate in the traditional method was overcome. The endpoint hitting ratio was raised.