Accurate prediction of rolling forces in aluminum strip cold rolling was essential for process optimization and ensuring product quality. Traditional physical models often struggled to accurately capture the complex interactions among various factors, while purely data-driven models typically lacked physical constraints and exhibited limited generalization ability. In order to develop a rolling force prediction model for aluminum strip cold rolling that combined both physical interpretability and high prediction accuracy, taking 5182 aluminum strip as the research object, a yield strength model was fitted. After preprocessing a large volume of real production data, the traditional Hill rolling force model was optimized by using the PSO-Nelder-Mead algorithm, which significantly improved the predictive capability. Then, a PGNN model was proposed. This model was based on a convolutional neural network, integrating a physical constraint term derived from the optimized mathematical model into the loss function,which enabled the model to follow the physical laws while simultaneously being data-driven. Bayesian optimization was employed to optimize the model's hyperparameters. Finally, the established model was verified by using actual production data. The results show that the PGNN model exhibits excellent prediction performance on the validation set. The prediction accuracy is significantly higher than that of the mathematical models both before and after optimization, and shows strong generalization ability. Furthermore, the iterative analysis of the loss function further confirms the effectiveness of the physical constraints.
CHENYu, LIUWenwen, WANGTao, et al. Study on Influence Mechanism of Prefabricating Corrugation Process on Interface of Steel/Aluminum/Aluminum Alloy Laminated Plate [J]. Journal of Mechanical Engineering, 2023, 59(8): 74-82.
[3]
路丽英,王祝堂.中国铝板带冷轧工业发展[J].轻合金加工技术,2019,47(3):1-7.
[4]
LULiying, WANGZhutang. Industrial Development of Cold Rolling of Aluminum Sheet and Strip[J]. Light Alloy Fabrication Technology, 2019, 47(3): 1-7.
SUNJianliang, WUPanpan, ZHAOChen, et al. Study on Standard Curve of Strip Rolling Considering Requirements of Subsequent Process [J]. Journal of Central South University (Science and Technology), 2022, 53(7): 2416-2425.
LIXu, JINShuren, WANGPengfei, et al. Research Status and Perspectives for Cold Rolling Flatness Control Technology [J]. China Metallurgy, 2024, 34(7): 21-30.
[9]
连家创,刘宏民.板厚板形控制[M].北京:兵器工业出版社,1995.
[10]
LIANJiachuang, LIUHongmin. Control on thick and Shape of Strip[M].Beijing: Arms Industry Press, 1995.
LIUYaxing, GUQing, ZHANGWenjun, et al. Improved Model for Calculating Rolling Load of Ultra-high Strength Steel in Cold Rolling Process [J]. Iron and Steel, 2021, 56(10): 108-116.
WANGJiaqi, LIUXiao, ZHANGZengqiang, et al. Rapid Prediction of Rolling Force of Precision Thin Strip Based on Non Circular Arc Theory [J]. Iron and Steel, 2023, 58(10): 85-91.
LIXuetong, GUOZifei, WANGJianhui, et al. Calculation and Influence Analysis of Forward Slip of Ultra-high Strength Steel during Cold Rolling [J]. Journal of Central South University(Science and Technology), 2025, 56(1): 34-43.
ZHANGWenjun, WANGWenqi, ZHANGXiaodong, et al. Comprehensive Thickness Control Technology of 1180 MPa Grade Ultra-high Strength Steels in Cold Tandem Rolling [J]. China Mechanical Engineering, 2024, 35(2): 347-353.
LIUYaxing, GUQing, QIANCheng, et al. Feedforward Control Technology for Flatness and Cross-sectional Shape of Cold-rolled Ultra-high Strength Steel[J]. China Mechanical Engineering, 2021, 32(24): 2981-2988.
[21]
HUZ Y, WEIZ H, SUNH, et al. Optimization of Metal Rolling Control Using Soft Computing Approaches:a Review[J].Archives of Computational Methods in Engineering,2019,28(2):405-421.
[22]
ShenS H, GuyeD, MaX P, et al. Multistep networks for Roll Force Prediction in Hot Strip Rolling Mill[J].Machine Learning with Applications,2021,7(4):100245.
XIAOGang, GUHairui, DONGJinjin, et al. Fault Transfer Diagnosis Method for Long-term Serviced Elevator Guide rails Driven by Simulation Data [J]. China Mechanical Engineering, 2024, 35(1): 125-135.
MENGKang, TENGWei, PENGDikang, et al. Fault Early Warning for Wind Power Gearbox System Driven by Both Operation Mechanism and Data [J]. China Mechanical Engineering, 2023, 34(12): 1476-1485.
WANGQi, YERenchuan, MAGuojie, et al. Research on Lightweight Recognition Algorithm for Steel Surface Defects[J]. Journal of Mechanical Engineering, 2025, 61(8): 18-31.
XIESongyu, SUYanqiang, HUANGXiaobing, et al. Dynamic Prediction of Hot Rolling Force Based on Feature Augmentation and Deep Learning [J]. China Metallurgy, 2025, 35(4): 145-154.
LIXiaoyang, PIAOChunhui, WANGXuelei, et al. DBO-DELM Prediction Method for Cold Rolling Force[J]. Journal of Harbin University of Science and Technology, 2024, 29(6): 112-123.
WUShuang, YANYi, LIShuang, et al. Parallel Optimization of Generalization Ability of Deep Neural Network Model for Cold Continuous Rolling Force [J]. Mechanical Design and Manufacturing, 2023(8): 171-174.
CAIYuang, HAOLiangliang, ZHOUYanzhen, et al. Fault Diagnosis of Multi-phase Annular Brushless Excitation System Rotating Rectifier Driven by Hybrid Mechanism and Data[J]. Transactions of China Electrotechnical Society, 2025, 40(8): 2643-2655.
WEIBin, TANShuo, ZHOUHua. Soft Measurement Model of Key Parameters of FCC Unit Integrating Deep Learning and Process Mechanism [J]. Acta Petrolei Sinica (Petroleum Processing Section), 2024, 40(6): 1624-1634.
ZENGYujiao, XIAOXin, YANGGang, et al. Surrogate Modeling and Optimization of Wet Process Phosphoric Acid Production Process Driven by Mechanism and Data Hybrid[J]. CIESC Journal, 2024, 75(3): 936-944.
MINGQiao, LIUYoubo, QIUGao, et al. Online Calculation of Static Voltage Stability Preventive Control Strategy Based on Physics-guided Neural Network[J]. Power System Technology, 2025, 49(7): 2680-2690.
[47]
WANGJ S, JIANGZ Y, TIEUA K, et al. Adaptive Calculation of Deformation Resistance Model of Online Process Control in Tandem Cold Mill [J]. Journal of Materials Processing Technology, 2005, 162/163: 585-590.
[48]
DUF S, WANGG G, ZANGX L, et al. Friction Model for Strip Rolling [J]. Journal of Iron and Steel Research, International 2010,17(7):19-23.
CHENShuzong, PENGWen, JIYafeng, et al. Adaptive Parameters of Cold Continuous Rolling Force Model Based on Objective Function [J]. Journal of Northeastern University(Natural Science Edition), 2013, 34(8): 1128-1131.
CHENGuangyao, LIHeng, HEZirui, et al. Effective Prediction and Compensation of Tube Bending Springback Based on Machine Learning [J]. China Mechanical Engineering, 2020, 31(22): 2745-2752.
WangXiaoyong. Research on Dynamics and Stability of Cold Rolling Processes for Plate and Strip Driven by Mechanism and Data[D]. Beijing: University of Science and Technology Beijing, 2025.