| Twinning Induced Plasticity(TWIP)steel has attracted the attention of the automobile manufacturing industry due to its high strength-plastic product and good impact resistance.In order to promote the large-scale application of TWIP steel,it is of great significance to study the effect of annealing process on the yield strength and formability of TWIP steel.In this paper,neural network is used to simulate and analyze the annealing process parameters and mechanical properties of Fe-Mn-C-Al TWIP steel;genetic algorithm is used to optimize the process;and the mechanical properties and metallographic structure of TWIP steel after process optimization are studied.Taking annealing temperature,holding time and cooling method as the research objects,a three-factor and four-level orthogonal test scheme for heat treatment of TWIP steel was designed,and the mechanical properties of the test steel were obtained by tensile test.Based on the experimental data,a BP neural network model was constructed to characterize the nonlinear relationship between the annealing process parameters and the mechanical properties of TWIP steel;and then the effects of cooling method,annealing temperature and holding time on yield strength were analyzed.The results show that the influence of the cooling method on the yield strength is restricted by the annealing temperature,and the effect of the cooling method is significant when the annealing temperature is low.The yield strength decreases with the increase of the annealing temperature,first decreases and then increases with the prolongation of the holding time.The reason for the above phenomenon is related to the process of recovery,recrystallization and grain growth of TWIP steel after cold rolling during heat treatment.The product of yield strength and elongation prediction model of TWIP steel was constructed by BP neural network,and the annealing process parameters and mechanical properties of TWIP steel were globally optimized by genetic algorithm.The results show that the BP neural network model can accurately reflect the nonlinear relationship between annealing process and mechanical properties of TWIP steel.The optimal combination of annealing process parameters obtained by genetic algorithm optimization is annealing temperature of 768℃,holding time of 35min and cool with the furnace.During tensile deformation,the elastic deformation stage of the TWIP steel specimen is extremely short,and there is no obvious yield plateau,which belongs to continuous yielding.In the plastic deformation stage,obvious A-type and B-type zigzag fluctuations appear on the engineering stress-strain curve;the true stress increases almost linearly with the increase of the true strain,showing excellent plastic deformation ability.Compared with the cold-rolled state,the microstructure of the TWIP steel sample treated by the optimized process is fully recrystallized equiaxed austenite grains,the grain size is relatively uniform,and there are a large number of annealing twins inside the grain.After tensile fracture,the slender and parallel distribution of deformation twins in the grains is obvious. |
