K3I-Cycling

AI-based optimization of the recirculation of plastic packaging

Recycling
© istock.com/aydinmutlu
The aim of the K3I-Cycling project is to promote the application of AI methods for a resource-efficient circular economy.

K3I-Cycling is one of two innovation labs of the AI Application Hub on Plastic Packaging, which is funded by the Federal Ministry of Education and Research. A total of 51 partners from business, science and society work closely together in the KIOpti-Pack (thematic cluster: design and production) and K3I-Cycling (thematic cluster: cycle closure) labs. The coordination of the consortium and the participating Fraunhofer Institutes is handled by Fraunhofer IIS. The aim is to promote the application of AI methods for a resource-efficient circular economy in the field of plastic packaging in Germany.

Innovation lab: K3I-Cycling AI-based optimization of the recirculation of plastic packaging

K3I-Cycling focuses on both the quantitatively and qualitatively significant improvement of the material recycling of post-consumer plastic packaging waste. By developing and providing a new, open, and standardizable artificial intelligence interface using Artificial Neural Twin for cross-sector collection of relevant information in the sense of a lightweight packaging product passport, it enables the digital networking of all stakeholders along the value chain for the first time. This represents a fully differentiable representation of the overall system, allowing for the optimization of individual components against a global quality measure. A first prototype of the Artificial Neural Twin (ANT) has already been installed in the participating material sorting facility. In spring 2025, a »DangerSort« will be integrated into the same facility to protect it from fires caused by incorrectly disposed lithium-ion batteries using X-ray technology and artificial intelligence. New approaches to sensor data collection will be pursued to capture the required data along the material flow. This will provide the scientific community with an annotated dataset as an important contribution to method development.

Collaboration as an AI hub for Plastic Packaging

The two innovation labs »Design and Production«  and »Cycle Closure« are working towards the common goal of closing the plastic packaging value chain as far as possible. To this end, approaches are being jointly developed and defined as to how the respective consortia can best interact in this context. The focus here is on making the results of the respective innovation labs accessible to the other innovation lab and thus coming closer to closing the loop.

In particular, the focus here is on a joint exchange of data, which makes it possible to view findings across the entire value chain. »Data space and networking« as an interface topic is defined as a concrete connection point within the AI hub.