Recurrence analysis of 3D point clouds for the detection of surface anomalies in advanced manufacturing

Abstract

Due to tool wear, machine malfunction, and other internal and external factors, surface anomalies are widely observed in diverse manufacturing processes, such as machining, stamping, and additive manufacturing. The detection of surface anomalies remains an important challenge for assuring the quality and reliability of manufacturing products. Conventional image-based approaches lack the ability to fully capture the 3-dimensional (3D) morphologies of surface defects, which hinder their applications in defect identification, characterization, and diagnosis. The emerging 3D sensing technologies, such as laser or structured-light scanning, enable the collection of point clouds, which embodies a comprehensive representation of defect-altered surface morphologies in 3D space. However, scanned point cloud data are unstructured and oftentimes contain large numbers of points, which pose significant challenges for the recognition of defective surface patterns. To address the challenges, this study develops a recurrence-based approach for the representation learning of 3D point clouds to detect surface defects in manufactured products. Specifically, with a scanned point cloud, key points are first extracted using a voxel-based sampling strategy, and each key point and its neighboring points form a localized sub-region. Then, a recurrence network is generated through a tailored approach, which considers both the morphology similarity and spatial closeness of sub-regions. For anomaly detection, a tensor-based one-class classification model is further deployed to distinguish abnormal surface patterns from normal ones. The developed methodology is experimentally evaluated through simulation and real-world case studies. Experimental results have demonstrated that the developed methodology outperforms benchmarks, highlighting its efficacy in the detection of surface anomalies.