锻压技术

基于混合人工神经网络的冷连轧水平力预测

英文标题：Prediction on horizontal force in cold continuous rolling based on hybrid artificial neural network

分类号：TG335.56

出版年,卷(期):页码：2024,49(3):86-93

摘要：

针对冷连轧机组辊系中工作辊沿带钢运动方向的水平力难以利用传统的数学模型进行计算的问题，提出了利用混合人工神经网络模型对其进行预测。分析了工作辊在轧制过程中的受力情况，并根据监测的状态参数，从中挑选了轧制力、弯辊力矩、张力、带钢厚度、弯辊力等几类对工作辊受到的沿带钢运动方向的水平力有影响的参数作为输入变量。提出了两种新型的粒子群优化算法，并对人工神经网络的初始化权值与阈值进行优化。通过对预测结果进行分析发现，提出的改进混合人工神经网络相比较改进前能够提高模型的预测精度，且拟合精度均达到90%以上，可用于指导实际生产。

For the problem that it is difficult to use the traditional mathematical model to calculate the horizontal force of working roll along the direction of strip steel movement in the cold continuous rolling mill roll system, a hybrid artificial neural network model was proposed to predict it, and the stress situation of working roll during the rolling process was analyzed. Then, based on the monitored state parameters, several types of parameters that had an impact on the horizontal force acting on the working roll along the direction of strip steel movement, such as rolling force, bending moment, tension, strip steel thickness and bending force, were selected as input variables, and two new particle swarm optimization algorithms were proposed to optimize the initialization weights and thresholds of artificial neural networks.The prediction analysis results show that the proposed improved hybrid artificial neural network can improve the prediction accuracy of the model compared with that before improvement, and the fitting accuracy is more than 90%, which can be used to guide the actual production.

基金项目：

国家自然科学基金资助项目（52005168）；武汉市科技成果转化专项（2020030603012342）；湖北省科技创新人才计划（2023DJCO68）

作者简介：夏军勇（1976-），男，博士，教授，E-mail：20171013@hbut.edu.cn；通信作者：卢奇（1995-），男，硕士研究生，E-mail：dzyx671@126.com

参考文献：

[1]康永林. “十三五”中国轧钢技术进步及展望[J]. 钢铁，2021，56(10)：1-15.

Kang Y L. China steel rolling technology progress in the 13th five-year plan and prospection[J]. Iron & Steel, 2021, 56 (10): 1-15.

[2]曹建国，宋纯宁，王雷雷，等. 新一代高技术轧机电工钢矩形断面板形控制创新研究[A]. 中国金属学会. 第十三届中国钢铁年会论文集——4.轧制与热处理钢铁[C]. 重庆：冶金工业出版社，2022.

Cao J G, Song C N, Wang L L, et al. Innovation research on rectangular section for profile and flatness control of electrical steel in new-generation high-tech rolling mills[A]. The Chinese Society for Metals. Proceedings of the 13th China Steel Annual Conference-4. Rolling and Heat Treatment of Steel[C]. Chongqing: Metallurgical Industry Press, 2022.

[3]曹建国，江军，邱澜，等. 新一代高技术宽带钢冷轧机全机组一体化板形控制[J]. 中南大学学报：自然科学版，2019，50 (7)：1584-1591.

Cao J G, Jiang J, Qiu L, et al. High precision integrated profile and flatness control for new-generation high-tech wide strip cold rolling mills[J]. Journal of Central South University：Science and Technology, 2019, 50 (7): 1584-1591.

[4]龚亮，张钢，董绍友，等. 冷轧机工作辊操作侧支承轴承系统力学特性分析[J]. 工业控制计算机，2020，33 (11)：74-77.

Gong L, Zhang G, Dong S Y, et al. Analysis of mechanical characteristics of supporting bearing system on operating side of work roll of cold mill[J]. Industrial Control Computer, 2020, 33 (11): 74-77.

[5]张大志，李谋渭，孙一康，等. 四机架冷连轧机轧制力模型的研究与应用[J]. 轧钢，2000，17 (3)：15-17.

Zhang D Z, Li M W, Sun Y K, et al. The research and application of the rolling force model for 4-stand tandem cold strip mill[J]. Steel Rolling, 2000, 17 (3): 15-17.

[6]宋纯宁，曹建国，王雷雷，等. 六辊冷连轧机电工钢矩形断面控制弯辊力模型[J]. 哈尔滨工业大学学报，2022，54 (7)：143-150.

Song C N, Cao J G, Wang L L, et al. Model of rectangular section control roll bending force for electrical steel in six-high tandem cold mill[J]. Journal of Harbin Institute of Technology, 2022, 54 (7): 143-150.

[7]邢德茂，姚利辉，李学通. 2030 mm冷连轧机组板形预报及影响因素研究[J]. 塑性工程学报，2021，28 (3)：210-216.

Xing D M, Yao L H, Li X T. Study on prediction and influencing factors of flatness of 2030 mm tandem cold rolling mill[J]. Journal of Plasticity Engineering, 2021, 28 (3): 210-216.

[8]刘华强，唐荻，杨荃，等. 模糊小脑模型神经网络在多辊冷连轧机轧制力预报模型中的应用[J]. 北京科技大学学报，2006，28 (10)：969-972.

Liu H Q, Tang D, Yang Q, et al. Rolling force prediction model of a multi-roll cold tandem mill by fuzzy cerebellum model articulation controller[J]. Journal of University of Science and Technology Beijing, 2006, 28 (10): 969-972.

[9]严国平. 六辊轧机小辊径工作辊变形受力分析[J]. 冶金设备，2015，(6)：19-21.

Yan G P. Stress analysis on the deformation of the small working rolls of six roller mill [J]. Metallurgical Equipment, 2015, (6): 19-21.

[10]白振华，刘亚星，钱承，等. 小型四辊轧机工作辊水平位移对板形的影响[J]. 中国机械工程，2017，28 (9)：1085-1091.

Bai Z H, Liu Y X, Qian C, et al. Influences of work roll horizontal displacements on shape in small four high rolling mills [J]. China Mechanical Engineering, 2017, 28 (9): 1085-1091.

[11]郭利华，张振营，严裕宁. 基于有限元的六辊轧机机架变形分析[J]. 轧钢，2012，29 (2):12-14，20.

Guo L H, Zhang Z Y, Yan Y N. Finite element analysis of the stand deformation of a 6-high mill[J]. Steel Rolling, 2012, 29 (2): 12-24，20.

[12]Bai Z H, Xing Y, Liu S Y, et al. Calculating the flattening coefficient between roll gaps at the horizontal deflection of work rolls[J]. Ironmaking & Steelmaking, 2019, 46 (2):184-192.

[13]周富强，曹建国，张杰，等. 冷连轧机轧制力的影响因素[J]. 机械工程学报，2006，43 (10)：94-97.

Zhou F Q, Cao J G, Zhang J, et al. Influence factors of rolling force in tandem cold rolling[J]. Chinese Journal of Mechanical Engineering, 2006, 43 (10): 94-97.

[14]周富强，曹建国，张杰，等. 基于神经网络的冷连轧机轧制力预报模型[J]. 中南大学学报：自然科学版，2006，37 (6)：1155-1160.

Zhou F Q, Cao J G, Zhang J, et al. Prediction model of rolling force for tandem cold rolling mill based on neural networks and mathematical models[J]. Journal of Central South University：Science and Technology, 2006, 37 (6): 1155-1160.

[15]孙登月，杜凤山，朱泉封，等. 五机架冷连轧机轧制力人工神经网络预报[J]. 钢铁，2002，37 (2)：28-30，34.

Sun D Y, Du F S, Zhu Q F, et al. Prediction on five-stand cold rolling mill of rolling force by neural network[J]. Iron & Steel, 2002, 37 (2): 28-30，34.

[16]Wang Z H, Gong D Y, Li X, et al. Prediction of bending force in the hot strip rolling process using artificial neural network and genetic algorithm (ANN-GA)[J]. The International Journal of Advanced Manufacturing Technology, 2017, 93 (4): 3325-3338.

[17]Deng J F, Sun J, Peng W, et al. Application of neural networks for predicting hot-rolled strip crown[J]. Applied Soft Computing, 2019, 78: 119-131.

[18]曹建国，江军，赵秋芳，等. 基于数据挖掘的宽厚板板凸度控制[J]. 中南大学学报：自然科学版，2019，50 (11)：2743-2752.

Cao J G, Jiang J, Zhao Q F, et al. Wide and heavy plate crown control based on data mining[J]. Journal of Central South University：Science and Technology, 2019, 50 (11): 2743-2752.

[19]Liu J Y, Liu X X, Ba T L. Rolling force prediction of hot rolling based on GA-MELM[J]. Complexity, 2019, （4）: 1-11.

[20]张俊明，刘军，康永林，等. 应用RBF神经网络预测冷连轧机轧制力[J]. 钢铁，2007，42 (8)：46-48.

Zhang J M, Liu J, Kang Y L, et al. Application of RBF neural networks to prediction of rolling force of tandem cold mill[J]. Iron & Steel, 2007, 42 (8): 46-48.

[21]Kennedy J, Eberhart R. Particle swarm optimization[A]. Proceedings of the 1995 ICNN-International Conference on Neural Networks[C]. Perth: IEEE Press, 1995.

[22]Shi Y, Eberhart R. A modified particle optimizer[A]. Proceedings of the 1998 IEEE International Conference on Evolutionary Computation[C]. Anchorage, 1998.

[23]Shi Y. Particle swarm optimization[J]. IEEE Connections, 2004, 2(1): 8-13.

[24]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. Rolling force prediction of hot strip rolling based on GA-PELM[J]. Forging & Stamping Technology, 2022, 47 (1): 43-48.

[25]张浩，王国文，曾凡宜，等. 基于BP神经网络的6082铝合金固溶时效处理后的晶粒尺寸预测[J]. 锻压技术，2023，48 (3): 227-235.

Zhang H, Wang G W, Zeng F Y, et al. Grain size prediction of 6082 aluminum alloy after solution and aging treatment based on BP neural network[J]. Forging & Stamping Technology, 2023, 48 (3): 227-235.

[26]张海霞，李灿. 基于比例损失去噪自编码器的冷连轧轧制力预测分析[J]. 锻压技术，2022，47 (4): 190-194.

Zhang H X, Li C. Rolling force prediction analysis of tandem cold rolling based on proportional loss denoising autoencoder[J]. Forging & Stamping Technology, 2022, 47 (4): 190-194.

[27]王辉，廖旭洲，蔡继文，等. AZ31B镁合金电流辅助旋压回弹角预测及工艺参数优化[J]. 锻压技术，2022，47 (8): 29-34.

Wang H, Liao X Z, Cai J W, et al. Prediction on springback angle and process parameter optimization in electro-assisted spinning for AZ31B magnesium alloy[J]. Forging & Stamping Technology, 2022, 47 (8): 29-34.

[28]Yan Z W, Bu H N, Hu C Z, et al. Rolling force prediction during FGC process of tandem cold rolling based on IQGA-WNN ensemble learning[J]. The Internation Journal of Advanced Manufacturing Technology, 2023, 125 (5-6): 2869-2884.

服务与反馈：

【文章下载】【加入收藏】