THE STUDY OF THE DECOUPLING CONTROL IN A RECTIFYING TOWER BASED ON NEURAL NETWORKS
It is analyzed that coupling relations among each variable in the operating processes of a rectifying tower in which BP neural network is applied for the temperature of decoupling control according to dynamic characteristics of multivariate , nonlinear and strong coupling system. Based on traditional PID controls we have suggested a new control algorithm of BP neural net works with decouple network ahead of adjuster and then, an intelligent controller with decoupling ability is made up. The result of simulating tests shows that this algorithm is provided with good control effects.
Rectifying tower Multivariate system BP neural network Decoupling control
LI-JUN HAO ZENG-TAO XUE ZHI-HONG WANG
Collage of Electricity and Information, Hebei University of Science and Technology, Shijiazhuang 050018,China
国际会议
2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)
昆明
英文
2170-2174
2008-07-12(万方平台首次上网日期,不代表论文的发表时间)