To address circularity and resource recovery in modern structural applications, industry is seeking materials that are sustainable and lightweight. Although natural fiber-reinforced composites offer sustainability advantages, their mechanical properties remain inferior to those of synthetic fiber systems, limiting practical deployment. Flax fibers were selected as reinforcement due to their high specific stiffness, biodegradability, and wide availability. This study implements a three-level strategy to enhance the flexural performance of flax fiber-reinforced composites: at the process level, curing under distinct heating rates to promote a more uniform polymer network; at the material level, incorporation of a carbonaceous additive derived from fuel–oil furnace waste to strengthen interfacial adhesion; and at the structural level, adoption of a sandwich configuration with a recycled PET core to increase section bending inertia. Specimens were fabricated via vacuum-assisted resin transfer molding (VARTM) and tested using a three-point bending method. Mechanical testing shows clear improvements in flexural performance, with the sandwich architecture yielding the highest values and increasing flexural strength by up to 4.52× relative to the other conditions. For the curing series, FTIR indicates greater reaction extent, evidenced by lower intensities of the epoxide ring at 915 cm⁻¹ and glycidyl/oxirane band near 972 cm⁻¹, together with a more pronounced C–O–C stretching region, consistent with the higher flexural response. While SEM observations revealed interfacial debonding at 5% FCB, a hybrid mechanism with crack deflection appeared at 10%. This transition created tortuous crack paths, consistent with the higher flexural strength and modulus at 10% FCB. A distinctive feature of this work is the integration of three reinforcement strategies—controlled curing, waste-derived carbon additive, and recycled PET sandwich design. This integration not only enhances the performance of natural fiber composites but also emphasizes sustainability by valorizing recycled and waste-derived resources, thereby supporting the development of greener composite materials.

Growing environmental awareness and the challenges posed by climate change have driven the development of sustainable composites to reduce dependence on fossil resources and mitigate ecological impacts. Conventional composites, despite their high mechanical performance, are constrained by greenhouse gas emissions and limited recyclability, motivating the adoption of “green composites” based on natural fibers, recycled constituents, and bio-based resins. This study presents a sustainable sandwich composite integrating flax fibers, a bio-based epoxy matrix, and a recycled PET foam core. Flexural performance was evaluated through finite element analysis (FEA) in ANSYS Workbench and validated by three-point bending tests. The results show that the 3C specimen achieved a maximum load of 579.92 N, with a deviation of 4.2% from simulation at 6 mm deflection, and all tested specimens exhibited discrepancies below 5%. These findings confirm the suitability of the developed composites for structural applications such as UAV wings, aligning high mechanical performance with environmental sustainability.

Ensuring the cleanliness of precision components is critical in Hard Disk Drive (HDD) manufacturing, where microscopic dust contamination on the Voice Coil Motor Assembly (VCMA) can lead to positioning errors, unstable head movement, and long-term reliability failures. However, automated inspection of such contamination remains challenging because dust particles are extremely small, visually irregular, and often appear under complex microscopic backgrounds. This study presents an explainable hybrid deep learning framework for microscopic dust inspection by integrating object detection for precise localization and image classification for defect confirmation. Three YOLO architectures, namely YOLOv5, YOLOv8, and YOLOv11, were comparatively evaluated for dust detection, while three convolutional neural network (CNN) models, ResNet50, EfficientNetB0, and MobileNetV2, were implemented using transfer learning with frozen feature extraction layers for Good (G) and Not Good (NG) image-level classification. The experimental dataset consisted of annotated microscopic VCMA images, with data augmentation applied to the training subset to mitigate limited sample size and class imbalance. Experimental results showed that YOLOv8 achieved the strongest overall aggregate detection performance, whereas YOLOv5 was selected as the preferred detector for subsequent hybrid integration because it produced fewer false positives under reflective and textured microscopic backgrounds. YOLOv11 exhibited lower detection performance in the present setting, likely due to its architectural characteristics being less suited to the limited-data and high-background-complexity conditions of this study. In the present experimental setting, YOLOv5 achieved mAP@0.5 = 0.62, precision = 0.75, and recall = 0.69. For image-level classification, EfficientNetB0 achieved the highest classification accuracy of 93.10%, with F1-score = 0.932 and AUC = 0.986. In addition, Grad-CAM visualizations demonstrated that EfficientNetB0 consistently focused on physically meaningful dust-contaminated regions, thereby enhancing the interpretability of the classification results. Overall, the proposed hybrid framework integrating YOLOv5-based localization with EfficientNetB0-based defect confirmation showed promising potential for improving inspection reliability, false-alarm control, and explainability in automated VCMA quality inspection. These findings support the feasibility of explainable deep learning for microscopic defect inspection in HDD manufacturing and suggest its potential applicability to other precision manufacturing environments.