Wireless sensors are the key components of structural health monitoring systems. During the signal transmission, sensor failure is inevitable, among which, data loss is the most common type. Missing data problem poses a huge challenge to the consequent damage detection and condition assessment, and therefore, great importance should be attached. Conventional missing data imputation basically adopts the correlation-based method, especially for strain monitoring data. However, such methods often require delicate model selection, and the correlations for vehicle-induced strains are much harder to be captured compared with temperature-induced strains. In this article, a novel data-driven generative adversarial network (GAN) for imputing missing strain response is proposed. As opposed to traditional ways where correlations for inter-strains are explicitly modeled, the proposed method directly imputes the missing data considering the spatial–temporal relationships with other strain sensors based on the remaining observed data. Furthermore, the intact and complete dataset is not even necessary during the training process, which shows another great superiority over the model-based imputation method. The proposed method is implemented and verified on a real concrete bridge. In order to demonstrate the applicability and robustness of the GAN, imputation for single and multiple sensors is studied. Results show the proposed method provides an excellent performance of imputation accuracy and efficiency.

With the development of the Chinese transportation industry, the number of bridges has increased significantly, but this results in high pressure of structural maintenance and management. Bridge management system (BMS) is critical for efficient maintenance and ensured safety of bridge structures during long-term operation. Building information modeling (BIM) is an emerging technology with powerful visualization and informatization capability, making it an ideal tool for developing modern management systems. This paper introduces the development of a bridge management system based on the BIM technology. Industry Foundation Classes (IFC) and International Framework for Dictionaries (IFD) standards are studied and extended, and coding rules are proposed for the Chinese bridge industry. Also, a standard structural modeling method is proposed to fast build the bridge BIM model. Web-BIM oriented bridge management is proposed, and portable devices are introduced into the system. Collaborative management is realized for different users. The BIM-based maintenance management system is designed. Finally, a practical BIM-based BMS is established for a long-span cable-stayed bridge in China. This system integrates the BIM with the geographic information system (GIS) and contains information management, inspection management, technical condition evaluation, and enables users to cooperate with each other. Such a BMS could help to improve the management efficiency and ensure its normal operation, providing a useful platform for the maintenance of massive bridges in China.

Since physical parameters are much more sensitive than modal parameters, structural parameter identification with an extended Kalman filter (EKF) has received extensive attention in structural health monitoring for civil engineering structures. In this paper, EKF-based parameter identification technique is studied with numerical and experimental approaches. A four-degree-of-freedom (4-DOF) system is simulated and analyzed as an example. Different integration methods are examined and their influence to the final identification results of the structural stiffness and damping is also studied. Furthermore, the effect of different kinds of noise is studied as well. Identification results show that the convergence speed and estimation accuracy under Gaussian noises are better than those under non-Gaussian noises. Finally, experiments with a five-story steel frame are conducted to verify the damage identification capacity of the EKF. The results show that stiffness with different damage degrees can be identified effectively, which indicates that the EKF is capable of being applied for damage identification and health monitoring for civil engineering structures.

Most sensors for structural testing and health monitoring are “point” sensors which strongly limit the ability to correct damage detection and structural assessment. In this paper, long-gauge FBG sensor which can sense the whole area within the gauge length is introduced. Bridge assessment and health monitoring with the microstrain distribution acquired by the distributed long-gauge FBG sensor are also studied. Experiments were conducted and application to a real prestressed box bridge was also implemented. Static and dynamic testing results show that distributed long-gage FBG sensing technique can obtain not only the global information such as bridge deflection and natural frequency, but also the local parameters such as strain and modal macrostrain to detect damage of the bridge. It shows that structural assessment and health monitoring based on the proposed technique have great potential in maintenance of civil engineering infrastructures.

Research on three‐dimensional, randomly distributed BFRC in China is analyzed and summarized in relative depth in this study. The results indicate that the effect of the fiber component and alkali corrosion temperature on the alkali resistance of BF is significant; the BF has little effect on the compressive strength of the concrete; the tensile and flexural strengths of the composites significantly increase compared with plain concrete, and the fiber content has a significant effect on the strength. In light of some problems in the current research, six possible research topics are suggested: (1) investigating the alkali resistance of the BF under dynamic temperatures, lower alkali concentrations, and longer alkali corrosion times; (2) improving the alkali resistance of the BF by increasing its hydrophobicity; (3) determining the optimal fiber distribution orientation of the BF with various characteristic parameters; (4) establishing the calculation formulas for the critical content and critical aspect ratio of various types of BF; (5) determining the optimal mixture ratio of two or more fibers in the FRC while studying the complementary mechanisms between each other; and (6) improving the dispersion of the BF and the BF/matrix interfacial properties.