This voice is automatically generated. Please let us know if you have any feedback.
Diving overview:
- Researchers are studying how machine learning can play a role in advancing recyclable materials for multilayer film packaging. Multilayer film packaging is known for its performance benefits, but it is not easily recycled.
- An open access paper was written by partners across the Bottle Consortium and published this month in Nature Communications. “By challenging the status quo, MLF “In design, we advocate circularity in food packaging and stimulate innovation at the intersection of sustainability, materials science, and artificial intelligence,” the paper states.
- This process involves studying the structure-property relationship of current multilayer film polymers. Known polymer properties are input into an ML model such as: Poly ID Predict polymers with similar properties, especially polyesters. The researchers conclude that “there is a huge opportunity for computational tools to guide the development of the next generation.” MLFHowever, there are limitations, including a relative lack of published data linking polymer structure and performance properties.
Dive Insight:
Researchers are considering an important question: Is it possible to redesign multilayer films, which are meticulously designed to keep food fresh, with recycling in mind?
of The consortium is working to ensure that multilayer film packaging can be managed through mechanical recycling, chemical recycling and composting, and is using machine learning and AI tools to drive redesign, explained co-author Katrina. KnauerChief Technology Officer of the Bottle (“Biooptimization Technologies to Keep Thermoplastics Out of Landfills and the Environment”) Consortium, a plastics recycling research initiative supported by the U.S. Department of Energy.
“We really wanted a combination of chemists, plastic processing engineers, machine learning experts, and people who are on the front lines of working with businesses and consumers to make recycling better,” the polymer scientist said. Knauera senior research scientist at the National Laboratory of the Rockies.
Currently, these films include polyethylene (PE), polyvinylidene dichloride (PVDC), polyethylene terephthalate (PET), polyamide (P.A.) and ethylene vinyl alcohol (EVOH). But performance films have a central contradiction.
“Such films are often composites of polymers and metallized species, integrating barrier layers for low oxygen and moisture transmission, structural layers for increased mechanical robustness, and tie layers that act as adhesives during lamination,” the paper states. “The complex engineering that led to this technological importance is ultimately being overshadowed by incompatibility with recycling routes and negative impacts on environmental sustainability at the end of its useful life, both of which require urgent action.”
“The main challenge in attempting a redesign is to meet the excellent barrier performance provided by aluminum, PVDC, and EVOH (individually and in combination),” the paper states. “These polymers are often incompatible when melt-blended by mechanical recycling, and physically separating the individual layers remains functionally impractical.”
However, chemical recycling is not a silver bullet either. “Chemical processing techniques such as selective dissolution and precipitation have demonstrated effective separation and recovery of individual polymer components of MLF. However, these processes often produce polymers with reduced thermal properties and remain economically and energetically demanding, limiting large-scale implementation,” the researchers noted.
The Plastics Recyclers Association also contributed to this study, given its expertise in recyclability guidelines.
“Every day we see how much time, effort, and resources are being spent by brands and processors trying to transition to more recyclable products,” said co-author Rebecca Mick, APR’s program director for film and packaging innovation. organization frequently Hear about the challenges of replacing PVDC and aluminum foil. Companies struggle to find materials with comparable barrier levels that are suitable for recycling.
She said there’s a lot of excitement about AI when it comes to managing and sorting used materials, but when it comes to designing and even creating new polymers and structures, it’s even more novel. Machine learning has the potential to “exponentially” speed up design.
“With the right data input, we have the potential to speed up the process,” Mick says. “The more data you feed into this kind of model, the more data you can pull out of the model in terms of a design that is closer to what is accepted in today’s flow.”
Early research in this field was chemistry non-chlorinated ones, fluorinatedWe are getting closer and closer to the barrier performance that PVDC has dominated for decades,” Knauer said.
Further funding is desired for future prototypes. “We still need to do a lot of testing for that,” Knauer said, but hopefully “we can show the world that new polymers don’t have to be so scary.”
