By using machine learning, the tire retreading process - a process in which part of a worn tire is reused - is to be fundamentally revised and optimized. "The challenge we are facing is to automate the complex and labor-intensive reworking step within the skiving process in tire retreading," explains Raphaela Erbel, research associate at TTZ Günzburg.
To this end, they are working closely together to develop a control algorithm for a robot based on imitation learning. Imitation learning is an innovative approach in the field of machine learning in which a model performs tasks by imitating successful strategies of human experts. Direct observations of these successful strategies are used - in contrast to classic reinforcement learning, in which learning is based on trial and error and the application of a reward function.
In view of the fact that 571,000 tons of used tires are produced every year in Germany alone, this project can not only increase the efficiency of the retreading process and improve the competitiveness of retreaded tires compared to new tires, but also offers considerable potential for reducing the burden on the environment. It also addresses the shortage of skilled workers. Rigdon GmbH is thus underlining its commitment to innovation and sustainability in the industry.
The TTZ Günzburg
With a focus on artificial intelligence (AI) and data analytics, the TTZ aims to sustainably promote and strengthen the regional economy on behalf of the Bavarian state government. By implementing innovation projects, they actively support companies and their employees. Companies can contact the TTZ experts on the website (www.hnu.de/ttzguenzburg) or by email at info-ttz@hnu.de.
