CIESC Journal ›› 2018, Vol. 69 ›› Issue (3): 992-997.DOI: 10.11949/j.issn.0438-1157.20171534

Previous Articles     Next Articles

Research on hot metal Si-content prediction based on LSTM-RNN

LI Zelong, YANG Chunjie, LIU Wenhui, ZHOU Heng, LI Yuxuan   

  1. College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, Zhejiang, China
  • Received:2017-09-25 Revised:2017-11-13 Online:2018-03-05 Published:2018-03-05
  • Supported by:

    supported by the National Nature Science Foundation of China (61290321).

基于LSTM-RNN模型的铁水硅含量预测

李泽龙, 杨春节, 刘文辉, 周恒, 李宇轩   

  1. 浙江大学控制科学与工程学院, 浙江 杭州 310027
  • 通讯作者: 杨春节
  • 基金资助:

    国家自然科学基金项目(61290321)。

Abstract:

The ironmaking in blast furnace, with large delay and complex conditions, is a dynamic process. The traditional methods for prediction of silicon content in hot metal are mostly based on the statistics or the simple neural networks, leading to lower accuracy. However, a model based on the long short-term memory-recurrent neural network (LSTM-RNN) is proposed to exploit the characteristics of the mutual information before and after the time series in this paper. The independent variables are selected according to the time series trend and the correlation coefficient. After that, the silicon content is predicted according to the input variables by optimizing the parameters automatically. In order to verify the constructed model, the extremely complex production data is used to compare the LSTM-RNN and simple RNN models. Remarkably, the result shows that the prediction error of LSTM-RNN model is stable and the prediction accuracy is high.

Key words: prediction, dynamic modelling, neural network, ironmaking, silicon content

摘要:

针对高炉炼铁是一个动态过程,具有大延迟,工况复杂的特性。采用LSTM-RNN模型进行硅含量预测,充分发挥了其处理时间序列时挖掘前后关联信息的优势。首先根据时间序列趋势及相关系数选择自变量,并采用复杂工况的实际生产数据进行验证。然后用程序自动求解最优参数进行硅含量预测。最后将LSTM-RNN模型与PLS模型及RNN模型的结果进行对比,验证该方法的优势。研究发现LSTM-RNN模型预测误差稳定,预测精度较高,比传统的统计学及神经网络方法取得了更好的预测精度。

关键词: 预测, 动态建模, 神经网络, 高炉炼铁, 硅含量

CLC Number: