Fatigue failure is a significant problem in the structural safety of engineering structures. Human inspection is the most widely used approach for fatigue failure detection, which is time consuming and subjective. Traditional vision-based methods are insufficient in distinguishing cracks from noises and detecting crack tips. In this paper, a new framework based on convolutional neural networks (CNN) and digital image processing is proposed to monitor crack propagation length. Convolutional neural networks were first applied to robustly detect the location of cracks with the interference of scratch and edges. Then, a crack tip-detection algorithm was established to accurately locate the crack tip and was used to calculate the length of the crack. The effectiveness and precision of the proposed approach were validated through conducting fatigue experiments. The results demonstrated that the proposed approach could robustly identify a fatigue crack surrounded by crack-like noises and locate the crack tip accurately. Furthermore, crack length could be measured with submillimeter accuracy.

The accurate and efficient segmentation of large-scale urban point clouds is crucial for many higher-level tasks, such as boundary line extraction, point cloud registration, and deformation measurement. In this paper, we propose a novel supervoxel segmentation approach to address the problem of under-segmentation in local regions of point clouds at various resolutions. Our approach introduces distance constraints from boundary points to supervoxel planes in the merging stage to enhance boundary segmentation accuracy between non-coplanar supervoxels. Additionally, supervoxels with roughness above a threshold are re-segmented using random sample consensus (RANSAC) to address multi-planar coupling within local areas of the point clouds. We tested the proposed method on two publicly available large-scale point cloud datasets. The results show that the new method outperforms two classical methods in terms of boundary recall, under-segmentation error, and average entropy in urban scenes.

Pipe structures are at the base of the entire industry. In the industry structure, heat and vibration are transmitted in each pipe. The minimum distance between each pipe is significant to the security. The assembly error and the deformation of the pipeline positions after multiple runs are significant problems. The reconstruction of the multi-pipe system is a critical technical difficulty in the complex tube system. In this paper, a new method for the multi-pipes structure inspection is presented. Images of the tube system are acquired from several positions. The photogrammetry technology calculates positions, and the necessary coordination of the structure is reconstructed. A convolution neural network is utilized to detect edges of tube-features. The new algorithm for tube identification and reconstruction is presented to extract the tube feature in the image and reconstruct the 3D parameters of all tubes in a multi-pipes structure. The accuracy of the algorithm is verified by simulation experiments. An actual engine of the aircraft is measured to verify the proposed method.