Point cloud-based virtual assembly: a framework for shield segment inspection

Abstract The three-ring horizontal assembly test is essential to evaluate the accumulation of manufacturing errors in shield segments. However, traditional manual assembly suffers from poor precision and low efficiency. In response to the practical demands of the tunneling industry, this article proposes a point cloud-based, automated assembly framework for shield segments. To address practical engineering challenges in the proposed assembly framework, this study proposes three innovative methods. To address the uncertainty in the pose of scanned point clouds, a unified main direction positioning method based on structural features (UMDP) is proposed to achieve unified calibration of point cloud poses. To meet the requirement of assembling discrete segments into a smooth lining ring, a joint assembly method based on curvature consistency and seam vector is presented to integrate segments into a continuous smooth ring structure. To solve the gap coupling problem in inter-ring assembly, an inter-ring assembly method based on key surface positioning and iterative adjustment (KPIA) is developed to obtain the segment pose that meets engineering standards. Experiments conducted on a Redmi G Pro 2022 laptop equipped with an AMD Ryzen 7 6800 H processor and 16 GB of RAM demonstrated that the assembly test of three rings containing 7.17 × 10 8 points could be accomplished with 180.85 s with the assembly accuracy strictly controlled within 1 mm. Thus, the proposed framework offers an efficient and practical approach to assessing segment dimensions.