Yu Yabin, Liu Ying, Chen Jiawei, Jiang Dong, Zhuang Zilong, Wu Xiaoli
College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, China.
Sensors (Basel). 2021 Apr 29;21(9):3106. doi: 10.3390/s21093106.
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.
螺栓连接在木结构中广泛应用。螺栓松动是导致结构失效的最重要因素之一。目前，大多数螺栓松动检测方法在成本和准确性之间未能实现良好平衡。本文利用深度学习和机器视觉技术研究木结构中螺栓小角度松动的检测方法。首先，设计了三种方案，识别目标分别为螺母自身规格编号、矩形标记和圆形标记。采用单阶段多框检测器（SSD）算法训练图像数据集。识别角度误差最小的方案是识别圆形物体的方案，其识别角度误差为0.38°。然后，进一步提高识别精度，最小识别角度达到1°。最后，对四螺栓连接和八螺栓连接中的松动情况进行测试，证实了该方法应用于多螺栓连接时的可行性，并实现了低运营成本和高精度。
