Vortex-induced vibrations (VIV) of bridges can affect driving comfort, pose safety risks, and hinder regular operation and maintenance. Vibration amplitude is a key indicator for evaluating the influence of VIV. To enable rapid prediction and assessment of VIV amplitude, this study employs wind tunnel test data from a steel box girder segment model of a long-span bridge to develop prediction models based on four machine learning algorithms: Gaussian process regression (GPR), neural network (NN), random forest regression (RFR), and gradient boosting regression tree (GBRT). The model inputs include wind attack angle, aerodynamic measures and structural damping ratio, while the output is the amplitude of vortex vibration. To enhance prediction accuracy, hyperparameters are optimized using grid search, and 10-fold cross-validation is used to determine the optimal configuration. Model performance is evaluated using three common metrics: coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE). The results show that the R2 values on the test set for the four models are 0.81, 0.88, 0.84, and 0.90, respectively, indicating good predictive capabilities. Among them, the performance of the GBRT model is the best. Furthermore, the Shapley additive explanations (SHAP) method is applied to interpret the decision process of the optimal model. By ranking the importance of input features based on their contributions, it is found that structural damping ratio and railing-suppressor plates are the primary factors influencing the predicted vibration amplitude in this study.
XUF Y, DINGW, JIANGF,et al .Development and prospect of study on vortex-induced vibration of long-span bridges[J].Journal of Vibration and Shock,2010,29(10):40-49.(in Chinese)
[3]
GAOD L, DENGZ, YANGW H,et al .Review of the excitation mechanism and aerodynamic flow control of vortex-induced vibration of the main girder for long-span bridges:a vortex-dynamics approach[J].Journal of Fluids and Structures,2021,105:103348.
GEY J, ZHAOL, XUK .Review and reflection on vortex-induced vibration of main girders of long-span bridges[J].China Journal of Highway and Transport,2019,32(10):1-18.(in Chinese)
WANGF, XINGF, XIONGC, et al. Study on vortex-induced vibration performance of π-shaped side-box section and measure- ment parametric of guide vanes[J].Journal of Hunan University (Natural Sciences),2024,51(5):114-122.(in Chinese)
CHENZ Q, LIS Y, DENGY C,et al .Recent challenges and advances on study of wind-induced vibrations of bridge cables[J].Journal of Hunan University (Natural Sciences),2022,49(5):1-8.(in Chinese)
HUANGL, DONGJ H, WANGQ,et al .Influence of maintenance rail position and guide vanes on vortex-induced vibration performance of flat box girders[J].Journal of Southwest Jiaotong University,2023,58(3):535-545.(in Chinese)
[12]
LIC G, YANH B, ZOUM H,et al .Experimental study on the influence of maintenance track position on vortex-induced vibration performance of a box girder suspension bridge[J].Frontiers in Built Environment,2023,9:1264996.
[13]
WANGC Q, HUAX G, FENGZ Q,et al .Experimental investigation on vortex-induced vibrations of a triple-box girder with web modification[J].Journal of Wind Engineering and Industrial Aerodynamics,2021,218:104783.
LIUZ W, SHENJ S, CHENZ Q,et al .Experimental study on aerodynamic control measures for vortex-induced vibration of stay-cable[J].Journal of Vibration Engineering,2021,34(3):441-451.(in Chinese)
Editorial Department of China Journal of Highway and Transport .Review on China’s bridge engineering research:2024[J].China Journal of Highway and Transport,2024,37(12):1-160.(in Chinese)
[18]
LINP F, HUG, LIC,et al .Machine learning-based prediction of crosswind vibrations of rectangular cylinders[J].Journal of Wind Engineering and Industrial Aerodynamics,2021,211:104549.
[19]
MAZ X, LIJ W, WANGF,et al .Prediction of vortex-induced vibration response of open bridge girder based on machine learning method[J].International Journal of Structural Stability and Dynamics,2024,24(2):2450017.
[20]
YANZ X, ZHENGS X, TAIX Y,et al .Machine learning models for predicting VIV amplitude of streamlined steel box girders[J].Structures,2024,63:106444.
[21]
LIS W, LAIMAS, LIH. Data-driven modeling of vortex-induced vibration of a long-span suspension bridge using decision tree learning and support vector regression[J].Journal of Wind Engineering and Industrial Aerodynamics,2018,172:196-211.
ZHAOL, LIK, WANGC J,et al .Review on passive aerodynamic countermeasures on main girders aiming at wind-induced stabilities of long-span bridges[J]. China Journal of Highway and Transport, 2019, 32(10): 34-48.(in Chinese)
ZHUL D, ZHOUQ, GUOZ S,et al .Aerodynamic interference effects on flutter and vortex-excited resonance of bridges with twin-separate parallel box decks[J].Journal of Tongji University (Natural Science),2010,38(5): 632-638.(in Chinese)
WANGW H, LIL Y, LIJ Y,et al .Test study on effects of railings on vortex-induced vibration performance of blunt box girder pedestrian bridge[J]. Journal of Vibration and Shock,2025,44(11):254-267.(in Chinese)
[30]
ZHANGJ, XIAOC L, YANGW F, et al .Improving prediction of groundwater quality in situ ations of limited monitoring data based on virtual sample generation and Gaussian process regression[J].Water Research, 2024,267:122498.
[31]
MAY F, ZHANGB C, HUANGK,et al .Probabilistic prediction and early warning for bridge bearing displacement using sparse variational Gaussian process regression[J]. Structural Safety,2025,114:102564.
[32]
ZHANGT, ZHOUL H, LUX C,et al. HinMAD3R:representation learning on heterogeneous information networks via multiple attentions with dual dropout and dual residual[J]. Expert Systems with Applications,2025,282:127674.
[33]
AKSHYAJ, NEELAMEGAMG, SURESHKUMARC,et al .Enhancing UAV path planning efficiency through Adam-optimized deep neural networks for area coverage missions[J].Procedia Computer Science,2024,235:2-11.
[34]
TROFIMOVI, KOROTAEVP, IVANOVI,et al .Machine learning assisted design of reactor steels with high long-term strength and toughness[J]. Materials & Design,2025,254:114014.
[35]
KALOUDIN, LIJ Y .The ML-based sensor data deception targeting cyber-physical systems:a review[J].Computer Science Review,2025,57:100753.
[36]
LUNDBERGS M, LEES I. A unified approach to interpreting model predictions[C]//Advances in Neural Information Processing Systems. Long Beach, CA, USA: Curran Associates Inc., 2017: 4765-4774.