Strip Crown Prediction in Hot Rolling Process Using Random Forest

• Published in: International journal of precision engineering and manufacturing Vol. 22; no. 2; pp. 301 - 311
• Main Authors: Sun, Jie, Deng, Jifei, Peng, Wen, Zhang, Dianhua
• Format: Journal Article
• Language: English
• Published: Seoul Korean Society for Precision Engineering 01.02.2021; Springer Nature B.V
• Subjects: Coils; Coils (strip); Decision trees; Engineering; Hot rolling; Industrial and Production Engineering; Machine learning; Materials Science; Noise reduction; Outliers (statistics); Process variables; Regression analysis; Regular Paper; Root-mean-square errors; Strip; Support vector machines; Strip crown; Ensemble method; Random forest; Hot rolling
• ISSN: 2234-7593; 2005-4602
• DOI: 10.1007/s12541-020-00454-1

This paper established a model based on an ensemble method to predict strip crown using 230,000 coils of data obtained from a hot rolling line. Before modeling, a specific method was proposed to reduce noise and remove outliers, and a new dataset of 5657 samples was generated. Parameter tuning considering mean squared error (MSE) was carried out to establish three machine learning models including support vector machine (SVC), regression tree (RT), and random forest (RF). Determination coefficient (R 2 ), mean absolute error (MAE) and root mean squared error (RMSE) were used as indicators to evaluate the prediction of models. Results showed that the RF had the best performance with the highest R 2 of 0.707, as well as the lowest RMSE of 5.66 μm. Moreover, an additional method that repeated the three models 100 times was developed, and box plots were used to visualize the distribution of R 2 , MAE and RMSE. RF can correct for decision trees to reduce overfitting to their training set, improving the generalization, and in this paper, the trained RF which had stable performance is considered as the most recommended model. After that, for RF, rankings of rolling process variable were validated to make a comparison with the existing physical understanding.