Estimation and monitoring of cable tension is of great significance in the structural assessment of cable-supported bridges. For short cables, the traditional cable tension identification method via frequency measurement has large errors due to the influence of complex boundaries, which affect the accuracy of estimation. A new cable tension estimation method based on mode shape identification with a multiple sensor arrangement on the cable can take the influence of boundary conditions into account and its accuracy has been verified. However, it requires more sensors compared to the traditional frequency-based method, which will significantly increase the cost of long-term monitoring in practice. Therefore, a novel approach for cable tension monitoring considering both cost and accuracy is further proposed in this study. The approach adopts multiple sensors to measure the influence of boundary conditions. Then, only a single sensor is required for long-term monitoring of the cable. In this paper, an analytical model of the cable is firstly established. The influence of boundary conditions is calculated, which ensures the accuracy of mode shape identification. Furthermore, a field experiment is carried out to verify the effectiveness of the new approach. The results have demonstrated the effectiveness and accurateness of the proposed method in long-term short cable tension monitoring.

The tropical storm is a severe wind disaster that frequently attacks coastal structures and infrastructure facilities. Accurate wind speed forecasting of tropical storms, based on real-time measured data, has become a critical issue in the engineering community. Utilizing the measured data of typical tropical storms at Sutong Bridge, this study develops a new approach for wind speed forecasting, which integrates multi-step differencing with an artificial neural network-based model. Given the non-stationary nature of tropical storm wind speeds, a multi-step differencing operation is initially applied to the wind speed time series. Subsequently, multi-step predictions of the differenced wind speeds are made for future time points. Finally, an inverse differencing operation is employed to reconstruct the wind speeds to be forecasted. The forecasting errors associated with single-step differencing, multi-step differencing, and no differencing are compared to evaluate their respective performances. To validate the generalizability of the developed approach, it is further used in the wind speed forecasting of another typhoon wind speed dataset. The satisfactory performance demonstrates the effectiveness of the developed approach for multi-step wind speed forecasting of tropical storms.

Over the past few decades, rapid economic development has led to the establishment of numerous monitoring systems, resulting in the accumulation of vast amounts of monitoring data. Among these data, dynamic acceleration data stand out prominently. However, the quality of collected acceleration data is often compromised due to factors such as challenging operational environments and sensor malfunctions. This severely hampers the value extracted from the data. Although manual identification and classification of data anomalies are more reliable, they are time consuming and labor intensive. To address the challenge of identifying and classifying anomalies in massive acceleration data, this paper proposes a two-stage model for intelligent data cleaning. Firstly, raw acceleration data are transformed into IPDF and PSD features, and a one-dimensional convolutional neural network is trained to preliminarily identify and classify acceleration data anomalies. Subsequently, the RPV indicator is extracted from the original data of the normal and outlier categories to achieve precise classification based on threshold values. The proposed method is successfully validated using acceleration monitoring data from a large-span arch bridge, achieving an accuracy of over 99%. Furthermore, compared to directly employing a one-dimensional CNN classification model, the approach significantly enhances the model’s perception of local significant disturbances.

High-damping rubber (HDR) dampers have the advantages of convenience for various shapes of pressure blocks, aesthetic installation, easy maintenance, temperature stability, etc.; thus, they present good application prospects in the vibration reduction of stay cables. Hence, a model of a taut cable equipped with two types of HDR damper—i.e., HDR damper and tuned mass–high-damping rubber damper (TM-HDR-D)—is established herein. Then, based on this theoretical model, the effect of each damper acting alone and in combination on the cable’s additional modal damping is studied. Finally, an actual cable of a cable-stayed bridge is used to study the effectiveness of two dampers for practical engineering. The results show that, when the TM-HDR-D has a small mass, the total additional modal damping of the cable approximates the superposition of the respective effects of the two dampers. The damping effect of HDR mainly depends on its stiffness and installation position; meanwhile, the damping contribution of TM-HDR-D is mainly related to its tuning frequency and installation position. In practical engineering, the smaller installation mass of TM-HDR-D can make up for the lack of damping enhancement of the cable-end HDR damper.

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.

Vortex-induced vibration (VIV) occurs frequently on long-span bridges at low wind speeds and may cause fatigue damage and serviceability problems, so its reliable identification from field monitoring data is an important engineering task. However, existing automated identification methods rely mainly on single-point vibration indicators, and recognizing VIV events in massive, unlabeled monitoring datasets remains challenging. This study proposes an unsupervised VIV identification method based on a newly proposed feature, the Two-Point Vibration Phase Difference (TPVPD), computed between the vertical accelerations measured at the 1/4- and 3/4-span of the bridge. Because a VIV lock-in response is dominated by a single vibration mode, the phase difference between two spanwise locations remains nearly constant in time, whereas it fluctuates strongly under buffeting. The method was validated using six years (2013–2018) of monitoring data from a 1650-m main-span suspension bridge, covering 2.85 × 10⁵ valid 10-min windows. Spectral clustering of three features—acceleration RMS, TPVPD standard deviation, and an energy concentration coefficient—separated VIV from non-VIV states with a window-level F1 score of 0.84 with respect to a reference VIV inventory, and 99.8% of the windows identified as VIV exhibited spectral peaks at one of the six known VIV mode frequencies of the bridge. A rule-based cluster assignment calibrated on previous years transferred to subsequent years with F1 scores of 0.74–0.88, indicating the feasibility of operational deployment.