基于集成特征选择和SVR的热连轧板凸度预测

doi:10.13228/j.boyuan.issn0449-749x.20230387

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (0 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract As a key index to evaluate the shape quality of hot strip steel plate,the crown of hot strip steel plate has the characteristics of multi-variable,nonlinear and hereditary. The traditional crown model of hot continuous rolling plate has some problems, such as complicated mechanism, difference between theory and practice and limited accuracy of the model. In order to solve these problems, a prediction model for crown of hot continuous rolling plate based on integrated feature selection and support vector regression is proposed in this paper. Firstly, an ensemble learning model based on Random Forest (RF), eXtreme Gradient Boosting (XGBoost) and Gradient Boosting Decision Tree (GBDT) is established, and the comprehensive application of these base learners can fully mine the feature information in the data. Secondly, the feature importance obtained by the base learner is weighted by the ensemble learning model, and the most informative input features are selected according to the feature importance ranking after fusion, which can effectively reduce the feature dimension. Then, Grey Wolf Optimization (GWO) is used to optimize the parameters in the Support Vector Regression (SVR) prediction model, which can not only eliminate the subjectivity and blindness of traditional manual parameter selection. It can also better adapt to the characteristics of the data. Finally, the selected features are input into the SVR prediction model with optimized parameters, which is used to predict the crown of hot continuous rolling plate. The experimental results show that the absolute error of the model is more than 99% within 15 μm. The prediction model not only improves the prediction accuracy, but also provides powerful guidance and support for the precise control of crown and the improvement of shape quality of hot continuous rolling plate. It provides useful methods and ideas for solving the key problems in complex hot continuous rolling production and improving the sustainability and efficiency of the production process.

Key words： hot strip rolling crown integrated feature selection Grey Wolf Optimization support vector machine

Received: 04 July 2023

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	WANG Youlong
	LI Weigang
	WANG Yongqiang

Cite this article:

WANG Youlong,LI Weigang,WANG Yongqiang. Crown prediction of hot strip steel based on integrated feature selection and SVR[J]. Iron and Steel, 2024, 59(1): 99-107.

URL:

http://www.chinamet.cn/Jweb_gt/EN/10.13228/j.boyuan.issn0449-749x.20230387 OR http://www.chinamet.cn/Jweb_gt/EN/Y2024/V59/I1/99

[1] ZHANG X,ZHANG J,LI X,et al. Analysis of the thermal profile of work rolls in the hot strip rolling process[J]. Journal of Mineral Metallurgy and Materials,2004,11(2):173.
[2] 于孟,王春海,张晓峰,等.不锈钢/碳钢复合板平整轧制过程板形翘曲行为[J].钢铁,2022,57(7):106.(YU M,WANG C H,ZHANG X F,et al. Warping behavior of stainless steel/carbon steel composite plate during flat rolling[J]. Iron and Steel,2022,57(7): 106.)
[3] 张金飞,么洪勇,李子正,等.七机架热连轧机组板形综合控制技术[J].钢铁,2023,58(3):97.(ZHANG J F,YAO H Y,LI Z Z,et al. Profile integrated control technology of seven-stand hot tandem mill[J]. Iron and Steel,2023,58(3): 97.)
[4] WANG X D,LI F,LI B H,et al. VCR back-up roll and negative work roll contour design for solving roll spalling and transfer bar profile problems in hot strip mill[J]. Ironmaking and Steelmaking:Products and Applications,2010,37(8):633.
[5] 贾俊彪,严彪,吴成军.支撑辊倒角对热轧钢板板形的影响[J].上海金属,2022,44(1):105.(JIA J B, YAN B, WU C J. Effect of backup roll chamfer on flatness of hot-rolled plate[J]. Shanghai Metals, 2022,44(1):105.)
[6] MA X B,WANG D C,LIU H M. Influence of profile indicators of hot-rolled strip on transverse thickness difference of cold-rolled silicon steel[J]. Metallurgical Research and Technology,2019,116(1):1.
[7] 刘立忠,吕程,刘相华,等. CVC热连轧机的板凸度计算模型[J].东北大学学报,2001(1):95.(LIU L Z,LÜ C,LIU X H, et al. Crown calculation model of CVC hot tandem mill[J]. Journal of Northeastern University,2001(1):95.)
[8] 王雪松,张跃飞,田士平,等.PC轧机板形板凸度控制策略[J].钢铁,2012,47(11):45.(WANG X S,ZHANG Y F,TIAN S P,et al. PC mill flatness crown control strategy[J]. Iron and Steel,2012,47 (11):45.)
[9] 戚向东,董志奎,连家创,等.热连轧板凸度闭环控制的工业应用[J].钢铁,2013,48(5):51.(QI X D,DONG Z K,LIAN J C,et al. The industrial application of closed loop control of strip crown[J]. Iron and Steel,2013,48(5):51.)
[10] 李伯群,范璇,李伟红,等. 板形设定模型参数优化与控制技术应用[J].钢铁,2019,54(2):41.(LI B Q,FAN X,LI W H,et al. Strip shape set model parameters optimization and control technology application[J]. Iron and Steel,2019,54(2):41.)
[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 J G,JIANG J,ZHAO Q F,et al. Convexity control of wide and thick plates based on data mining[J]. Journal of Central South University (Natural Science Edition),2019,50(11):2743.)
[12] 张笑雄,苗宇,刘新忠,等.基于DBN-LSSVM的热连轧带钢厚度预测[J]. 冶金自动化,2020,44(2):17.(ZHANG X X, MIAO Y, LIU X Z, et al. Thickness prediction of hot continuous strip based on DBN-LSSVM[J]. Metallurgical Automation, 2020, 44(2):17.)
[13] 丁肇印,丁成砚,孙杰,等.基于类别特征梯度提升的冷轧带钢板形预测模型[J].轧钢,2022,39(6):99.(DING Z Y,DING C Y,SUN J,et al. Cold-rolled strip steel profile prediction model based on class feature gradient lifting[J]. Steel Rolling, 2022,39 (6):99.)
[14] 何垚东,李旭,丁敬国,等.融合轧制机理和深度学习的带钢精轧宽度预测[J]. 轧钢,2022,39(2):76.(HE Y D,LI X,DING J G,et al. Prediction of strip finishing width by combining rolling mechanism and deep learning[J]. Steel Rolling, 2022, 39(2):76.)
[15] 卜赫男,蔺明宇,闫注文.基于神经网络集成学习的冷连轧板形预测[J].轧钢,2021,38(1):65.(BU H N,LIN M Y,YAN Z W. Shape prediction of tandem cold rolling based on neural network ensemble learning[J]. Steel Rolling, 2021,38 (1):65.)
[16] 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[J].信息与控制,2014,43(3):270.(CAO W H,LI X,WU M,et al. Prediction model of rolling force of hot rolled sheet based on extreme learning machine[J].Information and Control,2014,43(3):270.)
[17] 纪英俊,勇晓玥,刘英林,等.基于随机森林的热轧带钢质量分析与预测方法[J].东北大学学报(自然科学版),2019,40(1):11.(JI Y J,YONG X Y,LIU Y L,et al. Quality analysis and prediction method of hot rolled strip based on Random forest[J]. Journal of Northeastern University (Natural Science),2019,40(1):11.)
[18] 易成新,李维刚,吕立华,等.基于RF-LSTM的热连轧板坯粗轧出口温度预报[J].钢铁研究学报,2021,33(9):952.(YI C X,LI W G,LU L H,et al. Exit temperature prediction of hot strip rough rolling based on RF-LSTM[J]. Journal of Iron and Steel Research,2021,33(9):952.)
[19] 于加学,孙杰,张殿华. 基于深度学习的热轧带钢头部厚度的命中预测[J]. 钢铁,2021,56(9):19.(YU J X,SUN J,ZHANG D H. Based on the deep study of hot rolled strip head thickness accuracy prediction[J]. Iron and Steel,2021,56(9):19.)
[20] 张帅,王俊杰,李爱莲,等. 基于改进GWO-ELM的热轧带钢卷取温度预测[J].电子测量技术,2021,44(22):50.(ZHANG S,WANG J J,LI A L,et al. Based on improved GWO comes-ELM hot-rolled strip coiling temperature predic-tion[J]. Journal of Electronic Measurement Technology,2021,44 (22):50.)
[21] 王晓雯,张勇军,郭强,等.基于轧制机理和混合神经网络的热轧精轧带宽预测[J].中国冶金,2023,33(2):114.(WANG X W,ZHANG Y J,GUO Q,et al. Prediction of hot finishing rolling bandwidth based on rolling mechanism and hybrid neural network[J]. China Metallurgy,2023,33(2):114.)
[22] 李维刚,刘玮汲,谢璐,等.基于图卷积网络的热轧带钢轧制力预测[J].钢铁,2023,58(3):89.(LI W G,LIU W J,XIE L,et al. Hot rolled strip steel rolling force prediction based on figure convolution networks[J]. Iron and Steel,2023,58 (3):89.)
[23] 吕庆,刘颂,刘小杰,等.基于大数据技术的烧结全产线质量智能控制系统[J].钢铁,2018,53(7):1.(LÜ Q,LIU S,LIU X J,et al. Intelligent quality control system of sintering production line based on big data technology[J]. Iron and Steel,2018,53(7):1.)
[24] 张敏,袁辉.拉依达(PauTa)准则与异常值剔除[J].郑州工业大学学报,1997(1):87.(ZHANG M,YUAN H. PauTa criterion and outlier elimination[J]. Journal of Zhengzhou University of Technology,1997(1):87.)
[25] 刘小杰,邓勇,李欣,等.基于大数据技术的高炉铁水硅含量预测[J].中国冶金,2021,31(2):10.(LIU X J,DENG Y,LI X,et al. Prediction of silicon content in hot metal of blast furnace based on big data technology[J]. China Metallurgy,2021,31(2):10.)
[26] 张振,李欣,刘颂,等.基于多类别生产状态的烧结矿转鼓指数预测模型[J].中国冶金,2022,32(1):27.(ZHANG Z,LI X,LIU S,et al. Prediction model of sinter drum index based on multi-class production state[J]. China Metallurgy,2022,32(1):27.)
[27] 宋勇,蔡志平.大数据环境下基于信息论的入侵检测数据归一化方法[J].武汉大学学报(理学版),2018,64(2):121.(SONG Y,CAI Z P. Intrusion detection data normalization method based on information theory in big data environment[J]. Journal of Wuhan University (Science Edition),2018,64(2):121.)
[28] 赵晨熙,徐金梧,黎敏,等.基于决策树算法规则抽取的COREX燃料配比模型[J].计算机应用研究,2012,29(12):4567.(ZHAO C X,XU J W,LI M,et al. COREX fuel ratio model based on rule extraction of decision tree algorithm[J]. Application Research of Computers,2012,29(12):4567.)
[29] 宋寅虎,郜志英,周晓敏,等.基于EMD-RF的冷轧机振动信号时频分析及识别[J].钢铁研究学报,2023,35(3):303.(SONG Y H,GAO Z Y,ZHOU X M,et al. Time-frequency analysis and recognition of cold rolling mill vibration signals based on EMD-RF[J]. Journal of Iron and Steel Research,2023,35(3):303.)
[30] 赵军,李红玮,刘小杰,等.基于Xgboost的高炉透气性指数预测模型[J].中国冶金,2021,31(3):22.(ZHAO J,LI H W,LIU X J,et al. Prediction model of BF permeability index based on Xgboost[J]. China Metallurgy,2021,31(3):22.)
[31] 杜岩,王义铭,张田,等.基于贝叶斯优化XGBoost模型的热轧中厚板终冷温度预测[J].轧钢,2022,39(6):91.(DU Y,WANG Y M,ZHANG T,et al. Prediction of final cold temperature of hot rolled medium thick plate based on Bayesian optimization XGBoost model[J]. Steel Rolling,2012,39(6):91.)
[32] 查伟,董艳伍,姜周华,等.基于GBDT算法真空自耗铸锭终点锰含量预测模型[J].中国冶金,2023,33(7):107.(ZHA W,DONG Y W,JIANG Z H,et al. Manganese content prediction model at the end point of vacuum self-consumption ingot based on GBDT algorithm[J]. China Metallurgy,2023,33(7):107)
[33] MIRJALILI S,MIRJALILI S M,LEWIS A. Grey wolf optimizer[J].Advances in Engineering Software,2014,69(3):46.
[34] 尹林子,李乐,蒋朝辉. 基于粗糙集理论与神经网络的铁水硅含量预测[J].钢铁研究学报,2019,31(8):689.(YIN L Z,LI L,JIANG Z H. Prediction of silicon content in hot metal based on rough set theory and neural network[J]. Journal of Iron and Steel Research,2019,31(8):689.)
[35] 党晓晶,石琳,赵娜,等.基于参数优化SVR方法预测高炉煤气利用率[J].钢铁研究学报,2021,33(4):279.(DANG X J,SHI L,ZHAO N,et al. Prediction of blast furnace gas utilization rate based on parameter optimization SVR method[J]. Journal of Iron and Steel Research,2021,33(4):279.)