| 基于RBF神经网络的汽包水位软测量模型研究 |
| |
| 引用本文： | 张强,仝卫国,田沛. 基于RBF神经网络的汽包水位软测量模型研究[J]. 仪器仪表用户, 2006, 13(2): 4-6 |
| |
| 作者姓名： | 张强 仝卫国 田沛 |
| |
| 作者单位： | 华北电力大学,自动化系,河北,保定,071003 |
| |
| 摘 要： | 热工系统往往表现出非线性和不确定性．难以建立精确的数学模型。以汽包水位为对象．结合机理分析确定原始变量作为神经网络的输入．通过k均值聚粪法则与梯度下降法实现了网络的学习功能，并最终建立了基于RBF神经网络的软测量模型。阐述了RBF神经网络在汽包水位洲量中的建模与应用。仿真实验表明该模型具有简单易行．精度高、训练时间短、运算速度快的特点．为汽包水位测量提供了一种新的方法。
|
| 关 键 词： | 软测量 RBF神经网络 k均值聚类法则 梯度下降法 |
| 文章编号： | 1671-1041（2006）02-0004-03 |
| 收稿时间： | 2005-11-02 |
| 修稿时间： | 2005-11-02 |
The study on soft-sensor model of water level of boiler drum based on RBF neural network |
| |
| ZHANG Qiang,TONG Wei-guo,TIAN Pei. The study on soft-sensor model of water level of boiler drum based on RBF neural network[J]. Electronic Instrumentation Customer, 2006, 13(2): 4-6 |
| |
| Authors: | ZHANG Qiang TONG Wei-guo TIAN Pei |
| |
| Abstract: | Pyrology systems always represent the characteristics of nonlinear and uncertainty, so it is too difficult to work out the exact mathematic model. Consider water level of boiler drum as the object for study, find out the proper variables as input of the ANN(Artificial Neural Network)throughout the analysis of the inner mechanism .The function of learning was realized using K-means Cluster method and Gradient Descent Algorithm. A soft-sensor model based on RBF is finally induced. The simulation experiment has prove the model can be simply realized and has the characteristics of perfect precision, short training time, high-speed calculation. A new method is provided for measurement of water level of boiler drum |
| |
| Keywords: | Soft sensor RBF neural network K-means Cluster method Gradient descent algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
