Multimodal data fusion enhanced deep learning prediction of crack path segmentation in CFRP composites

Carbon fiber-reinforced polymer (CFRP) composites are extensively used in various engineering applications due to their superior strength-to-weight ratio and excellent mechanical properties. Predicting crack propagation paths in CFRP composites is a complex challenge due to their multiphase nature a...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Composites science and technology Ročník 257; s. 110812
Hlavní autoři:	Zhang, Peng, Tang, Keke, Chen, Guangxu, Li, Jiangfeng, Li, Yan
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier Ltd 20.10.2024
Témata:	Composite materials Crack path prediction Deep learning Multimodal data fusion Segmentation Deep learning Crack path prediction Composite materials Segmentation Multimodal data fusion
ISSN:	0266-3538
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Carbon fiber-reinforced polymer (CFRP) composites are extensively used in various engineering applications due to their superior strength-to-weight ratio and excellent mechanical properties. Predicting crack propagation paths in CFRP composites is a complex challenge due to their multiphase nature and intricate microstructural interactions. While finite element (FE) simulations possess significant capabilities for this purpose, they entail substantial computational demands and extended execution times, thereby limiting their viability in applications with high computational requirements. To address this challenge, we propose an end-to-end deep learning framework specifically for predicting crack propagation paths in two-dimensional CFRP composites. Drawing inspiration from semantic segmentation techniques, we employ EfficientNet for feature extraction, enabling the capture of hierarchical and multiscale features from both microstructure images and stress field distributions. A key aspect of our framework is the utilization of multimodal data fusion and self-attention mechanisms to effectively integrate these diverse data sources. The results demonstrate the effectiveness of our multimodal feature integration approach, producing accurate segmentations of crack path. This novel framework offers a promising approach to understanding and predicting failure mechanisms in composite materials, with significant implications for the design and maintenance of advanced composite structures. [Display omitted] •Deep learning encoder-decoder with multimodal fusion and self-attention for crack path prediction in CFRP.•Semantic segmentation-inspired techniques for damage region identification using microstructure and stress data.•Custom preprocessing to convert high-resolution images to binary crack maps, addressing data imbalance.
ISSN:	0266-3538
DOI:	10.1016/j.compscitech.2024.110812