AI-powered Sorting Project Boosts Polypropylene Recycling
TotalEnergies, Valorplast and Recycleye say their novel mechanical recycling approach “opens new opportunities for circularity of polypropylene packaging.”
A coalition of European companies has combined artificial intelligence (AI) and computer vision with an efficient decontamination process to boost the recyclability of post-consumer polypropylene food packaging. The effort –– dubbed Project OMNI –– is being led by Brussels-based TotalEnergies, France’s Valorplast and London-based Recycleye.
Following 18 months of research, the partners say the new technology “provides a high-performing marketable solution to tackle the challenge of mechanically recycling polypropylene for food-contact applications.” The technology, they claim, offers an alternative to digital and physical marking solutions that require system-wide packaging changes.
AI sorting yields positive results
The AI and robotic sorting achieved a successful pick rate of 50 percent of the food-grade material, with more than 95 percent purity. Then, in a semi-industrial pilot, off-the-shelf mechanical recycling technologies were able to further decontaminate the sorted material. After that, TotalEnergies used its polymer expertise to produce odorless, clean, recycled polypropylene (rPP) suitable for high-end packaging applications.
Project OMNI leveraged Recycleye’s innovative expertise in robotics, advanced machine learning and computer vision, and applied it to plastic waste management. Courtesy of Recycleye
Project OMNI –– named for omniscience, the capacity to know everything –– is one of seven projects successfully selected in October 2020 by Citeo as part of a call for projects. Consumer goods and distribution companies created Paris-based Citeo in 1992 to reduce the environmental impact of household packaging and graphic paper. As part of that mission, Citeo has developed eco-design, collection, sorting and recycling services.
In a demonstration unit for this project, British robotic automation expert Recycleye built and trained an AI model. It applied that to post-consumer plastic waste collected from five locations across France. Valorplast, a nonprofit household plastic packaging collection service, supplied and characterized the waste that had been collected.
In 2022, Valorplast managed the recycling of more than 184,000 metric tonnes of plastic waste, including more than 172,000 tonnes of household plastic packaging. It says that facilities in Europe recycled all of these materials, with France handling the majority.
Recycling of food-grade PP food packaging is key
“Being able to recycle food-grade PP is a key factor in the establishment of a circular economy for PP packaging,” said Alban Cotard, Valorplast’s sales quality and development manager. “AI is a promising route for achieving this objective.”
Recycleye CEO Victor Dewulf added: “We are extremely excited to see this successful application of our robust AI-powered sorting technology at a semi-industrial scale. This application opens the possibility of creating new markets for recycled plastics materials; ultimately changing the economics of recycling.”
Nathalie Brunelle, TotalEnergies’ senior vice president of polymers, said: “This project not only demonstrates how cutting-edge technology can improve material circularity, but also paves the way for a wider range of accessible applications for recycled polymers to serve our customers. It provides a concrete response to the challenge of managing end-of-life plastics, and fully supports our ambition of reaching 1 million tons of circular polymers.”