Buy article PDF
The purchased file will be sent to you
via email after the payment is completed.
US$ 35
|
Smart Structures and Systems Volume 27, Number 5, May 2021 , pages 783-793 DOI: https://doi.org/10.12989/sss.2021.27.5.783 |
|
|
|
Detection and quantification of bolt loosening using RGB-D camera and Mask R-CNN |
||
Junyeon Chung and Hoon Sohn
|
||
| Abstract | ||
| Bolt loosening is one of the most common types of damage for bolt-connected plates. Existing vision techniques detect bolt loosening based on the measurement of bolt rotation or the exposure of bolt threads. However, these techniques examine bolt tightness only in a qualitative manner, or require a reference measurement at the initially tightened state of the bolt for quantitative estimation. In this study, the exposed shank length of a bolt is quantitatively measured using an RGB-depth camera and a mask-region-based convolutional neural network but without requiring any measurement from the initial state of the bolt. The performance of the proposed technique is validated by conducting lab-scale experiments, in which the angle and distance of the camera are varied with respect to a target inspection area. The proposed technique successfully detects bolt loosening at exposed shank length over 3 mm with a resolution of 1 mm and 97% accuracy at different camera angles (40°–90°) and distances (up to 65 cm). | ||
| Key Words | ||
| bolt-loosening detection; bolt-loosening quantification; RGB-depth camera; Mask R-CNN; deep learning | ||
| Address | ||
| Department of Civil and Environmental Engineering, Korea Advanced Institute for Science and Technology, Daejeon 34141, South Korea. | ||