STEINERT AI enables food-grade tray recycling at Cirrec

Since April 2024, Cirrec a part of Faerch company has been operating a recycling plant in the Netherlands that processes PET trays from household collection into food-grade material. 60,000 tonnes per year, more than three billion trays. True tray-to-tray recycling at industrial scale. The critical point: sorting.

Simone Tirelli, Technical Project Manager at Faerch, and Andreas Jäger, Sales Director Waste Recycling and Managing Director STEINERT UniSort (right to left), in front of the Cirrec plant in Duiven, Netherlands.

STEINERT UniSort PR EVO 5.0 at Cirrec reliably sorts PET trays according to food-specific quality criteria using sensor fusion and AI.

Inside the Cirrec plant: multiple STEINERT sensor sorters and magnetic separators clean and sort PET trays automatically.

Post-consumer PET trays are converted back into food-grade packaging material for new trays with the help of STEINERT sorting technology.

Plastic packaging from household waste forms the starting point for food-grade tray-to-tray recycling of PET trays at Cirrec.

Processing more than 3 billion PET packages annually, Cirrec is the largest and only recycler of its kind.

The problem: looking the same, being different

For food-grade rPET, EU Regulation 2022/1616 stipulates that only packaging which has already been in contact with food may re-enter the food cycle. A ready-meal tray is permitted; a blister pack for screws is not. Chemically, both are PET and therefore identical to conventional near-infrared (NIR) sorting systems.

"Achieving the stringent standard required for food-grade recycling has always demanded exceptional precision in sorting," says Simone Tirelli, Technical Project Manager at Faerch. "Here at this plant, we are committed to transforming plastic waste into valuable resources."

The solution: sensor fusion and AI recognition

Cirrec deploys three STEINERT UniSort PR EVO 5.0 systems that analyse each tray individually. The machines use sensor fusion: a hyperspectral NIR camera captures the chemical composition whilst a colour camera identifies visual characteristics. The key feature is that both sensors view the same point on the material at the same time. This improves data quality for AI training and, in turn, sorting accuracy.

The combination of the two data streams enables STEINERT Intelligent Object.Identifier (IOI), an AI-based sorting programme trained in this case to recognise food packaging. IOI detects characteristic patterns such as ready-meal tray shapes, typical printing and surface textures.

STEINERT sorting achieves the purity of over 95 per cent required for food-grade recycling, thereby creating the conditions for all subsequent process steps.

The process

After bales are delivered, material first passes through magnetic separation: STEINERT UME overhead magnet removes ferrous metals; STEINERT CanMaster eddy current separator extracts non-ferrous metals. Optical sorting with three UniSort PR EVO 5.0 systems follows, then grinding, washing and further processing into flakes and pellets.

The results

The processed material feeds into production at the Faerch Group, where it is converted into new packaging with an average recycled content of 70 per cent. A life-cycle analysis shows that tray-rPET generates 57 per cent fewer CO₂ emissions than virgin PET.

Cirrec is thus the world's only operator recycling post-consumer PET trays to food-grade material at industrial scale. For the recycling industry, this is proof that a genuine circular economy for rigid food packaging works - provided the sorting is right.

Technology with development potential

The Intelligent Object Identifier is not a static solution. The AI can be trained for new sorting tasks. Should the composition of input material change or new packaging designs enter the market, the system can be adapted without hardware replacement. What works in Duiven can be scaled and demonstrates that tray-to-tray recycling is no longer a pilot project.