Search

Accurate 3D representations of multiphase layered composite fabric, including distinguish and label the pores, matrices, warp and weft yarns, can assist in understanding and ultimately improving composite material design performance. In this work, a new data enhancement algorithm is proposed to generate realistic-looking artificial learning datasets for expanding the datasets. Then, we demonstrate how supervised, the Swin Transformer approach can help to realize accurate segmentation of low-resolution and poor-contrast fabric datasets by populating databases with real and artificial learning datasets. Most of the pixels were correctly identified and the boundaries of the yarn could be identified clearly, except for some spots and a few merged boundaries. The work presented here provides an effective tool that can be widely used in semantic segmentation for various composite materials (woven composites, fiber-reinforced composites, short-fiber materials, etc.), which enables higher-precision reconstruction of fiber-composites and significant reduction in dataset processing time, and provides a route to generating artificial learning dataset. [ABSTRACT FROM AUTHOR]

• Advantages of symmetric intercalation hybridization on impact strength and resilience. • Correlation of apparent damage area index and internal damage volume data. • Damage mechanism of symmetric and asymmetric carbon/Kevlar structures. Hybrid fiber composite laminates with the same materials, manufacturing methods and molding processes may present different mechanical behaviors. In this paper, the effect of intercalation sequence on the mechanical performance of carbon/Kevlar plain laminates were studied. According to different intercalation methods, the hybrid layout was divided into symmetric and asymmetric configurations. It is found that the symmetric intercalation structures (KCCK and CKKC) possess better load-bearing and resilience capacity compared with asymmetric structures (CCKK and CKCK), even better than pure carbon structure (CCCC) under high energy impact. The impact damage volume of symmetric specimens was significantly smaller than that of asymmetric specimens by quantitative micro-CT analysis. The apparent damage index (d f and d r) can be used to estimate the internal damage data (d CT , H and V). KCCK, a typical symmetric sandwich-like structure, presented the most slight damage among all symmetric and asymmetric configurations, with shear cracks observed at the brittle carbon fiber core layers, while the delamination cracks between Kevlar-carbon interlayers were away from the central damaged region. In CKCK, interlaminar cracks were formed at each carbon-Kevlar interlayers, which shared and relieved the primary interlaminar crack at the core layers compared with CCKK. [ABSTRACT FROM AUTHOR]