|
|
Property prediction of steel rolling process based on machine learning |
YANG Jian1,2, WU Si-wei1,2 |
1. School of Materials Science and Engineering, Shanghai University, Shanghai 200444, China; 2. State Key Laboratory of Advanced Special Steels, Shanghai 200444, China |
|
|
Abstract In order to achieve rapid optimization design of hot rolling process,the property prediction of steel based on industrial data has attracted great attention of researchers. The research progress of steel rolling process property prediction using machine learning was reviewed. Firstly,the main machine learning algorithms commonly used in steel rolling process property prediction were introduced,including artificial neural network,fuzzy neural network,support vector machine,random forest,intelligent optimization algorithm and so on. Secondly,the research progress and the applications of steel rolling process property prediction model were summarized respectively. Finally,the prospect of the research on the property prediction of steel rolling process was presented,and the possible development directions were pointed out,such as the improvement of data quality,the modeling of small sample data,the encryption of modeling data,the research of model interpretability,the prediction of steel microstructure and the effective process optimization design by using the model.
|
Received: 06 May 2021
|
|
|
|
[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(2):174.(ZHANG Dian-hua,PENG Wen,SUN Jie,et al. Key intelligent technologies of steel strip rolling process[J]. Journal of Iron and Steel Research,2019,31(2):174.) [2] 刘振宇,曹光明,周晓光,等. 组织性能预测技术及其在智能热轧中的核心作用[J]. 轧钢,2019,36(2):1.(LIU Zhen-yu,CAO Guang-ming,ZHOU Xiao-guang,et al. The predicting technologies for microstructure and properties and their core roles in smart hot rolling processes[J]. Steel Rolling,2019,36(2):1.) [3] 何安瑞,荆丰伟,刘超,等. 薄板坯连铸连轧过程控制技术的发展、应用及展望[J]. 轧钢,2020,37(3):1.(HE An-rui,JING Feng-wei,LIU Chao,et al. Development,application and prospect of process control technologies of thin slab continuous casting and rolling[J]. Steel Rolling,2020,37(3):1.) [4] 刘相华,赵启林,黄贞益. 人工智能在轧制领域中的应用进展[J]. 轧钢,2017,34(4):1.(LIU Xiang-hua,ZHAO Qi-lin,HUANG Zhen-yi. Prospect of artificial intelligent application in rolling[J]. Steel Rolling,2017,34(4):1.) [5] 康永林,丁波,陈其安. 我国轧制学科发展现状与趋势分析及展望[J]. 轧钢,2017,34(6):1.(KANG Yong-lin,DING Bo,CHEN Qi-an. Analysis and prospect of developing status and trends of rolling discipline in China[J]. Steel Rolling,2017,34(6):1.) [6] LIU Z Y,WANG W D,GAO W. Modelling of microstructure-property relationship of hot rolled C-Mn steels by using aritificial neural network[C]//Ipenz Conference. Palmerston North:Institution of Professional Engineers,1995:398. [7] 刘振宇,王昭东,王国栋,等. 应用神经网络预测热轧C-Mn钢力学性能[J]. 钢铁研究学报,1995,7(4):61.(LIU Zhen-yu,WANG Zhao-dong,WANG Guo-dong,et al. Prediction of mechanical properties of hot rolled C-Mn Steel by neural network[J]. Journal of Iron and Steel Research,1995,7(4):61.) [8] LIU Z Y,WANG W D,GAO W. Prediction of the mechanical properties of hot-rolled C-Mn steels using artificial neural networks[J]. Journal of Materials Processing Technology,1996,57(3/4):332. [9] Sterjovski Z,Nolan D,Carpenter K R,et al. Artificial neural networks for modelling the mechanical properties of steels in various applications[J]. Journal of Materials Processing Technology,2005,170(3):536. [10] Jagadish,Soni Dheeraj-lal,Barad Surajit. Prediction of mechanical properties of Fe415 steel in hot rolling process using artificial neural network[J]. Transactions of the Indian Institute of Metals,2020,73(6):1535. [11] Yang Y Y,Mahfouf M,Linkens D A,et al. Tensile strength prediction for hot rolled steels by Bayesian neural network model[J]. IFAC Proceedings Volumes,2009,42(23):255. [12] Khlybov O S,Dubinin I V. Algorithm for controlling mechanical properties of hot rolled steels using Bayesian network model[J]. Materials Science Forum,2012,706-709:1444. [13] 贾涛,刘振宇,胡恒法,等.基于贝叶斯神经网络的SPA-H热轧板力学性能预测[J]. 东北大学学报(自然科学版),2008,29(4):521.(JIA Tao,LIU Zhen-yu,HU Heng-fa,et al. Mechanical property prediction for hot rolled SPA-H steel using bayesian neural network[J]. Journal of Northeastern University(Natural Science),2008,29(4):521.) [14] JIA Tao,LIU Zhen-yu,HU Heng-fa,et al.The optimal design for the production of hot rolled strip with "tight oxide scale" by using multi-objective optimization[J]. ISIJ International,2011,51(9):1468. [15] 吴思炜,曹光明,周晓光,等. 基于大数据的C-Mn钢数据预处理及神经网络模型[J]. 东北大学学报(自然科学版),2016,37(12):1710.(WU Si-wei,CAO Guang-ming,ZHOU Xiao-guang,et al. Data preprocessing and neural network model of C-Mn steel based on big data[J]. Journal of Northeastern University(Natural Science),2016,37(12):1710.) [16] 吴思炜,周晓光,曹光明,等. 热轧C-Mn钢工业大数据预处理对模型的改进作用[J]. 钢铁,2016,51(5):88.(WU Si-wei,ZHOU Xiao-guang,CAO Guang-ming,et al. Hot rolling C-Mn steel industry big data preprocessing for improvements on the model[J]. Iron and Steel,2016,51(5):88.) [17] WU Si-wei,YANG Jian,LIU Zhen-yu. Composition-processing-property correlation mining of Nb-Ti microalloyed steel based on industrial data[J]. Materials Transactions,2020,61(4):691. [18] ZHAO Yong-hong,WENG Yang,PENG Ning-qi,et al. Prediction of mechanical properties of hot rolled strip by using semi-parametric single-index model[J]. Journal of Iron and Steel Research,International,2013,20(7):9. [19] WENG Yang,ZHAO Yong-hong,TANG Guang-bo,et al. Prediction of the mechanical properties of hot-rolled C-Mn steels by single index model[C]//8th International Conference on Computer Science and Education. Colombo:IEEE,2013:275. [20] WU Si-wei,REN Jia-kuan,ZHOU Xiao-guang,et al. Comparisons of different data-driven modeling techniques for predicting tensile strength of X70 pipeline steels[J]. Transactions of the Indian Institute of Metals,2019,72(5):1277. [21] SUI Xiao-yue,LÜ Zhi-min. Prediction of the mechanical properties of hot rolling products by using attribute reduction ELM[J]. The International Journal of Advanced Manufacturing Technology,2016,85(5-8):1395. [22] Hore S,Das S K,Banerjee S,et al. An adaptive neuro-fuzzy inference system-based modelling to predict mechanical properties of hot-rolled TRIP steel[J]. Ironmaking and Steelmaking,2017,44(9):656. [23] 李飞飞,宋勇,刘超,等. 热轧带钢力学性能预报模型的误差分布建模研究[J]. 冶金自动化,2019,43(6):28.(LI Fei-fei,SONG Yong,LIU Chao,et al. Error distribution modeling of mechanical properties prediction model for hot rolled strip[J]. Metallurgical Industry Automation,2019,43(6):28.) [24] 李维刚,杨威,赵云涛,等. 融合大数据与冶金机理的热轧带钢力学性能预报模型[J]. 钢铁研究学报,2018,30(4):302.(LI Wei-gang,YANG Wei,ZHAO Yun-tao,et al. Prediction model for mechanical properties of hot rolled strip based on big data and metallurgical mechanism[J]. Journal of Iron and Steel Research,2018,30(4):302.) [25] 李维刚,王肖,杨威,等. 数据清洗对热轧微合金钢性能预报模型的改进[J]. 钢铁研究学报,2019,31(10):920.(LI Wei-gang,WANG Xiao,YANG Wei,et al. Improvement of property prediction model of hot rolled microalloyed steel by data cleaning[J]. Journal of Iron and Steel Research,2019,31(10):920.) [26] LI Wei-gang,YANG Wei,ZHAO Yun-tao,et al. Modeling hot strip rolling process under framework of generalized additive model[J]. Journal of Central South University,2019,26(9):2379. [27] 杨威,李维刚,赵云涛,等. 基于随机森林的钢材性能预报与影响因素筛选[J]. 钢铁,2018,53(3):44.(YANG Wei,LI Wei-gang,ZHAO Yun-tao,et al. Prediction of steel properties and selection of influencing factors based on random forest[J]. Iron and Steel,2018,53(3):44.) [28] 吴思炜. 基于工业大数据的热轧带钢组织性能预测与优化技术研究[D]. 沈阳:东北大学,2018.(WU Si-wei. Prediction and Optimization of Microstructure and Properties of Hot Rolled Strip Based on Industrial Big Data[D]. Shenyang:Northeastern University,2018.) [29] 胡石雄,李维刚,杨威. 基于卷积神经网络的热轧带钢力学性能预报[J]. 武汉科技大学学报(自然科学版),2018,41(5):338.(HU Shi-xiong,LI Wei-gang,YANG Wei. Mechanical property prediction of hot-roiled strip based on convolutional neural network[J]. Journal of Wuhan University of Science and Technology(Natural Science Edition),2018,41(5):338.) [30] XU Zhi-wei,LIU Xiao-ming,ZHANG Kai. Mechanical properties prediction for hot rolled alloy steel using convolutional neural network[J]. IEEE Access,2019,7:47068. [31] WU Si-wei,YANG Jian,CAO Guang-ming,et al. Elevating prediction performance for mechanical properties of hot-rolled strips by using semi-supervised regression and deep learning[J]. IEEE Access,2020,8:134124. [32] Kurban V V,Yatsenko N L,Belyakova V I. Feasibility of using neural networks for real-time prediction of the mechanical properties of finished rolled products[J]. Metallurgist,2007,51(1/2):3. [33] Agarwal K,Shivpuri R. An on-line hierarchical decomposition based Bayesian model for quality prediction during hot strip rolling[J]. ISIJ International,2012,52(10):1862. [34] 李军凯. 基于物理冶金学和BP网络的热轧带钢组织-性能的模拟和预测[D]. 沈阳:东北大学,2008.(LI Jun-kai. Simulation and Prediction of Microstructure and Properties of Hot Rolled Strip Based on Physical Metallurgy and BP Neural Network[D]. Shenyang:Northeastern University,2008.) [35] 邓天勇. 基于组织性能预测的柔性化轧制工艺制定方法[D]. 沈阳:东北大学,2008.(DENG Tian-yong. Flexible Rolling Process Formulation Method Based on Microstructure and Properties Prediction[D]. Shenyang:Northeastern University,2008.) [36] Lalam S,Tiwari P K,Sahoo S,et al. Online prediction and monitoring of mechanical properties of industrial galvanised steel coils using neural networks[J]. Ironmaking and Steelmaking,2019,46(1):89. [37] GUO Shun,YU Jin-xin,LIU Xing-jun,et al. A predicting model for properties of steel using the industrial big data based on machine learning[J]. Computational Materials Science,2019,160:95. [38] Chen M Y,Linkens D A,Bannister A. Numerical analysis of factors influencing Charpy impact properties of TMCR structural steels using fuzzy modelling[J]. Materials Science and Technology,2004,20(5):627. [39] Ryu J H,Bhadeshia H K D H. Contribution of microalloying to the strength of hot-rolled steels[J]. Materials and Manufacturing Processes,2009,24(2):138. [40] 吴思炜,刘振宇,周晓光,等. 基于大数据的力学性能预测与工艺参数筛选[J]. 钢铁研究学报,2016,28(12):1.(WU Si-wei,LIU Zhen-yu,ZHOU Xiao-guang,et al. Prediction of mechanical properties and process parameters selection based on big data[J]. Journal of Iron and Steel Research,2016,28(12):1.) [41] WU Si-wei,YANG Jian,LIU Zhen-yu. Composition-processing-property correlation mining of Nb-Ti microalloyed steel based on industrial data[J]. Materials Transactions,2020,61(4):691. [42] Mohanty I,Datta S,Bhattacharjee D. Composition-processing-property correlation of cold-rolled IF steel sheets using neural network[J]. Materials and Manufacturing Processes,2008,24(1):100. [43] 贾涛,胡恒法,曹光明,等. 基于组织-性能预测的集装箱热轧板工艺优化[J]. 钢铁,2008,43(11):54.(JIA Tao,HU Heng-fa,CAO Guang-ming,et al. Optimization of process parameters of hot rolling SPA-H steel based on prediction of microstructure-properties[J]. Iron and Steel,2008,43(11):54.) [44] WU Si-wei,CAO Guang-ming,ZHOU Xiao-guang,et al. High dimensional data-driven optimal design for hot strip rolling of C-Mn steels[J]. ISIJ International,2017,57(7):1213. [45] WU Si-wei,ZHOU Xiao-guang,CAO Guang-ming,et al. High-dimensional data-driven optimal design for hot strip rolling of microalloyed steel[J]. Steel Research International,2018,89(7):1800015. |
[1] |
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. |
[2] |
SHI Can-tao, WU Xiu-ting, ZHU Tao. Supporting connotative development of iron and steel industry with digital infrastructure[J]. Iron and Steel, 2021, 56(9): 50-55. |
[3] |
SHI Jian-rui, SUN Wen-quan, CHEN Lu-zhen, YUAN Tie-heng, ZHANG Xi-bang, LI Li-gang. Rolling mill slip prediction model based on limit static friction torque[J]. Iron and Steel, 2021, 56(9): 96-101. |
[4] |
LI Cheng-gang, SHAN Wen-chao, LIU Yi-si, YANG Ming, WANG Hao, CAO Guang-ming. Corrosion resistance process based on control of oxide scale in whole process of hot rolling[J]. Iron and Steel, 2021, 56(9): 129-135. |
[5] |
WANG Xin-dong, CHANG Jin-bao, LI Jie. High efficiency and low carbon production technology and integrated application of bar[J]. Iron and Steel, 2021, 56(8): 26-31. |
[6] |
YIN Rui-yu. Topic of times of metallurgy—Get through process,communicate different levels and open up a new theory[J]. Iron and Steel, 2021, 56(8): 4-9. |
|
|
|
|