Research and application of hybrid intelligent control for coke oven heating process

Coke oven heating temperature was reflected by flue temperature and adjusted by gas flow. Aiming at the coke oven heating process characteristics of great inertia, pure time-delay, strong non-linear and time changeable, the control method of combining the intermittent heating control with the heating gas flow adjustment was adopted. Hybrid intelligent control strategy and model of coke oven heating process were established, which combined two feedback control, one feedforward control and fuzzy control. Energy-required prediction feed-forward model was built to give the initial gas flow. Carbonization index feedback model was proposed to revise the goal flue temperature in order to control coking process. Flue temperature soft measurement model based on linear regression and neural network was built to supply temperature feedback control. According to artificial experience and actual condition in the plant, fuzzy controller was designed. The proper amount of stopping heating time and heating gas flow were computed taking the operation condition of coke oven into account. The practical running results indicate that the system can achieve intelligent control of coke oven heating process, satisfy the actual production need, and has great practical value.