基于聚类和神经网络的热轧轧制力综合预报研究
首发时间:2014-12-11
摘要:为了提高热轧生产过程精轧机组的轧制力预设定精度,需要对轧制力进行高精度的预报。本文通过理论公式计算出轧制力的近似值,然后利用基于聚类方法的反向传播神经网络计算出轧制力的修正系数,通过二者结合来预报出高精度的轧制力值。结果表明,轧制力预报的平均相对误差为3.2%,满足了现场的生产要求。
For information in English, please click here
Research on comprehensive Prediction of Rolling Force in Hot-rlling Based on clustering and Neural Network
Abstract:In order to improve the setting accuracy of rolling force in finishing mill in hot rolling process, high precision prediction of rolling force is very important. In this paper, the approximate value of rolling forcewe is calculated through theoretical formula. And then, the correction coefficient of rolling force is computed based on the clustering method and back-propagation neural network. Through the combination of the two results, the rolling force value with high precision is predicted. The results show that the average relative prediction error of the rolling force is 3.2%, which can meet the production requirements of field.
Keywords: Hot-rolling Rolling Force Back Propagation Neural Network Clustering Prediction
论文图表:
引用
No.4621968946526141****
同行评议
共计0人参与
勘误表
基于聚类和神经网络的热轧轧制力综合预报研究
评论
全部评论0/1000