Using Digital Twins and Gen AI to Optimize Plastics Densification in the Recycling of Polypropylene (PP) and Polyethylene (PE)

Some critical challenges persist in the recycling of PP and PE because of some inefficiency in their densification processes, which is always burdening its quality and cost. The present research work focuses on proposing an integrated framework that applies Digital Twins and Generative AI for optimizing plastics densification. Digital Twins will digitally represent the physical recycling process and allow for monitoring in real-time, simulating various key parameters such as temperature, pressure, and size of particles. Meanwhile, the use of Gen AI will be meant to determine optimization of these values through the generation of adaptive models that can predict the conditions for maximum improvement in the densification process. Therefore, the proposed approach aims at improving the densification efficiency, reducing energy usage, and improving the quality of both recycled PP and PE. The approach was validated by extended simulations; the results obtained accordingly showed a high percentage of improvement with respect to traditional methodologies concerning process optimization and resource usage. This study provides the underground for new methodology, which will resolve the existing gaps present in current recycling technologies. Also, the Digital Twin coupled with Gen AI can be used as a revolutionary technology within the recycling industry. Further studies can broaden the scope to plastics of other types, and the use of more advanced AI models can be applied to optimize integration.