引用本文:王伟,吴敏,雷琪,曹卫华.炼焦生产过程综合生产指标的改进神经网络预测方法[J].控制理论与应用,2009,26(12):1419~1424.[点击复制]
WANG Wei,WU Min,LEI Qi,CAO Wei-hua.An improved neural network method for the prediction of comprehensive production indices in coking process[J].Control Theory and Technology,2009,26(12):1419~1424.[点击复制]
炼焦生产过程综合生产指标的改进神经网络预测方法
An improved neural network method for the prediction of comprehensive production indices in coking process
摘要点击 2189  全文点击 897  投稿时间：2008-09-10  修订日期：2009-04-17
查看全文  查看/发表评论  下载PDF阅读器
DOI编号  10.7641/j.issn.1000-8152.2009.12.CCTA080963
  2009,26(12):1419-1424
中文关键词  炼焦生产过程  主元分析  灰色关联分析  改进差分进化算法  改进BP神经网络  预测模型
英文关键词  coking process  principal component analysis  grey relational analysis  improved differential evolution algorithm  improved BP neural network  prediction model
基金项目  国家“863”计划重点项目课题(2008AA042902): 国家杰出青年科学基金资助项目(60425310).
作者单位E-mail
王伟 中南大学 信息科学与工程学院  
吴敏* 中南大学 信息科学与工程学院 min@csu.edu.cn 
雷琪 中南大学 信息科学与工程学院  
曹卫华 中南大学 信息科学与工程学院  
中文摘要
      针对炼焦生产过程综合生产指标(焦炭质量、产量和焦炉能耗)检测的严重滞后问题, 提出一种改进BP神经网络预测方法. 首先基于相关过程参数的主元分析和灰色关联分析, 确定出预测模型的输入输出变量; 然后采用基于改进差分进化算法的BP神经网络建立预测模型, 并与基本BP神经网络预测模型进行比较; 最后, 对改进BP神经网络预测模型进行了验证. 实验结果表明, 改进BP神经网络预测模型具有较快的收敛速度和较高的预测精度, 模型的预测效果可以满足生产工艺要求.
英文摘要
      A prediction method based on the improved back propagation(BP) neural network is proposed to solve the problem of large time-delay in the detection of the comprehensive production indices (quality and quantity of coke, and energy consumption of coke oven) in the coking process. First, the input and output variables of the prediction models are determined by analyzing the process mechanism correlation between process parameters based on principal components analysis and grey relational analysis. Then, the BP neural network based on an improved differential evolution algorithm is applied to establish prediction models, which are compared with the basic BP neural network prediction models. Finally, the prediction models are verified. Simulation results show that the proposed prediction models provide a better convergence rate and higher prediction accuracy, and the prediction effect of the obtained models satisfy the technological requirements.