No abstract

In this study, effective solutions for polyethylene terephthalate (PET) recycling based on hyperspectral imaging (HSI) coupled with variable selection method, were developed and optimized. Hyperspectral images of post-consumer plastic flakes, composed by PET and small quantities of other polymers, considered as contaminants, were acquired in the short-wave infrared range (SWIR: 1000–2500 nm). Different combinations of preprocessing sets coupled with a variable selection method, called competitive adaptive reweighted sampling (CARS), were applied to reduce the number of spectral bands useful to detect the contaminants in the PET flow stream. Prediction models based on partial least squares-discriminant analysis (PLS-DA) for each preprocessing set, combined with CARS, were built and compared to evaluate their efficiency results. The best performance result was obtained by a PLS-DA model using multiplicative scatter correction + derivative + mean center preprocessing set and selecting only 14 wavelengths out of 240. Sensitivity and specificity values in calibration, cross-validation and prediction phases ranged from 0.986 to 0.998. HSI combined with CARS method can represent a valid tool for identification of plastic contaminants in a PET flakes stream increasing the processing speed as requested by sensor-based sorting devices working at industrial level.

No abstract

Sensor-based sorting devices commonly used in plastic recycling plants, mainly working in the near infrared range (NIR), are unable to identify black plastics, due to their low spectral reflectance. The aim of this work was to investigate the potentialities offered by laser-induced fluorescence (LIF) technique (spectral range 270–750 nm) for the identification of black polymers inside a plastic waste stream, thus allowing the possibility to build efficient sorting strategies to be applied in recycling plants. Representative samples of black plastics collected among the most utilized in household packaging were selected, constituted by four different types of polymers, i.e., expanded polystyrene (EPS), polystyrene (PS), polypropylene (PP) and high-density polyethylene (HDPE). The acquired LIF spectra were processed using multivariate approaches in order to optimize polymer classification. The developed hierarchical—partial least square-discriminant analysis (Hi-PLS-DA) classification model, showed excellent performances, confirmed by the values of sensitivity and specificity values in prediction, being equal to 1. The correctness of classification obtained by LIF was confirmed by the application of Fourier Transform Infrared spectroscopy (FTIR) on the same samples. The achieved results demonstrated the potential of LIF technique combined with a machine learning approach as sorting/quality control tool of black polymers in recycling plants. Graphical Abstract

No abstract