Long-span bridges play a crucial role in urbanization, connecting communities across vast obstacles. Structural health monitoring techniques have been deployed on these bridges, generate large amounts of data through sensor measurements, requiring data-driven approaches like deep learning (DL) for effective analysis. However, feature extraction from time-domain vibration response signals poses challenges for DL methods. To address this, the study proposes utilizing signal processing techniques such as the multivariate empirical mode decomposition (MEMD) and Wavelet transform (WT) to extract essential features for damage classification. The incorporation of MEMD and WT aims to overcome limitations and process nonstationary and nonlinear signals effectively. Three DL techniques, long-short-term memory (LSTM), one dimensional convolutional neural network (1D-CNN), multi-layer perceptron (MLP) are tuned and applied to Structural Health Monitoring of Tianjin Yonghe Bridge (located in China) as a real-world case study, in order to detect its condition by Deep signal anomaly detection and identify types of the damage. A powerful meta-heuristic algorithm called Observer-Teacher-Learner-Based Optimization, is used to optimize both hyperparameters and architecture of each DL models. The results demonstrate that the optimally tuned DLs are successful in identifying types of damage, as well as the condition of the structure, for the Tianjin Yonghe Bridge. The average accuracy values are obtained as 98.13, 97.96, and 97.79 for 1D-CNN, LSTM, and MLP, respectively. Such optimally tuned DLs are evaluated as effective solutions for detecting damage on large-scale bridges by extracting statistical time-domain and time–frequency domain features using the WT and MEMD.

Suspension bridges due to their long span can experience large displacement response under dynamic loading like earthquakes. Unlike other structures, their vertical vibration may make remarkable difficulty that a control strategy seems to be essential. Tuned mass damper is a passive control system that can be changed to active one by adding an external source producing the active control force called active tuned mass damper. Unlike passive systems, active ones need a controller system affecting the performance of them considerably. In this study, the efficiency of tuned mass damper and active tuned mass damper are investigated in the bridges. Two controllers, fuzzy type 2 and fuzzy type 1, are used to estimate control force of active tuned mass damper. Tuned mass damper’s parameters are optimized under wide range of ground motions. Also, fuzzy type 2 and fuzzy type 1’s parameters are optimized under the influence of three different conditions containing far-field and near-field ground motions and also combination of them. In addition, Lion Pride Optimization Algorithm is selected for optimizing section. Numerical analysis indicates that active tuned mass damper is more effective than tuned mass damper, and also active tuned mass damper does not make any instability matter of concern in active control systems. Furthermore, performance of fuzzy type 2 is better than fuzzy type 1.

Suspension bridges are structures that because of their long span and high flexibility can be prone to ambient vibrations such as ground motions. They can experience high amplitude vibrations in torsional mode during an earthquake, where a vibration control strategy seems necessary. Recently, control systems have been widely used to mitigate vibration of structures. Tuned mass damper is a passive control system. Its performance and effectiveness have been verified both theoretically and practically. In this study, a tuned mass damper system is used to mitigate the torsional vibration of a suspension bridge. The Vincent Thomas suspension bridge is selected as a case study, and its response is reduced by a tuned mass damper under ten pulse-type records from 10 major worldwide earthquakes. By using sensitivity analysis, a parametric study is carried out to optimize tuned mass damper parameters, namely, mass ratio, gyration radius, tuning frequency, and damping ratio according to the maximum reduction of the response maxima. Finally, the optimum range of each parameter that can give the best performance and provide both operational and economic justification for the implementation of the project is suggested. The numerical results indicate that the optimized tuned mass damper system can substantially reduce the maximum response and vibration time.