Abstract:Coke oven is a complex object with the characteristics of long timedelay, strong nonlinearity, multivariable coupling and parameters changeability. The mean flue temperature is affected by many factors and traditional control method is not satisfactory.A control principle of combining the intermittent heating control with heating gas flow adjustment was proposed and the intelligent control methods, namely fuzzy control and neural network, were adopted to establish intelligent control strategy and model of coke oven heating, which combines two feedback control, one feedforward control and intelligent control. According to coking mechanism,a feedforward model was built for heat supply, and carbonization index CI feedback model was proposed to control coking.A flue temperature soft measurement model based on linear regression and RBF neural network was built to establish temperature feedback control. Intelligent control methods were used to control heating time and heating gas flow. Finally a compound intelligent control system of coke oven was developed. The practical operation indicated that the system can realize intelligent control of coke oven, stabilize production, improve effectively coke quality and decrease energy consumption.
李公法;孔建益;蒋国璋;熊禾根;杨金堂;侯宇. 焦炉加热复合智能控制系统的研究与应用[J]. 钢铁, 2008, 43(8): 89-0.
LI Gongfa;KONG Jianyi;JIANG Guozhang;XIONG Hegen;YANG Jintang;HOU Yu. Research and Application on Compound Intelligent Control System for Coke Oven Heating. Iron and Steel, 2008, 43(8): 89-0.