Optimizing industrial e-waste recycling with attention-driven deep learning for PCB segmentation using hyperspectral imaging

Recently, the generation of electronic waste (E-waste) has increased significantly due to rapid changes in consumer demand and advancements in technology. Recycling E-waste is essential for boosting the economy and advancing the sustainability of the electronics industry. Printed circuit boards (PCBs) contribute significantly to E-waste, as they are widely used in various electronic devices. However, a challenge in recycling E-waste is the rapidly and diversely changing material composition. To enhance the efficacy of E-waste recycling, an automated, non-invasive method is essential for process control and decision-making. By exploiting hyperspectral imaging (HSI), which offers spectroscopic analysis to accurately identify materials, this paper presents attention-based deep learning segmentation models to accurately identify components in PCBs. This approach allows for the automatic extraction of information from E-waste, leading to more efficient and optimized recycling practices.