Black Plastic Waste Classification by Laser-Induced Fluorescence Technique Combined with Machine Learning Approaches

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