Xinzheng Lu

Xinzheng Lu
Tsinghua University | TH · Department of Civil Engineering

PhD

About

276
Publications
138,220
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
6,003
Citations
Introduction
Xinzheng Lu is a Full Professor and the Head of the Institute of Disaster Prevention and Mitigation of the Department of Civil Engineering at Tsinghua University. His major research interests cover disaster prevention and mitigation, structural numerical simulation, and collapse prevention. Prof. Lu has published more than 200 papers in refereed journals and ten books. He has been listed as one of “the most cited Chinese researchers from 2014-2021”.
Additional affiliations
January 2005 - present
Tsinghua University

Publications

Publications (276)
Article
Full-text available
Collapse resistance of high-rise buildings has become a research focus because of the frequent occurrence of strong earthquakes and terrorist attacks in recent years. Research development has demonstrated that numerical simulation is becoming one of the most powerful tools for collapse analysis in addition to the conventional laboratory model tests...
Article
When a reinforced concrete (RC) frame subjected to an edge-column-removal scenario, its floor system exhibits a complicated mechanism against progressive collapse due to the interaction between beams and slabs and the two-way load transfer characteristics. In this study, laboratory tests of five 1/3-scaled RC frame substructure specimens, including...
Book
Full-text available
The first edition of this monograph, presenting accurate and efficient simulations of seismic damage to buildings and cities, has received significant attention from the research community. To keep abreast of the rapid development in recent years, our latest breakthrough achievements have been added to this new edition, including novel resilient st...
Article
Every year, earthquakes result in severe economic losses and a significant number of casualties worldwide. In limiting the losses that occur after these extreme events, timely and accurate assessment of seismic damages and mobilizing proportionate post‐event relief efforts play crucial roles. Traditional on‐site investigation generally results in p...
Article
Full-text available
Automated rule checking (ARC) is expected to significantly promote the efficiency and compliance of design in the construction industry. The most vital and complex stage of ARC is interpreting the regulatory text into a computer-processable format. However, existing systems and studies of rule interpretation either require considerable time-consumi...
Article
Monitoring the deformation or displacement response of buildings is critical for structural safety. Recently, the development of computer vision has led to extensive research on the application of vision-based measurements in the structural monitoring. This enables the use of urban surveillance video cameras, which are widely installed and can prod...
Article
Full-text available
Strong motion data recorded by strong-motion networks are essential for preventing and mitigating earthquake disasters, such as earthquake early warning and earthquake emergency responses, and the type of accelerometer can significantly influence the quality of recorded ground motions (GMs) and the subsequent usage. Different types of accelerometer...
Article
Full-text available
As an essential task for the architecture, engineering, and construction (AEC) industry, information processing and acquiring from unstructured textual data based on natural language processing (NLP) are gaining increasing attention. Although deep learning (DL) models for NLP tasks have been investigated for years, domain-specific pretrained DL mod...
Data
OpenSees program with data-physics coupling-driven simulation framework. A uniaxial material BraceNN is developed, which can load the pre-trained neural network model pt file, and calculate the reaction force vector based on the input displacement vector. For details: Advanced corrective training strategy for surrogating complex hysteretic behavio...
Data
These networks are modified based on LSTM, Transformer and GRU+Attention network, respectively. For more details of the modified network, please refer to the paper of our research group: Yongjia Xu, Xinzheng Lu, Yifan Fei, Yuli Huang. Data-driven hysteretic behavior simulation based on weighted stacked pyramid neural network architecture. (Under R...
Preprint
Long-span cable-stayed bridges often have a design service life of more than a hundred years, during which they may experience multiple earthquake events and accumulate seismic damage if they are located in seismic-prone regions. Earthquake occurrence is discretely and randomly distributed over the life cycle of a long-span cable-stayed bridge and...
Article
Despite the advances in modeling component behavior, high-fidelity finite element simulation remains challenging and is limited by the computational efficiency of large-scale models. A predictive simulation framework based on deep learning is proposed to provide accurate and efficient hysteretic models for structural analysis. The proposed framewor...
Article
Beam and slab design is a critical component of shear wall structure design. Currently, conventional manual design is time-consuming, and defining objective functions and design variables of an optimization design is challenging. In contrast, deep learning methods can learn high-dimensional image features and generate new designs, providing new sol...
Article
In densely-populated cities, complex site-city interaction (SCI) effects can occur and may result in non-negligible influences on the input motions to buildings. Due to its complexity, topographic amplification has not yet been considered in most SCI investigations, particularly in experimental tests. This study conducted seven sets of shaking tabl...
Article
The strong ground motions (GMs) recorded by strong motion networks are significant to increase the accuracy of seismic damage assessment. However, the influence of sensor density on seismic damage assessment remains unclarified. Therefore, a workflow is proposed in this study to quantitatively analyze the influence of sensor density on seismic dama...
Article
Full-text available
Glass curtain walls (GCWs) are among the most commonly used building envelope components in modern buildings, and they can be divided into point-supported or frame-supported GCWs. Much of the current literature on the seismic performance of GCWs has focused on frame-supported GCWs, resulting in a dearth of data about point-supported GCWs. In this w...
Preprint
An accurate and efficient simulation of the hysteretic behavior of materials and components is essential for structural analysis. The surrogate model based on neural networks shows significant potential in balancing efficiency and accuracy. However, its serial information flow and prediction based on single-level features adversely affect the netwo...
Article
Flat plate-column joints with in-plane constraints exhibit a suspension mechanism under large deformations after punching shear failure, which significantly affects the progressive collapse behavior of the entire flat plate structural systems. However, in-plane constraints were ignored in the existing tests by which the suspension mechanism could n...
Article
Full-text available
We are pleased to announce a Special Issue dedicated to AI and Data-driven Methods in Earthquake Engineering, with Professor Xinzheng Lu and Professor Henry Burton as the Guest Editors. The objective of this Special Issue is to present the cutting-edge integration of AI techniques and earthquake engineering. The special issue covers novel AI and da...
Article
Windows are one of the non-structural components of buildings that are most vulnerable to wind damage. It is important to obtain rapid and accurate predictions of wind-induced window damage in urban areas. A novel automated method for simulating the wind damage to building windows at the city scale is proposed in this study based on oblique photogr...
Article
Full-text available
Earthquake disasters have caused enormous casualties and economic losses so far, threatening the social and economic development of humanity. At present, artificial intelligence (AI) is one of the frontiers and central issues in both academic research and engineering practice. AI refers to the branch of computer science that develops machines and s...
Article
Damping is fundamental to structural dynamics. Reasonable damping models facilitate accurate and reliable dynamic analyses of damped structures. Existing experiments indicate that damping is dependent but not proportional to the frequency. Hence, it may be challenging for viscous and rate-independent damping models to accurately simulate the freque...
Preprint
Full-text available
As an essential task for the architecture, engineering, and construction (AEC) industry, information retrieval (IR) from unstructured textual data based on natural language processing (NLP) is gaining increasing attention. Although various deep learning (DL) models for IR tasks have been investigated in the AEC domain, it is still unclear how domai...
Article
Intelligent structural design using generative adversarial networks (GANs) is a revolutionary design approach for building structures. Despite its far‐reaching capability, the data quantity and quality may have limited the performance of such a data‐driven network. This study proposes to enhance the objectiveness of training processes by innovative...
Article
A novel seismic resilient outrigger was developed in this study, which is composed of high-strength steel chords with reduced beam sections (RBSs) and buckling restrained braces (BRBs). This energy-dissipating outrigger had a good deformation capacity and stable load-bearing capacity. Its chords remained elastic under the maximum considered earthqu...
Article
A slab-column joint in a flat plate structure may exhibit upward or downward punching shear (UPS and DPS) failure when subjected to different abnormal loading conditions. This can cause distinct residual deformations of the slabs, which in turn influences the behavior of the consequent progressive collapse of the entire structure. This paper presen...
Article
The progressive collapse of structures often causes serious casualties and property loss. The intrinsic characteristic of progressive collapse is large-scale domino-like structural damage caused by accidental local failure induced by uncertainty factors. Therefore, it is vital to conduct uncertainty analyses on the progressive collapse of reinforce...
Article
Full-text available
Due to uncertainties stemming from climate change, natural and man-made disasters, and extreme events, unexpected disruptions in the operation of our countries’ infrastructure may put the functioning of our societies and their economies at risk [...]
Article
Artificial intelligence is reshaping building design processes to be smarter and automated. Considering the increasingly wide application of shear wall systems in high-rise buildings and envisioning the massive benefit of automated structural design, this paper proposes a generative adversarial network (GAN)-based shear wall design method, which le...
Article
Full-text available
On June 24, 2021, a 40-year-old reinforced concrete flat plate structure building in Miami suffered a sudden partial collapse. This study analyzed the overall performance and key components of the collapsed building based on the building design codes (ACI-318 and GB 50010). Punching shear and post-punching performances of typical slab-column joints...
Article
Full-text available
Computational fluid dynamics (CFD) simulation is a core component of wind engineering assessment for urban planning and architecture. CFD simulations require clean and low-complexity models. Existing modeling methods rely on static data from geographic information systems along with manual efforts. They are extraordinarily time-consuming and have d...
Article
To enhance post-punching strengths and deformation capacities of flat plate-column joints for mitigating progressive collapse, two strengthening methods including stirrups and embedded ring beams within the joint regions were proposed. An experimental test program on six flat plate-column joint specimens with in-plane constraints was conducted unde...
Article
Accidental events that may lead to a progressive collapse (e.g., explosions and collisions) and earthquakes are two types of destructive hazards for super-tall buildings. The study of the resilience of super-tall buildings against these hazards has become a crucial issue. Corresponding research outcomes have important social, political, and economi...
Article
Progressive collapse of reinforced concrete (RC) flat plate systems can be significantly influenced by the post-punching performance of their slab-column joints under large deformations. This work presents a series of static collapse tests on four flat slab-column joint specimens with slab in-plane restraint. The effects of different punching direc...
Article
Fragility analysis is widely used in seismic performance assessment of bridges but uncertainties in seismic demand and bridge modelling affect the accuracy of assessment results. This study proposes a digital twin-based collapse fragility assessment method for long-span cable-stayed bridges under strong earthquakes. A scaled long-span cable-stayed...
Article
Full-text available
The cost of dedicated sensors has hampered the collection of the high-quality seismic response data required for real-time health monitoring and damage assessment. The emergence of crowdsensing technology, where a large number of mobile devices collectively share data and extract information of common interest, may help remove such obstacles and mi...
Chapter
Full-text available
In addition to the earthquake-induced damage to the buildings, regional seismic loss estimation is also critical for disaster management. Consequently, this chapter presents the building-level and component-level seismic loss estimation methods. To solve data acquisition challenges in seismic loss prediction, various loss estimation methods using d...
Chapter
Full-text available
This chapter proposes nonlinear multiple degree-of-freedom (MDOF) models for city-scale nonlinear time-history analyses in an attempt to predict seismic damage to buildings in large urban areas. The computational models and the corresponding parameter determination methods are developed for multi-story masonry buildings, reinforced concrete and ste...
Chapter
Full-text available
Using the methods proposed in Chaps. 7– 11, this chapter presents six typical examples of urban building seismic simulation. Up to hundreds of thousands of buildings are simulated, demonstrating the advantages and applicability of the proposed methods.
Chapter
Full-text available
Using the proposed high-fidelity computational models in Chap. 2, this chapter presented the earthquake-induced collapse simulation of two real-world landmark supertall buildings, i.e., the Shanghai Tower (H = 632 m) and the CITIC Tower (H = 528 m). In-depth discussions are also provided with respect to the collapse process and failure mechanisms o...
Chapter
Full-text available
Following Chap. 3 which primarily focuses on the overall structural performance of supertall buildings, this chapter is developed on the basis of increased demand on seismically resilient tall buildings. It details the structural performance and seismic resilience of typical concrete and steel tall buildings designed based on the Chinese and US cod...
Chapter
Full-text available
This chapter proposes a suite of high-fidelity computational models for tall building simulation (covering fiber-beam element model, multi-layer shell element model, and so forth), followed by model validation against published experimental results. Subsequently, graphics processing unit (GPU)-based high performance matrix solvers in conjunction wi...
Chapter
Full-text available
This chapter firstly introduces the experimental work on the seismic resilient outriggers. It is worthy to mention that as supertall buildings are important landmarks of a modern city, the progressive collapse prevention of the secondary frames of the buildings is also frequently required in addition to the seismic design requirement. To overcome t...
Chapter
Full-text available
Despite the improved accuracy of the high-fidelity computational models, excessive computational workload limits their scope of applications in the preliminary design phase. Therefore, simplified models are proposed in this chapter, which can greatly reduce the modeling and computational cost without compromising desired accuracy. The simplified mo...
Chapter
Full-text available
To facilitate interpretation of the urban building seismic simulation results, realistic visualizations are highly critical particularly for nonprofessional stakeholders and users. With this in mind, 2.5D, 3D, and photo-realistic visualization models are proposed in this chapter to enhance visualization capabilities of urban building seismic simula...
Chapter
Full-text available
The city-scale nonlinear THA can also be used to evaluate the extent of the emergency response and recovery after an earthquake. This chapter firstly proposes a real-time earthquake damage assessment using recorded ground motions and city-scale nonlinear THA, which can significantly reduce the uncertainties of the ground motion inputs. Subsequently...
Chapter
Full-text available
This chapter firstly presents the fire following earthquake (FFE) simulation method considering the earthquake-induced damage to the sprinkler systems. Subsequently, physics-based FFE simulation and high-fidelity visualization, considering seismic damage to buildings, are proposed. In addition, prediction models replicating the falling behavior and...
Article
Earthquake-induced landslides (EQILs) can cause severe economic losses and casualties. The prompt assessment of EQILs can provide an important reference for emergency rescue. Based on recorded ground motions and the Newmark sliding block method, a near-real-time prediction method for EQILs is proposed, and the corresponding prompt assessment system...
Article
Full-text available
Effective vibration recognition can improve the performance of vibration control and structural damage detection and is in high demand for signal processing and advanced classification. Signal-processing methods can extract the potent time-frequency-domain characteristics of signals; however, the performance of conventional characteristics-based cl...
Article
In this study, comparative investigations of a typical steel moment frame and a steel frame-braced core-tube structure, designed following different seismic codes, are conducted to evaluate the significant differences between the Chinese and the United States (US) seismic codes for steel buildings. The study outcomes can enhance the understanding o...
Article
Regional ground-motion simulation is important for the post-earthquake seismic damage assessment. Herein, a ground-motion simulation method using recorded ground motions is proposed. Inverse-distance-weighted interpolation of the response spectra is performed to obtain the response spectrum at the target location. Then, the ground motion time histo...
Chapter
Post-earthquake fires occur frequently, and the seismic damage to non-structural components results in dangerous fire and evacuation environments. Both firefighters and trapped people will face serious threats to life during the rescue. Consequently, a simulation framework of an indoor post-earthquake fire rescue scenario based on building informat...
Conference Paper
p>After earthquakes, an accurate and efficient seismic damage prediction is indispensable for emergency response. Existing methods face the dilemma between accuracy and efficiency. A real-time and accurate seismic damage prediction method based on machine-learning is proposed here. 48 intensity measures are used as input to represent the ground mot...
Article
Community resilience against major disasters is a multidisciplinary research field that garners an ever-increasing interest worldwide. This paper provides summaries of the discussions held on the subject matter and the research outcomes presented during the Second Resilience Workshop in Nanjing and Shanghai. It, thus, offers a community view of pre...
Article
During typhoon events, wind damage to trees in urban areas may have various adverse impacts on urban functions and cause direct and indirect economic losses. To realize the near real-time prediction of wind damage to urban trees, this study proposes a high-efficiency simulation framework by coupling computational fluid dynamics and mechanistic tree...
Preprint
Full-text available
Automated rule checking (ARC) is expected to significantly promote the efficiency and compliance of design in the construction industry. The most vital and complex stage of ARC is interpreting the regulatory text into a computer-processable format. However, existing systems and studies of rule interpretation either require considerable time-consumi...
Article
Accurate finite element models play significant roles in the design, health monitoring and life-cycle maintenance of long-span bridges. However, due to uncertainties involved in finite element modelling, updating of the finite element model to best represent the real bridge is inevitable. This is particularly true after a long-span bridge experienc...
Article
Effective post-earthquake response requires a prompt and accurate assessment of earthquake-induced damage. However, existing damage assessment methods cannot simultaneously meet these requirements. This study proposes a framework for real-time regional seismic damage assessment that is based on a Long Short-Term Memory (LSTM) neural network archite...
Article
After earthquakes, an accurate and efficient seismic-damage prediction is indispensable for emergency response. Existing methods face the dilemma between accuracy and efficiency. A real-time and accurate seismic-damage prediction method based on machine-learning algorithms and multiple intensity measures (IMs) is proposed here. 48 IMs are used for...