TY - JOUR
T1 - A machine learning and genetic algorithm-based method for predicting width deviation of hot-rolled strip in steel production systems
AU - Ji, Yingjun
AU - Liu, Shixin
AU - Zhou, Mengchu
AU - Zhao, Ziyan
AU - Guo, Xiwang
AU - Qi, Liang
N1 - Funding Information:
This work is supported by the National Natural Science Foundation of China [Grant No. 62073069]; LiaoNing Revitalization Talents Program [Grant No. XLYC2002041, XLYC1907166]; the Natural Science Foundation of Shandong Province [Grant No. ZR2019BF004]; the Ministry of Science and Higher Education of the Russian Federation as part of World-class Research Center program: Advanced Digital Technologies under contract No. 075-15-2020-903.
Publisher Copyright:
© 2021 Elsevier Inc.
PY - 2022/4
Y1 - 2022/4
N2 - Width deviation is an important metric for evaluating the quality of a hot-rolled strip in steel production systems. This paper considers a width deviation prediction problem and proposes a Machine-learning and Genetic-algorithm-based Hybrid method named MGH to obtain a prediction model. Existing work mainly focuses on high prediction accuracy, while ignoring interpretability. This work aims to build a prediction model that can make a good trade-off between two industry-required criteria, i.e., prediction accuracy and interpretability. It first collects some process variables in a hot rolling process and includes them as well as some constructed variables in a feature pool. Then we propose MGH to find representative variables from it and build a prediction model. MGH results from the integration of hierarchical clustering, genetic algorithm, and generalized linear regression. In detail, hierarchical clustering is applied to divide variables into clusters. Genetic algorithm and generalized linear regression are innovatively combined to select a representative variable from each cluster and develop a prediction model. The computational experiments conducted on both industrial and public datasets show that the proposed method can effectively balance prediction accuracy and interpretability of its resulting model. It has better overall performance than the compared state-of-the-art models.
AB - Width deviation is an important metric for evaluating the quality of a hot-rolled strip in steel production systems. This paper considers a width deviation prediction problem and proposes a Machine-learning and Genetic-algorithm-based Hybrid method named MGH to obtain a prediction model. Existing work mainly focuses on high prediction accuracy, while ignoring interpretability. This work aims to build a prediction model that can make a good trade-off between two industry-required criteria, i.e., prediction accuracy and interpretability. It first collects some process variables in a hot rolling process and includes them as well as some constructed variables in a feature pool. Then we propose MGH to find representative variables from it and build a prediction model. MGH results from the integration of hierarchical clustering, genetic algorithm, and generalized linear regression. In detail, hierarchical clustering is applied to divide variables into clusters. Genetic algorithm and generalized linear regression are innovatively combined to select a representative variable from each cluster and develop a prediction model. The computational experiments conducted on both industrial and public datasets show that the proposed method can effectively balance prediction accuracy and interpretability of its resulting model. It has better overall performance than the compared state-of-the-art models.
KW - Feature construction
KW - Generalized linear regression
KW - Genetic algorithm
KW - Hierarchical clustering
KW - Hot-rolled strip
KW - Width deviation prediction
UR - http://www.scopus.com/inward/record.url?scp=85122573654&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85122573654&partnerID=8YFLogxK
U2 - 10.1016/j.ins.2021.12.063
DO - 10.1016/j.ins.2021.12.063
M3 - Article
AN - SCOPUS:85122573654
SN - 0020-0255
VL - 589
SP - 360
EP - 375
JO - Information Sciences
JF - Information Sciences
ER -