Automated Process Optimization for High-Strength Aluminum Alloy Stamping Using Bayesian Optimization and Digital Twin Simulation

**Abstract:** The automotive industry faces increasing demands for lightweighting to improve fuel efficiency and reduce emissions. High-strength aluminum alloys offer significant potential for weight reduction, but their formability during stamping operations is often challenging due to complex material behavior. This paper introduces a framework for automated process optimization in high-strength aluminum alloy stamping utilizing Bayesian optimization coupled with a high-fidelity digital twin simulation. The approach minimizes defects and maximizes formability through adaptive parameter adjustment, leading to improved production efficiency and reduced material waste. The proposed system exhibits a 10x advantage over traditional trial-and-error optimization by intelligently navigating the parameter space and identifying optimal stamping conditions previously inaccessible to human operators.