摘要
针对静态前馈网络和Elman网络在软测量建模中的不足,提出了一种新的改进的Elman网络模型,并将此模型应用于精馏塔出口成分含量的软测量建模中。实验模拟结果表明:改进的Elman网络模型具有更高的预测精度和较快的收敛速度,能够更好地实现精馏塔出口成分含量的软测量建模,为进一步实现产品质量控制提供了保证。
Aimed at the shortcomings of static feedforward network and Elman network in soft sensor modeling,a new modified Elman neural network is proposed,and applied to soft sensor modeling of Rectifying Column.Simulation results show that the modified Elman neural network has better precision and faster convergence rate.It performances better in soft sensor modeling of Rectifying Column,and provides the guarantee for the production quality control.
出处
《计算机工程与应用》
CSCD
北大核心
2008年第16期233-235,共3页
Computer Engineering and Applications
