The Prediction of the Hot Strip's Width Based on Bayesian Neural Network

Abstract:

The prediction and control of the hot strips width is one of the key factors to reducing metal loss in hot roughing. Bayesian approach can control the parameters of neural network by calculating some super-parameters. This paper proposes a prediction model of the hot-rolled steel strips width based on Bayesian Neural Network, through application on the data of a 1500mm steel rolling production line in China, the MAE (Mean Absolute Error) between the predicted width value and real width value less than 10mm, this result shows that the precision of prediction is superior to some traditional mathematical model such as BP-neural networks. In this paper, we conclude that Bayesian neural network can improve the forecast precision of the hot strips width.

• Periodical: Advanced Materials Research (Volume 823)
• Pages: 489-493
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.823.489
• Online since: October 2013
• Authors: Xiang Rong Song, Zheng Hang Hu, Xi Qin He, Liang Ping Tu
• Keywords: Bayesian Neural Network, Hot Continuous Rolling, Width Prediction

References

[1] B.H. Hou. (2007). influence factors of hot rolled strip width control precision. Metallurgical Automation. 307-309.

[2] X.B. Li, & X. M Xia. (2008). Analysis of the width control of Meishan steel rolling steel strip 1422MM. Meishan science and technology. (1), 42-45.

[3] C. Lu, G.D. Wang, & X.H. Liu. (1997). Automatic width control of hot continuous rolling. Iron and Steel Research. (5), 52-56.

[4] S.W. Xiong, & L. Han force. (1994). Adjustment process and method to Width of hot strip rough mills for improving the yield. Iron and Steel. 29 (12), 75-79.

[5] B. Liu, in: Rolling Equipment. (Metallurgical Industry Press, Beijing 1984).

[6] M.D. Jiang, & G.D. Wang: High Precision of Plate and Strip Rolling Theory and Practice. (Metallurgical Industry Press, Beijing 2000).

[7] Z.Y. Zhao: The Metal Plastic Deformation and Rolling Theory. (Metallurgical Industry Press, Beijing 1980).

[8] K.X. Peng, & S.Z. Yu. (2010). Prediction and control of strip thickness based on Bias neural network. Journal of University of Science and Technology Beijing. 32 (2), 256-262.

[9] Foresee F D, & Hagan M T. (2007). Gauss-Newton approximation to Bayesian learning. Proceedings of the International Conference on Neural Networks, Houston.

DOI: 10.1109/icnn.1997.614194

[10] D. Wei, M.L. Zhang, & Z.J. Jiang. (2005). Nonlinear model identification based on Bayesian Neural Network method. Engineering and Applications. (11), 5-9.