To address the problem that traditional deformation resistance models are difficult to accurately describe the coupled effects of multiple factors such as temperature, true strain, and strain rate under dynamic rolling conditions, the modeling and prediction methods for deformation resistance of non-oriented silicon steel during hot strip rolling were investigated. Based on the wedge deformation characteristics and the dynamic evolution laws of process parameters in the hot strip rolling deformation zone, a mechanism model of deformation resistance comprehensively considering key influencing factors was established. On this basis, a genetic algorithm optimized backpropagation(GA-BP) neural network model was introduced, and the deformation resistance was predicted and analyzed. The model was trained and validated using Gleeble hot compression experimental data. The results indicate that the model has high prediction accuracy and good generalization ability, which provides a theoretical basis for the optimization of the hot strip rolling process.
ZhongB L, ChengZ Y, VolkovaO, et al. Effect of microstructure modification on magnetic and mechanical properties of high-grade non-oriented silicon steel during annealing treatment[J]. Journal of Materials Research and Technology, 2023, 27:7730-7739.
[2]
XuC, XuH J, ShuX D, et al. . Effect of normalizing treatment on microstructure and mechanical properties of non-oriented Fe-3.0% Si steel[J]. Journal of Materials Engineering and Performance, 2025,34(11):10184-10192.
[3]
HuY, MiodownikM A, RandleV. Experimental and computer model investigations of microtexture evolution of non-oriented silicon steel[J]. Materials Science and Technology, 2008, 24 (6): 705-710.
CaoJian-guo, SongChun-ning, SunLei, et al. Research progress on high precision profile contour and flatness control of electrical steel for new generation of high-tech wide strip rolling mills [J]. Journal of Plasticity Engineering, 2024, 31(4): 131-142.
[6]
SongC N, CaoJ G, XiaoJ, et al. High-temperature constitutive relationship involving phase transformation for non-oriented electrical steel based on PSO-DNN approach [J]. Materials Today Communications, 2023, 34(4): 105210.
HuangWang-ya, KangQi, HuangRuo-lin. Knowledge-data fusion driven stacking ensemble model for mechanical property prediction of cold-rolled non-oriented electrical steel strip [J]. Electrical Steel, 2025, 7 (5): 63-71.
[9]
LiS S, WangS Z, LiW, et al. Rolled thickness prediction for titanium/steel‐clad plates based on combined method of theoretical and neural network [J]. Steel Research International, 2025, 96 (3): 2400602.
[10]
ZhouY T, XiaY F, JiangL, et al. Modeling of the hot flow behaviors for Ti-6Al-4V-0.1Ru alloy by GA-BPNN model and its application[J]. High Temperature Materials and Processes, 2018, 37(6):551-562.
[11]
DingS F, SuC Y, YuJ Z. An optimizing BP neural network algorithm based on genetic algorithm[J]. Artificial Intelligence Review, 2011, 36(2):153-162.
[12]
ChenZ J. Optimization of neural network based on improved genetic algorithm[C]// International Conference on Computational Intelligence and Software Engineering. Wuhan, 2009:1-3.
[13]
LuJ H, LiuB T, HuangS Y, et al. The effect of hot forming-quenching and heat treatment processes on the mechanical properties of AA6016 aluminum alloy sheets[J]. Metals, 2024,14(5):599.
[14]
DewanM W, HuggettD J, LiaoT W, et al. Prediction of tensile strength of friction stir weld joints with adaptive neuro-fuzzy inference system (ANFIS) and neural network[J]. Materials & Design, 2016, 92:288-299.