Search

Physics-informed neural networks (PINNs) have recently emerged and attracted extensive attention as an alternative approach to computational fluid dynamics (CFD) methods, which can provide competitive solutions to a variety of forward and inverse fluid problems. In this study, we reconstruct a 3D wind field around a building model in wind tunnel test with a Reynolds number of 2.4 × 104 by formulating a novel PINN framework, which is the first exploration of PINNs for building wind engineering problems. To surmount the hurdle in multi-objective optimization for PINN training, a dynamic prioritization (dp) self-adaptive loss balance strategy is proposed (termed dpPINN), which adaptively reconciles the loss terms of distinct scales to facilitate convergence in PINN training. A zero-equation turbulence model and the wind velocity data collected in near-wall regions are embedded in dpPINN training. Comparison results indicate that dpPINN predictions show good consistency with observation data, which is superior to two current PINN paradigms in prediction accuracy. Furthermore, the influence of neural network configurations, turbulence models, and the layout arrangements of training points on the dpPINN prediction is investigated. It is demonstrated that the dpPINN could be a powerful auxiliary means for airflow simulation and reconstruction in wind engineering applications. [ABSTRACT FROM AUTHOR]

The high-speed railway has become an important passenger transport mode. Relying on the abundant passenger transport experience and expansive railway network, the high-speed freight train (HSFT) is feasible to be developed and has great application potential. As a critical component of HSFT, the cargo plays an important role in the overturning safety of HSFT under strong wind conditions. Previous studies about the aerodynamic performance of the high-speed train usually regarded the loaded carbody as an individual rigid body. Limited attention was paid to the variability inside the vehicle. In order to improve the running safety of HSFT under strong wind conditions, the multibody dynamics simulation is adopted to demonstrate the effect of cargo property on the overturning risk of HSFT under the aerodynamic loads obtained through the computational fluid dynamics (CFD) simulations. It is demonstrated that the inner side crosswind is more dangerous than the outer side crosswind. The speed of HSFT should be limited according to the cargo quantity, and the maximum speed for a fully loaded HSFT can be 305 km/h when the crosswind velocity is 20 m/s. The larger cargo density should be encouraged because it is good for train overturning safety in severe working conditions. [ABSTRACT FROM AUTHOR]

The acceleration of land desertification has led to an increasingly serious threat to the operation safety of tunnel entrance in the Gobi and desert regions by wind-sand flow, and it is urgent to study and enhance the running safety of train. Firstly, an ultrasonic anemometer is used to collect the characteristics of wind-sand flow at a tunnel entrance site in Xinjiang, China. Then, based on the Euler multiphase flow and the SST k-w model, the variation difference law of the train running at the tunnel entrance is revealed under the four inflow conditions of constant crosswind, constant wind-sand flow, pulsating crosswind and pulsating wind-sand flow respectively. Finally, the disturbance law of the solid wind barrier at the tunnel entrance on the wind-sand flow and the influence mechanism on the train's flow field structure and pressure are revealed. The results show that compared with other cases, the pulsating wind-sand flow has the most significant effect on the moving trains' aerodynamic loads (ALs), and the sand particles carried in the air cause the trains' ALs to fluctuate within 9.09%. The solid wind barrier has a significant disturbing effect on the wind-sand flow, and the lightweight sand particles follow the air flow over the top of the wind barrier and are not deposited on the embankment during a short period, and the wind-sand flow's impact on the HSTs is dramatically reduced. The wind barrier changes the HST's flow field, and the AL fluctuation of the train is sharply reduced. The maximum values of the head train's AL coefficients are reduced by 46.53-85.75%. [ABSTRACT FROM AUTHOR]

The acceleration of land desertification has led to an increasingly serious threat to the operation safety of tunnel entrance in the Gobi and desert regions by wind-sand flow, and it is urgent to study and enhance the running safety of train. Firstly, an ultrasonic anemometer is used to collect the characteristics of wind-sand flow at a tunnel entrance site in Xinjiang, China. Then, based on the Euler multiphase flow and the SST k-w model, the variation difference law of the train running at the tunnel entrance is revealed under the four inflow conditions of constant crosswind, constant wind-sand flow, pulsating crosswind and pulsating wind-sand flow respectively. Finally, the disturbance law of the solid wind barrier at the tunnel entrance on the wind-sand flow and the influence mechanism on the train’s flow field structure and pressure are revealed. The results show that compared with other cases, the pulsating wind-sand flow has the most significant effect on the moving trains’ aerodynamic loads (ALs), and the sand particles carried in the air cause the trains’ ALs to fluctuate within 9.09%. The solid wind barrier has a significant disturbing effect on the wind-sand flow, and the lightweight sand particles follow the air flow over the top of the wind barrier and are not deposited on the embankment during a short period, and the wind-sand flow’s impact on the HSTs is dramatically reduced. The wind barrier changes the HST’s flow field, and the AL fluctuation of the train is sharply reduced. The maximum values of the head train’s AL coefficients are reduced by 46.53–85.75%.