Post-consumer plastic identification using Raman spectroscopy

Raman spectroscopy is evaluated as a spectroscopic method for identificatio n of common household plastics for recycling purposes. The methods of K-nea rest neighbor (KNN), cyclic subspace regression (CSR), and library searchin g are compared for computerized plastic classification. Plastics studied co nsist of polyethylene terephthalate, high-density polyethylene, polyvinyl c hloride, low-density polyethylene, polypropylene, and polystyrene. With pri ncipal component analysis (PCA), visual distinction between the different p lastics becomes possible. Correct class membership to all six plastic types is provided by KNN. To date, all development and uses of CSR have been bas ed on building models for each prediction property analogous to the form of partial least-squares known as PLS1. Cyclic subspace regression is modifie d in this paper to also allow modeling of multiple properties, as does PLS2 . The new form of CSR was able to correctly classify all six plastic types when seven-factor models were used. This paper reports that key observation s made in comparing PCR to PLS1 are verified for the interrelationships of PCR and PLS2 models. Most notable is that even though PLS2 uses spectral re sponses and plastic identifications to form factors, PLS2 eigenvector weigh ts are not much different from PCR eigenvector weights where PCR only uses spectral responses to form eigenvector weights. Library searching showed le ss significant results than KNN and CSR. Regardless of the identification a pproach, polyethylene samples could be identified as either being high dens ity or low density with the use of Raman spectroscopy.