期刊文献+

石墨化炉人工神经网络预测控制的研究 被引量:3

Study on ANN Forecast Control of Graphitizing Furnace
下载PDF
导出
摘要 针对目前石墨化炉控温精度不高,时有裂纹废品出现的现状,为提高石墨电极质量,实现石墨化炉的精确控温问题,提出了石墨化炉神经网络预测控制策略。利用径向基函数神经网络建立了石墨化炉稳态模型;利用工业过程裸模化方法,建立了石墨化炉的动态模型,为进一步实现石墨化炉的神经网络预测控制,完成了至关重要的第一步。该石墨化炉神经网络模型,计算机仿真结果非常理想,拟和精度很高,完全可以作为下一步实现预测控制的模型。 At present, the accuracy of controlling the temperature in graphitizing furnaces is not high, and there are several wasters with flaws ustoally. One approach is presented that adapts predictive control based neural network to control the temperature of graphitizing furnace. The approach is for improving the electrode quality and making precise temperature control. The static model of graphitizing furnace is maked using RBF network and finished the dynamic model of graphitizing furnace using the industrial process bare model method. The first important step of predictive control based neural network of graphitizing furnace has been finished. The model has obtained very good simulation result on comput- ers. The precision of the model is very satisflng.
出处 《控制工程》 CSCD 2006年第5期466-468,共3页 Control Engineering of China
关键词 石墨化 神经网络预测控制 径向基函数网络 最小二乘法 动态网络 graphitizing predictive control based neural network radial basis function network least square method dynamic network
  • 相关文献

参考文献10

  • 1韦保林,罗晓曙,汪秉宏,郭维,傅金阶.EEG信号的径向基函数神经网络预测[J].中国生物医学工程学报,2003,22(6):488-492. 被引量:9
  • 2高倩,阎威武,邵惠鹤.基于正则化RBF神经网络的软测量技术及其在质量预测中的应用(英文)[J].系统仿真学报,2005,17(7):1609-1612. 被引量:5
  • 3Karayiannis N B.Gradient descent learning of radial basis neural networks[J].IEEE Int Conf Neural Networks,1997,3(9):1815-1820.
  • 4He X D,Lapedes A.Successire approximation radial basis function networks for nonlinear modeling and prediction[J].Int J Control,1993,2(25):1997-2000.
  • 5Chen S,Billings S A,Cowan C F N,et al.Non-linear systems identification using radial basis functions[J].Int J Syst Sci,1990,21(12):2513-2539.
  • 6Chen S,Billings S A.Neural networks for nonlinear dynamic system modeling and identification[J].Int J Control,1992,56(2):319-346.
  • 7Chen T,Chen H.Approximation capability to functions of several variables,nonlinear functionals,and operators by radial basis function neural networks[J].IEEE Trans Neural Networks,1995,6(4):904-910.
  • 8Karayiannis N B,Behnke S.New radial basis neural networks and their application in a large-scale handwritten digit recognition problem[A].Recent Advances in Artificial Neural[C].Boca Raton,FL:Networks CRC,2000.
  • 9万亚民,王孙安,杜海峰.液压并联机器人的动态神经网络控制研究[J].西安交通大学学报,2004,38(9):955-958. 被引量:15
  • 10王永祥,黄筱调.基于神经网络移动机器人PID控制[J].控制工程,2005,12(5):458-460. 被引量:5

二级参考文献42

  • 1王耀南,童调生,蔡自兴.基于神经元网络的智能PID控制及应用[J].信息与控制,1994,23(3):185-189. 被引量:44
  • 2[1]Dasgupta B, Mruthyunjaya T S. The stewart platform manipulator: a review[J]. Mechanism and Machine Theory, 2000, 35(2): 15-40.
  • 3[2]Honegger M, Brega R, Schweitzer G. Application of a nonlinear adaptive controller to a 6 DOF parallel manipulator[A]. Proc of the 2000 IEEE International Conference on Robotics and Automation[C]. San Francisco: Hoes Lane, 2000. 1 930-1 935.
  • 4[5]Ku C C, Lee K Y, Edwards R M. Improved nuclear reactor temperature control using diagonal recurrent neural networks[J]. IEEE Transactions on Nuclear Science, 1992, 39(6): 2 298-2 308.
  • 5Mathwork Inc. System identification Toolbox user's guide[M]. New York: The Mathwork Inc, 2003.
  • 6Burger M,Neubauer A.Error bounds for approximation with neural networks [J].Journal of Approximate Theory,2001,112(2):235-250.
  • 7Xin Li.On simultaneous approximations by radial basis function neural networks [J].Applied Mathematics and Computation,1998,95(1):75-89.
  • 8Krzyzak A,Linder T,Lugosi C.Nonparametric estimation and classification using radial basis function nets and empirical risk minimization [J].IEEE Trans.on Neural Networks,1996,7(2):475-487.
  • 9Xudong Wang,Rongfu Luo,Huihe Shao.Designing a Soft Sensor for Distillation Column with the Fuzzy Distributed Radial Basis Function Neural Network.Proceeding of the 35th conference of decision and control,1996,12:1714-1719.
  • 10Kuo R J,Cohen P H.Multi-sensor integration for on-line tool wear estimation through radial basis function networks and fuzzy neural network [J].Neural Network,1999,12(2):355-370.

共引文献28

同被引文献25

  • 1顾鹏,冯俊杰,张胜恩.内串石墨化炉炉体的优化与改进[J].炭素技术,2019,0(5):64-67. 被引量:1
  • 2宫赤坤,闫雪.基于RBF神经网络的预测控制[J].上海理工大学学报,2005,27(5):421-424. 被引量:13
  • 3刘耀年,李迎红,刘俊峰,姚玉萍.基于人工鱼群算法的径向基神经网络的研究[J].东北电力大学学报,2006,26(4):23-27. 被引量:12
  • 4Karayiannis N B. Gradient descent learning of radial basis neural networks[J]. IEEE Int Conf Neural Networks, 1997, 3 (9): 1815-1820.
  • 5Gong Chikun, Yah Xue. MPC based on RBF Neu-ral network. Shanghai Science and Engineering College, 2005, 27(5):421.
  • 6Qu Liping, Qu Yongyin.NN-MPC on graphitizing furnace. Control Engineering, 2006, 13(5): 466.
  • 7Yang Peng, Liu Pinjie. An Improved MPC based on RBF neural network.Computer Simulation, 2009, 16(1):39-41.
  • 8Wang Dongqing. NN-MPC on nonlinear time delay systems. TianJin University Doctor Thesis. 2005:75-80.
  • 9Hu Pinhui. Multivariable state feedback model predictive control and its application.China University of Petroleum Doctor Thesis. 1999:9-10.
  • 10Shu Diqian. Predictive Control System and Its Application. Beiiing: Machinery Industry Publishing House, 1998: 98.

引证文献3

二级引证文献6

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