Abstract
Bolts are widely applied to the connections of structural components. Under the actions of alternative forces induced by the external loads, the bolts are commonly inevitable to be loosening in engineering, which will be a threat to structural safety. To avoid the reduction of the pretightening force, it is vital to examine the status of bolts periodically. So far, manual inspection with a torque wrench is the most frequently used approach, even though it is time-consuming, labor-intensive, and low frequency of data acquisitions for structural maintenance. Due to the looseness of bolts which commonly follows with relative rotation between bolts and nuts, in this study, a vision-based bolt monitoring system with an Internet of Things (IoT) device is proposed. Specifically, to observe the relative rotation between bolts and nuts, a novel barcode marker (termed PAC-code) is introduced at first. As followed, a corresponding smart device embedded with PAC-code decoding algorithm is also described for the further long-term monitoring of bolt looseness. Finally, a laboratory-based experiment was carried out to validate the reliability and precision of our system. The results indicate that the proposed system is sensitive in the identification of angular changes and can be used to monitor the looseness of bolts as precise as 0.1°. This technique is not only easy to be deployed with high economic efficiency in engineering but also meaningful for the data acquisition in bolts looseness-proof research.
