A discrimination model in waste plastics sorting using NIR hyperspectral imaging system

摘要

Highlights•NIR spectral data were preprocessed by the method of Savitzy-Golay and the wavelet analysis.•Principle Component Analysis (PCA) was applied to select characteristic wavelengths.•Five polynomial functions were available to discriminate the known and unknown waste plastics.•The accuracy of the model to identify the unknown plastics was 100%.AbstractClassification of plastics is important in the recycling industry. A plastic identification model in the near infrared spectroscopy wavelength range 1000–2500 nm is proposed for the characterization and sorting of waste plastics using acrylonitrile butadiene styrene (ABS), polystyrene (PS), polypropylene (PP), polyethylene (PE), polyethylene terephthalate (PET), and polyvinyl chloride (PVC). The model is built by the feature wavelengths of standard samples applying the principle component analysis (PCA), and the accuracy, property and cross-validation of the model were analyzed. The model just contains a simple equation, center of mass coordinates, and radial distance, with which it is easy to develop classification and sorting software. A hyperspectral imaging system (HIS) with the identification model verified its practical application by using the unknown plastics. Results showed that the identification accuracy of unknown samples is 100%. All results suggested that the discrimination model was potential to an on-line characterization and sorting platform of waste plastics based on HIS.