Extrusion International 3-2026

45 Extrusion International 3/2026 rectly into their existing management systems. This en- ables managers to query waste statistics or purity levels through their own dashboards without needing to log into a separate system. The platform also introduces two powerful new search methods to help plants respond to changing ma- terial streams: • Similarity search: Operators can right-click a prob- lematic object, such as an electronic vape, to instantly identify every other visually similar item in the stream. This is critical for spotting re hazards like batteries without the need to train a new AI model. • Text and brand search: Users can search for speci c brands or object types, such as ' lled refuse bags' or 'di - apers', to see exactly what is passing through the facility in real time. “AI has always been part of TOMRA’s DNA, but we are now entering an entirely new phase," says Lars Enge, EVP and Head of TOMRA Recycling. "With our acquisition of a majority stake in PolyPerception, we are moving beyond AI as a sorting tool to AI as a cen- tral intelligence for the recycling plant. By combining our advanced sorting systems and digital solutions with PolyPerception’s AI platform we are creating an end-to- end solution that doesn’t just optimize machines but fundamentally rede nes how plants operate.” Expanding the GAINnext™ ecosystem To complement this technological progress, TOMRA is also introducing three new deep learning applica- tions for its GAINnext™ ecosystem. This solution targets long-standing industry bottlenecks where traditional sensor-based sorting has reached its limits. The first application addresses the rising demand for food-grade PET trays as tray material is becoming a critical new feedstock alongside bottles. By train- ing GAINnext™ on thousands of images, the system can now distinguish between takeaway or super- market trays and consumer or medical packaging based on shape and use. This breakthrough achieves purity levels over 95%, demonstrating that PET tray sorting is no longer a technical challenge but a viable business case. In the metals sector, TOMRA is launching a high- precision application for 'copper meatballs', support- ing a steel market that is starting its journey towards decarbonization. The new GAINnext™ automatically identifies complex copper-steel composites, such as motor armatures, even in oxidized or dirty streams, delivering outstanding selectivity and helping recy- clers to upgrade rebar-grade scrap to premium fur- nace feedstock. The third addition is a high-throughput solution for used beverage can (UBC) aluminum recovery from pack- aging streams – an application that was successfully launched in North America and has now been adapted for the European market. The GAINnext™ UBC applica- tion offers up to 33 times more throughput than manu- al sorting, delivering 98% purity or higher. By instantly detecting and ejecting non-UBC materials, the system provides a more ef cient, automated path for alumi - num can-to-can recycling. Technology turning point "These launches signal a true technology turning point for the industry," Enge concludes. "Deep learning is no longer just enhancing individual processes or tack- ling increasingly complex sorting challenges – it is link- ing insights directly to action across the plant. We are moving beyond high-speed detection toward a new era of intelligent, connected sorting, where complex chal- lenges are solved and data is understood, contextual- ized and communicated directly to the operator. Once again, TOMRA is at the forefront of innovation, trans- lating today’s most advanced AI into real, measurable value for customers." TOMRA Recycling www.tomra.com PET-tray-food PET-tray-non-food PET-tray-food PET-tray-food PET-tray-food PET-bottle-non-food PET-blister-non-food PET-tray-food PET-bottle-non-food PET-tray-food PET-tray-food GAINnext™ achieves 95% purity in PET tray sorting, turning a technical challenge into a viable business case TOMRA introduces three new deep learning applications for its GAINnext™ ecosystem to boost sorting precision