锻压技术

非稳态变工况下动态轧制力模型研究

英文标题：Study on dynamic rolling force model under unsteady state and variable working conditions

单位：1.河北工程大学河北省智能工业装备技术重点实验室 2.河钢集团邯钢公司技术中心

分类号：TG335

出版年,卷(期):页码：2023,48(12):170-176

摘要：

考虑工作辊水平振动、垂直振动和动态轧制工艺参数，建立基于一维卷积神经网络（1D CNN）和长短时记忆网络(LSTM)相结合的CNN-LSTM动态轧制力模型。针对热轧过程产品规格多、频繁换辊等非稳态变工况问题，采用迁移学习方法加强对小样本目标数据的动态轧制力预测。结果显示：CNN-LSTM模型具有更好的泛化能力，在10354组数据时，CNN-LSTM动态轧制力模型的预测精度为96.7%，相对误差在0.3%以内；针对变工况情况，迁移学习模型需600组数据才使预测精度达到90%以上。使用迁移学习方法节省了数据训练和参数调整时间，提升了小样本目标数据的预测精度，能够更好地适应实际生产，为动态轧制力快速预测和抑振提供了新的思路。

Considering the horizontal vibration, vertical vibration and dynamic rolling process parameters of work roll, a CNN-LSTM dynamic rolling force model based on a combination of one-dimensional convolutional neural network (1D CNN) and long short-term memory network (LSTM) was established. Then, aiming at the problems of unsteady state and variable working conditions such as multiple product specifications and frequent roll changes in the hot rolling process, the dynamic rolling force prediction of small sample target data was enhanced by the transfer learning method. The results show that the CNN-LSTM model has better generalization ability. With 10354 sets of data, the prediction accuracy of the CNN-LSTM dynamic rolling force model is 96.7%, and the relative error is within 0.3%. For variable working conditions, the transfer learning model needs 600 sets of data to achieve the prediction accuracy of more than 90%. The time of data training and parameter adjustment is saved by the transfer learning method, the prediction accuracy of small sample target data is improved to better adapt to the actual production, which provides a new idea for the rapid prediction of dynamic rolling force and vibration suppression.

基金项目：

国家自然科学基金青年项目（52005148）

作者简介：陈浩炎（1998-），男，硕士研究生 E-mail：2215683698@qq.com 通信作者：张明（1988-），男，博士，副教授 E-mail：zhangming@hebeu.edu.cn

参考文献：

[1]何坤,王立.中国钢铁工业生产能耗的发展与现状[J].中国冶金,2021,31(9):26-35.

He K, Wang L. Development and status of production energy consumption of China′s iron and steel industry[J]. China Metallurgy, 2021,31(9):26-35.

[2]张福明,李林,刘清梅. 中国钢铁产业发展与展望[J].冶金设备,2021,265(1):1-6，29.

Zhang F M, Li L, Liu Q M. Prospect and developmentof China′s steel industry[J]. Metallurgical Equipment, 2021, 265(1):1-6，29.

[3]Peng Y, Zhang M, Sun J L, et al. Experimental and numerical investigation on the roll system swing vibration characteristics of a hot rolling mill [J]. ISIJ International, 2017, 57(9):1567-1576.

[4]和东平. 基于动态轧制力的波纹辊轧机非线性垂振及稳定性控制研究[D].太原:太原理工大学,2021.

He D P. Study on Nonlinear Vertical Vibration and Stability Control of the Corrugated Rolling Mill Based on Dynamic Rolling Force[D].Taiyuan:Taiyuan University of Technology, 2021.

[5]崔金星. 热连轧机辊系与板带动态行为分析及动力学建模[D]. 秦皇岛:燕山大学,2022.

Cui J X. Dynamic Behavior Analysis and Dynamic Modeling of Rollsystem and Strip of Hot Tandem Mill[D]. Qinhuangdao: Yanshan University, 2022.

[6]侯东晓,郭大武,陈小辉. 基于动态轧制力的四辊轧机垂直-扭转耦合非线性振动特性研究[J]. 振动与冲击,2020,39(20):106-112.

Hou D X, Guo D W, Chen X H. A study on vertical-torsional coupled nonlinear vibration characteristics of 4-h rolling mill based on dynamic rolling force[J].Journal of Vibration and Shock, 2020, 39(20):106-112.

[7]杨彦博,彭艳,刘洋,等.考虑辊缝变化的板带热轧动态理论模型[J].钢铁,2022,57(2):85-93.

Yang Y B, Peng Y, Liu Y, et al. Dynamic theoretical model of strip hot rolling considering change of roll gap[J]. Iron and Steel, 2022, 57(2):85-93.

[8]刘彬,赵红旭,朱月,等. 基于动态轧制力的冷轧机两自由度垂直振动特性[J].中国机械工程,2014,25(17):2344-2350.

Liu B, Zhao H X, Zhu Y, et al. Two degree of freedom vertical vibration characteristics of cold rolling mill based on dynamic rolling force[J]. China Mechanical Engineering, 2014, 25(17):2344-2350.

[9]刘相华,赵启林,黄贞益.人工智能在轧制领域中的应用进展[J].轧钢,2017,34(4):1-5.

Liu X H, Zhao Q L, Huang Z Y. Prospect of artif-icial intelligent application in rolling[J]. Steel Rolling, 2017, 34(4):1-5.

[10]丁敬国,金利,孙丽荣,等. 板带热轧过程智能化建模方法的研究现状与展望[J].冶金自动化,2022,46(6):25-37.

Ding J G, Jin L, Sun L R, et al. Research status and prospect of intelligent modeling method for hot strip rolling process[J]. Metallurgical Industry Automation, 2022, 46(6):25-37.

[11]张瑞成,曹志新. 基于EEMD-LSTM的冷连轧机振动预测研究[J].锻压技术,2022,47(9):174-181.

Zhang R C, Cao Z X. Research on vibration prediction of tandem cold rolling mill based on EEMD-LSTM[J]. Forging & Stamping Technology, 2022,47(9):174-181.

[12]马威,李维刚,赵云涛,等.基于深度学习的热连轧轧制力预测[J].钢铁研究学报,2019,31(9):805-815.

Ma W, Li W G, Zhao Y T, et al.Prediction of hot-rolled roll force based on deep learning[J]. Journal of Iron and Steel Research, 2019, 31(9):805-815.

[13]刘明华,张强,刘英华,等.基于机器学习的热轧轧制力预测[J].锻压技术,2021,46(10):233-241.

Liu M H, Zhang Q, Liu Y H, et al. Prediction of rolling force in hot rolling based on machine learning[J]. Forging & Stamping Technology, 2021,46(10):233-241.

[14]Wang C L,Zhang M. Research on dynamic rolling force prediction model based on CNN-BN-LSTM[J]. Journal of Advanced Mechanical Design, Systems, and Manufacturing, 2022,16(3):1-14.

[15]王俊成,邹斌.基于迁移学习的切削力神经网络预测模型优化策略[J].组合机床与自动化加工技术,2021，(5):43-46.

Wang J C, Zou B. Optimization strategy of neural network prediction model for cutting force based on transfer learning[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2021,(5):43-46.

[16]张西宁,余迪,刘书语.基于迁移学习的小样本轴承故障诊断方法研究[J].西安交通大学学报,2021,55(10):30-37.

Zhang X N, Yu D, Liu S Y. Fault diagnosis method for small sample bearing based on transfer learning[J]. Journal of Xi′an Jiaotong University,2021,55(10):30-37.

[17]陈仁祥,唐林林,胡小林,等. 不同转速下基于深度注意力迁移学习的滚动轴承故障诊断方法[J].振动与冲击, 2022,41(12):95-101,195.

Chen R X, Tang L L, Hu X L, et al. A rolling bearing fault diagnosis method based on deep attention transfer learning at different rotations[J]. Journal of Vibration and Shock, 2022,41(12):95-101,195.

[18]Luai A S,Zyad S,Basel K. Data mining: A preprocessing engine[J]. Journal of Computer Science,2006,2(9):735-739.

[19]刘阳,郜志英,周晓敏,等.工业数据驱动下薄板冷轧颤振的LSTM智能预报[J].机械工程学报,2020,56(11):121-131.

Liu Y, Gao Z Y, Zhou X M,et al. Industrial data-driven intelligent forecast for chatter of cold rolling of thinStrip with LSTM recurrent neural network[J]. Journal of Mechanical Engineering,2020,56(11):121-131.

[20]刘建伟,赵会丹,罗雄麟,等.深度学习批归一化及其相关算法研究进展[J].自动化学报,2020,46(6):1090-1120.

Liu J W, Zhao H D, Luo X L, et al. Research progress on batch normalization of deep learning and its related algorithms[J]. Acta Automatica Sinica, 2020,46(6):1090-1120.

[21]杨静,任彦,高晓文，等.基于GA-PELM的板材热连轧轧制力预测[J].锻压技术,2022,47(1):43-48.

Yang J, Ren Y, Gao X W, et al. Prediction of rolling force of sheet metal hot tandem rolling based on GA-PELM[J]. Forging & Stamping Technology, 2022,47(1):43-48.

[22]Chicco D,Warrens M J,Jurman G. The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation[J]. Peer J. Computer Science,2021,7(1):1-24.

服务与反馈：

【本网站尚未开通全文下载服务】【加入收藏】