基于神经网络的转炉炼钢终点控制

转炉炼钢是一种非常重要的炼钢方法,终点控制是转炉炼钢后期的重要操作.由于冶炼过程温度极高,很难进行准确及时地测量,无法形成通常意义下的反馈控制.采用RBF神经网络预报转炉炼钢终点温度和碳含量,在此基础上提出了基于神经网络的动态终点控制方法来确定在补吹阶段需要的吹氧量和加入的冷却剂量,克服了传统控制方法中基于热平衡和氧平衡控制模型不准确的缺点,提高了终点命中率.

BOF steelmaking endpoint control based on neural network

BOF steelmaking is a kind of paramount steelmaking method. The endpoint control is an important operation in the later period of BOF steelmaking. Because the temperature is very high in the smelting, it is very difficult to take measurement accurately and timely. There is not method to form common feedback control. The BOF endpoint temperature and carbon content were predicted by means of RBF neural network. On the basis of this, the dynamic endpoint control method based on neural network was proposed so as to determine the blown oxygen and the added coolant during the reblowing. The shortcoming that the control model based on the heat balance and the oxygen balance was not accurate in the traditional method was overcome. The endpoint hitting ratio was raised.