The bolt-loosening detection method using vision-based technique is summarized and a new gray gradient enhancement method is proposed to improve the stability of the nut edge detection and bolt-loosening detection. The Influence of the thresholds in Canny edge detector is studied and a new gray gradient enhancement method is proposed to enhance the gray gradient at the pixels on the outer boundary of the nut. Meanwhile, the suggestion on the high threshold value in Canny edge detector is given and can be used to reduce the subjectivity of parameter determination in Canny detector and the interference of uninterested edge lines. The proposed method is verified using a bolt connection in laboratory. The results show that the proposed method can effectively highlight the outer boundary of the nut and improve the stability of the nut edge detection and bolt-loosening detection.
AnYKKimMKSohnH (2012) Airplane hot spot monitoring using integrated impedance and guided wave measurements. Structural Control and Health Monitoring19(7): 592–604.
2.
ChenKTsaiHLiuY (2008) Development of the RFID System for nuclear materials management. In: Proceedings of the 49th Institute of Nuclear Materials Management (INMM) Annual Meeting, Nashville, TN, 13–17 July 2008.
3.
ChaYJYouKChoiW (2016) Vision-based detection of loosened bolts using the Hough transform and support vector machines. Automation in Construction71(2): 181–188.
4.
DudaROHartPE (1972) Use of the Hough transformation to detect lines and curves in pictures. Cacm15(1): 11–15.
5.
HoDDNguyenTHLeQH (2017) Bolt-loosening detection in steel column connections using impedance responses. Congrès International de Géotechnique–Ouvrages–Structures. Springer, Singapore. October.
6.
HuynhTCParkJHJungHJ, et al. (2019) Quasi-autonomous bolt-loosening detection method using vision-based deep learning and image processing. Automation in Construction105: 102844.
7.
HaiCPTaQBKimJT, et al. (2020) Bolt-loosening monitoring framework using an image-based deep learning and graphical model. Sensors20(12): 3382.
8.
IkhlasAQOsamaAMichaelEK (2003) Analysis of edge-detection techniques for crack identification in bridges. Journal of Computing in Civil Engineering17(4): 255–263.
LiuGMaoZToddM, et al. (2014) Localization of nonlinear damage using state-space-based predictions under stochastic excitation. Smart Materials and Structures23(2): 204–204.
11.
LohCHLohKJYangYS, et al. (2017) Vibration-based system identification of wind turbine system. Structural Control and Health Monitoring24(3): e1876–e1876.19.
12.
MottersheadJELinkMFriswellMI (2011) The sensitivity method in finite element model updating: a tutorial. Mechanical Systems and Signal Processing25(7): 2275–2296.
13.
NguyenTCHuynhTCRyuJY, et al. (2016) Bolt-loosening identification of bolt connections by vision image-based technique. In: Proceedings of SPIE- Nondestructive Characterization and Monitoring of Advanced Materials, Aerospace, and Civil Infrastructure, 8 April 2016, Las Vegas, Nevada, United States.
14.
NguyenTCHuynhTCYiJH, et al. (2017) Hybrid bolt-loosening detection in wind turbine tower structures by vibration and impedance responses. Wind & Structures An International Journal24(4): 385–403.
15.
ParkKTYuYJShinH, et al. (2011) Monitoring system for bolt joints on steel structures. In: SPIE Smart Structures and Materials+ Nondestructive Evaluation and Health Monitoring, 14 April 2011, San Diego, CA, USA.
16.
RamanaLChoiWChaYJ (2018) Fully automated vision-based loosened bolt detection using the Viola-Jones algorithm. Structural Control and Health Monitoring18(2): 1–13.
17.
RamanaLChoiWChaYJ (2019) Fully automated vision-based loosened bolt detection using the Viola-Jones algorithm. Structural Health Monitoring18(2): 422–434.
18.
TrendafilovaIHeylenW (2003) Categorisation and pattern recognition methods for damage localisation from vibration measurements. Mechanical Systems and Signal Processing17(4): 825–836.
19.
TsaiHCChenKLiuY, et al. (2008) Applying RFID technology in nuclear materials management. Packaging, Transport, Storage and Security of Radioactive Material19(1): 41–46.
20.
WuJCuiXXuY (2016) A novel RFID-based sensing method for low-cost bolt loosening monitoring. Sensors16(2): 168–183.
21.
YuenKV (2010) Recent developments of bayesian model class selection and applications in civil engineering. Structural Safety32(5): 338–346.
22.
ZhangYZhangXChenJ, et al. (2017) Electro-mechanical impedance based position identification of bolt loosening using LibSVM. Intelligent Automation & Soft Computing24(1): 1–7.
23.
ZhaoXZhangYWangN (2018) Bolt loosening angle detection technology using deep learning. Structural Control and Health Monitoring26(1): e2292.
24.
ZhangYZhaoXSunX, et al. (2019) Bolt loosening detection based on audio classification. Advances in Structural Engineering22(13): 2882–2891.
25.
ZhangYSunXLohK, et al. (2020) Autonomous bolt loosening detection using deep learning. Structural Health Monitoring19(1): 105–122.
