基于深度学习的热轧带钢头部厚度的命中预测

doi:10.13228/j.boyuan.issn0449-749x.20210044

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (3230 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Aiming at the problem of low precision of hot rolled strip head thickness, a hit prediction method of hot rolled strip head thickness based on deep learning was proposed. In the process of finish rolling, the tension of the head end of the steel is small, and the temperature is usually lower. At the same time, the process parameters of the rolling mill are complex, and it is difficult to set accurately. The thickness of the rolled strip head is often unqualified. This study intends to use the nonlinear fitting ability of the deep neural network to design the prediction model of strip head thickness, to provide a reference for the parameter setting of rolling mill, improve the hit rate of head thickness and reduce the waste of steel. The deep neural network (DNN) consists of the input layer, hidden layer, and output layer structure. The prediction model is designed by TensorFlow open-source machine learning framework and implemented by program. By adjusting the parameters of the neural network and studying their effects on the model performance, the prediction model is optimized. Finally, the model of head thickness prediction was trained and tested with the test data of various thicknesses of strip steel, and the result showed that the accuracy of classification prediction was more than 80%.

Key words： hot-rolled strip deep learning thickness prediction hit ratio of head thickness open source machine learning

Received: 20 January 2021

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	YU Jia-xue
	SUN Jie
	ZHANG Dian-hua

Cite this article:

YU Jia-xue,SUN Jie,ZHANG Dian-hua. Accurate prediction of head thickness of hot-rolled strip based on deep learning[J]. Iron and Steel, 2021, 56(9): 19-25.

URL:

http://www.chinamet.cn/Jweb_gt/EN/10.13228/j.boyuan.issn0449-749x.20210044 OR http://www.chinamet.cn/Jweb_gt/EN/Y2021/V56/I9/19

[1] 王东城, 徐扬欢, 段伯伟, 等. 数据驱动的热轧带钢边部线状缺陷智能预报模型[J]. 钢铁, 2020, 55(11): 82. (WANG Dong-cheng, XU Yang-huan, DUAN Bo-wei, et al. Data-driven intelligent prediction model of edge seam defects for hot rolling strip[J]. Iron and Steel, 2020, 55(11): 82.)
[2] 陈丰,杨子江,王庆军,等. 热连轧带钢生产线计算机控制系统的研发与应用[J]. 轧钢, 2019, 36(3): 59.(CHEN Feng,YANG Zi-jiang,WANG Qing-jun,et al. Development and application of control system of hot continuous strip rolling line[J]. Steel Rolling, 2019, 36(3): 59.)
[3] 王东城, 张亚林, 徐扬欢. 热轧带钢尾部“伪板形不良”问题研究[J]. 钢铁, 2020, 55(9): 64.(WANG Dong-cheng, ZHANG Ya-lin, XU Yang-huan. Research on problem of "pseudo-bad flatness" at tail of hot rolling strip[J]. Iron and Steel, 2020, 55(9): 64.)
[4] 张宏献, 回士敏, 马欣然. 提高热轧带钢成品的宽度控制精度[J]. 中国冶金, 2020, 30(8): 60. (ZHANG Hong-xian, HUI Shi-min, MA Xin-ran. Improvements of width controlling precision for finished hot-rolled strips[J]. China Metallurgy, 2020, 30(8): 60.)
[5] 李维刚,徐文胜,马威,等. 基于热连轧实测数据的模型钢族层别优化[J]. 钢铁, 2018, 53(10): 54. (LI Wei-gang,XU Wen-sheng,MA Wei,et al. Optimization for steel grade family of model based on measured data during hot continuous rolling[J].Iron and Steel, 2018, 53(10): 54.)
[6] 杨平,陈志军. 针对热轧带钢头部拉窄的活套控制系统改进[J]. 中国冶金, 2018, 28(12): 36. (YANG Ping,CHEN Zhi-jun. Improvement of looper control system for hot rolled strip head narrowing[J]. China Metallurgy, 2018, 28(12): 36.)
[7] 孙一康. 带钢热连轧的模型与控制[M]. 北京:冶金工业出版社,2002.(SUN Yi-kang. Model and Control of Hot Strip Rolling[M]. Beijing: Metallurgical Industry Press, 2002.)
[8] 李新创,栾治伟,施灿涛. 人工智能技术在钢铁行业中的应用研究[J]. 冶金自动化,2020,44(1):1.(LI Xin-chuang,LUAN Ye-wei,SHI Can-tao.Appliacation of artficial intelligence in iron and steel industry[J].Metallurgical Industy Automation, 2020,44(1):1.)
[9] Mieghem P V. Graph Spectra for Complex Networks[M]. Cambridge: Cambridge University Press, 2011.
[10] 王新东, 闫永军. 智能制造助力钢铁行业技术进步[J]. 冶金自动化, 2019, 43(1): 1. (WANG Xin-dong, YAN Yong-jun. Promoting the technical progress of steel industry with intelligent manufacturing[J]. Metallurgical Industry Automation, 2019, 43(1): 1.)
[11] 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. (CAO Jian-guo, JIANG Jun, ZHAO Qiu-fang, et al. Wide and heavy plate crown control based on data mining[J]. Journal of Central South University (Natural Science), 2019, 50(11): 2743.)
[12] 任新意, 王松涛, 高慧敏, 等. 冷连轧机ESS辊型板形控制性能分析[J]. 钢铁. 2018, 53(3): 50.(REN Xin-yi, WANG Song-tao, GAO Hui-min, et al. Analysis on shape control performance of cold tandem mill with ESS roll profile[J]. Iron and Steel. 2018, 53(3): 50.)
[13] 曹卫华,李熙,吴敏,等. 基于极限学习机的热轧薄板轧制力预测模型. 信息与控制,2014,43(3):270. (CAO Wei-hua,LI Xi,WU Min,et al.force prediction model for hot rolled sheets based on extreme learning machine[J]. Information and Control, 2014,43(3):270.)
[14] Hinton G, Deng L, Yu D, et al. Deep neural networks for acoustic modeling in speech recognition[J]. IEEE Signal Processing Magazine, 2012, 29(6): 82.
[15] YU L, XUN C, HU P, et al. Multi-focus image fusion with a deep convolutional neural network[J]. Information Fusion, 2017, 36(36): 191.
[16] Rumelhart D E, Hinton G E, Williams R J. Learning internal representations by error propagation[J]. Parallel Distributed Processing, 1986, 1(2): 399.
[17] Schmidhuber J. Deep learning in neural networks: An overview[J]. Neural Networks, 2015, 61(61): 85.
[18] JIA Sen, JIANG Shu-guo, LIN Zhi-jie et al. A survey: Deep learning for hyperspectral image classification with few labeled samples[J].Neurocomputing, 2021, 448.
[19] Hinton G E, Srivastava N, Krizhevsky A, et al. Improving neural networks by preventing co-adaptation of feature detectors[J]. Computer Science, 2012, 3(4): 212.