Translator Disclaimer
Presentation + Paper
8 April 2016 Bolt-loosening identification of bolt connections by vision image-based technique
Author Affiliations +
In this study, an algorithm using image processing techniques is proposed to identify bolt-loosening in bolted connections of steel structures. Its basic concept is to identify rotation angles of nuts from a pictured image, and is mainly consisted of the following 3 steps: (1) taking a picture for a bolt joint, (2) segmenting the images for each nut by image processing techniques, and (3) identifying rotation angle of each nut and detecting bolt-loosening. By using the concept, an algorithm is designed for continuous monitoring and inspection of the bolt connections. As a key imageprocessing technique, Hough transform is used to identify rotation angles of nuts, and then bolt-loosening is detected by comparing the angles before and after bolt-loosening. Then the applicability of the proposed algorithm is evaluated by experimental tests for two lab-scaled models. A bolted joint model which consists of a splice plate and 8 sets of bolts and nuts with 2×4 array is used to simulate inspection of bridge connections, and a model which is consisted of a ring flange and 32 sets of bolt and nut is used to simulate continuous monitoring of bolted connections in wind turbine towers.
Conference Presentation
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Tuan-Cuong Nguyen, Thanh-Canh Huynh, Joo-Young Ryu, Jae-Hyung Park, and Jeong-Tae Kim "Bolt-loosening identification of bolt connections by vision image-based technique", Proc. SPIE 9804, Nondestructive Characterization and Monitoring of Advanced Materials, Aerospace, and Civil Infrastructure 2016, 980413 (8 April 2016);

Back to Top