Title :
The study of the decoupling control in a rectifying tower based on neural networks
Author :
Hao, Li-jun ; Xue, Zeng-tao ; Wang, Zhi-hong
Author_Institution :
Coll. of Electr. & Inf., Hebei Univ. of Sci. & Technol., Shijiazhuang
Abstract :
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 networks 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.
Keywords :
backpropagation; intelligent control; neurocontrollers; nonlinear control systems; petrochemicals; three-term control; BP neural network; PID controls; coupling system; decoupling control; intelligent controller; multivariate system; neural networks; nonlinear system; rectifying tower; Control systems; Couplings; Intelligent networks; Neural networks; Nonlinear control systems; Nonlinear dynamical systems; Poles and towers; Temperature control; Testing; Three-term control; BP neural network; Decoupling control; Multivariate system; Rectifying tower;
Conference_Titel :
Machine Learning and Cybernetics, 2008 International Conference on
Conference_Location :
Kunming
Print_ISBN :
978-1-4244-2095-7
Electronic_ISBN :
978-1-4244-2096-4
DOI :
10.1109/ICMLC.2008.4620765
