<<
[an error occurred while processing this directive] | [an error occurred while processing this directive] >>
Research on Automatic Detection Technology for Shield Tunnel Segment Misalignment Based on Point Cloud Data
（1. National Engineering Research Center of High-Speed Railway Construction Technology, Changsha 410075； 2. China Railway Group Limited, Beijing 100039；3. China Railway Academy Group Co., Ltd, Chengdu 610032； 4. China Railway Southwest Research Institute Co., Ltd., Chengdu 611731； 5. Sichuan Communication Survey & Design Institute Co., Ltd., Chengdu 610017）
Abstract Segment misalignment is a common defect in shield tunnels. To detect the segment misalignment in shield tunnels, this paper proposes an automatic detection method based on point cloud data. The method involves unfolding the 3D laser point cloud data of the tunnel into a 2D grayscale image, automatically identifying the circumferential joint positions using image processing and Hough transformation, extracting the cross-sectional point clouds on both sides of the circumferential joints, fitting the cross-sections using an improved least squares algorithm, and finally calculating the misalignment through cross-section matching. The research results demonstrate that this method can accurately detect the misalignment on both sides of the segment circumferential joints, with an overall detection accuracy within 5 millimeters and a manual verification accuracy rate exceeding 90%. This method provides an effective means for the automated detection of segment misalignment in shield tunnels.
Abstract：
Segment misalignment is a common defect in shield tunnels. To detect the segment misalignment in shield tunnels, this paper proposes an automatic detection method based on point cloud data. The method involves unfolding the 3D laser point cloud data of the tunnel into a 2D grayscale image, automatically identifying the circumferential joint positions using image processing and Hough transformation, extracting the cross-sectional point clouds on both sides of the circumferential joints, fitting the cross-sections using an improved least squares algorithm, and finally calculating the misalignment through cross-section matching. The research results demonstrate that this method can accurately detect the misalignment on both sides of the segment circumferential joints, with an overall detection accuracy within 5 millimeters and a manual verification accuracy rate exceeding 90%. This method provides an effective means for the automated detection of segment misalignment in shield tunnels.
ZHOU Bin1,
2,
3 etc
.Research on Automatic Detection Technology for Shield Tunnel Segment Misalignment Based on Point Cloud Data[J] MODERN TUNNELLING TECHNOLOGY, 2025,V62(1): 83-91
2025, Vol. 62 