Abstract
Bolted connections are widely used in timber structures. Bolt looseness is one of the most important factors leading to structural failure. At present, most of the detection methods for bolt looseness do not achieve a good balance between cost and accuracy. In this paper, the detection method of small angle of bolt loosening in a timber structure is studied using deep learning and machine vision technology. Firstly, three schemes are designed, and the recognition targets are the nut’s own specification number, rectangular mark, and circular mark, respectively. The Single Shot MultiBox Detector (SSD) algorithm is adopted to train the image datasets. The scheme with the smallest identification angle error is the one identifying round objects, of which the identification angle error is 0.38°. Then, the identification accuracy was further improved, and the minimum recognition angle reached 1°. Finally, the looseness in a four-bolted connection and an eight-bolted connection are tested, confirming the feasibility of this method when applied on multi-bolted connection, and realizing a low operating costing and high accuracy.
Highlights
For the deep learning algorithm, the evaluation of the model was mainly based on parameters such as loss, average precision (AP), and mean AP (MAP)
Loss refers to the errors between the predicted results and the actual results in the training sets, AP is the identification accuracy of each class, and MAP represents the average identification accuracy of all of the classes
The detection method of small angle of loosening for timber structure bolts based on deep learning was studied
Summary
In terms of the advantages of reliability and convenience, bolted connections are widely applied in timber structures. Wood packaging cases are impacted by continuous vibrations load during transportation, which causes bolted connections to loosen. The connections within could fail on account of the continuous vibration loads; research on the detection methods of timber structure bolt connection loosening is of great significance. The detection methods of bolt loosening are mainly divided into two methods—direct detection and indirect detection. The two key parameters in the direct detection method are axial force and applied torque. Most of these methods were proposed a long time ago, but they are still used in various industries. Goodier and Sauer et al [1,2]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
