The recycling industry could be in for a major boost thanks to the development of new plastic-separation technology at a Danish university.
Researchers at Aarhus University have developed a new camera technology that is able to differentiate between 12 different types of plastics, including those most commonly used in households.
Plastics recycling is usually processed via density tests or mechanical sorting, which traditionally uses near-infrared technology (NIR) to distinguish between the various types of plastics recycled.
The resulting plastics usually offer a purity of between 75 and 95 percent – short of the 96 percent purity levels required by industry.
The new technology, which uses a camera and machine learning to analyse images of plastic waste, is able to distinguish between polyethylene (PE), polypropylene (PP), polyethylene terephthalate (PET), polystyrene (PS) and polyvinyl chloride (PVC) – which make up the majority of household plastic waste – along with seven other types of plastic.
The Danish study, published in the scientific journal Vibrational Spectroscopy, used unsupervised machine learning on short wave infrared hyperspectral data to build a model that classifies plastics.
This new technology can identify a greater range of plastic types than the NIR technology, whilst also classifying their chemical purity – a potential breakthrough for the plastics recycling industry.
Associate Professor Mogens Hinge, head of the Aarhus University research team, explained to Resource magazine how the technology works.
“Fundamentally, it is a camera that images a conveyer belt. The plastics are then transported past the camera. When the camera has taken the images, we employ unsupervised machine learning to analyse the images and detect and distinguish between the individual plastic types,” he said.
“The camera is special, as it records images within the infrared area and with multiple channels. For reference, a mobile phone has three channels – red, blue, and green – making up an image. Our IR camera has 90 channels.
“I would like to note that we have intentionally only used industrial components – this includes all components and systems in our setup. This means that we have not used highly sensitive, dedicated, specialised and delicate research equipment for our work. This restriction is done to ensure the industrial relevance of our work.”
The new technology is set to be installed in two plastic recycling companies, Plastix and Dansk Affaldsminimering, for testing.
According to Hinge, this testing will allow his team to “properly adjust and adapt the source code and machine learning training algorithms” to “maximise performance”, but he believes that the system will be directly transferable to industries, where it could help to transform our ability to recycle.
“Aside from the camera, all you need is a stand to position it over a conveyer belt in the production line. Due to its ability to detect a range of plastic types, the technology enables the sorting of unwanted impurities or unwanted materials from the plastic waste stream,” he added.
“This will deliver recycled plastic fractions with a higher purity, which then can be applied in more demanding products. Hence, enabling more recycling – and in some cases enabling recycling at all – of plastic waste. We have a special focus on the purification of household collected plastics and ghost nets from the fishing industry.”
Photo by Hans Braxmeier on Pixabay.
