IoT-Driven Defect Detection System for Plastic Recycling Plants Based on Convolutional Neural Networks

Abstract

To improve the accuracy of plastic recycling facilities this paper introduces an Internet of Things (IoT)driven defect detection system that uses Convolutional Neural Networks (CNNs). Traditional techniques of fault identification are time-consuming and prone to human error, which makes plastic recycling less than ideal from an environmental sustainability perspective. To track the movement of plastics in real time, the system makes use of IoT sensors placed all throughout the recycling facility. To correctly detect plastic material flaws like contamination, discoloration, or physical damage, this data is then input into a CNNs model that has been tuned for image analysis. The proposed system outperforms conventional approaches in terms of efficiency and accuracy of flaw identification, as shown by rigorous testing. This method improves the quality and longevity of plastic recycling operations while simultaneously streamlining defect identification procedures via the use of IoT technology and CNNs. The IoT presents exciting new methods to lessen the negative effects of plastic recycling facilities on the environment while simultaneously increasing their efficiency and effectiveness, meeting the growing demand for environmentally friendly waste management solutions throughout the world.