We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Determining the percentage of recycled plastic content in a plastic product
AI summary Read the abstract
Researchers developed a non-destructive, multi-modal technique combining triboelectric properties, dielectric spectroscopy, infrared spectroscopy, and machine learning to quantify recycled plastic content in products. The approach achieved over 97% accuracy across PET samples with 0–50% recycled content.
As global plastic waste continues to rise, accurately identifying and quantifying recycled content in plastic products is critical for developing a circular economy. At present, there is no method that can accurately determine the percentage of recycled plastic content in a plastic product. Here, we demonstrate a multi-modal, non-destructive sensing technique to determine the percentage of recycled plastic in plastic products. We have developed a multi-modal, multi-physics approach that integrates triboelectric properties, dielectric/impedance spectroscopy, capacitance measurements, mid-infrared spectroscopy, combined with machine learning and artificial intelligence to quantify the recycled content in plastics. Experimental results reveal that increasing recycled content leads to enhanced charge retention, reduced permittivity, and increased dielectric loss, consistent with polymer chain scission and defect-induced polarization. The machine learning model trained on the multi-modal dataset achieves we achieved over 97% classification accuracy across PET samples ranging from 0% to 50% recycled content, which is the expected regime of required recycled content in plastic products. This method offers a solution for control and regulatory compliance for recycled plastics.
More Papers Like This
ATR-FTIR Spectroscopy Combined with Chemometric Methods for the Classification of Polyethylene Residues Containing Different Contaminants
AI summary Read the abstract
Researchers combined ATR-FTIR spectroscopy with chemometric methods to classify polyethylene residues containing different types of contaminants. The approach successfully distinguished between contaminated and uncontaminated low- and high-density polyethylene, offering potential for improving plastic recycling quality control.
Comparative Study of Chemometric Approaches and Machine Learning for Miniaturized Near-infrared (micronir) Spectroscopy in Plasticwaste Sorting
AI summary Read the abstract
This study tested a miniaturized near-infrared (NIR) spectroscopy device combined with chemometric and machine learning methods to sort different types of plastic waste. The approach accurately identified polymer types, supporting more efficient plastic recycling operations that could reduce microplastic generation.
Rapid and Nondestructive On-Site Classification Method for Consumer-Grade Plastics Based on Portable NIR Spectrometer and Machine Learning
AI summary Read the abstract
Researchers used a portable near-infrared spectrometer combined with machine learning to rapidly identify and classify seven types of consumer plastic waste on-site without damaging the samples. Faster and cheaper plastic identification tools are important for improving plastic recycling efficiency and ultimately reducing the amount of plastic that ends up as microplastic pollution.
Deep learning for chemometric analysis of plastic spectral data from infrared and Raman databases
AI summary Read the abstract
A novel deep learning architecture called PolymerSpectraDecisionNet was trained to identify common recyclable plastics from infrared and Raman spectral databases. The model outperformed conventional chemometric methods for polymer classification and was designed to handle real-world spectral variability relevant to the plastics recycling industry.
Online Characterization of Mixed Plastic Waste Using Machine Learning and Mid-Infrared Spectroscopy
AI summary Read the abstract
Researchers developed a machine learning framework combining convolutional neural networks and mid-infrared spectroscopy to identify mixed plastic waste compositions in real time, achieving near-100% accuracy at 100 Hz on a moving platform, paving the way for high-throughput industrial plastic sorting and recycling.
Research digests by email
When a large batch of papers lands in the Atlas, we read through it and send a short write-up of what stood out.