Random Forest Based Quality Analysis and Prediction Method for Hot-Rolled Strip

被引：6
|
作者：
Ji Y.-J. [1 ]
Yong X.-Y. [1 ]
Liu Y.-L. [2 ]
Liu S.-X. [1 ]
机构：
[1] School of Information Science & Engineering, Northeastern University, Shenyang
[2] Big Data Department, Shanghai Baosight Software Co., Ltd., Shanghai
来源：
Dongbei Daxue Xuebao/Journal of Northeastern University | 2019年 / 40卷 / 01期
关键词：
Data driven; Defect prediction; Feature selection; Hot-rolled strip; Random forests;
D O I：
10.12068/j.issn.1005-3026.2019.01.003
中图分类号：
学科分类号：
摘要：
The process data of hot-rolled strips from an iron and steel enterprise were analyzed to find out the inherent relationship between process parameters and production quality by using an improved random forests algorithm. After critical features being extracted, a defect prediction model was built. According to the experiment, balancing operation can improve the prediction accuracy of the imbalanced data sets. Meanwhile, the combination of CART and C4.5 can further improve the prediction accuracy than each single method. Furthermore, in consideration of the characteristics whose features have high or low correlations with the response variable, mutual information was introduced as an evaluation criterion for feature selection. Mutual information makes great contribution to classification effect of random forest algorithm, and recognition rate of defects of hot-rolled strips is obviously improved by using three strategies. © 2019, Editorial Department of Journal of Northeastern University. All right reserved.
引用
收藏
页码：11 / 15
页数：4
相关论文
共 12 条
  • [1] Wang Y.-S., Cheng Z.-W., Li H., Et al., Analysis on surface defect of hot rolled slab, Journal of Iron and Steel Research, 14, 2, pp. 75-76, (2002)
  • [2] Ghorai S., Mukherjee A., Gangdaran M., Et al., Automatic defect detection on hot-rolled flat steel products, IEEE Transactions on Instrumentation and Measurement, 63, 3, pp. 612-621, (2013)
  • [3] Sui X.Y., Lyu Z.M., Prediction of the mechanical properties of hot rolling products by using attribute reduction ELM, International Journal of Advanced Manufacturing Technology, 85, 5-8, pp. 1395-1403, (2016)
  • [4] Li W., Yao X.L., Yu L., Et al., Application of SVM regression in HAGC system, The 27th Chinese Control and Decision Conference(CCDC), pp. 3490-3494, (2015)
  • [5] Royston P., Multiple imputation of missing value, Stata Journal, 4, 3, pp. 227-241, (2004)
  • [6] Laurikkala J., Instance-based data reduction for improved identification of difficult small classes, Intelligent Data Analysis, 6, 4, pp. 311-322, (2002)
  • [7] Chawla N.V., Bowyer K.W., Hall L.O., Et al., SMOTE: synthetic minority over-sampling technique, Journal of Artificial Intelligence Research, 16, 1, pp. 321-357, (2002)
  • [8] Leo B., Classification and Regression Trees, (1984)
  • [9] Quinlan J.R., C4.5: Programs for Machine Learning, (1994)
  • [10] Yong K., Research on feature selection and model optimization of random forest, (2008)
12