Aarhus University optimizes mixed plastic sorting with “groundbreaking” camera tech
11 Jan 2022 --- Researchers at Aarhus University, Denmark, are developing a camera machine capable of distinguishing between 12 different types of plastic, making it possible to sort and recycle materials according to their chemical components.
The plastic waste solution is part of the RePlast project, which aims to create technology that can support the identification and proper recycling of industrial components.
Although the technology will primarily be used for purifying household collected plastics and fishing nets, the researchers believe the machine’s applicability can be extended further.
Mogens Hinge, associate professor at Aarhus University and head of the plastic and polymer engineering group, tells PackagingInsights: “This is groundbreaking [technology] and it will increase the rate of recycling of plastics immensely.”
In partnership with Vestforbrænding, Dansk Affaldsminimering Aps, and Plastix, the researchers have developed the camera technology to identify the difference between 12 different types of plastics: polyethylene, polypropylene, PET, polystyrene, polyvinyl chloride, polyvinylidene fluoride, polyoxymethylene, polyether ether ketone, acrylonitrile butadiene styrene, poly(methyl methacrylate), polycarbonate, and PA12/Nylon12).
“Together, these constitute the vast majority of household plastic types,” says Hinge.
New recycling opportunities
The researchers note this technology makes it possible to separate plastics based on a purer chemical composition than currently possible, opening up completely new opportunities for plastics recycling.
The tech makes it possible to separate plastics based on a purer chemical composition than currently possible, opening up new recycling opportunities.Hinge explains that fundamentally, the technology is simply a camera that photographs the mixed plastic waste as it passed on a conveyor belt.
“When the camera has taken the images, we employ unsupervised machine learning to analyze the images and detect and distinguish between the individual plastic types. The camera is special as it records images within the infrared area and with multiple channels.”
“With this technology, we can now see the difference between all types of consumer plastics and several high-performance plastics. We can even see the difference between plastics that consist of the same chemical building blocks, but which are structured slightly differently.
“It’s a breakthrough that will have a huge impact on all plastics separation,” Hinge reiterates.
Extended uses
Hinge stresses the technology will primarily be used for purifying household collected plastics and fishing nets. However, the researchers do not see the machine’s purpose limited to these uses.
“Being able to detect plastic types enables out-sorting of unwanted impurities in unwanted materials from the plastic waste stream so the industrial-demanded 95% purity can be achieved,” he continues.
“This will result in recycled plastic fractions with higher purity that can be applied in more demanding products, hence, enabling more recycling (and in some cases, enabling recycling in the first place) of the plastic waste.”
Concerning commercialization, Hinge confirms the research is focusing on using industrial components exclusively. “Thus the system is directly transferable into industrial settings,” he says.
All important chemical purity
Up until now, plastics have been traditionally separated using near-infrared technology or density tests (floats or sinks in water).
Axel Kristensen, Plastix’s CEO, says although these methods can separate certain plastic fractions, they cannot do so with the same accuracy as this new technology in terms of the composition’s chemical purity, which is vital for increasing plastic recycling rates.
A collection of plastic waste the camera is able to separate by its chemical compounds.
“The technology we’ve developed in collaboration with the university is nothing short of a breakthrough for our ability to recycle plastics. We look forward to installing the technology in our processing hall and starting in earnest on the long journey towards 100% utilization of waste plastic,” adds Kristensen.
Machine optimization
The researchers explain that plastic must be at least 96% pure by polymer type to be recycled by conventional industry.
“Using the new technology, we are now a big step along the way,” concludes Hinge, who shares that the machine is continuously being developed, with data indicating it may be possible to differentiate even further between polymer types and additives in the near future.
The hyperspectral camera technology has been developed in cross-disciplinary collaboration, including BSc and MSc engineering students and researchers at the Department of Biological and Chemical Engineering at Aarhus University, and experts from the participating companies.
According to the Ellen MacArthur Foundation, only 14% of all plastic packaging is collected for recycling after use and vast quantities escape into the environment.
By Natalie Schwertheim
