Yokohama Rubber has developed a proprietary tyre design support system using explainable AI, known as XAI, a process for using AI that helps human users understand and explain AI’s results and output. The new system aids in creating desired tyre features by supplementing the knowledge and experience of development staff, making it easier for less-experienced staff to design tyres, Yokohama Rubber said.
The new tyre design support system is based on Yokohama Rubber’s HAICoLab AI utilization concept, launched in October 2020. According to Yokohama Rubber, tyre development begins with a search for features that will improve the tyre’s characteristic values and achieve development goals. Yokohama Rubber said its new system was developed using a customized version of XAI called SHAP (Shapley Additive Explanations), which provides developers with features useful for realizing the desired tyre characteristics. Additionally, the system provides multifaceted indicators for developers to understand how to adjust the obtained features. The system will enable less-experienced developers to develop new tyre designs, the manufacturer said.
According to Yokohama Rubber, XAI uses the standard specifications and targeted characteristic values set by development staff to determine the targeted characteristics that need to be improved and related quantitative values, and it then presents the features that will be useful to improving the targeted characteristics. It then presents the features useful for improving the targeted characteristics. Development staff interpret the information presented by XAI from multiple perspectives and modify the specifications. The staff then apply the characteristic value estimation AI developed by Yokohama Rubber in 2021 to check whether each characteristic value is achieving the targeted level, Yokohama said. Final specifications are determined after repeating this process, and XAI confirms the basis for each of these specifications — the design factors that help improve or maintain each characteristic value and its contribution rate.
Yokohama Rubber said it plans to use this system to develop a wide range of tyre products and broaden the applicable areas of its HAICoLab.
HAICoLab is a framework that aims to achieve digital transformation by merging human creativity with AI’s data processing capability, Yokohama Rubber said. Yokohama Rubber tyre characteristics (2021) and an AI system for generating rubber compounds (2022). To facilitate the use of HAICoLab in other areas, Yokohama Rubber said it recently began using dotData, a general-purpose AI tool that does not require programming.
