For the problem of inaccuracy of temperature control caused by large inertia, time variability; pure lag in the heating furnace, this article combined the learning mechanism of neural network control with the human thinking and reasoning of fuzzy control, establishing the 3 d fuzzy neural network system. Neural network is used to implement membership function, and drive the fuzzy reasoning. Using neural network, fuzzy modeling, achieve the goal of refinement fuzzy rules. Then I established the temperature control model of heating furnace which based on the fuzzy neural network. After using the model, the control accuracy and the uniformity of the slab temperature has been improved; the temperature difference between head and tail of slab has been reduced; which have a positive impact on the reducing of fuel consumption in the heating furnace, the improvement of yield in production line and the achievement of energy conservation and environmental protection.
