The Application Of Single Neuron Adaptive PID Controller In Gas Collector Pressure Of Coke Oven

With the development of national economy, the iron and steel industry already plays an important role in the national economy development. Coke and coke-oven gas are very important sources of energy in the field. In coking process, the stable pressure of gas collector is the main parameter for the coke normally producing. But the gas collector pressure system is a complex multi-variable non-linear, time-varying, long time-delay control system and is not easy to set up its mathematical model. The shortages of traditional PID (Proportion Integral Differential) controller are that the system's overshoot is large, regulation time is long and parameter is hard to be real-time adjusted and the system is difficult to meet the real-time control.The neuron has the very strong ability in information synthesis, study memory, self-study, and adaptation, so, it can deal with some processes that are difficult to describe with the model or rule. The neuron combined with PID can make control intelligent and parameters are real-time adjusted and its application in gas collector pressure of coke oven makes the control system have a stronger anti-disturbance ability, adaptive ability and a better robustness performance.In this paper, based on the gas collector pressure control system of the NO.1~NO.4 coke oven in the coking plant, Xiantan iron and steel company, the theory of single neuron adaptive PID control is researched, mainly in its algorithm and the algorithm modification. A perfect control performance is obtained after the improved algorithm is applied in the gas collector pressure control system.