Bolts looseness detection in construction machinery. Issue 1 (1st January 2023)

• Record Type: Journal Article
• Authors: Song, Yancheng; Liu, Guangjun; Wang, Yunfei
• Is Part Of: Journal of physics. Volume 2419:Issue 1(2023)
• Publication Date: 2023-01-01
• Subjects: Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/2419/1/012068
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: Bolt connections have increasingly wide applications in the mechanical industry, such as civil construction, construction machinery, etc. However, along with the vibration of the mechanical operation, bolt looseness is unavoidable and thus can lead to severe consequences. Therefore, the detection of loose bolts deserves an in-depth study. However, conventional bolt looseness detection techniques require a lot of time and labor, and direct contact sensor-based detection techniques are sensitive to interference from the surroundings. To tackle these challenges mentioned above, this work proposes a vision-based bolt looseness detection method, with the advantages of low cost, easy deployment, and non-contact. Specifically, an innovative attention mechanism is introduced into the Yolov4 framework to improve the accuracy and speed of bolt detection. Each bolt image is cropped by the recognition result of the detector, then the bolt contour is extracted by edge detection, and the bolt is determined to be loose or not based on the angle of bolt rotation. Comprehensive experiments in real-world settings verify the effectiveness and efficiency of the proposed method.