Hyperspectral imaging analysis for PE and PVC separation

An appropriate design of a product life cycle may contribute to the optimization of primary raw material uses and the reduction of waste environmental impacts. Recycling improve life cycle of materials with the production of secondary raw materials and the reduction of toxic compounds in incinerator ash or waste extensive landfills disposal. Traditional systems for plastic separation employ material physical properties like density. Due to the small variability of these properties of polymers, the output quality may not be adequate enough. Sensing technologies based on hyperspectral imaging appear suitable to separate materials and increase the quality of recycled products, which have to comply with specific standards determined by industrial applications. This paper presents results of hyperspectral imaging application for PVC and PE separation in different phases of their life cycle (raw materials, waste and regenerate conditions). This is accomplished by the use of two platforms allowing the comparisons between the spectral response of plastic materials. The first Platform A presents two linear spectrometers to investigate the VIS (400-1000 nm) and the NIR (900-1700 nm) ranges of wavelengths. The classification results obtained applying different strategies validate the hyperspectral methodology.