SORTING | TECHNOLOGY
Smarter sorting comes to recycling industry
Systems powered by artificial intelligence are enhancing sorting technology and other parts of the materials recycling process. Chris Saunders finds out what suppliers have developed
As the recycling industry faces increasing pressure to deliver consistently higher-quality materials, sort- ing technology has become one of the most critical areas of innovation across the entire value chain. From MRFs to packaging waste sorters and plastics recyclers, artificial intelligence (AI) is being intro- duced by many suppliers of technology and software for various stages in the materials recy- cling stream. At the plant level, new digital prod- ucts and services are being promoted for improv- ing efficiency and automation in the way recycling plants are monitored, managed, and optimised. Sorting and separation technology companies
are also innovating. Established optical sorting methods for plastics recycling are now being complemented by sophisticated multi-sensor platforms capable of identifying polymers accord- ing to chemistry, colour, shape, density and molecular composition, but perhaps the greatest technological leap forward in recent years has been the implementation of AI. Unlike conventional rule-based systems, machine-learning algorithms improve as they go along, enabling recyclers to adapt to changing packaging designs without
www.plasticsrecyclingworld.com
hardware modifications. AI can distinguish be- tween objects that appear almost identical to traditional optical systems, such as food-grade and non-food-grade PET packaging, with some systems also capable of recognising damaged or partially obscured packaging that would previously have been rejected or incorrectly classified. Indicative of this growing emphasis on AI, Tomra
has increased its investment in tech company PolyPerception to 51% and unveiled the next
evolution of the Waste Analyzer, an AI-powered analytics solution that improves sorting perfor-
mance through end-to-end material tracking. One of the most significant upgrades is the natural language interface that enables operators to extract plant data in plain language. The platform also introduces a ‘similarity search’ function, which enables operators to instantly identify visually similar items in the stream, and a more sophisti- cated text and brand search. “AI has always been part of Tomra’s DNA, but we
are now entering an entirely new phase,” said Lars Enge, EVP and Head of Tomra Recycling. “With our majority stake in PolyPerception, we are moving
September 2026 | PLASTICS RECYCLING WORLD 23
Main image: Artificial
intelligence is increasingly featuring on plastic waste sorting lines
IMAGE: SHUTTERSTOCK
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46
