Deep Learning-based Dynamic Modeling of Hot Rolled Gague-looper System

doi:10.3901/JME.260181

Abstract

Abstract: In the control process of hot strip rolling, the gague control and the looper control are interdependent and influence each other, which significantly impacts the overall performance of the gague control system. Traditional modeling methods struggle to accurately represent the intricate characteristics of multivariable coupling and nonlinearity present in the strip rolling process. To address the challenges in modelling nonlinear systems, focusing on a 2160 mm hot rolling line gague control process. A convolution-attention mechanism-long and short-term memory prediction model(CNN-ATT-LSTM) is established based on actual production data, and the hyper-parameters are optimized using the Gray Wolf algorithm. The prediction performance of this model is then compared with that of the long-short term memory network model(LSTM), the deep neural network model (DNN), and the convolutional network-long-short term memory network model(CNN-LSTM). The results indicate that the R² of the proposed prediction model reaches 93%, demonstrating a higher prediction accuracy for the dynamic changes within the gague-looper system. The generalization performance of the proposed model has been verified using three different strip sizes, demonstrating that the model is capable of providing guidance for high-precision control of gague.

Key words: hot rolling, gague, looper, deep learning

CLC Number:

TG335

LEI Jiawei, WANG Shuting, YUE Chongxiang, LIN Ping, PENG Wen, SUN Jie, ZHANG Dianhua. Deep Learning-based Dynamic Modeling of Hot Rolled Gague-looper System[J]. Journal of Mechanical Engineering, 2025, 62(6): 142-153.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

URL: http://www.cjmenet.com.cn/EN/10.3901/JME.260181

http://www.cjmenet.com.cn/EN/Y2025/V62/I6/142

References

[1] SUN Jie，HU Yunjian，YIN Fangchen，et al. Looper-gauge integrated control in hot strip finishing mill using inverse linear quadratic theory[J]. ISIJ International，2019，59(9)：1562-1572.

[2] PITTNER J，SIMAAN M A. Streamlining the tandem hot-metal-strip mill：Threading progress stems from the use of advanced control with virtual rolling[J]. IEEE Industry Applications Magazine，2018，24(2)：35-44.

[3] ZHONG Zhaozhun，WANG Jingcheng，ZHANG Jianmin，et al. Looper-tension sliding mode control for hot strip finishing mills[J]. Journal of Iron and Steel Research International，2012，19(1)：23-30.

[4] PITTNER J，SIMAAN M A. Improving the availability of tandem hot metal strip rolling：The use of fault-tolerant techniques with virtual rolling[J]. IEEE Industry Applications Magazine，2019，25(4)：66-76.

[5] KALMAN R E. A new approach to linear filtering and prediction problems[J]. Journal of Basic Engineering，1960，82(1)：35-45.

[6] SUN Jie，HOU Fan，HU Yunjian，et al. Application of distributed model predictive control based on neighborhood optimization in gauge-looper integrated system of tandem hot rolling[J]. Journal of Iron and Steel Research International，2023，30(2)：277-292.

[7] 王雨刚. 梅钢1780热轧活套控制改进[J]. 冶金自动化，2019，43(4)：61-65.

WANG Yugang. Improvement of looper control in 1780 mm hot strip mill of Baosteel Meishan[J]. Metallurgical Industry Automation，2019，43(4)：61-65.

[8] 陈宜华. 热连轧窄带钢的活套高度闭环控制[J]. 轧钢，1997(5)：8-10.

CHEN Yihua. Closed loop control for height of loops in continuous hot rolling of narrow strip steel[J]. Steel Rolling，1997(5)：8-10.

[9] 雷亚国，贾峰，周昕，等. 基于深度学习理论的机械装备大数据健康监测方法[J]. 机械工程学报，2015，51(21)：49-56.

LEI Yaguo，JIA Feng，ZHOU Xin，et al. A deep learning-based method for machinery health monitoring with big data[J]. Journal of Mechanical Engineering，2015，51(21)：49-56.

[10] 杨健，吴思炜. 基于机器学习的钢铁轧制过程性能预测[J]. 钢铁，2021，56(9)：1-9.

YANG Jian，WU Siwei. Property prediction of steel rolling process based on machine learning[J]. Iron and Steel，2021，56(9)：1-9.

[11] DONG Zishuo，LI Xu，LUAN Feng，et al. Prediction and analysis of key parameters of head deformation of hot-rolled plates based on artificial neural networks[J]. Journal of Manufacturing Processes，2022，77：282-300.

[12] MENG Lingming，DING Jingguo，DONG Zishuo，et al. Prediction of roll wear and thermal expansion based on informer network in hot rolling process and application in the control of crown and thickness[J]. Journal of Manufacturing Processes，2023，103：248-260.

[13] 朱挺，陈兆祥，周笛，等. 基于Bayesian-LSTM神经网络的热轧轧辊剩余寿命预测及不确定性评估[J]. 机械工程学报，2024，60(11)：181-190.

ZHU Ting，CHEN Zhaoxiang，ZHOU Di，et al. Bayesian-lstm neural network-based remaining useful life prediction and uncertainty estimation of rollers in a hot strip mill [J]. Journal of Mechanical Engineering，2024，60(11)：181-190.

[14] LI Jingdong，ZHAO Jianwei，WANG Xiaochen，et al. An industrial IoT-based deformation resistance prediction and thickness control method of cold-rolled strip in steel production systems[J]. Information Sciences，2024，674：120735.

[15] HE Hainan，DAI Zhuohao，WANG Xiaochen，et al. Whole process prediction model of silicon steel strip on transverse thickness difference based on Takagi-Sugeno fuzzy network[J]. Journal of Iron and Steel Research International，2023，30(12)：2448-2458.

[16] SHAHANI A R，SETAYESHI S，NODAMAIE S A，et al. Prediction of influence parameters on the hot rolling process using finite element method and neural network[J]. Journal of Materials Processing Technology，2009，209(4)：1920-1935.

[17] MILNE A，XIANGHUA X. Steel surface roughness parameter prediction from laser reflection data using machine learning models[J]. The International Journal of Advanced Manufacturing Technology，2024，132(9)：4645-4662.

[18] BOUGUETTAYA A，ZARZOUR H. CNN-based hot-rolled steel strip surface defects classification：A comparative study between different pre-trained CNN models[J]. The International Journal of Advanced Manufacturing Technology，2024，132(1)：399-419.

[19] YUAN Hao，LI Xu，WANG Xiaojun，et al. A looper-thickness coordinated control strategy based on ILQ theory and GA-BP neural network[J]. The International Journal of Advanced Manufacturing Technology，2023，127(9)：4845-4860.

[20] DENG Jifei，SIERLA S，SUN Jie，et al. Mass customization with reinforcement learning：Automatic reconfiguration of a production line[J]. Applied Soft Computing，2023，145：110547.

[21] 刘星辰，周奇才，赵炯，等. 一维卷积神经网络实时抗噪故障诊断算法[J]. 哈尔滨工业大学学报，2019，51(7)：89-95. LIU Xingchen，ZHOU Qicai，ZHAO Jiong，et al. Real-time and anti-noise fault diagnosis algorithm based on 1-D convolutional neural network[J]. Journal of Harbin Institute of Technology，2019，51(7)：89-95.

[22] 付孟新，郭世伟，王泽兴，等. 基于一维卷积神经网络的列车异响识别系统研究[J]. 电子测量技术，2023，46(14)：9-17.

FU Mengxin，GUO Shiwei，WANG Zexing，et al. Research on train noise recognition system based on one-dimensional convolutional neural network[J]. Electronic Measurement Technology，2023，46(14)：9-17.

[23] LIOU Y L，HSU J Y，CHEN C S，et al. A fully integrated 1.7 mW attention-based automatic speech recognition processor[J]. IEEE Transactions on Circuits and Systems II：Express Briefs，2022，69(10)：4178-4182.

[24] CHEN Yafei，PENG Lianggui，WANG Yu，et al. Prediction of tandem cold-rolled strip flatness based on attention-LSTM model[J]. Journal of Manufacturing Processes，2023，91：110-121.

[25] JIANG Pei，WANG Zuoxue，LI Xiaobin，et al. Energy consumption prediction and optimization of industrial robots based on LSTM[J]. Journal of Manufacturing Systems，2023，70：137-148.

[26] LIU Xin，ZHOU Jun. Short-term wind power forecasting based on multivariate/multi-step LSTM with temporal feature attention mechanism[J]. Applied Soft Computing，2024，150：111050.

[27] 田斌，赵晨，李俊，等. 基于小波变换和压缩感知的工频磁异常信号降噪方法[J]. 探测与控制学报，2024，46(3)：94-99，104.

TIAN Bin，ZHAO Chen，LI Jun，et al. Power frequency magnetic anomaly signals denoising method based on wavelet transform and compressive sensing[J]. Journal of Detection and Control，2024，46(3)：94-99，104.

[28] 孙波，周健康，赵玉清，等. 基于改进灰狼优化算法的机器人全局路径规划[J]. 科学技术与工程，2024，24(33)：14287-14297.

SUN Bo，ZHOU Jiankang，ZHAO Yuqing，et al. Global path planning of robot based on improved gray wolf optimization algorithm[J]. Science Technology and Engineering，2024，24(33)：14287-14297.

[29] KUMAR R，SINGH L，TIWARI R. Path planning for the autonomous robots using modified grey wolf optimization approach[J]. Journal of Intelligent & Fuzzy Systems，2021，40(5)：9453-9470.