TOMRA Pioneers New Deep Learning-Based Solution to Upgrade Wrought Aluminum Scrap

Thu March 27, 2025
TOMRA Recycling

TOMRA Recycling has expanded its portfolio of advanced metals recycling with an AI-based solution to upgrade wrought aluminum scrap.

This development represents the first application of GAINnext — TOMRA's deep learning-based sorting technology — in the metals industry. This AI innovation enables aluminum scrap processors and recyclers to upgrade their wrought aluminum scrap and produce exceptionally high purity fractions by instantly recovering low alloy cast from the wrought fraction and reducing alloying elements such as silicon. GAINnext complements TOMRA's X-TRACT, which separates based on atomic density.

TOMRA's X-TRACT, featuring X-ray Transmission (XRT) technology, is the industry standard for sorting aluminum from heavy metals based on atomic density. X-TRACT initially sorts shredded mixed non-ferrous metals (zorba) to produce high-purity aluminum scrap (twitch), then removes high alloy aluminum cast and high-density wrought aluminum to further refine the twitch. This process yields a high-quality fraction, containing both wrought aluminum and minor amounts of low alloy cast, which other currently available sorting methods cannot fully separate.

Now, by integrating GAINnext into the sorting process after X-TRACT, a pure wrought fraction can be achieved. GAINnext leverages the power of deep learning and artificial neural networks. Using RGB cameras, it rapidly processes tens to hundreds of thousands of images per millisecond, 'perceiving' and 'classifying' materials by shape, size and dimension with exceptional accuracy. This advanced system, trained over years by TOMRA's experts, mimics human vision but with superior speed, facilitating high throughput sorting of up to 2,000 ejections per minute. In its first metals industry application, by precisely detecting and removing low alloy cast from the wrought fraction that TOMRA's X-TRACT produces, GAINnext delivers an exceptionally high purity wrought product that commands premium market prices, according to TOMRA.

For TOMRA customers seeking to achieve even higher granularity levels in aluminum sorting, the wrought fraction recovered by GAINnext can be further refined using TOMRA's AUTOSORT PULSE system, which employs dynamic laser-induced plasma spectroscopy (Dynamic LIBS) for precise identification and sorting of different alloy types. Launched in 2023, AUTOSORT PULSE, TOMRA's breakthrough innovation, leverages precise elemental composition analysis and advanced dynamic laser detection to accurately distinguish between different alloy types e.g. 5xxx and 6xxx aluminum.

This combination of X-TRACT, GAINnext and AUTOSORT PULSE represents the pinnacle of sorting innovation, delivering the highest levels of material separation available on the market today.

"We are excited to launch this new deep learning-based application to upgrade wrought aluminum," said Tom Jansen, head of the metals segment, sales of TOMRA Recycling. "Deep learning is a powerful addition to our traditional sensor-based technology and expanding our GAINnext ecosystem aligns with our broader AI strategy. Building on our proven success and the significant results our customers have achieved with GAINnext in the waste segment, we are confident in delivering similar value to our metals customers."

"Our latest innovative solution optimizes dry mechanical sorting of mixed metals," added Giuseppe Petro Granara, Segment Manager Metals — Americas of TOMRA Recycling. "Along with its complementing other technologies within the TOMRA portfolio, GAINnext provides a highly efficient, cost-effective alternative that minimizes manual labor and maximizes throughput. Its low cost per ton makes it an attractive option for recyclers aiming to consistently produce smelter-ready, high-purity aluminum. Beyond metal recycling, the technology's adaptability opens opportunities for use in other industries requiring manual sorting. As a key addition to our recycling solutions portfolio, we expect strong adoption from businesses focused on refining materials and generating premium feedstock for circular manufacturing."

TOMRA pioneered deep learning technology in 2019, and GAINnext has been proven in the field across various complex recycling streams, including waste, plastics, paper, metals and wood, according to TOMRA. In 2024, TOMRA introduced a groundbreaking GAINnext application to separate food-grade from non-food-grade plastics for PET, PP and HDPE. This latest expansion of the GAINnext ecosystem is part of TOMRA's broader AI strategy. Further GAINnext applications are due to be announced in 2025.