Sustainable environmental design using circular economy in the plastic manufacturing industry for decarbonization

Plastic waste is one of the most controversial environmental issues because of the poor recyclability and high carbon emissions of traditional plastic production systems. Traditional processes can be inefficient in sorting materials, consume high amounts of energy, and lack lifecycle integration for plastic products. This research proposes a Sustainable Environmental Design Circular Economy (SEDC) framework that overcomes the limitation and provides an entire end-to-end solution from designing the product to recycling processes. The proposed method applies a Novel Convolutional Neural Network- Naive Gradient Boost- Sandpiper Optimization (CNN-NB-SPO) algorithm to determine high-level features that improve the recyclability and modularity of products. SPO is used in refinement stages to improve the decisions and consequently, energy efficiency with regard to recyclability potential is improved at the design stage. Novel Generative Adversarial Network- Artificial Neural Network (GAN-ANNs), improve reverse logistics so that supply chain operations become efficient, and the recycling waste of cyclicality decreases. The framework is applied to the Kaggle Plastic Waste dataset, in which its effectiveness in improving classification accuracy, material recovery, and reduction of carbon emissions is demonstrated. Basic performance parameters—recyclability rate, energy consumption, CO2 emissions, and accuracy—confirm that the proposed model significantly outperforms traditional approaches to plastic production manufacturing for the advancement of the goals of a circular economy. An integrated, data-driven approach from SEDC provides a scalable solution toward sustainable plastic production and waste management for the support of global decarbonization efforts.