Search for: All records

Abstract Surface defect identification is a crucial task in many manufacturing systems, including automotive, aircraft, steel rolling, and precast concrete. Although image-based surface defect identification methods have been proposed, these methods usually have two limitations: images may lose partial information, such as depths of surface defects, and their precision is vulnerable to many factors, such as the inspection angle, light, color, noise, etc. Given that a three-dimensional (3D) point cloud can precisely represent the multidimensional structure of surface defects, we aim to detect and classify surface defects using a 3D point cloud. This has two major challenges: (i) the defects are often sparsely distributed over the surface, which makes their features prone to be hidden by the normal surface and (ii) different permutations and transformations of 3D point cloud may represent the same surface, so the proposed model needs to be permutation and transformation invariant. In this paper, a two-step surface defect identification approach is developed to investigate the defects’ patterns in 3D point cloud data. The proposed approach consists of an unsupervised method for defect detection and a multi-view deep learning model for defect classification, which can keep track of the features from both defective and non-defective regions. We prove that the proposed approach is invariant to different permutations and transformations. Two case studies are conducted for defect identification on the surfaces of synthetic aircraft fuselage and the real precast concrete specimen, respectively. The results show that our approach receives the best defect detection and classification accuracy compared with other benchmark methods. 

Abstract We conducted simulations with a 4‐km resolution for Hurricane Joaquin in 2015 using the weather research and forecast (WRF) model. The model data are used to study stratospheric gravity waves (GWs) generated by the hurricane and how they correlate with hurricane intensity. The simulation results show spiral GWs propagating upward and anticlockwise away from the hurricane center. GWs with vertical wavelengths up to 14 km are generated. We find that GW activity is more frequent and intense during hurricane intensification than during weakening, particularly for the most intense GW activity. There are significant correlations between the change of stratospheric GW intensity and hurricane intensity. Therefore, the emergence of intensive stratospheric GW activity may be considered a useful proxy for identifying hurricane intensification.