The Yokohama Rubber Co., Ltd., announces that it developed a proprietary tire mould design support system using simulations (FEM: finite element method) and the Company’s AI technology in April 2026.

The new system supplements the knowledge and experience of the Company’s development staff and makes it easier even for less-experienced staff to design new moulds by providing information (such as changes in tire characteristics due to different mold design factors) obtained by conducting a large number of virtual experiments.

This system increases mould development speed, while reducing costs and the reworking often required to realize a new mould design. In addition, by facilitating greater understanding of the relationship between mould design factors and tire characteristics from multiple perspectives, this system will provide the Company’s development staff with new insights and inspirations that will contribute to the development of tires capable of higher-performance levels.

Overcoming Traditional Trial-and-Error Processes

This new system was developed under Yokohama Rubber’s proprietary HAICoLab* AI utilization concept, which was launched in October 2020 with the aim of creating a more innovative development process.

Mould design greatly affects the key characteristics of tires. Previously, obtaining a thorough understanding of the relationship between mould design factors and tire characteristics required a costly and time-consuming trial-and-error process, including trial production and follow-up evaluations. In addition, much of this process relied heavily on the know-how of highly experienced staff, which resulted in the mould design’s accuracy and development time differing based on the individual’s experience and knowledge. An acronym for “Humans and AI Collaborate” for digital innovation. It also refers to a laboratory for joint research by humans and AI.

How the AI Simulation System Works

This tire mould design support system uses automated simulations and AI-based prediction and visualization to resolve traditional development bottlenecks:

1. Automated Modeling: The system automatically generates a large number of tire FEM models with different mould shapes and calculates tire characteristics in a virtual space.

2. Surrogate Model Training: The calculation results are used as training data to construct an AI model (surrogate model) that instantly predicts the relationship between mould design factors and tire characteristics.

3. Quantitative Visualization: By applying XAI (eXplainable AI) technologies such as SHAP (SHapley Additive exPlanations) and PDP (Partial Dependence Plots) to this model, development staff can quantitatively visualize the impact of mould design factors. This enables them to easily determine how much they need to alter each mould design factor to achieve target tire characteristics.

Yokohama Rubber previously used its HAICoLab AI concept to develop a system that predicts the values of key tire characteristics (2021) and a tire design support system (2024), realizing an environment where development staff can easily obtain optimal design guidelines. This new tire mould design support system is the latest achievement in the company’s efforts to enhance its tire development environment and accelerate the rollout of innovative tires.