Research on Thickness Defect Control of Strip Head Based on GA-BP Rolling Force Preset Model

Due to the inaccuracy of preset rolling force cold rolling, there is a severe thickness defect in strip head after due flying gauge change (FGC), which affects yield strip. This paper establishes model (RFPM) by combining optimization (RFOM) and deviation prediction (RFDPM). The RFOM used genetic algorithm (GA) optimize deformation resistance friction coefficient models. RFDPM constructed using backpropagation (BP) neural network. calculation result RFPM shows that average fraction only 1.24%, proves has good accuracy. Experiments show length proportion at less than 20 m FGC increases from 38.8% 55.8%, while decreases 47.3 29.6 m, effectively improving rolling.