基于即时学习算法的铸坯质量预测方法

doi:10.13228/j.boyuan.issn1005-4006.20220160

Abstract
Figure/Table
References
Related Citation (7)

Download: PDF (3167 KB) HTML (0 KB)
Export: BibTeX | EndNote (RIS)

Abstract Traditional models for the prediction of casting slab quality were mostly built using the global modeling method, which had poor self-adaptive ability and unsteady prediction accuracy. In this study, a new method based on the just-in-time learning algorithm was proposed for the prediction of casting slab quality. The main feathers of the method included the local model based on the just-in-time learning algorithm was built to replace the traditional global model, and the just-in-time modeling method make the prediction model more adapted to the continuous casting process with complex production scenarios and various working conditions. According to the time-varying characteristics of continuous casting production data, the time weighting factor was introduced into the similarity calculation to strengthen the correlation between the sample data and the data to be predicted, which was more beneficial to increasing the model accuracy for the prediction of casting slab quality. Taking the triangular crack of No.65 high-carbon steel slab in a steel plant as an example, the application of just-in-time learning algorithm in the construction of local model for casting slab quality prediction is illustrated, and the prediction results are compared with the global model for casting slab quality prediction. The results showed that the performance of the local model was better than that of the global model based on the assessment indexes. The prediction accuracy of the global model was 65%, while that of the local model was increased to 90%. The effectiveness of the local model for the prediction of casting slab quality was confirmed by comparing the prediction results.

Key words： just-in-time learning local model similarity degree quality prediction triangular cracks

Received: 08 October 2022

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	ZHAO Ji-min
	HE Yang
	LIU Jian-hua
	ZHENG Zhong
	YOU Da-li

Cite this article:

ZHAO Ji-min,HE Yang,LIU Jian-hua等. Predictive method of casting slab quality based on just-in-time learning algorithm[J]. CONTINUOUS CASTING, 2022, 41(6): 54-60.

URL:

http://www.chinamet.cn/Jweb_lz/EN/10.13228/j.boyuan.issn1005-4006.20220160 OR http://www.chinamet.cn/Jweb_lz/EN/Y2022/V41/I6/54

[1]	李新创. 新时代钢铁工业高质量发展之路[J]. 钢铁, 2019, 54(1): 1.
[2]	Anders L, Matthew J T. Morphology-based crack detection for steel slabs[J]. IEEE Journal of Selected Topics in Signal Processing, 2012, 6(7): 866.
[3]	邹雷雷,黄俊雄,李权辉,等. 连铸坯裂纹与偏析预测研究进展[J]. 连铸, 2022(2): 2.
[4]	苏航,潘涛,李灏. 钢铁材料产线质量能力分级——理论与实践[J]. 钢铁, 2021, 56(12): 103.
[5]	ZHAO L P, DOU R S, YIN J J, et al. Intelligent prediction method of quality for continuous casting process[C]//2016 IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference(IMCEC). Xian: IEEE and Xi′an Peihua University, 2016.
[6]	Sayed M S, Hamid R E. Applying data mining methods to predict defects on steel surface[J]. Journal of Theoretical and Applied Information Technology, 2010, 20: 87.
[7]	陈恒志,杨建平,卢新春,等. 基于极限学习机(ELM)的连铸坯质量预测[J]. 工程科学学报. 2018, 40(7): 815.
[8]	WEI L X, ZHAI B H, SUN H, et al. An ensemble JITL method based on multi-weighted similarity measures for cold rolling force prediction[J]. ISA Transactions,2022, 126: 326.
[9]	SUN L L, HUANG Y R, YANG M Y. Quality prediction model of KICA-JITL-LWPLS based on wavelet kernel function[J]. Processes, 2022, 10(8): 1562.
[10]	GE Z Q, SONG Z H. A comparative study of just-in-time-learning based methods for online soft sensor modeling[J]. Chemometrics and Intelligent Laboratory Systems, 2010, 104(2): 306.
[11]	YUAN X F, GE Z Q, HUANG B, et al. A probabilistic just-in-time learning framework for soft sensor development with missing data[J]. IEEE Transactions on Control Systems Technology, 2017, 25(3): 1124.
[12]	ZHENG W, LIU Y, GAO Z L, et al. Just-in-time semi-supervised soft sensor for quality prediction in industrial rubber mixers[J]. Chemometrics and Intelligent Laboratory Systems, 2018, 180: 36.
[13]	任明仑,宋月丽,褚伟. 灰铸铁抗拉强度预测的局部加权线性回归建模[J]. 电子测量与仪器学报, 2019, 33(3): 65.
[14]	Venkata V S, Mohanta H K, Pani A K. Support vector regression modeling in recursive just-in-time learning framework for adaptive soft sensing of naphtha boiling point in crude distillation unit[J]. Petroleum Science, 2021, 18(4): 1230.
[15]	彭开香,张学艺,胡鑫裕. 一种基于即时学习的局部模型集成转炉炼钢终点预测方法[J]. 冶金自动化, 2022, 46(2): 110.
[16]	陈鹏,齐超,刘人玮,等. 基于支持向量机回归的LIBS飞灰含碳量定量分析[J]. 光学学报, 2022, 42(9): 278.
[17]	周志华. 机器学习[M]. 北京: 清华大学出版社, 2016: 225.
[18]	杨友良,王禄,马翠红. 改进粒子群算法优化SVR的LIBS钢液元素定量分析[J]. 激光与光电子学进展, 2020, 57(5): 264.
[19]	蔡开科. 连铸坯质量控制[M]. 北京: 冶金工业出版社, 2010: 283.
[20]	齐新霞,包燕平. 宽板坯连铸工艺优化与铸坯质量[J]. 钢铁, 2009, 44(7): 24.
[21]	丁成砚. 基于PSO-PNN的铸坯全长表面纵裂纹预测研究[D]. 北京: 北京科技大学, 2021.
[22]	江中块,苏志坚,赫冀成. 板坯连铸过程铸坯质量判定参数采集与定位[J]. 连铸, 2018(4): 64.
[23]	赵烁, 李祖树, 朱雨逸, 等. 低碳热轧板卷的表面黑线和翘皮缺陷形成机制[J]. 中国冶金, 2021, 31(4): 37.
[24]	刘喜锚, 史伟宁. 连铸二冷系统喷嘴堵塞物来源分析和控制措施[J]. 中国冶金, 2022, 32(9): 73.
[25]	杜肖臣, 刘青, 张江山, 等. 喷淋水量分布对C38N2钢大方坯冷却效果的影响[J]. 中国冶金, 2022, 32(5): 93.
[26]	翟俊, 李欢, 陈法涛, 等. 保护渣对430不锈钢铸坯边部凹陷缺陷的影响[J]. 中国冶金, 2022, 32(5): 102.
[27]	王奕, 李志伟, 徐翔宇,等. SAE1144钢铸坯中硫化物分布及其偏析行为分析[J]. 中国冶金, 2022, 32(4): 34.
[28]	潘文峰, 蔡兆镇, 王少波, 等. 连铸板坯二冷高温区传热均匀性研究与优化[J]. 中国冶金, 2021, 31(8): 23.
[29]	修立策. 连铸板坯三角区裂纹成因分析及改进措施[J]. 中国冶金, 2007,17(5): 59.