摘要
以全混流反应器为例 ,对反馈神经网络在动态过程数据校正中的应用进行了研究 ,并对 Elman网络及其改进形式进行了比较。由校正结果得出 ,Elman网络引入自反馈后 ,能更好地反映系统的动态特性。
In this paper, the use of recurrent neural network in dynamic process for data reconciliation is studied with a example of CSTR, and a comparison of the results produced between using Elman network and its modified form is presented. It can be seen from the reconciliation results that Elman network can give the dynamic characteristics of the system with improved quality when the self-recurrent introduced into the reconciliation process.
出处
《青岛科技大学学报(自然科学版)》
CAS
2003年第3期251-253,276,共4页
Journal of Qingdao University of Science and Technology:Natural Science Edition