Study On The Temperature Optimized Of Billet Reheating Furnace Control Based On Improved BP Neural Network

As the main energy -consuming equipment in metallurgy enterprise,the strategy of automatic control of heating furnace is one of the most important research Topics in the field of related process control. How to design an excellent automatic control system that can not only ensure the heating quality,but also ensure good burning quality,economize energy consume,prolong the life of the equipments and reduce the pollution of the environment ,is a main problem waiting to be solved.The traditional PID control which based on mathematic model was steady and reliable, and was applied in many fields. The characteristic of the combustion ,such as, the great inertia, the nonlinearity, the long time delay, makes us very difficult to control the reheating furnace. So it is difficult to establish an accurate model of controlled object, and we can not control the reheating furnace with traditional technique.Artificial neural network, as an important part of artificial intelligence, has great potential in application. This thesis mainly studies the structures and algorithms of BP neural network and its application to PID control. At last, based on the temperature control model , this paper does contrast research of the algorithms' control performance.The results indicates obviously that the BP neural network PID controller optimized by improved conjugate gradient algorithm is better than other algorithms in training velocity and constringency precision, which confirm the availability and practicability of new algorithm, and achieve the expectant intention of the paper.