Classification of PS and ABS Black Plastics for WEEE Recycling Applications

TL;DR

This paper demonstrates that convolutional neural networks can effectively classify black plastics, specifically PS and ABS, from WEEE using image analysis, achieving high accuracy and showing potential for improved recycling processes.

Contribution

The study develops and tests a CNN-based system for classifying black plastics, highlighting its effectiveness and potential for enhancing WEEE recycling.

Findings

Validation accuracy of 95% for training

Test set accuracy of 86.6%, with perfect classification of ABS

Potential for improved accuracy with larger datasets

Abstract

Pollution and climate change are some of the biggest challenges that humanity is facing. In such a context, efficient recycling is a crucial tool for a sustainable future. This work is aimed at creating a system that can classify different types of plastics by using picture analysis, in particular, black plastics of the type Polystyrene (PS) and Acrylonitrile Butadiene Styrene (ABS). They are two common plastics from Waste from Electrical and Electronic Equipment (WEEE). For this purpose, a Convolutional Neural Network has been tested and retrained, obtaining a validation accuracy of 95%. Using a separate test set, average accuracy goes down to 86.6%, but a further look at the results shows that the ABS type is correctly classified 100% of the time, so it is the PS type that accumulates all the errors. Overall, this demonstrates the feasibility of classifying black plastics using CNN machine learning techniques. It is believed that if a more diverse and extensive image dataset becomes available, a system with higher reliability that generalizes well could be developed using the proposed methodology.