水泥篦冷机出口熟料温度自适应辨识模型
Adaptive identification model for export clinker temperature in cement grate cooler
摘要点击 69  全文点击 72  投稿时间:2017-12-15  修订日期:2018-10-28
查看全文  查看/发表评论  下载PDF阅读器
DOI编号  10.7641/CTA.2018.70932
  2019,36(4):651-658
中文关键词  篦冷机  熟料温度  神经网络  辨识模型
英文关键词  Grate cooler  clinker temperature  neural network  identification model
基金项目  国家自然科学基金
学科分类代码  
作者单位E-mail
赵志彪 燕山大学 magicalbiao@163.com 
刘彬 燕山大学 liubin@ysu.edu.cn 
中文摘要
      为优化水泥篦冷机控制,提高热回收效率,研究篦冷机内熟料换热机理,找出熟料冷却过程的关键影响因素,利用回声状态网络辨识篦冷机运行数据,基于递归最小二乘法推导网络的在线学习算法,实现权值自适应调整,构建篦冷机内熟料温度的自适应模型。仿真实验可知,构建的模型能够在系统发生变化时自适应调整网络的输出权值矩阵,使模型快速收敛,相比其它离线方法,自适应模型可以持续逼近篦冷机出口数量温度曲线,可作为辨识模型来指导篦冷机控制,为篦冷机的优化控制奠定了基础。
英文摘要
      In order to optimize the heat recovery efficiency of the cement cooler, the heat exchange mechanism of the clinker in the grate cooler was studied, the key factors affecting the clinker cooling process were found and the operating data of grate cooler is trained by echo state network (ESN). In order to solve the mismatch problem of off-line identification model, t a network online learning algorithm was deduced based on the recursive least squares, an adaptive model of the clinker temperature in the grate cooler was built. Base on that, adaptive identification approach and process for the export of clinker temperature is given. Simulation experiments show that the model can adjust the output weight matrix of the network adaptively when the system changes, so that the model converges quickly. Compared with other off-line methods, the RLS-ESN self-adaptive model of the clinker temperature of the grate cooler can ensure prolonged and effective. The completion of these basic work can guides grate cooler control and lays the foundation for the optimal control and energy conservation and emission reduction of grate coolers.