Detection of Brominated Plastics from E-Waste by Short-Wave Infrared Spectroscopy

Abstract

In this work, the application of Short-Wave Infrared (SWIR: 1000–2500 nm) spectroscopy was evaluated to identify plastic waste containing brominated flame retardants (BFRs) using two different technologies: a portable spectroradiometer, providing spectra of single spots, and a hyperspectral imaging (HSI) platform, acquiring spectral images. X-ray Fluorescence (XRF) analysis was preliminarily performed on plastic scraps to analyze their bromine content. Chemometric methods were then applied to identify brominated plastics and polymer types. Principal Component Analysis (PCA) was carried out to explore collected data and define the best preprocessing strategies, followed by Partial Least Squares—Discriminant Analysis (PLS-DA), used as a classification method. Plastic fragments were classified into “High Br content” (Br > 2000 mg/kg) and “Low Br content” (Br < 2000 mg/kg). The identified polymers were acrylonitrile butadiene styrene (ABS) and polystyrene (PS). Correct recognition of 89–90%, independently from the applied technique, was achieved for brominated plastics, whereas a correct recognition ranging from 81 to 89% for polymer type was reached. The study demonstrated as a systematic utilization of both the approaches at the industrial level and/or at laboratory scale for quality control can be envisaged especially considering their ease of use and the short detection response.

Prediction of Thermogravimetric Data in Bromine Captured from Brominated Flame Retardants (BFRs) in e-Waste Treatment Using Machine Learning Approaches

“…However, we would like to cite a few works that applied ML techniques for identification of Br concentration in e-waste and prediction of optimum extraction conditions in this field. In the work by Bonifazi et al, PLS-DA (partial least-squares-discriminant analysis) and principal component analysis (PCA) were used to classify samples as having low or high Br content, and an accuracy of ∼90% was achieved for classification. XRF and SWIR were the characterization techniques used in this work, and the chemometric methods of PCA and PLS-DA were applied on these data sets.…”

“…The usefulness of regression models as building blocks of ML methods goes a long way in predicting not only TGA data but also other characterization data such as short-wave infrared spectra (SWIR) and X-ray Fluorescence (XRF), that are used to detect the presence of BFRs in plastic waste. Bonifazi et al applied two chemometric methods, namely, principal component analysis (PCA) followed by partial least-squares–discriminant analysis (PLS-DA), on XRF and SWIR data collected on plastic waste samples to explore the potential preprocessing strategies and to identify samples with high Br content (>2000 mg/kg) and low Br content (<2000 mg/kg). The accuracy of classification achieved was reported to be ∼90%, but this work did not utilize regression models to predict the actual XRF or SWIR data.…”

Towards recycling of challenging waste fractions: Identifying flame retardants in plastics with optical spectroscopic techniques

“…HSI has been used in pure plastic identification (Serranti et al, 2011; Ulrici et al, 2013). However, for detection of plastic additives, only a handful of studies have been conducted (Amigo et al, 2015; Bonifazi et al, 2021; Caballero et al, 2019). The studies are related to identifying BFRs in plastics, and the used wavelength ranges were in the SWIR range in all studies.…”

Sensor-Based Technologies in Effective Solid Waste Sorting: Successful Applications, Sensor Combination, and Future Directions

“…Practices of NIR in classifying plastics were initiated in early 2010. Researchers classified HDPE/LDPE with the assistance of PCA and PLA/PET by PLS-DA. , Since then, classification has been extended to all main kinds of plastics (PVC, PP, PE, PET, PS) with appropriate chemometric tools and acquired very high accuracy except for PS/ABS and LDPE/HDPE. ,− NIR is also utilized in separating plastic and nonplastic wastes …”