论文部分内容阅读
针对传统轧制力模型的固有缺陷,提出了一种基于灰色关联分析的ELM(极限学习机)轧制力预报模型.首先通过灰色关联分析对输入变量进行相关性分析,用于提高模型的性能;然后结合10次10折交叉验证确定ELM模型的隐含层节点数,建立热轧薄板的轧制力预测模型.运用现场数据对该网络进行训练和测试,并与传统的模型相比较.实验结果表明,该模型能快速、准确地预报轧制力,能满足在线预测的要求.
Aiming at the inherent defects of the traditional rolling force model, an ELM (Eluting Learning Machine) rolling force forecasting model based on gray relational analysis is proposed.First, the correlation analysis of input variables is carried out by gray relational analysis to improve the performance of the model Then, the number of hidden layer nodes of the ELM model was determined by 10 10-fold cross-validation, and the rolling force prediction model of hot-rolled sheet was established. The network was trained and tested with on-site data and compared with the traditional model. The results show that the model can predict the rolling force quickly and accurately and meet the requirements of online prediction.