Conditional Generation of Tire Patterns using Generative AI

The conventional tire tread pattern development process has successfully produced and manufactured many tire tread patterns. However, a conceptual design process, which is a major part of the whole process, is still time-consuming due to repetitive manual interaction works between designers and engineers. In the worst case, the whole design process must be performed again from the beginning to obtain the required results. In this thesis, a deep generative tire tread pattern design framework is proposed to automatically generate various tread patterns satisfying the target tire performances in the conceptual design process. The main concept of the proposed method is that desired tread patterns are obtained through optimization based on integrated functions, which combine generative models and tire performance evaluation functions. Suitable image pre-processing methods, latent diffusion models, two-dimensional (2D) image-based tire performance evaluation functions and reusing the evaluation results for further training, are proposed with the help of domain knowledge of the tread pattern.