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

doi:10.11900/0412.1961.2021.00283

Acta Metall Sin

2023, Vol. 59

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

Research paper

Current Issue | Archive | Adv Search

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

Cite this article:

JI Xiumei, HOU Meiling, WANG Long, LIU Jie, GAO Kewei. Modeling and Application of Deformation Resistance Model for Medium and Heavy Plate Based on Machine Learning. Acta Metall Sin, 2023, 59(3): 435-446.

Download:

HTML

PDF(2306KB)
Export: BibTeX | EndNote (RIS)

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

Received: 12 July 2021

ZTFLH:

TG335.5

About author: WANG Long, senior engineer, Tel: 18616377700, E-mail: longwang@shu.edu.cn

	Service

	E-mail this article
	Add to citation manager
	E-mail Alert
	RSS
	（）
	Articles by authors
	Xiumei JI
	Meiling HOU
	Long WANG
	Jie LIU
	Kewei GAO

URL:

https://www.ams.org.cn/EN/10.11900/0412.1961.2021.00283 OR https://www.ams.org.cn/EN/Y2023/V59/I3/435

Table 1 Chemical composition of samples

Fig.1 Stress-strain curves of samples under deformation temperatures of t = 900^oC (a), t = 1000^oC (b), and t = 1100^oC (c) and strain rates of $ε ˙$ = 0.1 s^-1 and $ε ˙$ = 10 s^-1

Fig.2 Relationship between deformation resistance and deformation temperature (a), strain rate (b), and strain (c)

Process parameter/composition	Relational degree	Process parameter/composition	Relational degree
Al	0.9437	Ti	0.9033
C	0.9435	Ni	0.9017
Cu	0.9428	V	0.8589
Mn	0.9345	Mo	0.8544
P	0.9328	Cr	0.8517
Si	0.9324	N	0.8171
$ε$	0.9309	Sn	0.7974
t	0.9291	W	0.7832
$ε ˙$	0.9288	As	0.6871
B	0.9133	Bi	0.6453
S	0.9084	Sn	0.6098
Nb	0.9059	Ca	0.5074

Table 2 Grey correlation degrees of influencing factors of deformation resistance

Fig.3 Calculation diagram of extreme learning machine (ELM) neural network and mathematical model (W(C), W(Al), $?$ , W(Cr)—mass fractions of C, Al, …, and Cr, respectively; $K t K ε K ε ˙$ —product of the influence coefficients of temperature, strain, and strain rate on deformation resistance)

Fig.4 Network structure of reference deformation resistance model (σ_{0, chem}—reference deformation resistance relative to chemical composition)

Fig.5 Change curves of loss function under different strategies (MSE—mean square error)

Table 3 Data distributions of deformation resistance and its influencing factors

Table 4 Prediction accuracies of the original model and four groups of schemes

Fig.6 Comparisons of the measured value and the predicted value of deformation resistance for scheme 1 (a), scheme 2 (b), scheme 3 (c), scheme 4 (RM) (d1), and scheme 4 (FM) (d2)

Fig.7 Comparisons of the distribution of the absolute value of the deviation between the true value of RM deformation resistance and the predicted value obtained by Deep_RM (a) and Deep_All (b) ( $Δ y$ —absolute value of the deviation between the true value and predicted value)

Fig.8 Comparisons of the distribution of the absolute value of the deviation between the true value of FM deformation resistance and the predicted value obtained by Deep_FM (a) and Deep_All (b)

Fig.9 Relative error distributions of rolling force prediction
(a) before model modification
(b) the first month after model modification
(c) the second month after model modification
(d) the third month after model modification

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
	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
	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
	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
	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
	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
	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
	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
	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
	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
	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
	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
	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
	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
	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
	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
	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]	MU Yahang, ZHANG Xue, CHEN Ziming, SUN Xiaofeng, LIANG Jingjing, LI Jinguo, ZHOU Yizhou. Modeling of Crack Susceptibility of Ni-Based Superalloy for Additive Manufacturing via Thermodynamic Calculation and Machine Learning[J]. 金属学报, 2023, 59(8): 1075-1086.
[2]	YANG Lei, ZHAO Fan, JIANG Lei, XIE Jianxin. Development of Composition and Heat Treatment Process of 2000 MPa Grade Spring Steels Assisted by Machine Learning[J]. 金属学报, 2023, 59(11): 1499-1512.
[3]	GAO Jianbao, LI Zhicheng, LIU Jia, ZHANG Jinliang, SONG Bo, ZHANG Lijun. Current Situation and Prospect of Computationally Assisted Design in High-Performance Additive Manufactured Aluminum Alloys: A Review[J]. 金属学报, 2023, 59(1): 87-105.
[4]	HE Xingqun, FU Huadong, ZHANG Hongtao, FANG Jiheng, XIE Ming, XIE Jianxin. Machine Learning Aided Rapid Discovery of High Perfor-mance Silver Alloy Electrical Contact Materials[J]. 金属学报, 2022, 58(6): 816-826.
[5]	ZHAO Wanchen, ZHENG Chen, XIAO Bin, LIU Xing, LIU Lu, YU Tongxin, LIU Yanjie, DONG Ziqiang, LIU Yi, ZHOU Ce, WU Hongsheng, LU Baokun. Composition Refinement of 6061 Aluminum Alloy Using Active Machine Learning Model Based on Bayesian Optimization Sampling[J]. 金属学报, 2021, 57(6): 797-810.
[6]	XIE Jianxin, SU Yanjing, XUE Dezhen, JIANG Xue, FU Huadong, HUANG Haiyou. Machine Learning for Materials Research and Development[J]. 金属学报, 2021, 57(11): 1343-1361.
[7]	XU Wei,HUANG Minghao,WANG Jinliang,SHEN Chunguang,ZHANG Tianyu,WANG Chenchong. Review: Relations Between Metastable Austenite and Fatigue Behavior of Steels[J]. 金属学报, 2020, 56(4): 459-475.

No Suggested Reading articles found!

Viewed

Full text

Abstract

Cited

Shared

Discussed