Plastic pollution poses a significant global challenge, with traditional waste management methods proving inadequate. This study introduces a novel three-stage framework for sustainable plastic waste management, integrating artificial intelligence (AI) with literature-based microbial degradation guidance. In Stage 1, three Convolutional Neural Network (CNN) models, namely Custom CNN, EfficientNetV2, and MobileNetV2, were used to classify waste images into 34 categories and identify whether each item was plastic or non-plastic. Among them, MobileNetV2 achieved the highest accuracy, reaching 96.8% in multi-class classification and 98.8% in binary plastic versus non-plastic classification. In Stage 2, Support Vector Machine (SVM), Random Forest, and a one-dimensional Convolutional Neural Network (1D-CNN) were applied to Fourier Transform Infrared (FTIR) spectroscopy data to identify six common plastic types. The 1D-CNN model demonstrated superior performance, achieving 99.50% accuracy, outperforming the other models. Stage 3 provides a conceptual, literature-driven recommendation module for the management of non-recyclable plastics by associating polymer types with reported microbial degradation pathways, including microorganisms such as Ideonella sakaiensis for polyethylene terephthalate (PET) and Pseudomonas species for polystyrene (PS). This stage does not involve experimental biodegradation, simulation, or computational validation, and is intended to highlight potential end-of-life treatment directions informed by existing studies. Overall, the framework combines experimentally validated AI-based material classification and polymer identification with conceptual biodegradation recommendations, supporting informed decision-making across the plastic waste management pipeline. By aligning with the United Nations Sustainable Development Goal 12 (UN SDG 12), the proposed approach provides a structured and extensible foundation for advancing sustainable plastic waste management.
This work contributes to the understanding of material changes during the repeated recycling of glass fibre-reinforced styrene maleic anhydride (SMA). The present study investigates the influence of repeated recycling on its mechanical, rheological and thermal properties. The injection-moulded SMA was shredded, regranulated and subsequently injection-moulded. This was repeated five times in order to compare the material behaviour after multiple recycling runs with respect to the virgin material. In order to distinguish between the influence of polymer degradation and that of reinforcing fibre deterioration, pure SMA was also investigated. Tensile properties, melt volume rate (MVR) and fibre length were evaluated after each recycling run. Gel permeation chromatography (GPC) and infrared spectroscopy (IR) provided insight into the structural changes. The IR spectra and GPC analyses show that the chemical structure of the material is largely retained. The rheological tests show a decrease in the MVR values after each recycling path, indicating an increase in polymer viscosity. It was observed, that the tensile strength of the pure SMA under investigation increased after each recycling path, which could be attributed to the increase in the average molecular weight, as evidenced by the GPC analysis. Despite this increase in strength, the tensile tests of the fibre reinforced polymer showed a significant decrease in strength with each recycling run, while the elongation at break remained relatively constant. The impact strength decreases by 45% compared to the initially processed material. The deterioration in mechanical properties was mainly attributed to the shortened glass fibres. This is supported by the fibre length measurements, which show an average length reduction from 284 & micro;m for the virgin material to 104 & micro;m after five recycling runs. The research results show that SMA with and without glass fibre reinforcement can be mechanically recycled with little loss in mechanical performance.
A new sustainable and environmentally friendly composite material has been developed from coconut fibre particles and recycled polystyrene dissolved in chloroform. Three particle sizes and four reinforcement ratios were used. The composite was moulded by cold pressing without measuring the pressure but by fixing the thickness. The density (592.53 - 723.03) kg.m-3 shows the lightness of the material. The moisture content (6.63 - 8.35%), water absorption rate (54.06 - 109.42) % and thickness swelling rate (2.86 - 16.09) % are within the acceptable range of <= 16% for use in dry and wet areas, except for formulations with a 55% reinforcement rate. The absorption kinetics of the composites produced show hydrophilicity and correlate with Page's model. Microscopic examination shows better interfacial cohesion with low visible porosity for composites with the lowest particle content and reinforcement rate. Young's modulus (129.29 - 530.95) MPa and mechanical stress at break (1.26 - 6.508) MPa are relatively low compared to structural materials. Thermal conductivity (0.22 - 0.347) W.m-1.k-1 and thermal effusivity (571.9 - 856.7) J.m-2.K-1.S-1/2 are within the range of thermally insulating materials. Smaller particles show better cohesion with the matrix. These materials are intended for use in furniture, false ceilings, house partitions, computer stands and telephone booth doors.
This work focuses on optimising the thermal expansion and dimensional stability of calcium-borosilicate (CaO-B2O3-SiO2) glass fibre R-12 reinforced epoxy-934 laminates. Due to their superior mechanical strength, thermal performance, and durability, these laminates are widely used in the aerospace industry. R-12 glass fibre offers high tensile strength and enhanced thermal resistance, while Epoxy 934 resin ensures excellent adhesion and stability under thermal and mechanical stresses. The temperature of interest was selected as 80 degrees C, representing the service limit, which is typical of operational simulations in aerospace conditions with an extreme working range of around 70 degrees C. The fibre orientations tested were [+/- 0 degrees](5S), [+/- 15 degrees](5S), [+/- 30 degrees](5S), [+/- 45 degrees](5S), [+/- 60 degrees](5S) in a series of 13 experiments designed using Response Surface Methodology (RSM) and Central Composite Design (CCD) in Design-Expert software, to determine their effect on thermal expansion and dimensional stability. The model was experimentally validated, confirming its accuracy and demonstrating its reliability in optimising fibre-reinforced epoxy composites for aerospace applications.
In order to improve the oil and water resistance of the lunch box, wheat straw was used to produce the lunch box, while chitosan and beeswax served as raw materials for the oil- and water-resistant coating. The surface of the food box is coated by spraying. Firstly, a single chitosan solution is sprayed onto the surface of the wheat straw food box, and oil and water resistance tests are conducted. Subsequently, a composite oil and water resistant agent was prepared by adding beeswax to the chitosan solution. Optimization experiments were conducted on the dosage of the composite oil and water resistant agent from the perspectives of coating solution concentration and coating amount. The results showed that under the conditions of chitosan concentration of 2.0 wt%, beeswax solid content of 50 wt%, and coating amount of 2 g/m2, the oil resistance level of the food box could reach level 9 or above, and the water absorption rate decreased to 11.3%. The food box met the requirements for oil and water resistance, providing a promising green alternative to traditional plastic tableware.
