Despite the substantial advancements made over the past 50 years in solving flow problems using numerical discretization of the Navier–Stokes (NS) equations, seamlessly integrating noisy data into existing algorithms remains a challenge. In addition, mesh generation is intricate, and addressing high-dimensional problems governed by parameterized NS equations is difficult. The resolution of inverse flow problems is notably resource-intensive, often necessitating complex formulations and the development of new computational codes. To address these challenges, a physics-informed neural network (PINN) has been proposed to seamlessly integrate data and mathematical models. This innovative approach has emerged as a multi-task learning framework, where a neural network is tasked with fitting observational data while reducing the residuals of partial differential equations (PDEs). This study offers a comprehensive review of the literature on the application of PINNs in solving two-dimensional and three-dimensional NS equations in structural wind engineering. While PINN has demonstrated efficacy in many applications, significant potential remains for further advancements in solving NS equations in structural wind engineering. This work discusses important areas requiring improvement, such as addressing theoretical limitations, refining implementation processes, and improving data integration strategies. These improvements are essential for the continued success and evolution of PINN in computational fluid dynamics.
1 December 2022 in Journal of Structural Engineering
The time-varying mean (TVM) component has a major influence on the characterization of nonstationary wind events and associated parameters of the fluctuating components. However, it is challenging to determine the optimal TVM of the nonstationary wind speed accurately due to variability in the low-frequency signal contents. To address this challenge, this study develops an effective wavelet-based method together with necessary conditions to calculate the optimal TVM from nonstationary wind speed data. For comparison, the time-dependent memory method is also used and enhanced to obtain the optimal TVM. Wind field turbulence characteristics of Typhoon Mangkhut are then analyzed and presented based on the conventional stationary model and nonstationary model with the proposed optimal TVM. In addition, this study also proposes an empirical description of the wind spectrum, which provides a better fit to the typhoon-related nonstationary winds than those offered by classical wind spectral description.
29 July 2021 in International Journal of Structural Stability and Dynamics
Accurate estimation of modal parameters is crucial for various aspects of tall buildings, including structural design, vibration control, and state assessment. This paper first presents a combined approach for the structural modal parameter estimation by combining the empirical wavelet transform (EWT), smoothed discrete energy separation algorithm‐1 (SDESA‐1), and half‐cycle energy operator (HCEO), referred to as EWT‐SH. A numerical study on a five‐story frame structure is conducted using the Newmark‐β method to validate its effectiveness and accuracy. The results demonstrate that relative errors in estimating the natural frequency and damping ratio using the EWT‐SH method are significantly smaller compared to traditional methods. Furthermore, the EWT‐SH method is applied to estimate the modal parameters of a real super‐tall building, i.e., the SEG Plaza building in Shenzhen, using acceleration responses. Identified results confirm the applicability and accuracy of the EWT‐SH method in real‐world scenarios and indicate that the frequencies and damping ratios of the SEG Plaza building noticeably decrease after 20 years of service, which could partially explain the SEG building vibration event on May 18, 2021. Since the identified frequencies are quite different from those of the original finite element (FE) model of the tall building, the dual‐loop particle swarm optimization (PSO) is specifically developed to update the FE model of SEG Plaza building.