Traditional statistical pattern identification methods, such as artificial neural network and support vector machine, have limited ability to identify minor damage of bridges. Deep learning can mine the inherent law and representation level of sample data. As a typical algorithm of deep learning, convolutional neural network is a feedforward neural network with deep structure and convolution calculation, and its ability of image identification is very outstanding. The recurrence graph of structural response can reveal the internal structure, similarity, and damage information. The original structure response signal involves the coupling vibration of vehicle and bridge is filtered and reconstructed by wavelet packet, and then the recurrence graph of different damage cases is obtained, which is used as the input image of convolutional neural network as a new type of damage feature; thus, a damage identification method based on convolutional neural network and recurrence graph is established. The results of numerical simulation and model experiment show that the recurrence graph contains more damage information; compared with the traditional statistical pattern identification methods, convolutional neural network can achieve more accurate feature extraction and identification through intelligent learning layer by layer, so as to realize more accurate identification of damage location and damage degree.

The variation of the temperature and humidity significantly affects the modal parameters of the structure, and the effect and the quantitative statistics of single environmental factors such as temperature on the frequency of bridge are intensively studied, but the study on the mechanism and the effective model considering the comprehensive effect of multi-environmental factors is relatively rare. The principle and analysis method of co-integration is introduced, and the frequency-modified method based on co-integration is presented. Through the monitoring of a three-span concrete bridge model in the natural environment, the effective monitoring data are analyzed to establish a long-term equilibrium model about “frequency–temperature–humidity” based on co-integration theory. The experimental results indicate that the model has a better fitting ability and accuracy, and it is can be used to predict the variation trend of frequency. Based on the mathematical model of co-integration analysis, the modified frequency model considering multi-environmental factors is proposed, which can eliminate the comprehensive effect of temperature and humidity on frequency, and the variation of dynamic characteristics due to the internal causes of structure is revealed. The extracted sequence can provide effective information for further safety assessment and damage detection of bridge.