TY - GEN
T1 - Data-driven Surplus Material Prediction in Steel Coil Production
AU - Zhao, Ziyan
AU - Yong, Xiaoyue
AU - Liu, Shixin
AU - Zhou, Mengchu
N1 - Funding Information:
The authors would like to thank the China Scholarship Council scholarship, the National Key R&D Program of China under Grant No. 2017YFB0304201, and National Natural Science Foundation of China under Grant No. 61573089.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/5
Y1 - 2020/5
N2 - A steel enterprise is currently trying to avoid the presence of surplus materials since they can greatly increase its operational cost. The complicated production process of steel products makes it difficult to find the causes of surplus materials. In this work, we propose a surplus material prediction problem and solve it based on statistical analysis and machine learning methods. In the concerned problem, we predict whether there are surplus materials under a given group of production parameters. The dataset used in this work is from a real-world three-month steel coil production process. First, data cleaning is conducted to standardize the industrial dataset. Then, the production parameters highly correlated with surplus material prediction results are selected by a series of feature selection methods. Finally, two prediction models based on extreme gradient boosting and logistic regression are presented according to the selected features. The experimental results reveal that the proposed prediction models have similar effectiveness. A visible regression function makes the logistic regression method more suitable for practical application.
AB - A steel enterprise is currently trying to avoid the presence of surplus materials since they can greatly increase its operational cost. The complicated production process of steel products makes it difficult to find the causes of surplus materials. In this work, we propose a surplus material prediction problem and solve it based on statistical analysis and machine learning methods. In the concerned problem, we predict whether there are surplus materials under a given group of production parameters. The dataset used in this work is from a real-world three-month steel coil production process. First, data cleaning is conducted to standardize the industrial dataset. Then, the production parameters highly correlated with surplus material prediction results are selected by a series of feature selection methods. Finally, two prediction models based on extreme gradient boosting and logistic regression are presented according to the selected features. The experimental results reveal that the proposed prediction models have similar effectiveness. A visible regression function makes the logistic regression method more suitable for practical application.
KW - Surplus material prediction
KW - extreme gradient boosting
KW - industrial data
KW - logistic regression
KW - machine learning
UR - http://www.scopus.com/inward/record.url?scp=85091938188&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85091938188&partnerID=8YFLogxK
U2 - 10.1109/WOCC48579.2020.9114917
DO - 10.1109/WOCC48579.2020.9114917
M3 - Conference contribution
AN - SCOPUS:85091938188
T3 - 2020 29th Wireless and Optical Communications Conference, WOCC 2020
BT - 2020 29th Wireless and Optical Communications Conference, WOCC 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 29th Wireless and Optical Communications Conference, WOCC 2020
Y2 - 1 May 2020 through 2 May 2020
ER -