应用RBF神经网络预测冷连轧机轧制力

Application of RBF Neural Networks to Prediction of Rolling Force of Tandem Cold Mill

针对传统轧制力模型的固有缺陷,为提高冷连轧机组轧制力预测精度,使用一种RBF算法的人工神经网络预测冷轧带钢屈服应力,把预测值用于传统数学模型中计算轧制力;并在此基础上,组合使用机架相关网络(RBF类型)、速度相关网络(RBF类型)修正轧制力计算值。应用结果表明,此方法满足生产的需要,预报最终误差范围为±6.5%。

In view of intrinsic imperfection of traditional models of rolling force, in order to improve the prediction precision of rolling force of tandem cold mill, a sort of artificial neural networks with RBF algorithm was used to predict yield stress of cold rolled steel strip,and then this value was used to calculate rolling force with traditional mathematical model; and then the stand network（RBF type）, speed network（RBF type） were combined to correct calculated rolling force. Application of this method indicated that it has a final error within ±6.5%.