期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

基于KF与ESN的糖厂澄清工段在线预测

Online Prediction for Clarifying Process in Sugar Mill Based on KF and ESN
下载PDF
导出
摘要 糖厂澄清工段是甘蔗制糖的重要工艺环节之一,是一个复杂的物理、化学过程,具有非线性、大时滞、时变等特点。而且不同的榨季、甘蔗的品种、新技术的应用等情况,都可能导致过去良好的控制模型往往不能及时适应新情况的发生。基于大量离线、在线数据,结合回声状态网络(ESN)和Kalman滤波(KF)的特点,设计了应用于糖厂澄清工段的在线自适应预测方法。该方法将Kalman滤波应用于ESN的高维状态空间中,可以直接对网络的输出权值进行更新。将仿真结果与基于EKF的RBF网络相比较,说明了基于KF与ESN的糖厂澄清工段在线预测模型的优越性。 As a very important part,the clarification process in the cane sugar manufacturing is a complex physical and chemical process,with the characteristics of nonlinear,large time delay and time-varying.Under the conditions of different press quarter,cane sugar varieties,new technologies,and so on,the past good control model can not timely adjust to the new situation.According to a large number of offline and online data,a method of online adaptive prediction based on echo state network（ESN） and Kalman filter（KF） algorithm in the clarification process of the cane sugar manufacturing is designed.The KF is adopted to the high-dimension state space to directly update the output weights of the ESN.Compared with RBF network based on EKF,the simulation results illustrate the superiority of the algorithm based on KF and ESN applied to the clarification process of cane sugar manufacturing.
作者 宋春宁 夏友才 林小峰
机构地区 广西大学电气工程学院
出处 《测控技术》 CSCD 2015年第4期63-66,共4页 Measurement & Control Technology
基金 国家自然科学基金项目(61364007) 广西自然科学基金项目(2011GXNSFC018017)
关键词 糖厂澄清工段 回声状态网络 卡尔曼滤波 在线预报 clarifying process in the cane sugar manufacturing echo state network（ESN） Kalman filter（KF） online prediction
分类号 TP183 [自动化与计算机技术—控制理论与控制工程]
  • 相关文献

参考文献8

  • 1宋绍剑,史长城,林小峰,宋春宁.糖厂澄清过程中和pH值控制的RBF神经网络建模研究[J].自动化技术与应用,2009,28(11):7-10. 被引量：7
  • 2杨文,侍洪波,汪小帆.卡尔曼一致滤波算法综述[J].控制与决策,2011,26(4):481-488. 被引量：30
  • 3Boutayed M, Rafaralahy H, Darouach M. Covergence analysis of the extended Kalman filter used as an observer for nonlin- ear deterministic discrete-time systems [ J ].IEEE Transac- tions on Automatic Control, 1997,42(4) :581 -586.
  • 4Sum J, Leung C S, Young G H, et al. On the Kalman filtering method in neural network training and pruning [ J ]. IEEE Transactions on Neural Networks, 1999,10( 1 ) : 161 - 166.
  • 5Jaeger H, Haas H. Harnessing nonlinearity:predicting chaotic systems and saving energy in wireless communication [ J ]. Science, 2004,304 : 78 - 80.
  • 6刘颖,时飞飞,赵珺,王伟,丛力群,冯为民.基于改进回声状态网络的高炉煤气产耗预测[J].系统仿真学报,2011,23(10):2184-2189. 被引量：10
  • 7陈维钧,许斯欣,等.甘蔗制糖原理与技术[M].北京:中国轻工业出版社,2001.
  • 8Cemansky M, Benuskova L. Simple recurrent network trained by RTRL and extended Kalman filter algorithms [ J ]. Neural Network World, 2003,13 (3) : 223 - 234.

二级参考文献53

  • 1J.D POWELL.Radial Basis Function Approscimations to Poly-nomials[C].Proc.of 12th Biennial Numerial Analysis Conf., 1987,223-241.
  • 2陈其斌,周重吉.甘蔗制糖手册(第十二版)[M].广州:华南理工大学出版社,1993.
  • 3CHEN S.Nonlinear time series modeling and prediction using Gaussian RBF network with enhanced clustering and RLS learning[J]. Electronics Letters, 1995,31 (2) : 319-329.
  • 4M R Cowper, B Mulgrew, C P Unsworth. Nonlinear prediction of chaotic signals using a normalized radial basis function network [J]. Signal Processing (S0165-1684), 2002, 82(5): 775-789.
  • 5K R Muller, A J Smola, G Ratsch, B Scholkopf, J Kohlmorgen, V N Vapnik. Predicting time series with support vector machines [C]// Proc. 7th Int. Conf. Artificial Neural Networks (ICANN'97), London, UK. USA: IEEE, 1997: 999-1004.
  • 6S Mukherjee, E Osuna, F Girosi. Nonlinear prediction of chaotic time series using support vector machines [C]//Proc. 7th IEEE Workshop Neural Network. Signal Process, (NNSP), Amelia Island, USA, 1997. USA: IEEE, 1997: 24-26.
  • 7L J Cao, F E H Tay. Support vector machine with adaptive parameters in financial time series forecasting [J]. IEEE Trans. Neural Network (S 1045-9227), 2003, 14(6): 1506-1518.
  • 8J Vesanto. Using the SOM and local models in time-series prediction [C]// Proc. Workshop Self-Organizing Maps (WSOM'97), 1997: 209-214.
  • 9L A Feldkamp, D Prokhorov, C F Eagen, F Yuan. Enhanced multi-stream Kalman filter training for recurrent networks [M]. Nonlinear modeling: advanced black-box techniques. Netherland: Kluwer Academic Publishers, 1998 : 29-53.
  • 10J C Principe, J M Kuo. Dynamic modeling of chaotic time series with neural networks [C]// Advances in Neural Information Processing Systems, 1994:311-318.

共引文献57

测控技术
2015年 第4期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部