基于机器学习的中厚板变形抗力模型建模与应用

doi:10.11900/0412.1961.2021.00283

金属学报

2023, Vol. 59

Issue (3): 435-446 DOI: 10.11900/0412.1961.2021.00283

研究论文

本期目录 | 过刊浏览

基于机器学习的中厚板变形抗力模型建模与应用

冀秀梅¹^,², 侯美伶², 王龙¹(

), 刘玠¹, 高克伟²

1 上海大学材料科学与工程学院上海 200444
2 江阴兴澄特种钢铁有限公司江阴 214400

Modeling and Application of Deformation Resistance Model for Medium and Heavy Plate Based on Machine Learning

JI Xiumei¹^,², HOU Meiling², WANG Long¹(

), LIU Jie¹, GAO Kewei²

1 School of Materials Science and Engineering, Shanghai University, Shanghai 200444, China
2 Jiangyin Xingcheng Special Steel Co. Ltd., Jiangyin 214400, China

引用本文:

冀秀梅, 侯美伶, 王龙, 刘玠, 高克伟. 基于机器学习的中厚板变形抗力模型建模与应用[J]. 金属学报, 2023, 59(3): 435-446.
Xiumei JI, Meiling HOU, Long WANG, Jie LIU, Kewei GAO. Modeling and Application of Deformation Resistance Model for Medium and Heavy Plate Based on Machine Learning[J]. Acta Metall Sin, 2023, 59(3): 435-446.

全文: PDF(2306 KB) HTML

摘要:

为提高变形抗力预测精度，以兴澄特钢中厚板轧机实际生产数据为基础，针对性提出2种利用机器学习对变形抗力进行预测的方法：一种是极限学习机(ELM)与传统数学模型结合的多钢种变形抗力模型及建模方法，另一种是基于TensorFlow深度学习框架的变形抗力模型及建模方法。方法一参考周纪华-管克智变形抗力模型，改进原变形抗力模型结构形式，计算出低合金钢、合金钢及高合金钢代表钢种的基准变形抗力；通过非线性回归计算出与钢种无关的变形参数影响系数，引进ELM神经网络算法，采用灰色关联分析及交叉验证优选神经网络参数，通过线性插值对预测结果进行平滑处理，减小ELM预测残差，最后与传统数学模型相结合得到变形抗力。方法二基于深度学习技术，结合机理，构建2种不同结构的深度神经网络，采用小批量(mini-batch)和均方根传播(RMSprop)优化算法寻优，结合批标准化(BN)和早停(early stopping)正则化策略提高模型泛化能力与稳定性，最后综合工艺特性，分别对粗轧机(RM)、精轧机(FM)建立变形抗力预测模型，提高模型精度。研究结果表明，利用深度学习预测变形抗力具有较高的预测精度，经离线分析，平均绝对百分误差(MAPE)由原模型的9.27%降至平均2.59%；在线应用后，轧制力预测精度相对误差10%以内比例由72.31%提高到平均90.24%，提高了现场生产的工艺水平。

关键词 ：机器学习, 变形抗力预测, ELM神经网络, 深度学习, 基准变形抗力, 灰色关联分析

Abstract：

Based on the actual production data of the plate mill of Xingcheng Special Steel, two machine learning methods for predicting deformation resistance are proposed to improve prediction accuracy. The first is a multi-steel deformation resistance model and modeling method that is combined with an extreme learning machine (ELM) and a traditional mathematical model, and the second is a deformation resistance model and modeling method that is based on the TensorFlow deep learning framework. Method one: The structural form of the original deformation resistance model was improved by referring to the Zhou Jihua-Guan Kezhi deformation resistance model, and the reference deformation resistances of representative steel grades of low alloy steel, alloy steel, and high alloy steel were calculated. The influence coefficient of deformation parameters independent of steel grade was calculated using nonlinear regression. The ELM neural network algorithm was presented, and neural network parameters were optimized using grey correlation analysis and cross-validation. To reduce the residual error of ELM prediction, the prediction results were smoothed using linear interpolation and then combined with the traditional mathematical model to obtain the deformation resistance. Method two: Based on deep learning technology, two types of deep neural networks with different structures were built and combined with the mechanism. To improve the generalizability and stability of the model, the mini-batch and RMSprop optimization algorithms were used in conjunction with batch normalization (BN) and early stopping regularization strategies. Finally, deformation resistance prediction models for roughing mill (RM) and finishing mill (FM) were developed respectively in conjunction with the process characteristics to improve model accuracy. The results showed that the deformation resistance prediction using deep learning has high prediction accuracy. Offline analysis indicated that the mean absolute percentage error decreased from 9.27% of the original model to an average of 2.59%. The online application demonstrated that the ratio of rolling force prediction accuracy within 10% relative error increased from 72.31% to an average of 90.24%, raising the technological level of onsite production.

Key words： machine learning prediction of deformation resistance ELM neural network deep learning reference deformation resistance grey relational analysis

收稿日期: 2021-07-12

ZTFLH:

TG335.5

作者简介: 冀秀梅，女，1986年生，硕士生

	服务

	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	冀秀梅
	侯美伶
	王龙
	刘玠
	高克伟
44.8K

链接本文:

https://www.ams.org.cn/CN/10.11900/0412.1961.2021.00283 或 https://www.ams.org.cn/CN/Y2023/V59/I3/435

表1 试样化学成分 (mass fraction / %)

图1 试样在不同变形温度(t)和不同应变速率(ε˙)下的应力-应变曲线

图2 变形抗力与变形温度、应变速率和应变的关系

表2 变形抗力影响因素的灰色关联度

图3 极限学习机(ELM)神经网络与数学模型结合计算框图

图4 基准变形抗力模型网络结构图

图5 不同策略下损失函数变化曲线(a) no regularization (b) early stopping and batch normalization

表3 变形抗力及其影响因素数据分布

表4 原模型及4组方案预测精度

图6 变形抗力预测值和实测值比较

图7 Deep_RM和Deep_All预测值分别与RM真实值的偏差绝对值分布对比

图8 Deep_FM和Deep_All预测值分别与FM真实值的偏差绝对值分布对比

图9 模型改造前、后轧制力预测相对误差分布

1	Zhang D H, Peng W, Sun J, et al. Key intelligent technologies of steel strip rolling process [J]. J. Iron Steel Res., 2019, 31: 174
1	张殿华, 彭文, 孙杰等. 板带轧制过程中的智能化关键技术 [J]. 钢铁研究学报, 2019, 31: 174
2	Liu X H, Wang G D. Development of advanced technology in hot strip rolling [J]. Res. Iron Steel, 2000, (5): 1
2	刘相华, 王国栋. 热轧带钢新技术的发展 [J]. 钢铁研究, 2000, (5): 1
3	Li Y, Liu J X, Ke X T. Development and research of deformation resistance model in hot rolling process [J]. Res. Iron Steel, 2009, 37(6): 59
3	李英, 刘建雄, 柯晓涛. 轧制变形抗力数学模型的发展与研究动态 [J]. 钢铁研究, 2009, 37(6): 59
4	Zhou J H, Guan K Z. Plastic Deformation Resistance of Metal [M]. Beijing: Machinery Industry Press, 1989: 212
4	周纪华, 管克智. 金属塑性变形阻力 [M]. 北京: 机械工业出版社, 1989: 212
5	Wang J, Wang X G, Yang H T, et al. A new mathematical model for predicting flow stress of X70HD under hot deformation [J]. J. Cent. South Univ., 2015, 22: 2052 doi: 10.1007/s11771-015-2728-y
6	Feng Y L, Li J, Ai L Q, et al. Deformation resistance of Fe-Mn-V-N alloy under different deformation processes [J]. Rare Met., 2017, 36: 833 doi: 10.1007/s12598-015-0678-z
7	Kingkam W, Zhao C Z, Li H, et al. Hot deformation and corrosion resistance of high-strength low-alloy steel [J]. Acta Metall. Sin. (Engl. Lett.), 2019, 32: 495 doi: 10.1007/s40195-018-0797-2
8	Wei L X, Zhang Y, Sun H, et al. Online cold rolling prediction based on improved OS-ELM [J]. Acta Metrol. Sin., 2019, 40: 111
8	魏立新, 张宇, 孙浩等. 基于改进OS-ELM的冷连轧在线轧制力预报 [J]. 计量学报, 2019, 40: 111
9	Wang J, Wang Y, Xie H B, et al. Deformation resistance model based on measured data of hot rolling [J]. J. Plast. Eng., 2015, 22(1): 55
9	王健, 王宇, 谢红飙等. 基于热连轧实测数据的金属材料变形抗力模型 [J]. 塑性工程学报, 2015, 22(1): 55
10	Li W G, Liu C, Zhao Y T, et al. Modeling deformation resistance for hot rolling based on generalized additive model [J]. J. Iron Steel Res. Int., 2017, 24: 1177 doi: 10.1016/S1006-706X(18)30015-3
11	Xie X Q, Li W G, Fu W P, et al. Deformation resistance model for hot-rolled strip based on measured data [J]. Metall. Ind. Autom., 2019, 43(2): 29
11	谢向群, 李维刚, 付文鹏等. 基于实测数据的热轧带钢变形抗力模型 [J]. 冶金自动化, 2019, 43(2): 29
12	Su Y J, Fu H D, Bai Y, et al. Progress in materials genome engineering in China [J]. Acta Metall. Sin., 2020, 56: 1313
12	宿彦京, 付华栋, 白洋等. 中国材料基因工程研究进展 [J]. 金属学报, 2020, 56: 1313
13	Wang T, Wan Z P, Sun Y, et al. Dynamic softening behavior and microstructure evolution of nickel base superalloy [J]. Acta Metall. Sin., 2018, 54: 83 doi: 10.11900/0412.1961.2017.00241
13	王涛, 万志鹏, 孙宇等. 镍基变形高温合金动态软化行为与组织演变规律研究 [J]. 金属学报, 2018, 54: 83
14	Li M Q, Yao X Y, Luo J, et al. Modeling for flow stress of the nickel-based GH4169 superalloy at high temperature deformation [J]. Acta Metall. Sin., 2007, 43: 937
14	李淼泉, 姚晓燕, 罗皎等. 镍基高温合金GH4169高温变形流动应力模型研究 [J]. 金属学报, 2007, 43: 937
15	Phaniraj M P, Lahiri A K. The applicability of neural network model to predict flow stress for carbon steels [J]. J. Mater. Process. Technol., 2003, 141: 219 doi: 10.1016/S0924-0136(02)01123-8
16	Zhou J H, Guan K Z, Liu J, et al. An mathematical model of flow stress for hot strip mill [J]. J. Univ. Sci. Technol. Beijing, 1991, 13: 20
16	周纪华, 管克智, 刘玠等. 热轧碳钢流动应力的数学模型 [J]. 北京科技大学学报, 1991, 13: 20
17	Zhao M M, Qin S, Feng J, et al. Effect of Al and Ni on hot deformation behavior of 1Cr9Al(1~3)Ni(1~7)WVNbB steel [J]. Acta Metall. Sin., 2020, 56: 960 doi: 10.11900/0412.1961.2019.00403
17	赵嫚嫚, 秦森, 冯捷等. Al、Ni对1Cr9Al(1~3)Ni(1~7)WVNbB钢热变形行为的影响 [J]. 金属学报, 2020, 56: 960 doi: 10.11900/0412.1961.2019.00403
18	Ji X M, Wang L, Gao K W, et al. Application of ELM to predict plate rolling force [J]. J. Iron Steel Res., 2020, 32: 393
18	冀秀梅, 王龙, 高克伟等. 极限学习机在中厚板轧制力预报中的应用 [J]. 钢铁研究学报, 2020, 32: 393
19	Mei Y, Sun Q L, Yu L H, et al. Grain size prediction of aluminum alloy dies castings based on GA-ELM [J]. Acta Metall. Sin., 2017, 53: 1125
19	梅益, 孙全龙, 喻丽华等. 基于GA-ELM的铝合金压铸件晶粒尺寸预测 [J]. 金属学报, 2017, 53: 1125
20	Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: Theory and applications [J]. Neurocomputing, 2006, 70: 489 doi: 10.1016/j.neucom.2005.12.126
21	Deng C W, Huang G B, Xu J, et al. Extreme learning machines: New trends and applications [J]. Sci. China Inform. Sci., 2015, 58: 1
22	Huang G B, Zhou H M, Ding X J, et al. Extreme learning machine for regression and multiclass classification [J]. IEEE Trans. Syst. Man Cybern., 2012, 42B: 513
23	Poudel P, Bae S H, Jang B. Comparison of different deep learning optimizers for modeling photovoltaic power [J]. J. Chosun Nat. Sci., 2018, 11: 204
24	Li W G, Yang W, Zhao Y T, et al. Modeling hot strip rolling process under framework of generalized additive model [J]. J. Cent. South Univ., 2019, 26: 2379 doi: 10.1007/s11771-019-4181-9
25	Ma W, Li W G, Zhao Y T, et al. Prediction of hot-rolled roll force based on deep learning[J]. J. Iron Steel Res., 2019, 31: 805
25	马威, 李维刚, 赵云涛等. 基于深度学习的热连轧轧制力预测 [J]. 钢铁研究学报, 2019, 31: 805
26	Liu D H, Li J H, Peng Y, et al. Comprehensive evaluation of sintering basic characteristics of iron ore based on grey relational analysis [J]. J. Iron Steel Res. Int., 2019, 26: 691 doi: 10.1007/s42243-019-00259-1
27	Zhang T, Zhang Z H, Tian Y, et al. Research and application of deep learning method for plate ultra fast cooling [J]. J. Northeastern Univ. (Nat. Sci.), 2019, 40: 635
27	张田, 张子豪, 田勇等. 深度学习在中厚板轧后超快速冷却系统中的研究与应用 [J]. 东北大学学报(自然科学版), 2019, 40: 635

[1]	穆亚航, 张雪, 陈梓名, 孙晓峰, 梁静静, 李金国, 周亦胄. 基于热力学计算与机器学习的增材制造镍基高温合金裂纹敏感性预测模型[J]. 金属学报, 2023, 59(8): 1075-1086.
[2]	杨累, 赵帆, 姜磊, 谢建新. 机器学习辅助2000 MPa级弹簧钢成分和热处理工艺开发[J]. 金属学报, 2023, 59(11): 1499-1512.
[3]	高建宝, 李志诚, 刘佳, 张金良, 宋波, 张利军. 计算辅助高性能增材制造铝合金开发的研究现状与展望[J]. 金属学报, 2023, 59(1): 87-105.
[4]	何兴群, 付华栋, 张洪涛, 方继恒, 谢明, 谢建新. 机器学习辅助高性能银合金电接触材料的快速发现[J]. 金属学报, 2022, 58(6): 816-826.
[5]	赵婉辰, 郑晨, 肖斌, 刘行, 刘璐, 余童昕, 刘艳洁, 董自强, 刘轶, 周策, 吴洪盛, 路宝坤. 基于Bayesian采样主动机器学习模型的6061铝合金成分精细优化[J]. 金属学报, 2021, 57(6): 797-810.
[6]	谢建新, 宿彦京, 薛德祯, 姜雪, 付华栋, 黄海友. 机器学习在材料研发中的应用[J]. 金属学报, 2021, 57(11): 1343-1361.

Viewed

Full text

Abstract

Cited

Shared

Discussed