China Mechanical Engineering ›› 2026, Vol. 37 ›› Issue (5): 1199-1209.DOI: 10.3969/j.issn.1004-132X.2026.05.020
ZHANG Ji1(
), YUAN Haibo1, WANG Zhixuan1, ZHU Sihua1, BAI Zhenhua1,2(
)
Received:2025-05-31
Online:2026-05-25
Published:2026-06-09
Contact:
BAI Zhenhua
张冀1(
), 袁海博1, 王智璇1, 朱思华1, 白振华1,2(
)
通讯作者:
白振华
作者简介:张冀,男,1999年生,博士研究生。研究方向为钢铁智能制造工艺。E-mail:1332011776@qq.com基金资助:CLC Number:
ZHANG Ji, YUAN Haibo, WANG Zhixuan, ZHU Sihua, BAI Zhenhua. Physics-guided Neural Network Model for Predicting Rolling Forces in Aluminum Strip Cold Rolling[J]. China Mechanical Engineering, 2026, 37(5): 1199-1209.
张冀, 袁海博, 王智璇, 朱思华, 白振华. 物理引导的神经网络模型预测铝带冷轧轧制力[J]. 中国机械工程, 2026, 37(5): 1199-1209.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.cmemo.org.cn/EN/10.3969/j.issn.1004-132X.2026.05.020
| 辊系参数 | 数值 |
|---|---|
| 工作辊直径 | 450 |
| 中间辊直径 | 600 |
| 支撑辊直径 | 1400 |
| 工作辊辊身长度 | 3000 |
| 中间辊辊身长度 | 3000 |
| 支撑辊辊身长度 | 3000 |
Tab.1 Parameters of six-high cold rolling mill roll system
| 辊系参数 | 数值 |
|---|---|
| 工作辊直径 | 450 |
| 中间辊直径 | 600 |
| 支撑辊直径 | 1400 |
| 工作辊辊身长度 | 3000 |
| 中间辊辊身长度 | 3000 |
| 支撑辊辊身长度 | 3000 |
| 性能指标 | 训练集 | 验证集 |
|---|---|---|
| R2 | 0.993 | 0.988 |
| RRMSE/kN | 199.8 | 259.5 |
| RMAPE/% | 0.91 | 1.10 |
Tab.2 Performance of purely data-driven models on training and validation set
| 性能指标 | 训练集 | 验证集 |
|---|---|---|
| R2 | 0.993 | 0.988 |
| RRMSE/kN | 199.8 | 259.5 |
| RMAPE/% | 0.91 | 1.10 |
| 性能指标 | 训练集 | 验证集 |
|---|---|---|
| R2 | 0.895 | 0.886 |
| RRMSE/kN | 753.8 | 770.9 |
| RMAPE/% | 7.42 | 7.70 |
Tab.3 Performance of pure physical models on training and validation set
| 性能指标 | 训练集 | 验证集 |
|---|---|---|
| R2 | 0.895 | 0.886 |
| RRMSE/kN | 753.8 | 770.9 |
| RMAPE/% | 7.42 | 7.70 |
| 训练集 | 验证集 | |||||
|---|---|---|---|---|---|---|
| R2 | RRMSE/kN | RMAPE/% | R2 | RRMSE/kN | RMAPE/% | |
| 0.1 | 0.962 | 448.7 | 4.58 | 0.969 | 401.9 | 4.10 |
| 0.2 | 0.961 | 456.3 | 4.71 | 0.967 | 414.8 | 4.26 |
| 0.3 | 0.963 | 444.4 | 4.52 | 0.969 | 401.0 | 4.08 |
| 0.4 | 0.958 | 477.1 | 4.84 | 0.965 | 425.5 | 4.27 |
| 0.5 | 0.962 | 455.1 | 4.70 | 0.968 | 409.8 | 4.18 |
| 0.6 | 0.954 | 494.8 | 5.03 | 0.962 | 442.5 | 4.42 |
| 0.7 | 0.959 | 466.0 | 4.86 | 0.966 | 421.5 | 4.37 |
| 0.8 | 0.961 | 454.6 | 4.64 | 0.968 | 404.8 | 4.10 |
| 0.9 | 0.956 | 486.3 | 5.03 | 0.964 | 431.1 | 4.43 |
Tab.4 Sensitivity analysis results
| 训练集 | 验证集 | |||||
|---|---|---|---|---|---|---|
| R2 | RRMSE/kN | RMAPE/% | R2 | RRMSE/kN | RMAPE/% | |
| 0.1 | 0.962 | 448.7 | 4.58 | 0.969 | 401.9 | 4.10 |
| 0.2 | 0.961 | 456.3 | 4.71 | 0.967 | 414.8 | 4.26 |
| 0.3 | 0.963 | 444.4 | 4.52 | 0.969 | 401.0 | 4.08 |
| 0.4 | 0.958 | 477.1 | 4.84 | 0.965 | 425.5 | 4.27 |
| 0.5 | 0.962 | 455.1 | 4.70 | 0.968 | 409.8 | 4.18 |
| 0.6 | 0.954 | 494.8 | 5.03 | 0.962 | 442.5 | 4.42 |
| 0.7 | 0.959 | 466.0 | 4.86 | 0.966 | 421.5 | 4.37 |
| 0.8 | 0.961 | 454.6 | 4.64 | 0.968 | 404.8 | 4.10 |
| 0.9 | 0.956 | 486.3 | 5.03 | 0.964 | 431.1 | 4.43 |
| 超参数 | 数值 |
|---|---|
| 学习率 | 0.009 583 |
| 批量大小 | 27 |
| 卷积核大小 | 5 |
| 卷积核数量 | 49 |
Tab.5 Optimal hyperparameters of PGNN model
| 超参数 | 数值 |
|---|---|
| 学习率 | 0.009 583 |
| 批量大小 | 27 |
| 卷积核大小 | 5 |
| 卷积核数量 | 49 |
| [1] | 陈宇,刘文文,王涛,等.预制波纹工艺对钢/铝/铝合金复合板界面影响机制研究[J].机械工程学报,2023,59(8):74-82. |
| CHEN Yu, LIU Wenwen, WANG Tao, 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. | |
| [2] | 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. |
| LU Liying, WANG Zhutang. Industrial Development of Cold Rolling of Aluminum Sheet and Strip[J]. Light Alloy Fabrication Technology, 2019, 47(3): 1-7. | |
| [3] | 孙建亮,吴盼盼,赵琛,等.考虑后续工序要求的轧机板形标准曲线研究[J].中南大学学报(自然科学版),2022,53(7):2416-2425. |
| SUN Jianliang, WU Panpan, ZHAO Chen, 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. | |
| [4] | 李旭,金树仁,王鹏飞,等.冷轧板形控制技术的研究现状及展望[J].中国冶金,2024,34(7):21-30. |
| LI Xu, JIN Shuren, WANG Pengfei, et al. Research Status and Perspectives for Cold Rolling Flatness Control Technology [J]. China Metallurgy, 2024, 34(7): 21-30. | |
| [5] | 连家创,刘宏民.板厚板形控制[M].北京:兵器工业出版社,1995. |
| LIAN Jiachuang, LIU Hongmin. Control on thick and Shape of Strip[M].Beijing: Arms Industry Press, 1995. | |
| [6] | 刘亚星,顾清,张文军,等.超高强钢冷轧过程轧制力计算的改进模型[J].钢铁,2021,56(10):108-116. |
| LIU Yaxing, GU Qing, ZHANG Wenjun, 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. | |
| [7] | 王家琪,刘晓,张增强,等.基于非圆弧理论的精密极薄带轧制力快速预测[J].钢铁,2023,58(10):85-91. |
| WANG Jiaqi, LIU Xiao, ZHANG Zengqiang, 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. | |
| [8] | 李学通,郭子飞,王俭辉,等.超高强钢冷轧过程前滑计算及影响分析[J].中南大学学报(自然科学版),2025,56(1):34-43. |
| LI Xuetong, GUO Zifei, WANG Jianhui, 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. | |
| [9] | 张文军,王文奇,张晓东,等.1180 MPa级超高强钢冷连轧过程的厚度综合控制技术[J].中国机械工程,2024,35(2):347-353. |
| ZHANG Wenjun, WANG Wenqi, ZHANG Xiaodong, 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. | |
| [10] | 刘亚星,顾清,钱承,等.冷轧超高强钢平直度与断面形状前馈控制技术[J].中国机械工程,2021,32(24):2981-2988. |
| LIU Yaxing, GU Qing, QIAN Cheng, 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. | |
| [11] | HU Z Y, WEI Z H, SUN H, 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. |
| [12] | Shen S H, Guye D, Ma X P, et al. Multistep networks for Roll Force Prediction in Hot Strip Rolling Mill[J].Machine Learning with Applications,2021,7(4):100245. |
| [13] | 李鹏,王一棠,王佳茜,等.数据驱动的混凝土泵车臂架疲劳载荷谱编制[J].中国机械工程,2024,35(10):1881-1889. |
| LI Peng, WANG Yitang, WANG Jiaqian, et al. Data-driven Compilation of Fatigue Load Spectrum for Concrete Pump Truck Boom [J]. China Mechanical Engineering, 2024, 35(10): 1881-1889. | |
| [14] | 肖刚,顾海瑞,董锦锦,等.仿真数据驱动的长期服役电梯导轨故障迁移诊断方法[J].中国机械工程,2024,35(1):125-135. |
| XIAO Gang, GU Hairui, DONG Jinjin, 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. | |
| [15] | 蒙康,滕伟,彭迪康,等.运行机理与数据双驱动的风电齿轮箱系统故障预警[J].中国机械工程,2023,34(12):1476-1485. |
| MENG Kang, TENG Wei, PENG Dikang, 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. | |
| [16] | 焦华超,孙文磊,王宏伟.基于类小波辅助分类生成对抗网络的轴承故障数据生成方法[J].中国机械工程,2025,36(3):546-557. |
| JIAO Huachao, SUN Wenlei, WANG Hongwei. Bearing Fault Data Generation Method Based on Wavelet-like Assisted Classification Generative Adversarial Network [J]. China Mechanical Engineering, 2025, 36(3): 546-557. | |
| [17] | 王祺,叶仁传,马国杰,等.钢材表面缺陷轻量化识别算法研究[J].机械工程学报,2025,61(8):18-31. |
| WANG Qi, YE Renchuan, MA Guojie, et al. Research on Lightweight Recognition Algorithm for Steel Surface Defects[J]. Journal of Mechanical Engineering, 2025, 61(8): 18-31. | |
| [18] | 谢松雨,苏燕强,黄小兵,等.基于特征增维和深度学习的热轧轧制力动态预测[J].中国冶金,2025,35(4):145-154. |
| XIE Songyu, SU Yanqiang, HUANG Xiaobing, et al. Dynamic Prediction of Hot Rolling Force Based on Feature Augmentation and Deep Learning [J]. China Metallurgy, 2025, 35(4): 145-154. | |
| [19] | 李晓阳,朴春慧,王雪雷,等.冷轧轧制力的DBO-DELM预测方法[J].哈尔滨理工大学学报,2024,29(6):112-123. |
| LI Xiaoyang, PIAO Chunhui, WANG Xuelei, et al. DBO-DELM Prediction Method for Cold Rolling Force[J]. Journal of Harbin University of Science and Technology, 2024, 29(6): 112-123. | |
| [20] | 吴爽,闫奕,李爽,等.冷连轧轧制力深度神经网络模型泛化能力并行优化[J].机械设计与制造,2023(8):171-174. |
| WU Shuang, YAN Yi, LI Shuang, 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. | |
| [21] | 蔡宇昂,郝亮亮,周艳真,等.机理数据混合驱动的多相环形无刷励磁系统旋转整流器故障诊断[J].电工技术学报,2025,40(8):2643-2655. |
| CAI Yuang, HAO Liangliang, ZHOU Yanzhen, 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. | |
| [22] | 魏彬,谭硕,周华.融合深度学习与过程机理的FCC装置关键参数软测量模型[J].石油学报(石油加工),2024,40(6):1624-1634. |
| WEI Bin, TAN Shuo, ZHOU Hua. 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. | |
| [23] | 曾玉娇,肖炘,杨刚,等.基于机理与数据混合驱动的湿法磷酸生产过程代理建模与优化[J].化工学报,2024,75(3):936-944. |
| ZENG Yujiao, XIAO Xin, YANG Gang, 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. | |
| [24] | 明巧,刘友波,邱高,等.基于物理引导神经网络的静态电压稳定预防控制策略在线计算[J].电网技术,2025, 49(7): 2680-2690. |
| MING Qiao, LIU Youbo, QIU Gao, 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. | |
| [25] | WANG J S, JIANG Z Y, TIEU A 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. |
| [26] | DU F S, WANG G G, ZANG X L, et al. Friction Model for Strip Rolling [J]. Journal of Iron and Steel Research, International 2010,17(7):19-23. |
| [27] | 陈树宗,彭文,姬亚锋,等.基于目标函数的冷连轧轧制力模型参数自适应[J].东北大学学报(自然科学版),2013,34(8):1128-1131. |
| CHEN Shuzong, PENG Wen, JI Yafeng, 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. | |
| [28] | 陈光耀,李恒,贺子芮,等.基于机器学习的管材弯曲回弹有效预测与补偿[J].中国机械工程,2020,31(22):2745-2752. |
| CHEN Guangyao, LI Heng, HE Zirui, et al. Effective Prediction and Compensation of Tube Bending Springback Based on Machine Learning [J]. China Mechanical Engineering, 2020, 31(22): 2745-2752. | |
| [29] | 王晓勇. 机理与数据驱动下板带冷轧过程的动力学及稳定性研究[D]. 北京:北京科技大学, 2025. |
| Wang Xiaoyong. 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. |
| [1] | SUN Yue, HUANG Hui, YIN Fangchen. Energy Consumption Prediction of Industrial Robots under High-load Dynamic Conditions [J]. China Mechanical Engineering, 2026, 37(4): 939-947. |
| [2] | WANG Liming, XIAO Xingyuan, LI Fangyi, WANG Xiaoguang, LI Jianfeng, NIE Yanyan, LIU Weitong, LI Liuyuan, WANG Yitong, WANG Boyun, CUI Yuqi. Overview and Prospects of Data-driven Low-carbon Design and Manufacturing of Electromechanical Products [J]. China Mechanical Engineering, 2026, 37(4): 764-779. |
| [3] | Liangliang YANG, Hong CHEN, Wenqi LU. Kernel Regularization Optimal Iterative Learning Control Based on Trajectory Learning under Actuator Constraints [J]. China Mechanical Engineering, 2025, 36(10): 2274-2283. |
| [4] | ZHAO Peirui1, DENG Chao1, ZHU Bo1, YAN Wenbin1, LIANG Min2, CHEN Min2. Modelling and Optimisation of Dynamic Scheduling in Chinese Materia Medica Pharmaceuticals Workshops Based on Multiple Motivation Drivers [J]. China Mechanical Engineering, 2025, 36(06): 1247-1260,1299. |
| [5] | JIANG Jiguang, HOU Jue, SU Chengzhi, BA Qijiao, TIAN Aixin, XU Mingyu. Research on Optimal Pose Set Planning Method under Physical Constraint Robot Kinematics Calibration [J]. China Mechanical Engineering, 2024, 35(03): 472-480. |
| [6] | XIAO Gang, GU Hairui, DONG Jinjin, WANG Qibing, LU Jiawei. Simulation Data-driven Migration Diagnosis Method for Guide Rail Faults in Long-term Service Elevators [J]. China Mechanical Engineering, 2024, 35(01): 125-135. |
| [7] |
LI Congbo;YIN Yuxian;XIAO Qinge;LONG Yun;ZHAO Xikun.
Data-driven Energy Consumption Prediction Method of CNC Turning Based on Meta-action
[J]. China Mechanical Engineering, 2020, 31(21): 2601-2611.
|
| [8] | WU Yangdong, ZHANG Taihua, LIU Dan, WANG Yiquan. Data-driven Multi-attribute Optimization Decision-making for Complex Product Design Schemes [J]. China Mechanical Engineering, 2020, 31(07): 865-870. |
| [9] | LI Hao, WANG Haoqi, CHENG Ying, TAO Fei, HAO Bing, WANG Xinchang, JI Yangjian, SONG Wenyan, DU Wenliao, WEN Xiaoyu, GONG Xiaoyun, LI Ke, ZHANG Yingfeng, LUO Guofu, LI Qifeng. Technology and Application of Data-driven Intelligent Services for Complex Products [J]. China Mechanical Engineering, 2020, 31(07): 757-772. |
| [10] | LIU Yinhua, SUN Rui, WU Huan. Latent Structure Modeling and Predictive Quality Control Based on Multi-source Data Streams in the Auto Body Assembly Processes [J]. China Mechanical Engineering, 2019, 30(02): 237-243. |
| [11] | YUAN Guangchao;BAO Jingsong;ZHENG Xiaohu;ZHANG Jie. Tool Life Prediction in Titanium High Speed Milling Processes Based on CNC Real Time Monitoring Data Driven [J]. China Mechanical Engineering, 2018, 29(04): 457-462,470. |
| Viewed | ||||||
|
Full text |
|
|||||
|
Abstract |
|
|||||