VIV-SDE-Net: A physics-informed neural framework for long-horizon prediction of bridge vortex-induced vibrations

Domain adaptation based automatic identification method of vortex induced vibration of long-span bridges without prior information

Bridge vortex-induced vibration (VIV) refers to the vertical resonance phenomenon that occurs in a bridge when pulsating wind passes over it and causes vortices to detach. In recent years, VIV events have been observed in numerous long-span bridges, leading to fatigue damage to the bridge structure and posing risks to driving safety. The advancement of technologies such as structural health monitoring (SHM), machine learning, and big data has opened up new research avenues for the intelligent identification of VIV in bridges. Machine learning algorithms can accurately identify the VIV events from historical data accumulated by SHM systems, thus providing an effective method for VIV recognition. Nevertheless, the existing identification methods have limitations, particularly in their applicability to bridges lacking historical VIV data. This study introduces an adaptive VIV recognition method in the main girders of long-span suspension bridges based on Transfer Component Analysis (TCA). The method can accurately identify VIV patterns in real-time or in historical data, even when specific VIV data are not available for the target bridge. The proposed method exhibits suitability for multiple long-span bridges. Experimental validation is performed using the SHM datasets from two long-span suspension bridges. The results show that the proposed VIV identification method can recognize more VIV samples compared to the benchmark model. When using sensor 1 data of bridge B as the source domain to identify the VIV of the L-section of bridge A, the F1 score of the TCA-based method is 0.836, while the F1 score of the benchmark model is 0.165. In the other 11 cases, the F1 score of the proposed model is higher than 0.8, which demonstrates the method’s robust generalization capabilities.

Data-driven modeling of vortex-induced vibration of a long-span suspension bridge using decision tree learning and support vector regression

Hangers of long-span suspension bridges are highly susceptible to vortex-induced vibration (VIV), which may influence structural safety and service life. Traditional field measurement studies typically adopt a 10-min window to process wind and vibration data. However, this approach may obscure the temporal evolution of VIV events and misrepresent VIV characteristics. Moreover, the identification method for girder VIV has limitations when applied to hanger VIV. To address this issue, this paper proposes an advanced analysis method based on the Gaussian mixture model combined with the expectation–maximization algorithm. The method enables complete reconstruction of VIV events, identification of inlet and outlet, and extraction of representative wind and vibration parameters. Field measurements from a long-span suspension bridge were analyzed to evaluate the method. Results demonstrate that the proposed approach significantly reduces false detections compared with the traditional method and identifies VIV evolution across development, maturity, and decay stages. Statistical analysis of 183 detected events reveals clear occurrence conditions: VIV primarily arises under mean wind velocities of 4.5–7.5 m/s and persists when wind direction remains stable within the ranges of 325°–25° and 145°–205°. Moreover, higher-order multimodal lock-in behavior is observed, with overlapping excitation ranges among multiple modes, indicating complex aerodynamic interactions. These findings provide new insights into the dynamic mechanisms of hanger VIV and demonstrate the importance of advanced data processing for structural health monitoring. The proposed method offers practical value for bridge operation and maintenance by enabling more accurate identification of VIV conditions and supporting the design of vibration control strategies.

Vortex-induced vibrations (VIVs) have been observed on a long-span suspension bridge. The nonstationary wind in the field characterized by the time-varying mean wind speed is likely to lead to time-varying aerodynamics of the wind-bridge system during VIVs, which is different from VIVs induced by stationary or even steady wind in wind tunnels. In this paper, data-driven methods are proposed to reveal the time-varying aerodynamics of the wind-bridge system during VIV events based on field measurements on a long-span suspension bridge. First, a variant of the sparse identification of nonlinear dynamics algorithm is proposed to identify parsimonious, time-varying aerodynamical systems that capture VIV events of the bridge. Thus we are able to posit new, data-driven, and interpretable models highlighting the aeroelastic interactions between the wind and bridge. Second, a density-based clustering algorithm is applied to discovering the potential modes of dynamics during VIV events. As a result, the time-dependent model is obtained to reveal the evolution of the aerodynamics of the wind-bridge system over time during an entire VIV event. It is found that the level of self-excited effects of the wind-bridge system is significantly time varying with the real-time wind speed and bridge motion state. The simulations of VIVs by the obtained time-dependent models show high accuracies of the models with an averaged normalized mean-square error of 0.0023. The clustering of obtained models shows underlying distinct dynamical regimes of the wind-bridge system, which are distinguished by the level of self-excited effects.

The bare-pipe riser vortex induced vibration (VIV) experiments described in Tognarelli et al [1] were extended to examine the influence of various lengths of strake coverage on riser vibrations. The objective of the tests was to demonstrate whether present riser VIV prediction formulations provide a robust basis for determining the effects of full and partial strake coverage on riser VIV. Continuous triple-start helical strakes with a height equal to 25% of the cylinder diameter and a pitch of 16 diameters were fitted to a test pipe with a length of 9.6m and a diameter of 20mm. Tests were performed in uniform and sheared currents. The model was instrumented to acquire records of bending strain and lateral acceleration in both cross-flow and in-line directions at a sufficient number of stations to allow accurate reconstruction of static and dynamic bending deflections along the riser. The dependence of these quantities n flow speed and current profile type was compared qualitatively with the physical concepts embodied in numerical models often used in riser design. In all cases tested, the vibration of the straked riser was significantly less than that of the bare pipe. However, the response measurements indicate that existing VIV prediction methods fail to reproduce even the qualitative characteristics of the motion of the straked riser. The data suggest that current-induced vibration of a riser with these high strakes is driven by a physical mechanism which is different from the vortex excitation of bare risers. A new prediction formulation is needed to properly represent the influence of full or partial strake coverage on riser vibration and fatigue, particularly for demanding applications in which accurate quantification of strake effectiveness is critical for design. The test results described here provide a basis for validating new methods as they are developed through further research. Introduction The development of methods for predicting the response of deepwater risers to VIV has been an area of active research in the oil industry for many years. As the industry continues to move into deeper water, continuous improvement is needed in VIV prediction methods to eliminate inaccuracies where possible and quantify the remaining uncertainties in the response predictions. An additional complication in the VIV analysis of deepwater risers involves the modeling of VIV suppression devices, such as helical strakes or fairings. In deepwater, it is now common for risers to be fitted with some length of VIV suppression. An accurate understanding of the effectiveness of VIV suppression devices is critical in making design decisions, such as the type of suppression device to use and the length of riser to cover with suppression. In an effort to better understand the dynamic response of deepwater risers to VIV, ExxonMobil undertook a series of tests during the summer of 2003 to measure the VIV response of a long, flexible highly instrumented cylinder. The goal of this test program was to produce a high-quality data set for use in validating and/or developing VIV prediction tools for both bare and straked risers.

Due to the designing characteristics of long span and low stiffness, the high-order vortex-induced vibration (VIV) of suspension bridges may occur under a special wind environment. The prototype monitoring data make it feasible to rapidly capture and evaluate the VIV behavior during bridge operation. Based on the multisource load-response data of a long-span suspension bridge in a rare VIV phenomenon, this paper comprehensively evaluated the entire process of the input–output behavior of bridge VIV. The cause of this bridge VIV phenomenon is discussed, and the VIV parameter is estimated. The human comfort of vehicle riding in the VIV phenomenon is evaluated. A fast early-warning method of bridge VIV driven by multisource monitoring data is proposed according to the analysis and evaluation results of the bridge VIV phenomenon. The main results demonstrated that continuous excitation of wind whose direction is almost perpendicular to the longitudinal direction of the bridge are more likely to cause VIV; the Strouhal number of the three-meter-high stiffening box-shape opening-below steel girder is approximately 0.101694 according to the k-means clustering of inversely-calculated results of the monitoring data. The evaluation results and proposed early-warning method support the wind-resistant design, health monitoring, and intelligent maintenance of long-span suspension bridges.

A significant vortex-induced vibration (VIV) was observed in a suspension bridge under a wind velocity of approximately 6 and 7 m/s, and with a maximum amplitude that exceeded the serviceability limitations. Since the observation of VIV in an operating bridge was an infrequent event, this study investigated the cause of unexpected VIV. A series of wind tunnel tests revealed the main cause of the VIV was temporary screens applied over the guardrails to shield the curing surface during replacement of epoxy-coated pavement. The characteristics of the measured VIV were consistent with those from experimental results in terms of amplitude and lock-in wind speed range. The effect of Scruton numbers on VIV amplitude was examined for several dominant modes with different modal mass and damping ratios. Since the VIV amplitude is sensitive to the inherent damping ratio, the modal damping ratios of the bridge were identified from output-only modal analysis by using the frequency domain decomposition. This approach was efficient in identifying the damping ratios of high modes that were challenging due to weakly excited signals. The damping ratio of the triggered mode for VIV was the lowest among the investigated modes and estimated to be the level of the design-damping ratio.

A long-span double-deck steel truss suspension bridge is easy to produce vortex-induced vibration (VIV) at low air velocity, which affects bridge service life. Additional aerodynamic measures play a role in suppressing VIV by changing the aerodynamic shape, which is a common control method. As the main aerodynamic measure to suppress the VIV response, wind fairing is widely used in engineering practice. In order to obtain the optimal additional position and shape parameters of the fairing, Huangjuetuo Yangtze River Bridge is the research target. Through the combination of a wind tunnel test and numerical simulation, the VIV response of the original and fairing section is studied. Based on data analysis, it is revealed that these additional fairings to the upper chord can significantly reduce the VIV response. When the shape parameters of the fairing are h/D = 1/4 and l/D = 1, the VIV inhibition efficiency is the highest, which can reach 65.51%. By analyzing the flow distribution, it can be seen that VIV is caused mainly by vortex separation in the upper bridge board area. Although this wind fairing does not change the original vortex shedding forms, it changes the first separation point and movement direction of the airflow, making the vortex scale generated by the airflow smaller and the vorticity lower, thus effectively suppressing VIV.

To ensure the safety of high-speed trains operating on bridges in complex environments, this study investigates the dynamic response of trains on long-span suspension bridges under vortex-induced vibrations (VIV). By simplifying the bridge’s VIV into an equivalent force and combining it with wind and train loads, an advanced train-track-bridge (TTB) coupled dynamic system considering VIV is established. This method overcomes the limitations of traditional VIV simplification simulation methods, which only compute train responses while neglecting the bridge’s dynamic behavior and the coupled effects. The results demonstrate that VIV induces significant periodic vibrations in the bridge, leading to increased displacements and accelerations. These effects further influence the train’s dynamic response, with higher-order VIV modes having a more pronounced impact. Specifically, vertical car body accelerations reach 0.35 m/s 2 , 0.49 m/s 2 , and 0.72 m/s 2 under mode 2, mode 4, and mode 10 vibrations, respectively. In addition, the proposed vortex-induced train-track-bridge coupled (VIV-TTB) method is innovatively compared with the calculation method that treats vortex-induced vibration as equivalent track irregularities. The results show a high degree of consistency, with an R 2 value of 0.9266, fully validating the accuracy and reliability of the method proposed in this study.

Ride comfort evaluation of stochastic traffic flow crossing long-span suspension bridge experiencing vortex-induced vibration

Vortex-induced vibration (VIV) has been occasionally observed on a few long-span steel box-girder suspension bridges. The underlying mechanism of VIV is very complicated and reliable theoretical methods for prediction of VIV have not been established yet. Structural health monitoring (SHM) technology can provide a large amount of data for further understanding of VIV. Automatic identification of VIV events from massive, continuous long-term monitoring data is a non-trivial task. In this study, a method based on the random decrement technique (RDT) is proposed to identify the VIV response automatically from the massive acceleration response without manual intervention. The raw acceleration data is first processed by RDT and it is found that the RDT-processed data show different characteristics for the VIV response and conventional random response. A threshold based on the coefficient of variation (COV) of peak values of processed data is defined to distinguish between the two kinds of responses. Both random vibration and VIV for a three-DOF (degree-of-freedom) mass-spring-damper system are obtained by numerical simulation to verify the proposed method. The method is finally applied to the Xihoumen suspension bridge for identifying VIV response from three-month monitoring data. It is shown that the proposed method performs comparably with the method of novelty detection. A total of 60 VIV events have been successfully identified. Vortex-induced vibrations for the second to ninth vertical modes with modal frequency within 0.1~0.5 Hz occurs at wind velocity 5–18 m/s, with wind direction nearly perpendicular to bridge axis. Amplitude of VIV generally decreases with increase of wind turbulence intensity; however, noticeable VIV amplitude are still observed for turbulence intensity up to 13% in some cases.

Vortex-induced vibration is a prevalent form of wind-induced vibration during the operation period of long-span suspension bridges. It significantly influences the comfort of drivers and passengers and reduces the bridge’s service capacity. Currently, the primary method for evaluating comfort relies on vibration acceleration standards, which lack a basis for assessing visual comfort. This paper presents a practical framework for the evaluation of visual comfort on long-span suspension bridges experiencing vertical vortex-induced vibration. A visual simulator is developed for drivers and passengers, taking the specific bridge modal shapes, vibration amplitudes, and vehicle speeds into consideration. By simulating the dynamic visual effects experienced by drivers and passengers on past vehicles, the comfort levels are investigated through a questionnaire based on visual comfort. An evaluation model is established for the drivers’ subjective comfort response during vortex-induced vibration. The applicability and rationality of this evaluation process are illustrated through a typical case study. The results of the case study demonstrate that the comfort level of drivers and passengers is negatively correlated with the modal shapes and amplitudes under vortex-induced vibration conditions. Consequently, based on the visual comfort evaluation model, it is suggested that the maximum limit value for vertical vortex-induced vibration of the case study is 0.2–0.3 m. The proposed visual comfort evaluation process offers a comprehensive approach applicable to bridge serviceability.

Abstract: Bridge vortex induced vibration (VIV) is a resonance phenomenon caused by the periodic shedding of vortices generated by natural wind passing through bridges. Bridge VIVs will not only cause fatigue damage to the structures but also affect driving safety for the passing vehicles. With the popularization of structural health monitoring (SHM) systems, machine learning technology is widely used in the field of vortex induced vibration identification for long-span bridges, due to its intelligence, real-time performance, and sensitivity to data. However, although traditional machine learning algorithms can identify the VIV based on the response data history of long-span bridges collected by SHM systems, they are difficult to apply to bridges which do not have historical vortex induced vibration data. Therefore, this paper proposes an adaptive transfer learning method for identifying VIV in the main girder of long-span suspension bridges. The proposed method can identify VIV without VIV history data of the target bridge. Results show that it can well identify VIVs at the earlier stage based on the SHM datasets of two long-span suspension bridges, verifying its effectiveness and generalization ability.

Bayesian inference based parametric identification of vortex-excited force using on-site measured vibration data on a long-span bridge