Sustainable Medical Materials: AI-Driven Assessment for Mechanical Performance of UVC-Treated Date Palm Epoxy Composites

This study investigates the AI-assisted analyses of radiation disinfection effects on the mechanical properties of recycled date kernel powder-epoxy composites for medical applications, utilizing Euclidean distances and the k-nearest neighbor (KNN) algorithm. Tensile and compression tests were conducted on twenty specimens following ASTM standards, with the data analyzed using a <i>t</i>-test to evaluate the impact of the UVC disinfection process on the material's mechanical properties. The application of AI through the KNN algorithm successfully identified the three most representative curves out of five for both tensile and compression tests. This targeted curve selection minimized variability and focused on the most relevant data, enhancing the reliability of the analysis. Following the application of UVC and AI, tensile tests showed a 20-30% increase in ultimate stress. Similarly, compression tests revealed a 25% increase in transition stress, an 18-22% improvement in ultimate stress, and approximately a 12% rise in fracture stress. This research underscores the potential of combining AI, sustainable materials, and UVC technology to develop advanced composites for medical applications. The proposed methodology offers a robust framework for evaluating material performance while promoting the creation of eco-friendly, high-performance materials that meet the stringent standards of medical use.