Bridge strain is an essential monitoring index for small to medium span bridges because abnormal strains could be attributed to bridge deterioration or damage. Thus, an early warning method for detecting abnormal strains is highly desired. In this study, a temperature–strain mapping model for predicting the temperature induced strains was proposed by fusing structural health monitoring data and deep learning neural networks. First, the sensitivity of temperature induced strains to structural damage was analyzed, and the thermal strain was chosen as a suitable indicator for bridge performance detection. Next, a high-precision prediction model was established to overcome the time-lag effect between the original temperature and temperature induced strain sequences. By comparing the model’s prediction with the identification of measurements, an early warning method for detecting the abnormal temperature induced strains was proposed. The evaluation results demonstrated that the proposed early warning method was able to accurately detect the abnormal strains, even when the abnormal strain is smaller than the normal daily variations.

The stiffness degeneration of small to medium span bridges has been increasingly observed in recent years, and it has become a major concern of government and bridge owners. A quantitative evaluation method for the bridge performance with strengthening measures is highly desired. Due to the advantages of uninterrupted traffic and long-term tracking capability, a temperature-driven approach for characterization of the correlation pattern between bridge temperature-induced strains and bridge status was proposed in the present study by using structural health monitoring data. First, a theoretical solution of the simplified bridge model was derived to establish the correlation between the stress and deterioration extent under temperature gradient load. After a numerical simulation that combines the thermal–structural interaction analysis and the vehicle–bridge interaction analysis, the strain range was proposed as an assessment index to ensure the stability and effectiveness of the evaluation results. Next, the Generalized Extreme Studentized Deviate method was used for detecting the outliers. The statistical results of the assessment index for different strengthening methods were compared to evaluate the associated strengthening efficiency, and the associated equivalent section height was calculated for visualizing the bridge condition after strengthening measures were taken. The results demonstrated that the proposed temperature-driven method was able to quantitatively evaluate the bridge strengthening effects with a high efficiency.

For river crossing bridges, the vehicle-induced vibration can be transmitted to the bridge tower and foundation system. This vibration induced low frequency underwater noise radiation can cause great harm to aquatic organisms. A river crossing suspension bridge was selected to study the sound contribution and spatial distribution of the underwater noise. A bridge-sediment coupling finite element model was developed, and the vehicle-bridge-sediment interaction analysis was conducted to investigate the dynamic response of the coupling system. An acoustic finite element model was built to predict the underwater noise radiated from the tower and sediment, and the noise contribution of these two sound sources was compared. The research shows that the noise radiated from the bridge tower and the sediment is below 6.3 Hz, and the peak frequency is around 3.15 Hz. The noise radiated from bridge tower only has a larger contribution to the total noise level in its vicinity than the sediment, especially around the water surface. In other space, the noise generated through the sediment vibration plays a dominant role in the total noise. The radiated noise from the tower has lateral directivity, and the directivity of the sediment radiation is similar to the point sound source.