Press release submitted on behalf of TOMRA.
Leading global sorting solutions provider, TOMRA Recycling, announces the expansion of its GAINnext™ deep-learning-based AI ecosystem to include two new applications in North America for material recovery facilities (MRFs) and secondary recyclers. Developed to recognize feed material encountered by recyclers in North America, TOMRA introduces new PET Cleaner and Paper Cleaning applications that leverage deep learning technology to recognize hard-to-classify objects, reducing the need for manual sorting. Capable of identifying thousands of objects by material and shape in milliseconds, these new GAINnext™ applications help recyclers to reduce PET and paper bale impurities, enabling operations to create new revenue streams, increase profitability and decrease costs.
The two new applications feature an intelligent system that simultaneously integrates multiple sensor data for higher sorting accuracy than traditional optical sorters alone. The system complements the TOMRA AUTOSORT™ sensor-based material identification with deep learning AI visual object recognition offered by GAINnext™ for outstanding high-purity performance. The combination maximizes recovery and purity of valuable PET and paper materials at high-throughput speeds.
“Recyclers can integrate GAINnext™ into existing lines to boost PET and paper recycling recovery and purity without the need for adding lines. This is a significant benefit for operations that are tight on space,” explains Ty Rhoad, TOMRA Recycling’s vice president of sales for the Americas. “These new GAINnext™ applications process material at up to 2,000 ejections per minute, depending on the application, and can help to reduce the need for manual sorting at the end of the line. This results in up to 33 times more throughput than manual sorting.”
Cleaner PET recyclates
By sorting opaque bottles for recycling, GAINnext™ PET Cleaner’s high-accuracy sorting of opaque white packaging, textiles and foils from PET can create new revenue streams for the recycler. It leverages deep learning AI technology to remove hard-to-classify PET materials that can lead to downstream sorting and recycling challenges. The system instantly identifies and removes over 92% of opaque objects with titanium dioxide protection.
GAINnext™ PET Cleaner significantly enhances sorting performance of transparent and color PET by removing polyester textile waste. It boosts the hit rate for difficult-to-eject and multilayer foils to deliver higher purity PET fractions. The flexible system allows recyclers to select opaque colors, opaque white, PET blue, light blue or transparent for the classification stream, enabling recyclers to instantly recover valuable light blue and transparent PET materials from the sorting line.
High purity paper
The GAINnext™ Deinking/Paper Cleaning application delivers high-accuracy sorting of office paper, newspaper and magazines for paper sorting. Capitalizing on multi-sensor integration, the paper cleaning application uses deep learning technology to effectively remove impurities like pizza boxes, egg cartons and other brown boards from the paper stream. The system also instantly differentiates and removes greyboard from the stream at high throughput speeds.
“Our GAINnext™ Deinking/Paper Cleaning application can also improve the sorting performance of cardboard-based objects such as frozen food packaging,” comments Indrajeed Prasad, product manager, deep learning at TOMRA Recycling. “By efficiently removing undesired materials like envelopes, wrapping paper and brown paper grocery bags, the system creates high-quality paper revenue streams.”
AI ecosystem expansion
TOMRA was the first to introduce for the recycling industry its field-proven deep learning AI technology in 2019 with an application to identify and remove polyethylene (PE) silicone cartridges from PE streams. Since then, TOMRA’s deep learning engineers have trained the company’s artificial neural networks with millions of object images to solve some of the world’s most complex automated sorting tasks, ranging from wood to plastics to used beverage cans (UBCs).
TOMRA introduced three revolutionary plastics applications in early 2024, initially in the European market, to efficiently separate food-grade from non-food-grade PET, PP and HDPE at high throughput rates with purity levels reaching 95%. Simultaneously, TOMRA launched the two non-food applications that included the PET cleaner application for higher purity PET bottle streams and the deinking application for cleaner paper streams for the European market. Today, the announced PET Cleaner and Paper Cleaning join the UBC application in expanding the GAINnext™ ecosystem to address the region-specific needs of recyclers in the Americas.
TOMRA Recycling Sorting
TOMRA Recycling Sorting designs and manufactures sensor-based sorting technologies for the global recycling and waste management industry to transform resource recovery and create value in waste.
The company was the first to develop advanced waste and metals sorting applications using high capacity near infrared (NIR) technology to extract the most value from resources and keep materials in a loop of use and reuse. To date, around 10,000 systems have been installed in 100 countries worldwide.
TOMRA Recycling is a division of TOMRA Group. TOMRA was founded on an innovation in 1972 that began with the design, manufacturing and sale of reverse vending machines (RVMs) for automated collection of used beverage containers. Today, TOMRA is leading the resource revolution to transform how the planet’s resources are obtained, used and reused to enable a world without waste. The company’s other business divisions are TOMRA Food and TOMRA Collection.
TOMRA has approximately 105,000 installations in over 100 markets worldwide and had total revenues of about 12 billion NOK in 2022. The Group employs 5,000 globally and is publicly listed on the Oslo Stock Exchange. The company headquarters are in Asker, Norway.
For further information about TOMRA, visit www.tomra.com and follow TOMRA Recycling Sorting on LinkedIn, Twitter, Facebook, and on Instagram.
