Precise identification of delamination defect based on optimized deep learning method to understand mechanical property reduction

Ceramic matrix composites are advanced thermal structural materials used in aerospace and other fields due to their excellent performance. However, the common delamination defects in the interior can easily lead to material failure, posing significant threats to component reliability. Addressing this issue requires the development of precise and intelligent methodologies for the rapid identification of delamination defects and the evaluation of their impact on mechanical properties. In this study, delamination defects were intentionally introduced into SiC_f/SiC composites to facilitate intelligent identification and quantitative analysis. We propose a novel network combining Mamba and Convolutional Neural Network, which surpasses existing models in defect segmentation by precisely capturing both global and local information, while optimizing computational efficiency and memory usage. Mechanical tests reveal that variations in delamination defects lead to an initial reduction followed by an increase in both tensile and compressive strengths. The minimum tensile and compressive strengths are 69.30 % and 74.30 % of those in non-defective control samples, respectively. Tensile strength is more sensitive to defect volume, as the reduced crack propagation path facilitates premature tensile fracture of the fibers, whereas compressive strength is more affected by defect depth due to compressive instability and stress concentration. This strategy provides a novel avenue for the intelligent identification and risk assessment of delamination defects in ceramic matrix composites.