Year-end Sale % OFF 
Abstract
In this study, we investigate a novel idea of using synthetic images of bolts which are generated from a graphical model to train a deep learning model for loosened bolt detection. Firstly, a framework for bolt-loosening detection using image-based deep learning and computer graphics is proposed. Next, the feasibility of the proposed framework is demonstrated through the bolt-loosening monitoring of a lab-scaled bolted joint model. For practicality, the proposed idea is evaluated on the real-scale bolted connections of a historical truss bridge in Danang, Vietnam. The results show that the deep learning model trained by the synthesized images can achieve accurate bolt recognitions and looseness detections. The proposed methodology could help to reduce the time and cost associated with the collection of high-quality training data and further accelerate the applicability of vision-based deep learning models trained on synthetic data in practice.
Highlights
Bolting is one of the most widely used fastening techniques for linking load-bearing members in civil structures
The study aims at reducing the time and cost associated with the collection of high-quality datasets and further accelerate the applicability of vision-based deep learning models trained on synthetic data in practice
Phase II is performed in four main steps: (a) the perspective distortion of the input image is corrected by the homography; (b) the detected bolts are cropped into sub-images; (c) the input image is corrected by the homography; (b) the detected bolts are cropped into sub-images; the bolt angles of the cropped images are estimated by the Hough transform; and, (d) loosened bolts are identified by computing the rotations of the detected bolts
Summary
Bolting is one of the most widely used fastening techniques for linking load-bearing members in civil structures. The above studies have demonstrated the feasibility and the applicability of vision-based deep learning approaches for on-site structural monitoring Researchers have put their efforts into developing vision-based deep learning approaches for loosened bolt detection in bolted joints. The limited number of labelled datasets will cause difficulties to generalize a trained deep learning model across a wide variety of structures and environmental conditions [7]. We investigate a novel idea to use synthetic datasets to train a vision-based deep learning model for loosened bolt detection. The study aims at reducing the time and cost associated with the collection of high-quality datasets and further accelerate the applicability of vision-based deep learning models trained on synthetic data in practice. The proposed idea is evaluated on the real-scale bolted connections of a historical bridge in Danang, Vietnam
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
