The prediction of dynamic recrystallization (DRX) plays an important role in design of hot forging process. In this work, a simulation model coupled cellular automaton (CA) with FEM was proposed to quantitatively simulate the microstructure evolution and flow stress during 7050 aluminium alloy wheel die forging. The model of dislocation density was established by isothermal compression test on Gleeble-1500. The physical fields, such as temperature, strain rate and strain, were obtained by DEFORM-3D for microstructure simulation. To refine grain size and improve uniformity, the isothermal forging parameters for 7050 aluminium alloy wheel were optimized by CA simulation. The simulation results showed that DRX percentage increased from 9.9% to 50% by using isothermal forging instead of hot die forging, while the flow stress decreased from 84MPa to 40MPa. Uniform density and small grain related with high mechanical properties were achieved via isothermal die forging process. The experiments of scaled wheel die forging were carried out on a hydraulic press with nominal working pressure 3150KN to verify simulation results. The good agreement between the simulation results and the experimental results indicate that the simulation model presented in this work can be used to predict the microstructure evolution of forging and optimization of forging process.