Fast Identification of Packaging Waste by near Infrared Spectroscopy with an InGaAs Array Spectrograph Combined with Neural Networks

Abstract
An optical set-up consisting of a high-throughput NIR spectrometer with an InGaAs array (800 nm to 1700 nm) and a specially designed collection optics was used to record spectra from post consumer packages (PE, PET, PP, PS and a cardboard–plastic compound) located on an industrial conveyor belt with an integration time of 6.3 milliseconds per sample. The spectra were classified by neural networks with an identification rate of better than 98%. The set-up is, hence, regarded as suitable for the on-line identification of package materials.