In this study, a preload monitoring method using impedance signatures obtained from a piezoelectric-based smart interface is presented for bolted girder connections. Firstly, the background theory of the piezoelectric-based smart interface and its implementation into the health monitoring of bolted connections are outlined. A simplified electro-mechanical (EM) impedance model of a smart interface-embedded bolted connection system is formulated to interpret a mechanistic understanding of the EM impedance signatures under the effect of bolt preload. Secondly, finite element modeling of a bolted connection is carried out to show the numerical feasibility of the presented method, and to predetermine the sensitive frequency band of the impedance signatures. Finally, impedance measurements are conducted on a lab-scaled bolted girder connection, to verify the predetermined sensitive frequency range and to assess the bolt preload changes in the test structure.

In this study, we investigate a novel idea of using synthetic images of bolts which are generated from a graphical model to train a deep learning model for loosened bolt detection. Firstly, a framework for bolt-loosening detection using image-based deep learning and computer graphics is proposed. Next, the feasibility of the proposed framework is demonstrated through the bolt-loosening monitoring of a lab-scaled bolted joint model. For practicality, the proposed idea is evaluated on the real-scale bolted connections of a historical truss bridge in Danang, Vietnam. The results show that the deep learning model trained by the synthesized images can achieve accurate bolt recognitions and looseness detections. The proposed methodology could help to reduce the time and cost associated with the collection of high-quality training data and further accelerate the applicability of vision-based deep learning models trained on synthetic data in practice.

In this study, the quantification of temperature effect on impedance monitoring via a PZT interface for prestressed tendon-anchorage is presented. Firstly, a PZT interface-based impedance monitoring technique is selected to monitor impedance signatures by predetermining sensitive frequency bands. An analytical model is designed to represent coupled dynamic responses of the PZT interface-tendon anchorage system. Secondly, experiments on a lab-scaled tendon anchorage are described. Impedance signatures are measured via the PZT interface for a series of temperature and prestress-force changes. Thirdly, temperature effects on measured impedance responses of the tendon anchorage are estimated by quantifying relative changes in impedance features (such as RMSD and CCD indices) induced by temperature variation and prestress-force change. Finally, finite element analyses are conducted to investigate the mechanism of temperature variation and prestress-loss effects on the impedance responses of prestressed tendon anchorage. Temperature effects on impedance monitoring are filtered by effective frequency shift-based algorithm for distinguishing prestress-loss effects on impedance signatures.

In this paper, a portable PZT interface for tension force monitoring in the cable‐anchorage subsystem is developed. Firstly, the theoretical background of the impedance‐based method is presented. A few damage evaluation approaches are outlined to quantify the variation of impedance signatures. Secondly, a portable PZT interface is designed to monitor impedance signatures from the cable‐anchorage subsystem. One degree‐of‐freedom analytical model of the PZT interface is established to explain how to represent the loss of cable force from the change in the electromechanical impedance of the PZT interface as well as reducing the sensitive frequency band by implementing the interface device. Finally, the applicability of the proposed PZT‐interface technique is experimentally evaluated for cable force‐loss monitoring in a lab‐scaled test structure.

In this study, a regional convolutional neural network (RCNN)-based deep learning and Hough line transform (HLT) algorithm are applied to monitor corroded and loosened bolts in steel structures. The monitoring goals are to detect rusted bolts distinguished from non-corroded ones and also to estimate bolt-loosening angles of the identified bolts. The following approaches are performed to achieve the goals. Firstly, a RCNN-based autonomous bolt detection scheme is designed to identify corroded and clean bolts in a captured image. Secondly, a HLT-based image processing algorithm is designed to estimate rotational angles (i.e., bolt-loosening) of cropped bolts. Finally, the accuracy of the proposed framework is experimentally evaluated under various capture distances, perspective distortions, and light intensities. The lab-scale monitoring results indicate that the suggested method accurately acquires rusted bolts for images captured under perspective distortion angles less than 15° and light intensities larger than 63 lux.