• Smart Structures and Systems
• /
• v.21 no.4
• /
• pp.407-420
• /
• 2018

In structural health monitoring, it is meaningful to comprehensively utilize accelerometers and strain gauges to obtain the modal information of a structure. In this paper, a modal estimation theory is proposed, in which the displacement modes of the locations without accelerometers can be estimated by the strain modes of selected strain gauge measurements. A two-stage sensor placement method, in which strain gauges are placed together with triaxial accelerometers to obtain more structural displacement mode information, is proposed. In stage one, the initial accelerometer locations are determined through the combined use of the modal assurance criterion and the redundancy information. Due to various practical factors, however, accelerometers cannot be placed at some of the initial accelerometer locations; the displacement mode information of these locations are still in need and the locations without accelerometers are defined as estimated locations. In stage two, the displacement modes of the estimated locations are estimated based on the strain modes of the strain gauge locations, and the quality of the estimation is seen as a criterion to guide the selection of the strain gauge locations. Instead of simply placing a strain gauge at the midpoint of each beam element, the influence of different candidate strain gauge positions on the estimation of displacement modes is also studied. Finally, the modal assurance criterion is utilized to evaluate the performance of the obtained multitype sensor placement. A bridge benchmark structure is used for a numerical investigation to demonstrate the effectiveness of the proposed multitype sensor placement method.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.237-250
• /
• 2022

Structural health monitoring (SHM) plays an important role in ensuring the safety and functionality of critical civil infrastructure. In recent years, numerous researchers have conducted studies to develop computer vision and machine learning techniques for SHM purposes, offering the potential to reduce the laborious nature and improve the effectiveness of field inspections. However, high-quality vision data from various types of damaged structures is relatively difficult to obtain, because of the rare occurrence of damaged structures. The lack of data is particularly acute for fatigue crack in steel bridge girder. As a result, the lack of data for training purposes is one of the main issues that hinders wider application of these powerful techniques for SHM. To address this problem, the use of synthetic data is proposed in this article to augment real-world datasets used for training neural networks that can identify fatigue cracks in steel structures. First, random textures representing the surface of steel structures with fatigue cracks are created and mapped onto a 3D graphics model. Subsequently, this model is used to generate synthetic images for various lighting conditions and camera angles. A fully convolutional network is then trained for two cases: (1) using only real-word data, and (2) using both synthetic and real-word data. By employing synthetic data augmentation in the training process, the crack identification performance of the neural network for the test dataset is seen to improve from 35% to 40% and 49% to 62% for intersection over union (IoU) and precision, respectively, demonstrating the efficacy of the proposed approach.