摘要
分析了影响鞍钢冷轧厂冷轧带钢表面粗糙度的主要因素,采用BP神经网络算法建立了预报冷轧带钢表面粗糙度的数学模型,利用鞍钢冷轧厂数据对模型离线应用表明,该数学模型的计算误差率在0~±3%范围内的比例为100%。
The main factors influencing the surface roughness of cold rolled steel strip produced in Cold Rolled Mill of Angang are analyzed and the mathematical model for forecasting the surface roughness is established by BP neural network method.The offline applications of the model based on data available from the Cold Rolled Mill of Angang show that the percentage of this mathematical model with calculation error rate less than 3% is 100%.
出处
《鞍钢技术》
CAS
2013年第1期36-39,共4页
Angang Technology
关键词
冷轧带钢
表面粗糙度
神经网络
数学模型
cold rolled steel strip
surface roughness
neural network
mathematical model
