锻压技术

基于EEMD-LSTM的冷连轧机振动预测研究

英文标题：Research on vibration prediction for tandem cold rolling mill based on EEMD-LSTM

作者：张瑞成曹志新

分类号：TG335

出版年,卷(期):页码：2022,47(9):174-181

摘要：

针对冷连轧机振动具有非线性、非平稳，以及与当前和历史状态息息相关的特点，提出了基于集合经验模态分解（EEMD）-长短时记忆循环神经网络（LSTM）的轧机振动预测模型。采用EEMD方法将轧机振动加速度分解为若干个频率单一、相对平稳的IMF模态分量和残差分量，有效地降低了振动加速度信号的复杂性；采用具有记忆单元的LSTM网络建立轧机振动预测模型，并通过引入历史振动信息显著提高了轧机振动的预测精度。仿真结果表明，EEMD-LSTM模型较LSTM模型的预测精度提高了11%，对轧机振动有很好的预测效果，并分析了各工艺参数与轧机振动之间的定量关系，为快速抑制轧机振动、优化轧制规程提供了参考。

For the characteristics of non-linear and non-stationary for vibration of tandem cold rolling mill, and it is closely related to the current and historical states, based on Ensemble Empirical Mode Decomposition (EEMD)-Long and Short Term Memory Recurrent Neural Network (LSTM), a rolling mill vibration prediction model was proposed. Then, the rolling mill vibration acceleration was decomposed into several IMF modal components and residual components with single frequency and relative stability by the EEMD method, and the complexity of vibration acceleration signal was reduced effectively. Furthermore, the prediction model of rolling mill vibration was established by using LSTM network with memory unit, and the prediction accuracy of rolling mill vibration was significantly improved by introducing historical vibration information. The simulation results show that the prediction accuracy of EEMD-LSTM model is 11% higher than that of LSTM model, and it has a good prediction effect on the rolling mill vibration. Meanwhile, the quantitative relationship between each process parameter and rolling mill vibration is analyzed, which provides a reference for quickly suppressing the rolling mill vibration and optimizing the rolling schedule.

基金项目：

河北省自然科学基金资助项目（F2018209201）

张瑞成（1975-），男，博士，教授 E-mail：rchzhang@126.com

参考文献：

[1]邹家祥, 徐乐江. 冷连轧机系统振动控制[M]. 北京：冶金工业出版社, 1998.

Zou J X, Xu L J. Vibration Control of Cold Tandem Mill System[M]. Beijing:Metallurgical Industry Press, 1998.

[2]孙志辉, 吕文泉. 基于形态非抽样小波和S变换的轧机振动信号分析[J].工程科学学报, 2013, 35(3): 365-370.

Sun Z H, Lyu W Q. Analysis of rolling mill vibration signal based on morphological undecimated wavelet and S transform[J]. Chinese Journal of Engineering, 2013, 35(3): 365-370.

[3]张瑞成, 于海峰, 周亚罗. 轧机垂振系统自抗扰控制器设计[J]. 计算机仿真, 2017, 34(3): 189-193.

Zhang R C, Yu H F, Zhou Y L. Design of active disturbance rejection controller for vertical vibration system of rolling mill[J]. Computer Simulation, 2017, 34(3):189-193.

[4]张柳柳, 钱承, 华长春, 等. 基于耦合反步法的轧机垂扭耦合振动控制策略研究 [J/OL].自动化学报:1-15[2022-04-14].DOI:10.16383/j.aas.c200936.

Zhang L L, Qian C, Hua C C, et al. Research on vertical-torsional coupled vibration control strategy of rolling mill based on coupled backstepping method[J/OL]. Acta Automatica Sinica: 1-15 [2022-04-14].DOI:10.16383/j.aas.c200936.

[5]王桥医, 崔明超, 王瀚, 等. 基于辊系多模态模式的连轧机机架间耦合振动系统模型的建立及仿真分析[J]. 中南大学学报：自然科学版, 2020, 51(10): 2834-2843.

Wang Q Y, Cui M C, Wang H, et al. Establishment and simulation analysis of the coupled vibration system model between the tandem mill stands based on the multi-mode mode of the roll system[J]. Journal of Central South University：Natural Science Edition, 2020, 51(10): 2834-2843.

[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. Research on vertical-torsion coupling nonlinear vibration characteristics of four-high rolling mill based on dynamic rolling force[J]. Journal of Vibration and Shock, 2020, 39(20): 106-112.

[7]吴继民, 张义方, 朱小龙, 等. 轧机主传动系统在双源扰动作用下的动力学特性研究[J]. 振动工程学报, 2019, 32(4): 581-589.

Wu J M, Zhang Y F, Zhu X L, et al. Research on dynamic characteristics of rolling mill main drive system under dual-source disturbance action[J]. Journal of Vibration Engineering, 2019, 32(4): 581-589.

[8]王桥医, 高翔, 蒋鑫, 等. 基于动态辊缝轧机垂直振动仿真及工程验证[J]. 杭州电子科技大学学报：自然科学版, 2016, 36(1): 63-69.

Wang Q Y, Gao X, Jiang X, et al. Vertical vibration simulation and engineering verification based on dynamic roll gap rolling mill[J]. Journal of Hangzhou Dianzi University：Natural Science Edition, 2016, 36(1): 63-69.

[9]钟掘, 唐华平. 高速轧机若干振动问题——复杂机电系统耦合动力学研究[J]. 振动、测试与诊断, 2002,(1): 3-10,69.

Zhong J, Tang H P. Several vibration problems of high speed rolling mill-Research on coupling dynamics of complex electromechanical system[J]. Journal of Vibration, Testing & Diagnosis, 2002,(1): 3-10,69.

[10]孙韵韵, 肖会芳, 徐金梧. 考虑轧制界面粗糙形貌的轧机辊系非线性振动特性研究[J]. 振动与冲击, 2017, 36(8): 113-120.

Sun Y Y, Xiao H F, Xu J W. Research on nonlinear vibration characteristics of rolling mill roll system considering the rough topography of rolling interface[J]. Journal of Vibration and Shock, 2017, 36(8): 113-120.

[11]唐华平, 段吉安, 钟掘. 一个轧机参数振动模型[J]. 机械科学与技术, 2002,(5): 802-804.

Tang H P, Duan J A, Zhong J. A rolling mill parameter vibration model[J]. Mechanical Science and Technology, 2002,(5): 802-804.

[12]Zheng Y J, Shen G X, Li Y G, et al. Spatial vibration and its numerical analytical method of four-high rolling mills[J]. Journal of Iron and Steel Research International, 2014, 21(9): 837-843.

[13]米凯夫, 张杰, 曹建国, 等. 基于小波和小波分形的冷连轧机振动识别方法[J].工程科学学报, 2013, 35(8): 1064-1071.

Mi K F, Zhang J, Cao J G, et al. Vibration identification method of tandem cold rolling mill based on wavelet and wavelet fractal[J]. Chinese Journal of Engineering, 2013, 35(8): 1064-1071.

[14]王鑫鑫, 闫晓强. 基于扩张状态观测器的轧机振动抑振器研究[J]. 振动与冲击, 2019, 38(5): 1-6.

Wang X X, Yan X Q. Research on rolling mill vibration suppressor based on extended state observer[J]. Journal of Vibration and Shock, 2019, 38(5): 1-6.

[15]闫晓强, 王辉, 周杰, 等. 现代连轧机耦合振动抑制重要进展[J]. 中国冶金, 2014, 24(4): 1-4.

Yan X Q, Wang H, Zhou J, et al. Important progress in coupled vibration suppression of modern continuous rolling mills[J]. China Metallurgy, 2014, 24(4): 1-4.

[16]侯福祥, 张杰, 曹建国, 等. 带钢冷轧机振动问题的研究进展及评述[J]. 钢铁研究学报, 2007，19(10): 6-10,39.

Hou F X, Zhang J, Cao J G, et al. Research progress and comments on vibration of strip cold rolling mill[J]. Journal of Iron and Steel Research, 2007，19(10): 6-10,39.

[17]杨旭, 童朝南. 板带轧机振动问题研究[J]. 钢铁研究学报, 2009, 21(11): 1-4，11.

Yang X, Tong C N. Research on vibration of strip mill[J]. Journal of Iron and Steel Research, 2009, 21(11): 1-4，11.

[18]Lu X, Sun J, Song Z X, et al. Prediction and analysis of cold rolling mill vibration based on a data-driven method[J]. Applied Soft Computing, 2020，96:1-13.

[19]彭艳, 张明, 刘宣亮, 等. 基于数据驱动的轧机振动预测研究[A]. 第十一届中国钢铁年会论文集[C]. 北京: 中国金属学会, 2017.

Peng Y, Zhang M, Liu X L, et al. Research on rolling mill vibration prediction based on data drive[A]. Proceedings of the Eleventh China Iron and Steel Annual Conference[C]. Beijing: China Institute of Metals, 2017.

[20]董志奎, 梁朋伟, 禚超越, 等. 基于DBN算法的热轧高强钢薄板轧机振动预报研究[J]. 矿冶工程, 2020, 40(4): 135-141,144.

Dong Z K, Liang P W, Ju C Y, et al. Research on vibration prediction of hot-rolled high-strength steel sheet mill based on DBN algorithm[J]. Mining and Metallurgical Engineering, 2020, 40(4): 135-141,144.

[21]马佳佳, 苏怀智, 王颖慧. 基于EEMD-LSTM-MLR的大坝变形组合预测模型[J]. 长江科学院院报, 2021, 38(5):47-54.

Ma J J, Su H Z, Wang Y H. Dam deformation combination prediction model based on EEMD-LSTM-MLR[J]. Journal of Yangtze River Scientific Research Institute, 2021, 38(5): 47-54.

[22]胡璇, 李春, 叶柯华. 风力机齿轮箱振动信号分解方法研究[J]. 动力工程学报, 2021, 41(4): 323-329.

Hu X, Li C, Ye K H. Research on vibration signal decomposition method of wind turbine gearbox[J]. Chinese Journal of Power Engineering, 2021, 41(4): 323-329.

[23]Li H, Zhang Y P, Zheng H Q. Hilbert-Huang transform and marginal spectrum for detection and diagnosis of localized defects in roller bearings[J]. Journal of Mechanical Science and Technology, 2009, 23(2):291-301.

[24]Lin Z F, Cheng L L, Huang G H. Electricity consumption prediction based on LSTM with attention mechanism[J]. IEEJ Transactions on Electrical and Electronic Engineering, 2020, 15(4):556-562.

服务与反馈：

【文章下载】【加入收藏】