• A machine-learning-assisted digital model predicts die forging force with high accuracy (error as low as 4.1% in simulation, 1.5% after Bayesian optimization).
• Autonomous control strategy using genetic algorithm adjusts forging velocity to maintain target forging force despite temperature disturbances, keeping relative error within −1.3% to +3.1%.
• The approach integrates finite element simulation, support vector regression, Bayesian optimization, and genetic algorithms for intelligent forging process control.
• This work provides a practical framework for real-time quality control in aluminum alloy aviation component forging, enhancing consistency and reducing defects.