Intelligent Detection Algorithm Based on 2D/3D-UNet for Internal Defects of Carbon Fiber Composites

ABSTRACTABSTRACTInfrared thermography testing (IRT) has been widely used in the defect detection of composite materials. However, the identification of defects characteristics is unsatisfying due to the interference of factors such as uneven background and noise in the original thermal image sequence. A novel thermography-based defect detection method with the semantic segmentation network is proposed to enhance the defect contrast and extract perfect features. To Figure out the abnormal distribution of temperature field in thermal images, AG-UNet was used with a spatial self-attention gate module to extract spatial features of thermal images. The 3D-UNet network was obtained by the 3D convolution module and the temporal convolution module to extract thermal temporal and spatial features simultaneously which could help the defect segmentation in thermal videos. Compared with traditional algorithms such as principal component analysis (PCA), thermographic signal reconstruction (TSR), and fast Fourier transform (FFT), defects detection results were significantly enhanced with the proposed method, and defects of smaller diameter-to-depth ratio can be detected by deep learning models.KEYWORDS: Deep learningdefectinfrared thermographymachine vision Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationFundingThis work was supported in part by the National Natural Science Foundation of China (62101184), in part by Key Project of Scientific Research of Hunan Provincial Education Department (20A053), in part by Training Program for Excellent Young Innovators of Changsha (kq1802023), in part by the Open fund for key laboratories of colleges and universities in Fujian Province (S2-KF2012), in part by Hunan Provincial Natural Science Foundation (2023JJ70004), in part by Key R&D Plan of Hunan Province (2022GK2012) and in part by the National Key Research and Development Program of China under Grant 2022YFB330380.