|
|
Quality prediction model of hot rolled coil based on big data of continuous casting process |
HOU Zi-bing1,2, PENG Zhi-qiang1,2, GUO Kun-hui1,2, LIU Qian1,2, ZENG Zi-hang1,2, GUO Dong-wei1,2 |
1. College of Materials Science and Engineering, Chongqing University, Chongqing 400044, China; 2. Chongqing Key Laboratory of Vanadium-Titanium Metallurgy and New Materials, Chongqing University, Chongqing 400044, China |
|
|
Abstract Hot charging or continuous casting and rolling technology of slabs have been gradually adopted by more and more steel enterprises, but its further development is restricted by the quality of slab. Therefore, the effective judgment of continuous casting slab defects can prevent the slab with quality problems from entering the rolling process, so as to reduce the extra energy consumption. Based on the difficulty of online quality detection for slabs, the quality prediction models of hot rolling coil of slabs were established from the perspective of big data production. Firstly, according to the highly unbalanced data of normal and defective products, the data preprocessing method combining correlation analysis, random classification of unbalanced data and dimensionality reduction with principal component analysis was proposed. Then, the GA-BP neural network algorithm was selected to construct the hot rolled coil quality prediction models for low carbon steel, peritectic steel and medium carbon steel, respectively. The results showed that the prediction model has a high accuracy, and the overall prediction accuracy of the low carbon steel model reaches 94.7%, and the defect prediction accuracy is 82.8%. The overall prediction accuracy of the peritectic steel model is 93.3%, and the defect prediction accuracy is 87.5%. The overall prediction accuracy of medium carbon steel model was 85.4%, and the defect prediction accuracy was 87.3%. Furthermore, an online prediction software for hot rolled coil quality was designed based on Python language, which could predict the quality of hot rolled coil in real time and trace the causes of defects conveniently and quickly.
|
Received: 29 July 2022
|
|
|
|
[1] |
吴光亮,孟征兵,李一为,等. 薄板坯连铸连轧过程中氧化铁皮变化规律[J]. 钢铁, 2011, 46(6): 79.
|
[2] |
任英,李鑫哲,袁天祥,等. 热轧卷板表面夹渣缺陷来源分析及控制现状[J]. 钢铁,2022, 57(1): 13.
|
[3] |
高龙永. 热轧中碳钢卷边部裂纹的形成机理与控制[J]. 连铸, 2022(3): 45.
|
[4] |
唐德池,季晨曦,肖宝亮,等. 热轧卷表面缺陷影响因素研究[J]. 连铸, 2016(5): 72.
|
[5] |
王春梅,周东东,徐科,等. 综述钢铁行业智能制造的相关技术[J]. 中国冶金, 2018, 28(7): 1.
|
[6] |
孙洁,孟庆娇,黄晓婷. 基于红外热像技术铸坯表面质量检测的研究[J]. 红外技术, 2015, 37(8): 707.
|
[7] |
秦道乾,徐科. 连铸板坯表面在线检测技术的研究“轨迹”[J]. 金属世界, 2010(5): 13.
|
[8] |
单多,徐安军,汪红兵,等. 连铸坯质量判定系统研究综述[J]. 连铸, 2011(2): 16.
|
[9] |
孟宪俭,李洪建,张伟,等. 铸坯质量判定与产品质量诊断系统功能及应用[J]. 连铸, 2011(增刊1): 457.
|
[10] |
杨健,吴思炜. 基于机器学习的钢铁轧制过程性能预测[J]. 钢铁, 2021, 56(9): 1.
|
[11] |
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.
|
[12] |
梁静召,田鹏,吴雨晨,等. 板坯连铸保护渣分钢种应用技术[J]. 连铸, 2020(5): 21.
|
[13] |
周玉,孙红玉,房倩,等. 不平衡数据集分类方法研究综述[J]. 计算机应用研究,2022, 39(6): 1615.
|
[14] |
王乐,韩萌,李小娟,等. 不平衡数据集分类方法综述[J]. 计算机工程与应用,2021, 57(22): 42.
|
[15] |
Zou K H, Tuncali K, Silverman S G. Correlation and simple linear regression[J]. Radiology,2003, 227(3): 617.
|
[16] |
Liu R, Gillies D F. Overfitting in linear feature extraction for classification of high-dimensional image data[J]. Pattern Recognit, 2016, 53: 73.
|
[17] |
叶奔,李立新,胡盛德. 统计学方法分析CSP精轧压力模型[J]. 钢铁, 2015, 50(10): 54.
|
[18] |
Trzaska J. Practical aspects of the design and use of the artificial neural networks in materials engineering[J]. Metals, 2021: 11.
|
[19] |
Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators[J]. Neural Networks,1989, 2(5): 359.
|
[20] |
DENG Z, CHEN T, WANG H, et al. Process parameter optimization when preparing Ti(C, N) ceramic coatings using laser cladding based on a neural network and quantum-behaved particle swarm optimization algorithm[J]. Applied Sciences,2020, 10(18): 6331.
|
[21] |
张波,刘胜辉. 基于遗传BP神经网络的数据挖掘技术[J]. 自动化技术与应用,2005(9): 4.
|
[22] |
周乃鹏, 佘昌莲, 柴锋, 等. 高湿热海洋环境低合金结构钢腐蚀研究进展[J]. 钢铁, 2022, 57(7): 137.
|
[23] |
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.
|
[24] |
秦大伟, 刘宏民, 张栋, 等. 带钢热镀锌镀层单位面积质量神经网络预测模型[J]. 钢铁, 2020, 55(5): 68.
|
[25] |
宋明明,王东城,张帅,等. 基于循环神经网络的板形模式识别模型[J]. 钢铁, 2018, 53(11): 56.
|
[26] |
黄华贵, 刘迎港, 黄海林, 等. 热轧板坯头部翘曲机器视觉检测与BP神经网络预测控制[J]. 中国冶金, 2022, 32(9): 85.
|
[27] |
朱硕, 王哲, 贺瑞军, 等. 基于人工神经网络模型的Ti-6Al-4V合金离子氮化层厚度、硬度预测[J]. 中国冶金, 2022, 32(10): 89.
|
[1] |
XIAO Jiong1,XIANG Junliang1,XU Guodong2,WANG Yingchun2,ZHONG Honggang1,ZHAI Qijie1. Thermal simulation of microstructure evolution in surface layer of 0.1 mass%C low carbon steel slab[J]. JOURNAL OF IRON AND STEEL RESEARCH , 2023, 35(3): 255-263. |
[2] |
ZHOU Guo-tao, CHEN Jin, HUANG Biao-cai, YAN Wei, LI Jing. Numerical simulation of solidification and heat transfer of Q355B slab during continuous casting[J]. CONTINUOUS CASTING, 2023, 42(2): 43-51. |
[3] |
ZHANG Ya-bing, WANG Dong-xing, ZHAO Li, ZUO Xiao-tan, HUANG Yan, YANG Wei-yong. Solute distribution of 35CrMnSi structural alloy steel billet under the effect of PMO[J]. CONTINUOUS CASTING, 2023, 42(2): 78-83. |
[4] |
SHI Wei-ning. Effect of mold water flow rate in 40Cr billet continuous casting on surface crack[J]. CONTINUOUS CASTING, 2023, 42(2): 84-89. |
[5] |
ZHOU Ye-lian, JIANG Zhong-kuai, ZHANG Fa-bin. Control process and mechanism analysis for tundish fluxes to form the solidified crusts[J]. CONTINUOUS CASTING, 2023, 42(2): 113-119. |
[6] |
YONG Xi, LIU Zhen-bao, WANG Chang-jun, NING Jing. Construction and application of genome database management platform of ultra high strength steel[J]. Iron and Steel, 2023, 58(2): 168-172. |
|
|
|
|