Plastic Recycling Through Artificial Intelligence

To close the loop for plastic packaging, 51 partners are participating in a new AI application hub. Funded by the German Federal Ministry of Education and Research, the measure aims to improve the sustainability of plastic packaging along the entire value chain by establishing two innovation labs.

Packaging accounts for by far the largest share of plastic waste worldwide. However, due to technical and economic challenges that are often too great, only a small proportion of the plastic re-enters the cycle as a secondary raw material. This is where the “AI Application Hub Plastic Packaging – Sustainable Circular Economy through Artificial Intelligence” wants to start. The Hub uses artificial intelligence (AI) methods to improve the sustainability of plastic packaging along the entire value chain from design to re-entry into the cycle – paving the way for a sustainable circular economy for plastic packaging.

Optimizing plastic packaging recycling with AI

In order to close the loop for plastic packaging as much as possible, 51 partners from business, science and society have joined forces in the new AI application hub. An important goal of the joint work is to share data across laboratories so that insights can be viewed across the entire value chain.

The central concern of the project also includes making topics of the hub about artificial intelligence and circular economy for plastics accessible to the general public. Central components of the hub are the two innovation labs KIOpti-Pack for the design and production of plastic packaging and K3I-Cycling for its mechanical recycling. Both labs are scheduled to run until August 31, 2025, explains the German Packaging Institute, which is a project partner of the K3I-Cycling innovation lab. The goal of K3I-Cycling, the institute says, is to significantly improve the quantity and quality of mechanical recycling of post-consumer plastic packaging waste.

To this end, K3I-Cycling is using an Artificial Neural Twin to develop a new, open and standardizable AI interface for the cross-sector collection of relevant information in the sense of a packaging product passport. The new AI interface makes it possible to digitally connect all stakeholders along the value chain for the first time. An Artificial Neural Twin is a fully differentiable representation of the entire system that allows the optimization of individual components in relation to the entire system. For this purpose, sensory information of all kinds is recorded as data along the material flow. The K3I-Cycling innovation lab is coordinated by the Fraunhofer Institute for Integrated Circuits (IIS).


The aim of KIOptiPack is to provide, validate and transfer to application practice-ready AI-supported tools for successful product design as well as quality-assured production of plastic packaging with a high recycled content in an AI application and data space. Linked to this is the formation of a central network platform for value engineering.

The project and the tools developed in it involve the entire value chain from secondary raw materials, material and packaging development, process design, packaging production to waste collection and processing. The coordinator of the KIOptiPack innovation lab is the Institute of Plastics Processing at RWTH Aachen University.

Visit Us
Follow Me