Page 65 - Plastics News June 2024

TECHNOLOGY NEWS

The Intersection of Plastics and Nanotechnology: A New Era

TOMRA’s sorting machines can now accurately distinguish between ing extensive data sets, these networks
food-grade and non-food-grade plastics, overcoming a long-standing learn and enhance their pattern recog-
challenge in the industry. nition capabilities, even in complex
scenarios. Consequently, employing
this technology in waste management
marks a substantial advancement in
circular economy practices, enabling
the efficient processing of packaging
into food grade and non-food grade
materials. Additionally, TOMRA has
pioneered waste sorting by combining
traditional sensors with deep learn-
ing, creating the market’s most accu-
rate solution. Finally, engineers have
trained neural networks using images,
allowing the machine to identify pat-
terns and properties and classify ma-
terials with various sensors
Pure Recycled Plastics Made Possi-
ble
TOMRA has achieved purity levels
Automated Sorting Waste effectively distinguish between them. over 95% in packaging applications,
However, the advent of a machine ca- opening new revenue opportunities for
leader in the sorting solutions pable of identifying various materials customers. Additionally, deep learn-
industry, TOMRA has been
developing and refining sen- has resolved this issue. It continuously ing allows more precise sorting by
learns over time and makes real-time identifying thousands of objects based
sor-based sorting technolo- decisions for their classification.
gies for over a century. They’ve played on material and shape. Beyond food-
a key role in optimizing processes Deep Learning In Packaging Sorting grade materials, TOMRA’s technology
across various sectors, including Equipped with the GAINnext™ AI- also provides solutions for deinking
food processing and recycling. Now, based system, TOMRA machines paper and enhancing PET bottle purity.
TOMRA’s deep learning technology is integrate deep learning technology As TOMRA advances its deep learn-
poised to revolutionize plastic recy- and optical waste sensors to classify ing technology, we expect increased
cling by accurately separating food- challenging materials. Deep learning, efficiency and accuracy in plastic sort-
grade and non-food-grade packaging. a transformative subfield of AI, mim- ing. This progress supports a more
The challenge of sorting materials such ics the human brain’s structure and sustainable future and drives the cir-
as PET, PP, and HDPE into food grade functions. Furthermore, deep learning cular economy, creating new revenue
and non-food grade has long plagued algorithms utilize artificial neural net- opportunities and contributing to a
the industry due to the similarities of works with multiple layers that process cleaner planet.
both types of packaging, making it dif- information dynamically. By process- Source – Plastic Engineering
ficult for current sorting systems to

64 PLASTICS NEWS June 2024 June 2024 PL 65 67
PLASTICS NEWSASTICS NEWS
June 2024