Paper
12 March 2020 Automatic segment assembly in shield method using multiple imaging sensors
Author Affiliations +
Abstract
The shield method is one of subsurface excavation method in underground construction. It’s a fully mechanized construction method using shield machine. However, the process of segment assembly now mainly relies on manual work, controlling the assembly robots by experience. This work aims to aid the automation of precise movement control of the assembly robot, especially the movements of sliding, rotating, and deflecting directions. It proposes a new method using multiple imaging sensors to collect image information needed for automatic assembly of segments, and uses information extraction, size measurement and other real-time image processing to determine the spatial attitude of the three directions of the segments to be assembled. By Importing the data into an automation solution, the segments could move along the correct path. Experiments are conducted to test the performance and reliability of the proposed method in an actual underground working environment. The results are validated by successful bolting process in the actual subway construction, showing several different types of segments can move to the correct assembly position and the process is reproducible. Some disadvantages of the method are discussed, and suggestions for improvements are suggested. The proposed method has the potential to be adopted to enable the automation of segment assembly in shield method and may be applied to actual construction.
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Kaixian Dong, Shundong Yang, Shuang Wang, Junfeng Jiang, Kun Liu, Zhiyang Wu, Jie Zhou, and Tiegen Liu "Automatic segment assembly in shield method using multiple imaging sensors", Proc. SPIE 11439, 2019 International Conference on Optical Instruments and Technology: Optoelectronic Measurement Technology and Systems, 114391H (12 March 2020); https://doi.org/10.1117/12.2550087
Lens.org Logo
CITATIONS
Cited by 1 scholarly publication.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image segmentation

Optical sensors

Image sensors

Neural networks

Real time image processing

Reliability

RELATED CONTENT

Compact disc serial number inspection system
Proceedings of SPIE (September 02 1993)
Ridge-flow determination in fingerprint images
Proceedings of SPIE (February 25 1994)
Real-Time Road Surveillance By An Optical Sensor
Proceedings of SPIE (April 11 1988)
Classifier fusion for multisensor image recognition
Proceedings of SPIE (January 19 2001)

Back to Top