Tomra Recycling harnesses AI for aluminum scrap sorting

Tomra Recycling has expanded its advanced metal recycling portfolio with the first application of its AI-based GainNext sorting technology. The deep learning solution can improve the purity of molded aluminum scraps, supporting processors and recyclers.

Tomra says its GainNext solution can instantly recover low alloy cast from the wrought aluminum fractions while reducing alloying elements such as silicon, wrestling in “high purity fractions.”

Tom Jansen, head of sales at the Tomra Metals Segment, says: “Deep learning is a powerful addition to our traditional sensor-based technology, and expanding our GainNnext ecosystem aligns with our broader AI strategy.”

“Building on our proven success and the significant results our customers have achieved with GainNnext in the waste segment, we are confident in delivering similar value to our metals customers,” he continues. 

“This latest application enhances dry mechanical sorting of mixed metals, offering a cost-effective solution with a low cost per ton thanks to its high throughput and significantly reduced manual sorting requirements.”

Removing low alloy cast

GainNnexts aims to complement Tomra’s X-Tract, which separates metals based on their atomic density. 

Tom Jansen, head of sales at the Tomra Metals Segment.The X-Tract machine features X-ray Transmission technology for the sorting of aluminum from heavy metals. X-Tract works by initially sorting mixed non-ferrous metals (Zorba) to produce high-purity aluminum scrap (Twitch). The machine then removes high alloy aluminum cast and high-density wrought aluminum to further refine the Twitch. 

This process produces high-quality fraction that contains wrought aluminum and minor amounts of low alloy cast — not possible to separate though other sorting methods. 

Tomra is now integrating its GainNnext into its sorting process, following the application of X-Tract, to achieve a “pure wrought fraction.”

“Gainext leverages the power of deep learning and artificial neural networks,” says the company. 

The solution uses RGB cameras to rapidly process tens to hundreds of thousands of images per millisecond, perceiving and classifying materials by shape, size, and dimension.

“This advanced system, trained over the years by our 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 X-Tract produces, GAINnext delivers a high purity wrought product that commands premium market prices,” Tomra continues.

Jansen adds that Tomra’s customers “will be able to consistently produce smelter-ready, premium-grade aluminum.”

“This is a significant enhancement to our metal recycling solutions portfolio, and we anticipate wide adoption by recyclers seeking to refine scrap and generate high-quality feedstock for circular manufacturing.”

Johannes Jacoby, head of Market Strategy at Tomra Recycling, discussed Tamra’s sorting technology at length in an interview with Packaging Insights.