BP Neural Network of Continuous Casting Technological Parameters and Secondary Dendrite Arm Spacing of Spring Steel

• Published in: Journal of iron and steel research, international international, 2011-08, Vol.18 (8), p.25-29
• Main Authors: JIANG, Li-hong, WANG, Ai-guo, TIAN, Nai-yuan, ZHANG, Wei-cun, FAN, Qiao-li
• Format: Article
• Language: English
• Subjects: Applied and Technical Physics; Back propagation; BP neural network; BP神经网络模型; Computer simulation; Continuous casting; Dendritic structure; Engineering; Machines; Manufacturing; Materials Engineering; Materials Science; Mathematical models; Metallic Materials; Neural networks; Physical Chemistry; Processes; secondary dendrite arm spacing; Slabs; Steels; technological parameter; 二次枝晶臂间距; 偏析行为; 冷却速度; 工艺参数; 工艺技术参数; 弹簧钢; 连铸
• ISSN: 1006-706X; 2210-3988
• DOI: 10.1016/S1006-706X(11)60099-X

The continuous casting technological parameters have a great influence on the secondary dendrite arm spacing of the slab, which determines the segregation behavior of materials. Therefore, the identification of technological parameters of continuous casting process directly impacts the property of slab. The relationships between continuous casting technological parameters and cooling rate of slab for spring steel were built using BP neural network model, based on which, the relevant secondary dendrite arm spacing was calculated. The simulation calculation was also carried out using the industrial data. The simulation results show that compared with that of the traditional method, the absolute error of calculation result obtained with BP neural network model reduced from 0.015 to 0.0005, and the relative error reduced from 6.76% to 0.22%. BP neural network model had a more precise accuracy in the optimization of continuous casting technological parameters.