Long-span cable-stayed bridges, integral to traffic infrastructure, require robust structural health monitoring(SHM) systems to withstand multi-load environments like earthquakes and wind vibrations. Traditional monitoring systems encounter challenges such as redundant sensor data, reliance on sensor quantity and quality, and a scarcity of real damage data. This study introduces a hybrid framework combining finite element model updating with deep learning to overcome these issues. Utilizing the OpenSees platform, a finite element model of the bridge is developed and refined using the Bayesian Optimization to update four critical parameters. A structural response database is created under various excitations, such as white noise, ground motions, and wind loads. A multi-head attention bidirectional LSTM (MHA-BiLSTM) network is employed, using acceleration data from main beam sensor locations to accurately predict displacements of the main beam and tower under single and cross-load scenarios, achieving an average R 2 (coefficient of determination) of 0.98284 with an R M S E (root-mean-square error) of 0.385 for single loads and an average R 2 of 0.97407 with an R M S E of 0.56133 for multi-loads. This hybrid methodology provides a generalizable technical paradigm for multi-load response monitoring of analogous large-scale cable-supported bridges.

Understanding and identifying the damage behavior of stay cables are of vital importance for ensuring the safety and serviceability of long‐span cable‐stayed bridges. In this study, the Sutong Yangtze River Bridge, one of the world’s longest‐span cable‐stayed bridges, was adopted as a case study to develop an integrated numerical‐data‐driven framework for cable damage identification. A high‐fidelity finite element model of the bridge was established using the OpenSees platform, and a Bayesian optimization (BO)‐based model updating approach was proposed to calibrate the model against field‐measured modal data, achieving a maximum frequency error of less than 2.4%, which meets engineering accuracy requirements. The calibrated model was then employed to systematically simulate the static responses of main girder displacement and cable forces under 136 single‐cable breakage scenarios, revealing the critical influence of long stay cables on structural global performance. Based on the simulated damage‐deflection dataset, an optimized 1D‐CNN model was developed for grouped cable fracture identification. Notably, this study presents the first systematic comparative evaluation of damage identification performance using time‐domain, frequency‐domain, and time–frequency‐domain features for kilometer‐scale cable‐stayed bridges and demonstrates that time‐domain data achieves the highest classification accuracy of 88.78%. The proposed framework provides a practical reference for damage identification of super‐long‐span cable‐stayed bridges and verifies the effectiveness of physics‐data fusion methods in large‐scale civil infrastructure health monitoring.

Stay cables are essential load-bearing elements of long-span cable-stayed bridges but are highly susceptible to degradation and fatigue. This study develops a deep learning framework for locating and quantifying stay cable damage. All training, validation, and independent test data in this study were generated by an OpenSees finite element model covering different cable damage locations and severities. A multilayer perceptron (MLP) classification model integrated with a spatial attention module (SAM) is constructed to achieve accurate localization of damaged stay cables. Based on this, a regression model with a similar architecture to the classification model is employed for damage quantification. In this identification procedure, SAM is adopted to enhance key spatial features, and MLP is used to separately train the Damage Location Identification Model (DLIM) and Damage Severity Identification Model (DSIM). After training, the identification accuracy of DLIM reaches 99.91%, and the identification reliability of DSIM reaches 99.95%. Under a signal-to-noise ratio (SNR) of 15 dB, the DLIM accuracy and DSIM reliability remain 94.76% and 97.33%. The framework provides a numerical case-study assessment of stay cable damage identification under the tested data protocol and Additive White Gaussian Noise (AWGN) condition.