论文部分内容阅读
根据电弧炉物料平衡理论与利用BP神经网络的方法,建立了理论模型结合神经网络的电弧炉炼钢全程钢水碳质量分数实时预测模型。通过模型得出冶炼过程中碳质量分数变化曲线,实现对全程钢水碳质量分数的实时监控。在接近冶炼终点时,由于脱碳反应中碳氧积的存在,因此模型对影响终点碳质量分数的因素进行分析,采用BP神经网络方法进行预测,满足了对电弧炉冶炼终点碳质量分数预报准确度的要求。
According to the material balance theory of EAF and the method of using BP neural network, a real-time prediction model of carbon mass fraction of molten steel in EAF steelmaking based on theoretical model and neural network was established. Through the model, the curves of carbon mass fraction in smelting process are obtained, and the real-time monitoring of the carbon mass fraction of molten steel in the whole process can be realized. Near the end of smelting, due to the presence of carbon and oxygen in the decarburization reaction, the model is used to analyze the factors that affect the end point carbon mass fraction, and the BP neural network prediction method is used to predict the carbon mass fraction at the end of arc furnace smelting Degree requirements.