A French research project has used artificial intelligence to deliver “groundbreaking” results in the identification of food-grade polypropylene, according to TotalEnergies (Paris; www.totalenergies.com). 

The French company and partners Valorplast (Puteaux; www.valorplast.com) and Recycleye (London; www.recycleye.com) are leading the collaborative project called Omni, which deploys AI and machine learning to identify and separate PP from household post-consumer waste for food-contact applications. 

Related: How will AI impact the European plastics industry?

Recycleye built and trained an AI-model based on waste collected from five locations across France supplied and characterised by Valorplast. 

According to Total Energies, the AI-assisted robotic sorting achieved a successful pick rate of 50% for food-grade PP with more than 95% purity. The sorted material was then further decontaminated at a semi-industrial pilot unit, using off-the-shelf mechanical recycling technologies. The company said it then produced odourless, clean recycled PP suitable for high-end packaging applications. 

Nathalie Brunelle, senior vice-president for polymers at TotalEnergies, 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 mn t of circular polymers”.

Recycleye CEO Victor Dewulf added that its AI-powered sorting technology could potentially change the economics of recycling. 

Omni was one of seven projects chosen by NGO Citeo (Paris; www.citeo.com) in October 2020 to reduce the environmental impact of householding packaging in France.