Post by TOMRA Recycling

Three new AI applications. Three long-standing sorting challenges. The GAINnext™ ecosystem is growing with new deep learning applications designed for industry bottlenecks where traditional sensor-based sorting has reached its limits. The latest launches focus on three areas: ➡️ PET tray sorting As PET trays become an increasingly important feedstock alongside bottles, GAINnext™ can distinguish takeaway and supermarket trays from consumer and medical packaging based on shape and use. The application can achieve purity levels above 95%, helping turn PET tray sorting into a viable business case. ➡️ UBC aluminum recovery After a successful launch in North America, our GAINnext™ UBC application has now been adapted for the European market. It delivers up to 33 times more throughput than manual sorting and can reach 98% purity or higher by detecting and ejecting non-UBC materials in real time. ➡️ Copper meatballs In steel streams, copper-steel composites such as motor armatures can affect scrap quality. GAINnext™ identifies these complex objects, even in oxidized or dirty streams. This helps recyclers remove copper-rich contaminants and upgrade rebar-grade scrap into higher-quality furnace feedstock. To learn more about our deep learning applications, visit the GAINnext™ page: https://lnkd.in/emc_egNE