一类用于连续过程逼近的过程神经元网络及其应用

许少华, 何新贵, 李盼池

许少华, 何新贵, 李盼池. 一类用于连续过程逼近的过程神经元网络及其应用[J]. 信息与控制, 2004, 33(1): 116-119.
引用本文: 许少华, 何新贵, 李盼池. 一类用于连续过程逼近的过程神经元网络及其应用[J]. 信息与控制, 2004, 33(1): 116-119.
XU Shao-hua, HE Xin-gui, LI Pan-chi. A Process Neural Network for Continuous Process Approximation and Its Application[J]. INFORMATION AND CONTROL, 2004, 33(1): 116-119.
Citation: XU Shao-hua, HE Xin-gui, LI Pan-chi. A Process Neural Network for Continuous Process Approximation and Its Application[J]. INFORMATION AND CONTROL, 2004, 33(1): 116-119.

一类用于连续过程逼近的过程神经元网络及其应用

基金项目: 黑龙江省自然科学基金资助项目(F0211)
详细信息
    作者简介:

    许少华(1962- ),男,博士,教授研究领域为模糊理论,模式识别,神经网络等.
    何新贵(1938- ),男,教授,博士生导师.研究领域为模糊逻辑,进化计算,神经网络,数据库理论等.
    李盼池(1969- ),男,硕士.研究方向为神经网络,模糊理论,进化计算等.

  • 中图分类号: TP183

A Process Neural Network for Continuous Process Approximation and Its Application

  • 摘要: 针对实际系统的输入输出是与时间有关的连续过程,提出了一类用于连续过程逼近的过程神经元网络模型.模型利用神经网络所具有的非线性映射能力,实现系统输入输出之间的连续映射关系.考虑过程神经网络计算的复杂性,在输入空间中选择一组函数正交基,将输入函数和网络权函数表示为该组正交基的展开形式,利用基函数的正交性,简化过程神经元计算.文中给出了学习算法,并以油藏开发三次采油过程模拟为例验证了模型和算法的有效性.
    Abstract: For the problem that the input and output of real systems is a continuous process relative to time,this paper proposed a process neural network model for continuous function approximation.Using the nonlinear mapping ability of neural network,this model performs the continuous-mapping relation between input and output of system.Considering the computation complexity of process neural network,a group of function orthogonal bases are selected in input space.Input function and network weight functions are expressed as the expansion form of the function orthogonal bases.Thus operation of process neuron is simplified by using orthogonality of functions.The learning algorithm is given,and the effectiveness of the model and algorithm is proved by tertiary oil recovery process simulation of oil reservoir development.
  • [1] McCulloch W S,Pitts W H.A logical calculus of the ideas immanent in neuron activity[J].Bulletin Mathematical Biophysics,1943,5(1):115~133.
    [2] Hornik K,Stinchcombe M,White H.Multilayer feedforword networks are universal approximators[J].Neural Networks,1989,2(3):359~366.
    [3] He X G,Liang J Z.Process neural network[A].World Computer Congress 2000,Proceedings of Conference on Intelligent Information Processing[C].Beijing:2000.143~146.
    [4] 何新贵,梁久祯,许少华.过程神经元网络的训练及其应用[J].中国工程科学,2001,3(4):31~35.
    [5] 柳重堪.正交函数及其应用[M].北京:国防工业出版社,1982.7~16.
计量
  • 文章访问数:  673
  • HTML全文浏览量:  0
  • PDF下载量:  54
  • 被引次数: 0
出版历程
  • 收稿日期:  2002-11-13
  • 发布日期:  2004-02-19

目录

    /

    返回文章
    返回
    x