东北大学学报（自然科学版）

东北大学学报(自然科学版) ›› 2007, Vol. 28 ›› Issue (8): 1140-1142.DOI: -

• 论著 • 上一篇    下一篇

改进BP网络在铁水预脱硫终点硫含量预报中的应用

张慧书;战东平;姜周华;   

  1. 东北大学材料与冶金学院;东北大学材料与冶金学院;东北大学材料与冶金学院 辽宁沈阳110004;辽宁沈阳110004;辽宁沈阳110004
  • 收稿日期:2013-06-24 修回日期:2013-06-24 出版日期:2007-08-15 发布日期:2013-06-24
  • 通讯作者: Zhang, H.-S.
  • 作者简介:-
  • 基金资助:
    辽宁省院校合作工程专项计划项目(200202004)

Application of improved BP neural network to final sulfur content prediction of hot metal pre-desulfurization

Zhang, Hui-Shu (1); Zhan, Dong-Ping (1); Jiang, Zhou-Hua (1)   

  1. (1) School of Materials and Metallurgy, Northeastern University, Shenyang 110004, China
  • Received:2013-06-24 Revised:2013-06-24 Online:2007-08-15 Published:2013-06-24
  • Contact: Zhang, H.-S.
  • About author:-
  • Supported by:
    -

RichHTML

1

PDF (PC)

443

摘要： 针对本溪钢铁集团有限公司的铁水罐喷吹CaO+Mg复合粉剂脱硫过程,采用BP神经网络建立铁水预处理终点硫含量预报模型.在模型建立过程中,为了克服标准BP算法迭代次数多、收敛速度慢的缺点,采用新的自适应调整学习率方法和最大误差学习法对标准BP算法进行了改进.用1 900炉数据进行模型训练,经100炉数据现场验证表明,有12%的炉次预报值与实际值完全一致,有89%的炉次误差≤0.003%,平均误差为0.002 0%.

关键词: 铁水预处理, BP神经网络, 硫含量, 预报, 模型

Abstract: A prediction model of final sulfur content is developed for hot metal pre-desulfurization by use of an improved BP neural network, especially for the desulfurization process by CaO+Mg powder co-injection in Benxi Steel Co. Ltd. To overcome the disadvantages of overmuch iterative repetition and slow convergence rate of normal BP algorithm, an approach to readjust adaptively the self-learning rate with self-learning for maximum error is used to improve the normal BP algorithm during modeling. The data from 1900 heats are used to train the model with other 100 heats randomly picked out as test samples. Test results showed that 12% of the predicted values got from the 100 samples are the same to the actually measured values, 89% have the error within 0.003% and the average error is 0.0020%.

中图分类号: