Diagnosis of Quality Defects in Hot Strip Rolled Products Based on Factor Analysis

doi:10.12068/j.issn.1005-3026.2022.06.007

Abstract

Abstract: In hot strip rolling process， the relationship between production quality and influencing factors remains unclear， which greatly affects the traceability of product quality defects and subsequent improvement of product quality. Factor analysis(FA)method is introduced to the quality diagnosis. Taking the width quality defects in the threading process as an example， GT² statistics are used to monitor the production process and the factor scores are used to characterize the parameters in production process. After obtaining the influencing degree of the width quality index and the contribution rate of each factor to the width defect， the defining reason of the width defect is finally realized. The results in-practice show that the correction of the key processing parameters based on the FA diagnosis can improve the width-control accuracy effectively， which guarantees the stability of production process and the improvement of product quality.

Key words: hot strip rolling; factor analysis; quality defect; quality diagnostics; traceability analysis

CLC Number:

TG335.5

PENG Wen， XIN Hong-san， LI Xu-dong， SUN Jie. Diagnosis of Quality Defects in Hot Strip Rolled Products Based on Factor Analysis[J]. Journal of Northeastern University(Natural Science), 2022, 43(6): 809-814.

References

[1]Manabu K，Yoshiaki N.Data-based process monitoring，process control，and quality improvement:recent developments and applications in steel industry ［J］.Computers & Chemical Engineering，2008，32(1/2):12-13.
[2]Venkatasubramanian V，Rengaswamy R，Kavuri S N，et al.A review of process fault detection and diagnosis:part Ⅲ.Process history based methods［J］.Computers & Chemical Engineering，2003，27(3):327-329.
[3]McGuire S A.Statistical process control for quality improvement［J］.Technometrics，1994，36(4):419-420.
[4]李扬，王京，张勇军.基于数据挖掘的热轧带钢质量分析方法［J］.工程科学学报，2015，37(sup1):56-64.(Li Yang，Wang Jing，Zhang Yong-jun.Quality analysis method of hot-rolled strip steel based on data mining ［J］.Journal of Engineering Science，2015，37(sup1):56-64.)
[5]赵旭，阎威武，邵惠鹤.基于多变量统计方法的产品质量控制［J］.上海交通大学学报，2007，41(1):126-130.(Zhao Xu，Yan Wei-wu，Shao Hui-he.The product quality control based on multivariable statistical methods［J］.Journal of Shanghai Jiaotong University，2007，41(1):126-130.)
[6]姚林，阳建宏，徐金梧，等.基于偏最小二乘回归模型的带钢热镀锌质量监控方法［J］.北京科技大学学报，2007，29(6):627-631.(Yao Lin，Yang Jian-hong，Xu Jin-wu，et al.Quality monitoring method of strip hot-dip galvanizing based on partial least squares regression［J］.Journal of University of Science and Technology Beijing，2007，29(6):627-631.)
[7]姬亚锋，宋乐宝，原浩，等.基于KPLS与SVM的热连轧板凸度预测［J］.中国冶金，2021，31(1):20-24.(Ji Ya-feng，Song Le-bao，Yuan Hao，et al.Crown prediction of hot strip rolling based on KPLS and SVM ［J］.China Metallurgy，2021(1):20-24.)
[8]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):2743-2752.(Cao Jian-guo，Jiang Jun，Zhao Qiu-fang，et al.Convex control of wide and heavy plate based on data mining［J］.Journal of Central South University(Natural Science Edition)，2019，50(11):2743-2752.)
[9]He F，Li M，Yang J H，et al.Research on nonlinear process monitoring and fault diagnosis based on kernel principal component［J］.Key Engineering Materials，2009，413/414:583-590.
[10]He F，Xu J W，Li M，et al.Product quality modelling and prediction based on wavelet relevance vector machines［J］.Chemometrics and Intelligent Laboratory Systems，2013，121:33-41.
[11]Jenssen R.Kernel entropy component analysis［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，2010，32(5):847-860.
[12]Jia F，Martin E B，Morris A J.Non-linear principal components analysis with application to process fault detection［J］.International Journal of Systems Science，2000，31(11):1473-1475.
[13]Cho J H，Lee J M，Choi S W，et al.Fault identification for process monitoring using kernel principal component analysis［J］.Chemical Engineering Science，2005，60(1):279-280.
[14]Rolf I.On fuzzy logic applications for automatic control，supervision and fault diagnosis［J］.IEEE Transactions on Systems，Man and Cybernetics，1998，28(2):221-235.
[15]赵忠盖，刘飞.因子分析及其在过程监控中的应用［J］.化工学报，2007，58(4):970-974.(Zhao Zhong-gai，Liu Fei.Factor analysis and its application in process monitoring［J］.Journal of Chemical Industry，2007，58(4):970-974.)
[16]Peng W，Chen S Z，Gong D Y，et al.Adaptive threading strategy based on rolling characteristics analysis in hot strip rolling［J］.Journal of Central South University，2017，24(7):1560-1572.
[17]Yin，F C，Zhang D H，Zhang Y C.Dynamic modeling and rolling data analysis of the tandem hot rolling process［J］.Simulation:Journal of the Society for Computer Simulation，2017，93(4):307-321.
[18]Deng J，Sun J，Peng W，et al.Application of neural networks for predicting hot-rolled strip crown ［J］.Applied Soft Computing，2019，78:119-131.