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

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.