Full
Outline
Targeting the problems of low efficiency, poor coverage, and insufficient accuracy in shield tunnel segment misalignment measurement, an automatic measurement algorithm integrating laser point cloud grayscale conversion with deep learning is proposed. This method can accurately measure segment misalignment, effectively reduce the risk of water leakage caused by misalignment, and maintain the service performance of tunnel structures. First, the collected three-dimensional laser point cloud is converted into grayscale images with enhanced edge features. Then, the lightweight EfficientNet network is utilized to efficiently identify the bounding boxes of inter-ring and intra-ring joints of segments. The bounding box coordinates are mapped to the three-dimensional point-cloud space to achieve precise segmentation and extraction of point clouds on both sides of segment joints. Finally, the average radial distances from the point clouds on both sides of joints to the center of the fitted ellipse of the tunnel segment structure are calculated respectively, with their difference representing the segment misalignment, enabling non-contact, high-precision measurement of shield tunnel segment misalignment. A tunnel structure inspection vehicle equipped with a three-dimensional laser scanner was developed, with the above algorithm integrated and supporting data acquisition and processing software developed. An engineering pilot application was conducted in a shield tunnel section of Hangzhou Metro Line 1, with laser scanning at a moving speed of 20 km/h. Comparative analysis between the inspection vehicle measurement results and manual measurement results shows that the two measurement results are close, with a maximum absolute deviation of 1.6 mm. This method can maintain high measurement accuracy even under high-speed movement conditions, meeting the industry demand for rapid, comprehensive detection of shield tunnel segment misalignment.
131
40
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62662699(Operation and Technical Support)
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
