• Wind and Structures
• /
• v.36 no.6
• /
• pp.355-366
• /
• 2023

Although machine learning (ML) techniques have been widely used in various fields of engineering practice, their applications in the field of wind engineering are still at the initial stage. In order to evaluate the feasibility of machine learning algorithms for prediction of wind loads on high-rise buildings, this study took the exposure category type, wind direction and the height of local wind force as the input features and adopted four different machine learning algorithms including k-nearest neighbor (KNN), support vector machine (SVM), gradient boosting regression tree (GBRT) and extreme gradient (XG) boosting to predict wind force coefficients of CAARC standard tall building model. All the hyper-parameters of four ML algorithms are optimized by tree-structured Parzen estimator (TPE). The result shows that mean drag force coefficients and RMS lift force coefficients can be well predicted by the GBRT algorithm model while the RMS drag force coefficients can be forecasted preferably by the XG boosting algorithm model. The proposed machine learning based algorithms for wind loads prediction can be an alternative of traditional wind tunnel tests and computational fluid dynamic simulations.

• Computers and Concrete
• /
• v.31 no.1
• /
• pp.23-32
• /
• 2023

Reinforced concrete flat slab (RCFS) with columns is a standard gravity floor system for tall buildings in North America. Typically, RCFS-column connections are designed to resist gravity loads, and their contribution to resisting seismic forces is ignored. However, past experimental research has shown that RCFS-column connections have some strength and ductility, which may not be ignored. Advanced numerical models have been developed in the past to determine the nonlinear cyclic behavior of RCFS-column connections. However, these models are either too complicated for nonlinear dynamic analysis of an entire building or not developed to model the behavior of modern RCFS-column connections. This paper proposes a new nonlinear model suitable for modern RCFS-column connections. The numerical model is verified using experimental data of specimens with various material and reinforcement properties. A 40-story RC shear wall building was designed and analyzed to investigate the influence of RCFS on the global response of tall concrete buildings. The seismic responses of the building with and without the RCFS were modelled and compared. The results show that the modelling of RCFS has a significant impact on the inter-story drifts and force demands on both the seismic force-resisting and gravity elements.

• Wind and Structures
• /
• v.36 no.4
• /
• pp.237-247
• /
• 2023

The emergence of high-rise buildings has necessitated frequent structural health monitoring and maintenance for safety reasons. Wind causes damage and structural changes on tall structures; thus, safe structures should be designed. The pressure developed on tall buildings has been utilized in previous research studies to assess the impacts of wind on structures. The wind tunnel test is a primary research method commonly used to quantify the aerodynamic characteristics of high-rise buildings. Wind pressure is measured by placing pressure sensor taps at different locations on tall buildings, and the collected data are used for analysis. However, sensors may malfunction and produce erroneous data; these data losses make it difficult to analyze aerodynamic properties. Therefore, it is essential to generate missing data relative to the original data obtained from neighboring pressure sensor taps at various intervals. This study proposes a deep learning-based, deep convolutional generative adversarial network (DCGAN) to restore missing data associated with faulty pressure sensors installed on high-rise buildings. The performance of the proposed DCGAN is validated by using a standard imputation model known as the generative adversarial imputation network (GAIN). The average mean-square error (AMSE) and average R-squared (ARSE) are used as performance metrics. The calculated ARSE values by DCGAN on the building model's front, backside, left, and right sides are 0.970, 0.972, 0.984 and 0.978, respectively. The AMSE produced by DCGAN on four sides of the building model is 0.008, 0.010, 0.015 and 0.014. The average standard deviation of the actual measures of the pressure sensors on four sides of the model were 0.1738, 0.1758, 0.2234 and 0.2278. The average standard deviation of the pressure values generated by the proposed DCGAN imputation model was closer to that of the measured actual with values of 0.1736,0.1746,0.2191, and 0.2239 on four sides, respectively. In comparison, the standard deviation of the values predicted by GAIN are 0.1726,0.1735,0.2161, and 0.2209, which is far from actual values. The results demonstrate that DCGAN model fits better for data imputation than the GAIN model with improved accuracy and fewer error rates. Additionally, the DCGAN is utilized to estimate the wind pressure in regions of buildings where no pressure sensor taps are available; the model yielded greater prediction accuracy than GAIN.

• Structural Engineering and Mechanics
• /
• v.86 no.1
• /
• pp.29-48
• /
• 2023

Pounding happens when contiguous structures with differing heights vibrate out of line caused by a seismic activity. The situation is aggravated due to the insufficient separation gap between the structures which can lead to the crashing of the buildings or total collapse of an edifice. Countries around the world have compiled building standards to address the pounding issue. One of the strategies recommended is the introduction of the separation gap between structures. AS1170.4-2007 is an Australian standard that requires 1% of the building height as a minimum separation gap between buildings to preclude pounding. This article presents experimental and numerical tests to determine the adequacy of this specification to prevent the occurrence of seismic pounding between steel frame structures under near-field and far-field earthquakes. The results indicated that the recommended minimum separation gap based on the Australian Standard is inaccurate if low-rise structure in a coupled case is utilised under both near and far field earthquakes. The standard is adequate if a tall building is involved but only when a far-field earthquake happens. The research likewise presents results derived by using the ABS and SRSS methods.

• Wind and Structures
• /
• v.35 no.5
• /
• pp.297-307
• /
• 2022

Over the past few decades, the use of wind tunnels has been increasing as a result of the rapid growth of cities and the urge to build taller and non-typical structures. While the accuracy of a wind tunnel study on a tall building requires several aspects, the precise extraction of wind pressure plays a significant role in a successful pressure test. In this research study, a low-cost expandable synchronous multi-pressure sensing system (SMPSS) was developed and validated at Ryerson University's wind tunnel (RU-WT) using electronically scanning pressure sensors for wind tunnel tests. The pressure system consists of an expandable 128 pressure sensors connected to a compact data acquisition and a host workstation. The developed system was examined and validated to be used for tall buildings by comparing mean, root mean square (RMS), and power spectral density (PSD) for the base moments coefficients with the available data from the literature. In addition, the system was examined for evaluating the mean and RMS pressure distribution on a standard low-rise building and were found to be in good agreement with the validation data.

• International Journal of High-Rise Buildings
• /
• v.11 no.4
• /
• pp.331-346
• /
• 2022

Reproducing the horizontally homogeneous atmospheric boundary layer in computational wind engineering is essential for predicting the wind loads on structures. One of the important issues is to use fully developed inflow conditions, which will lead to the consistence problem between inflow condition and internal roughness. Thus, by analyzing the previous results of computational fluid dynamic modeling turbulent horizontally homogeneous atmospheric boundary layer, we modify the past hypotheses, detailly derive a new type of inflow condition for standard k-ε turbulence model. A group of remedial approaches including formulation for wall shear stress and fixing the values of turbulent kinetic energy and turbulent dissipation rate in first wall adjacent layer cells, are also derived to realize the consistence of inflow condition and internal roughness. By combing the approaches with four different sets of inflow conditions, the well-maintained atmospheric boundary layer flow verifies the feasibility and capability of the proposed inflow conditions and remedial approaches.

• International Journal of High-Rise Buildings
• /
• v.2 no.3
• /
• pp.245-255
• /
• 2013

This paper presents the results of a set of wind tunnel tests carried out to examine wind-induced overall structural loads on rectangular medium-rise buildings. Emphasis was directed towards torsion and its correlation with peak shear forces in transverse and longitudinal directions. Two building models with the same horizontal dimensions but different gabled-roof angles ($0^{\circ}C$ and $45^{\circ}C$) were tested at different full-scale equivalent eave heights (20, 30, 40, 50, and 60 m) in open terrain exposure for all wind directions (every $15^{\circ}C$). Wind-induced pressures were integrated over building surfaces and results were obtained for along-wind force, across-wind force, and torsional moment. Maximum wind force component was given along with the other simultaneously-observed wind force components normalized by the overall peak. The study found that for flat-roofed buildings maximum torsion for winds in transverse direction is associated with 80% of the overall shear force perpendicular to the longer horizontal building dimension; and 45% of the maximum shear occurs perpendicular to the smaller horizontal building dimension. Comparison of the wind tunnel results with current torsion provisions in the American wind standard, the Canadian and European wind codes demonstrate significant discrepancies. Suggested load combination factors were introduced aiming at an adequate evaluation of wind load effects on rectangular medium-rise buildings.

• International Journal of High-Rise Buildings
• /
• v.10 no.3
• /
• pp.203-210
• /
• 2021

With the development of urbanization, the increasing of buildings density in urban core areas result in the complexity of construction environment. High-rise landmark building is always preferred in the construction of urban core areas. Super high-rise buildings construction are facing construction management difficulties due to the complex working conditions and enormous building system, especially with the complex surrounding environment of the urban core area, the construction management of super high-rise buildings in the area requires higher, refined and detailed standard. Based on a super high-rise project in a core area of Shanghai which has 370 m building height and 772,643 m² building area, with complex surrounding environment, narrow construction site and many super-high-altitude crossing works. With the application of BIM technology, the Internet of Things, the LAN communication and other various intelligent mechanical equipment, information management systems, the efficiency and refinement of construction management are improved, ensuring the smooth implementation of the project while effectively controlling the impact on the surrounding environment.

• International Journal of High-Rise Buildings
• /
• v.7 no.4
• /
• pp.397-408
• /
• 2018

In a recent tragic fire incident, the Plasco Tower collapsed after an intense outburst of fire lasting for three and a half hours and claiming the lives of 16 firefighters and 6 civilians. This paper will present continuing collaborative work between Hong Kong Polytechnic University and Queen's University in Canada to model the progressive collapse of the tower. The fire started at the 10th floor and was observed to have travelled along the floor horizontally and through the staircase and windows vertically. Plasco Tower was steel structure and all the steel sections were fabricated by welding standard European channel or angle profiles and no fire protection was applied. Four internal columns carried the loads transferred by the primary beams, and box columns were constructed along the perimeter of the building as a braced tube for resisting seismic loading. OpenSees fibre-based sections and displacement-based beam-column elements are used to model the frames, while shell elements are used for the reinforced concrete floor slabs. The thermal properties and elevated temperature mechanical properties are as recommended in the Eurocodes. The results in this preliminarily analysis are based on rough estimations of the structure's configuration. The ongoing work looks at modeling the Plasco Tower based on the most accurate findings from reviewing many photographs and collected data.

• International Journal of High-Rise Buildings
• /
• v.13 no.1
• /
• pp.97-102
• /
• 2024

In this paper, we would like to share our ongoing research on global population and demographic shifts and the corresponding need for diverse responses. As population growth varies worldwide, the pressing issue is the current global housing shortage. The USA alone lacks 4 million homes, underlining the urgency for new construction and renewal of existing. Our focus is primarily on new building processes, which must also incorporate elements of renewal for future sustainability. Our research addresses several key questions: How will roles for construction professionals change? What should be the primary goal of the design process? What types of technologies are currently available, and which aspects of the process can be enhanced with AI? A significant part of our study is exploring sustainable building methods that reduce embodied carbon and increase speed of construction. Our goal is to extend the transition from smart homes to cities, analyzing the evolution towards smart communities and cities. A critical aspect of our research is the 'kit of parts concept, involving prefabrication and modular construction. This approach is essential for both rebuilding and new projects, potentially lowering costs in manufacturing and design for long term. Lastly, we present a detailed comparison of the construction industry with manufacturing.