The proposal introduces an AI-driven framework for tire tread pattern and sipe optimization, integrating advanced machine learning models like generative adversarial networks and evolutionary algorithms with embedded constraints on moldability, symmetry, regulatory compliance and wear zones. The system generates innovative, manufacturable tread geometries informed by historical performance data. Validation employs a simulation-based workflow using finite element analysis to assess tread block stiffness and shear-induced energy dissipation, key determinants of rolling resistance and ride dynamics. A case study demonstrates the integration of AI-generated designs with FEA simulation tools, enabling iterative digital refinement and uncovering novel tread architectures beyond traditional manual design.

• How AI can automatically generate innovative tread designs that meet safety, durability and manufacturing needs
• How digital simulations replace lengthy prototyping by testing performance factors like strength, wear and energy efficiency quickly
• How AI and simulation together enable efficient, sustainable and EV-ready tire designs with better comfort and durability