Yokohama advances rubber compounding with artificial intelligence

TOKYO—Yokohama Rubber Co. Ltd. has begun applying a proprietary rubber compound design system that utilizes artificial intelligence for compound generation.

Developed in partnership with Yokohama's information system subsidiary Hamagomu Aicom, the technology uses AI to propose a compound that achieves targeted rubber physical property values, the tire maker said in an Aug. 10 news release.

This will enable the acquisition of new knowledge about compounds that "humans could not have conceived independently," Yokohama said

The technology has been developed as part of Yokohama's HAICoLab concept, which stands for "Humans and AI ColLaborate" for digital innovation.

Up until now, Yokohama used AI to predict compound property values based on compound design parameters input by humans.

The new system, however, takes the process one step further, with AI generating candidate compounds based on specific desired compound property values and then proposing compounds that satisfy the target physical property values.

"HAICoLab's AI has learned tens of thousands of rubber compounds and can generate candidate compounds that combine more than 100 types of compounding agents," said Yokohama.

The new system compares the predicted physical property values of the generated candidate compounds with the targeted physical property values and proposes the compounds that meet the targeted values.

In addition to specifying the basic compound and compounding agents to be used, the system makes it possible to search for data that is close to the specific selected compound.

The feature, Yokohama said, will facilitate collaborations between humans and AI that will lead to the acquisition of new knowledge.

Yokohama Rubber established HAICoLab in 2020 as a new concept aimed at fostering digital innovations.

With the concept, the Japanese tire maker aims to acquire new knowledge through creating and collecting data based on hypothetical conditions set by humans and then applying AI to predict, analyze and then search for the most optimal result.

Yokohama Rubber expects this new system to enable it to further speed up product development and design higher-performance products.