锻压技术

基于灰色理论和神经网络的轧制力预测

英文标题：Prediction of rolling force based on grey theory and neural network

作者：刘杰辉王桂霞刘永康

单位：河北工程大学

分类号：

出版年,卷(期):页码：2015,40(10):126-129

摘要：

针对热轧带钢轧制力预测精度不准确问题，建立了灰色轧制力预测模型，通过对比灰色轧制力预测模型和BP神经网络预测模型的优缺点，进一步提出将灰色理论和BP神经网络组合应用到热轧带钢轧制力预测中，并分析比较了轧制力预测模型的相对误差。同时，在相同的轧制条件下，对灰色神经网络轧制力预测模型的预测值和在线平整轧制的实测轧制力值作了比较，所得轧制力预测误差小于±5%。由此可以看出，灰色理论和BP神经网络组合应用的方法能够较准确地实现平整轧制力的预测。

For the issues of the inaccurate prediction of the hot strip rolling force, the prediction model of gray rolling force was established. Through comparing the advantages and disadvantages of the gray rolling force prediction model with BP neural network prediction model, the method combined gray theory with BP neural network into the prediction of hot strip rolling force prediction was put forward, and the relative error of the rolling force prediction model was analyzed and compared. In the meanwhile, the predicted value of rolling force prediction model of gray neural network was compared with the measured rolling force value of on-line flat rolling，and the error was controlled within ±5%. In this way, the prediction of on-line flat rolling can be accurately achieved by combining the gray theory and BP neural network.

基金项目：

河北省自然科学基金资助项目（E2015402112）

刘杰辉(1968-)，男，硕士，副教授

参考文献：

[1]黄玉萍,王波,邓兆虎,等遗传算法结合神经网络实现拉延筋优化设计[J]. 锻压技术,2007,32（5）:138-141.

Huang Y P, Wang B, Deng Z H, et al. Optimized design of drawbead using improved genetic algorithm combined with BP artificial neural network [J]. Forging & Stamping Technology, 2007,32（5）:138-141.

[2]杨景明,顾佳琪,闫晓莹,等. 基于改进遗传算法优化BP网络的轧制力预测研究[J]. 矿冶工程,2015,(1):111-115.

Yang J M, Gu J Q, Yan X Y, et al. Rolling force prediction based on BP network optimized by an improved genetic algorithm[J]. Mining and Metallurgical Engineering, 2015,(1):111-115.

[3]张俊明,刘军,俞晓峰,等. 轧制力预测中RBF神经网络的组合应用[J]. 钢铁研究学报,2008,(2):33-36.

Zhang J M,Liu J,Yu X F, et al. Application of combination of RBF neural network to prediction of rolling force[J]. Journal of Iron and Steel Research,2008,(2):33-36.

[4]刘杰辉,武杰,王桂梅. 基于灰色理论的非圆截面零件加工切削力的预测[J]. 煤矿机械,2013,(2):129-130.

Liu J H, Wu J, Wang G M. Based on grey system theory of non-circular machining cutting force prediction [J]. Coal Mine Machinery, 2013,(2):129-130.

[5]Dixit U S, Chandra S. A neural network based methodology for the prediction of roll force and roll torque in fuzzy form for cold flat rolling process[J]. The International Journal of Advanced Manufacturing Technology, 2003,2211:883-889.

[6]邱红雷,胡贤磊,矫志杰,等. 中厚板轧制过程中高精度的轧制力预测模型[J]. 钢铁,2005,(5):49-53.

Qiu H L, Hu X L, Jiao Z J, et al. High precision rolling force prediction model for plate rolling[J]. Iron and Steel,2005,(5):49-53.

[7]Johannes Lohmar,Markus Bambach,Gerhard Hirt,et al. The precise prediction of rolling forces in heavy plate rolling based on inverse modeling techniques[J]. Steel Research Int.,2014,8511:1525-1532.

[8]王智,谢延敏,胡静,等. 基于改进灰色神经网络模型的板料成形缺陷预测研究[J]. 中国机械工程,2013,26（22）:3075-3079.

Wang Z, Xie Y M, Hu J, et al. Research on defect prediction in sheet metal forming based on improved gray neural neural network model[J]. China Mechanical Engineering,2013,26（22）:3075-3079.

服务与反馈：

【文章下载】【加入收藏】