The shallow features extracted by the traditional artificial intelligence algorithm-based damage identification methods pose low sensitivity and ignore the timing characteristics of vibration signals. Thus, this study uses the high-dimensional feature extraction advantages of convolutional neural networks (CNNs) and the time series modeling capability of long short-term memory networks (LSTM) to identify damage to long-span bridges. Firstly, the features extracted by CNN and LSTM are fused as the input of the fully connected layer to train the CNN-LSTM model. After that, the trained CNN-LSTM model is employed for damage identification. Finally, a numerical example of a large-span suspension bridge was carried out to investigate the effectiveness of the proposed method. Furthermore, the performance of CNN-LSTM and CNN under different noise levels was compared to test the feasibility of application in practical engineering. The results demonstrate the following: (1) the combination of CNN and LSTM is satisfactory with 94% of the damage localization accuracy and only 8.0% of the average relative identification error (ARIE) of damage severity identification; (2) in comparison to the CNN, the CNN-LSTM results in superior identification accuracy; the damage localization accuracy is improved by 8.13%, while the decrement of ARIE of damage severity identification is 5.20%; and (3) the proposed method is capable of resisting the influence of environmental noise and acquires an acceptable recognition effect for multi-location damage; in a database with a lower signal-to-noise ratio of 3.33, the damage localization accuracy of the CNN-LSTM model is 67.06%, and the ARIE of the damage severity identification is 31%. This work provides an innovative idea for damage identification of long-span bridges and is conducive to promote follow-up studies regarding structural condition evaluation.

Rapid and accurate identification of moving load is crucial for bridge operation management and early warning of overload events. However, it is hard to obtain them rapidly via traditional machine learning methods, due to their massive model parameters and complex network structure. To this end, this paper proposes a novel method to perform moving loads identification using MobileNetV2 and transfer learning. Specifically, the dynamic responses of a vehicle–bridge interaction system are firstly transformed into a two-dimensional time-frequency image by continuous wavelet transform to construct the database. Secondly, a pre-trained MobileNetV2 model based on ImageNet is transferred to the moving load identification task by transfer learning strategy for describing the mapping relationship between structural response and these specified moving loads. Then, load identification can be performed through inputting bridge responses into the established relationship. Finally, the effectiveness of the method is verified by numerical simulation. The results show that it can accurately identify the vehicle weight, vehicle speed information, and presents excellent strong robustness. In addition, MobileNetV2 has faster identification speed and requires less computational resources than several traditional deep convolutional neural network models in moving load identification, which can provide a novel idea for the rapid identification of moving loads.

The damage monitoring and identification of arch bridges provide an important means to ensure the safe operation of arch bridges. At present, many methods have been developed, and the applicability and effectiveness of these methods depend on the damage type, structural configuration and available data. To guide the practical application of these methods, a systematic review is implemented in this paper. Specifically, the damage monitoring and identification methods of arch bridges are divided into the damage monitoring of local diseases and damage identification of overall performance. Firstly, the research on the damage monitoring of the local diseases of arch bridges is reviewed. According to the disease type, it is divided into four categories, including suspender inspection, void monitoring, stress detection and corrosion detection. For each disease, this paper analyzes the principles, advantages and shortcomings of various methods. Then, the damage identification methods of the overall performance of arch bridges are reviewed, including masonry arch bridges, steel arch bridges, reinforced concrete arch bridges and concrete-filled steel tubular arch bridges. And the commonly used damage indexes of damage identification methods are summarized. This review aims to help researchers and practitioners in implementing existing damage detection methods effectively and developing more reliable and practical methods for arch bridges in the future.

The accuracy improvement of deep learning-based damage identification methods has always been pursued. To this end, this study proposes a novel damage identification method using Swin Transformer and continuous wavelet transform (CWT). Specifically, the original structural vibration data is first transferred to a time-frequency diagram by CWT, thereby capturing the characteristic information of structural damage. Secondly, the Swin Transformer is applied to learn the two-dimensional time-frequency diagram layer by layer and extract the damage information, by which the damage identification is achieved. Then, the identification accuracy of the proposed method is analyzed under various sample lengths and different levels of environmental noise to validate the robustness of this approach. Finally, the practicality of this method is verified through laboratory test. The results show the proposed method can effectively recognize the damage and achieve excellent accuracy even under noise interference. Its accuracy reaches 99.6% and 99.0% under single damage and multiple damage scenarios, respectively.