Black plastics - sorting of uneasily-identified plastic fractions
|Coordinator||Swerim AB - Swerim AB, Kista|
|Funding from Vinnova||SEK 500 000|
|Project duration||November 2018 - July 2019|
|Venture||Banbrytande idéer inom industriell utveckling|
|Call||Banbrytande idéer inom industriell utveckling 2018|
Purpose and goal
The aim of the project is to develop a stable sensor-based measurement method for identification and sorting plastics; both regarding the plastic type and additives of regulated chemicals in the form of e.g. plasticizers and flame retardants. In order to realize this, analysis based on machine learning (ML) processes and laser induced breakdown spectroscopy (LIBS) will be developed.
Expected results and effects
The expected results are a method for developing analysis models that can identify relevant signals in LIBS spectra from plastic. The expected effect is to be able to sort plastics for which there currently does not exist a technology that works under relevant conditions. This applies in particular to black plastics, but also to the identification of specific additives.
Planned approach and implementation
Large amounts of relevant plastic materials will be collected and characterized. This is a crucial step for developing relevant models. The plastics material will then be analyzed with LIBS technology in the Swerim test bed for process monitoring. This is expected to generate a large amount of statistically relevant measurement data that will be used to develop analysis models based on machine learning. The results will then be verified by lab analysis on selected samples.