A transfer learning object detection model for defects detection in X-ray images of spacecraft composite structures

• Published in: Composite structures Vol. 284; p. 115136
• Main Authors: Gong, Yanfeng, Luo, Jun, Shao, Hongliang, Li, Zhixue
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 15.03.2022
• Subjects: Defect detection; Object detection; Spacecraft composite structures; Transfer learning; X-ray image; X-ray image; Spacecraft composite structures; Transfer learning; Object detection; Defect detection
• ISSN: 0263-8223; 1879-1085
• DOI: 10.1016/j.compstruct.2021.115136

•An improved deep transfer learning model is proposed for spacecraft composite structures.•Our method can detect inclusion and void defects. It still applies if there are enough samples of other types of defects.•Small-size defects can be detected using the proposed method.•It is suitable for the small-scale sample dataset. This is important in the application. Usually, defect detection in X-ray images of composite materials is mainly performed by humans, which is time consuming and inefficient. Some deep learning methods have been proposed, but they are only used to identify a certain type of defect or need a large number of training samples. Besides, the size of void and inclusion defects in X-ray images of spacecraft composite structures (SCS) is very small, which is difficult for common object detection methods, especially when the number of training samples is small. Thus, we propose a transfer learning object detection model for detection of both of these defects. Based on domain adaptive Faster R-CNN (DA Faster), the feature pyramid network (FPN) is added into the feature extraction sub-module for multi-scale features adaptation, and small anchor strategies and ROI Align are utilized, which are helpful for localization of small-size defects. Besides, big NMS threshold and conditional domain adaptation (CDAN) is adopted in the box classification branch for more accurate features alignment. The experiment results demonstrate that strong ability of the proposed model in detecting small-size void and inclusion defects of SCS.