Recycling : TOMRA makes food-grade sorting possible with AI

The recycling industry has faced the challenge of efficiently sorting food-grade plastics from non-food-grade plastics for many years. These hurdles, combined with increasing regulatory demands and hygiene concerns, have created significant obstacles in achieving high-quality, food-grade recycling streams.

Now, TOMRA Recycling's innovative GAINnext™ AI-technology offers a groundbreaking solution to this long-standing challenge. By combining deep learning with traditional sensor-based sorting, GAINnext™ enables the efficient separation of food-grade from non-food-grade plastics for PET, PP, and HDPE, achieving purity levels above 95%.

Dr. Volker Rehrmann, EVP, Head of TOMRA Recycling emphasizes the significance of TOMRA’s recent developments: “We have used AI technology to improve sorting performance for decades, but this latest groundbreaking application marks another industry first for us. AI has the power to transform resource recovery as we know it, and our latest sophisticated applications of deep learning and AI reinforce our position as a pioneer in this field.”

TOMRA has also launched two non-food applications that complement the company’s existing GAINnext™ ecosystem: an application for deinking paper for cleaner paper streams, and a PET cleaner application for even higher purity PET bottle streams.

GAINnext™'s advanced deep learning technology allows TOMRA’s world-renowned AUTOSORT™ units to identify hard-to-classify objects with unparalleled accuracy, driving resource circularity and sustainable practices. This sophisticated system adapts to future demands, providing reliable and adaptable solutions for the recycling industry.

Field-proven and trusted, TOMRA's GAINnext™ has been installed in over 100 AUTOSORT™ units worldwide, bringing substantial benefits to material recovery facilities and recycling plants. The technology accelerates the journey towards closing the loop on plastics and enhances the efficiency and cost-effectiveness of recycling processes.