Noise barriers need to be installed along high-speed railway lines to protect nearby inhabitants from the noise pollution caused by the running of high-speed trains (HSTs). The vertical noise barrier is the main structural type. However, when an HST passes through the noise barriers sited along the track, significant and transient aerodynamic pressure will act on the surface of the noise barriers, resulting in strong dynamic responses and even fatigue damage. Therefore, it is important to determine the train-induced aerodynamic load on the barrier surface and analyze the dynamic behaviors of the noise barriers under such a load for its structural design and to guarantee its safety and durability. This paper is a systematic review of the current literature on the aerodynamic load and dynamic behavior of vertical noise barriers; it includes (1) a summary and analysis of characteristics of such aerodynamic pressure and relevant influencing factors, (2) an introduction to measurement methods of aerodynamic load and relevant pressure models on the surface of noise barriers, and (3) a description of the dynamic response and fatigue analysis of noise barriers under such loads. Finally, potential further studies on this topic are discussed, and conclusions are drawn.

High-speed trains (HSTs) generate air disturbance, leading to significant aerodynamic pressure on the noise barriers. Differences in train geometry result in variations in the aerodynamic pressure on noise barriers, implying that existing European standard calculation models may not necessarily be suitable for all types of HSTs. In this paper, the influence of the width, height, and nose length of the train on the aerodynamic pressure on vertical noise barriers was studied using computational fluid dynamics (CFD) simulations. Results showed that taller and wider trains result in greater aerodynamic loads on noise barriers. Conversely, an increase in the nose length of a train leads to a reduction in such pressure. Using grey relational analysis, correlation of various factors with the train-induced aerodynamic pressure is, from strong to weak: distance to the track center, width, height, and nose length of the train. Building upon the EN 14067-4 calculation model, the shape coefficients of trains with varying geometric characteristics were derived using the simulation data obtained in this study. A modified pressure calculation model was established accounting for the differences in geometric features of HSTs and pressure distribution in the vertical direction of noise barriers and validated using relevant data from the literature.

Noise barriers play a crucial role in mitigating railway noise, with the aerodynamic pressure exerted by passing trains being a key factor in their structural design, particularly for those installed along high-speed railways. While previous studies have focused on the effects of train speed, geometry, and distance from the track centre, and have developed models incorporating these factors, limited attention has been given to the impact of bilateral layouts and barrier height on this pressure. Quantitative assessments of these two factors remain scarce, and existing pressure calculation models inadequately address their influence. This study addressed these gaps by employing computational fluid dynamics (CFD) simulations, validated by field test data, to qualitatively and quantitatively analyze the effects of barrier layout and height on the aerodynamic pressure acting on vertical noise barriers. The results demonstrate that two distinct transient pressure fluctuations over time are generated by the train’s nose and tail, in agreement with the findings of the field tests. A bilateral layout increases peak pressure by up to 8.5%, particularly as the distance to the train centreline decreases. Moreover, increasing barrier height from 2 to 4 m resulted in a maximum pressure amplification of 13.23%, though the amplification rate diminished with further height increases. To address the limitations of existing pressure calculation models, an exponential model was developed to account for the amplification effect of bilateral layouts, while a logarithmic correction factor was introduced to account for barrier height. These models were integrated into a comprehensive aerodynamic pressure calculation framework, effectively capturing the combined impacts of barrier layout and height. Validated through simulations, the proposed model offers a more accurate and practical approach for predicting train-induced aerodynamic pressure on noise barriers, providing valuable insights to inform their structural design.

Railway noise barriers are an essential piece of infrastructure for reducing noise propagation. However, these barriers experience aerodynamic loads generated by high-speed trains, leading to dynamic effects that may compromise their fatigue capacity. The most common structural design for railway noise barriers consists of vertical configurations of posts and panels. However, there have been few dynamic analyses of steel post/wood panel noise barriers under train-induced aerodynamic loads. This study used dynamic finite element analysis to assess the dynamic behavior of such noise barriers. Analysis of a 40-m-long noise barrier model and a triangular simplified load model, the latter of which effectively represented the detailed aerodynamic load, were first used to establish the model and input of the moving load during dynamic simulation. Then, the effects of different parameters on the dynamic response of the noise barrier were evaluated, including the damping ratio, the profile of the steel post, the span length of the panel, the barrier height, and the train speed. Gray relational analysis indicated that barrier height exhibited the highest correlations with the dynamic responses, followed by train speed, post profile, span length, and damping ratio. A reduction in the natural frequency and an increase in the train speed result in a higher peak response and more pronounced fluctuations between the nose and tail waves. The dynamic amplification factor (DAF) was found to be related to both the natural frequency and train speed. A model was proposed showing that the DAF significantly increases as the square of the natural frequency decreases and the cube of the train speed rises.

The passage of trains by railway noise barriers induces vibrations that may affect their fatigue performance and reduce their service life. However, long-term field monitoring of noise barriers under complex environmental and operation conditions remains rare. This study develops an interpretable machine learning (ML) framework to investigate the aerodynamic pressure and dynamic behaviors of noise barriers based on a nine-month long-term field monitoring campaign, yielding 12810 train runs over 105 valid days. Input variables include train type, speed, temperature, wind speed and direction, relative humidity, and air pressure, while the target responses cover train-induced aerodynamic pressure, stress near the base of the steel post, and displacement at the post top. Eight ML models, including four traditional and four ensemble algorithms, were used and systematically compared to evaluate their predictive capabilities and robustness. Ensemble models, particularly Gradient Boosting Decision Tree (GBDT), Light Gradient Boosting Machine (LGBM), and Extreme Gradient Boosting (XGBoost), achieved the best predictive performance, with R² values exceeding 0.935 for stress and displacement, and 0.895 for pressure. XGBoost, offering a strong balance of predictive accuracy and computational efficiency, was selected for SHapley Additive exPlanations (SHAP)-based interpretability analysis to uncover the physical relationships behind the data-driven predictions. Results reveal that aerodynamic pressure was the most challenging response to predict, given its higher sensitivity to turbulent airflow and environmental fluctuations, whereas stress and displacement exhibited more stable and predictable patterns. SHAP analysis identified train speed and type as the most influential factors across all responses. While environmental factors had comparatively lower influence, temperature and instantaneous wind direction consistently showed higher importance among them. Relative humidity has a moderate effect on aerodynamic pressure but a minor impact on dynamic behavior. Air pressure and wind speed exhibit limited influence on all outputs. These findings highlight the novelty and effectiveness of integrating long-term monitoring data, ML methods, and SHAP-based interpretability, offering new insights into the dynamic behavior of railway noise barriers.