4.7 Article

Rapid peak seismic response prediction of two-story and three-span subway stations using deep learning method

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Engineering, Geological

Seismic fragility analysis for subway station considering varying ground motion ensembles

Jiawei Jiang et al.

Summary: This study investigates the impact of the number of ground motion records in an ensemble on the post-earthquake failure probability of a subway structure. A 2D finite element model is used to consider the soil-subway station underground structure interaction. The cloud and incremental dynamical analysis methods are employed to analyze the seismic fragility of the structure. The results show that the number of records significantly affects the seismic fragility analysis in both methods, with optimal ensemble sizes of 300 records for the cloud-based analysis and 24 records for the IDA method.

SOIL DYNAMICS AND EARTHQUAKE ENGINEERING (2023)

Article Construction & Building Technology

Seismic response analysis of rectangular prefabricated subway station structure

Jinnan Chen et al.

Summary: The application of prefabricated assembly technology in underground engineering is still at an early stage, and research on the seismic behavior of prefabricated underground structures is limited. This study establishes refined finite element models and compares the seismic responses of prefabricated underground structures with different types of splicing joints to cast-in-place underground structures. The results show that prefabricated underground structures with rigid splicing joints have similar responses to cast-in-place structures, while those with non-rigid splicing joints experience slightly increased inter-story displacement but reduced internal forces and damage in the center column.

TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY (2023)

Article Engineering, Geological

Prediction of nonlinear seismic response of underground structures in single- and multi-layered soil profiles using a deep gated recurrent network

Yongxin Wu et al.

Summary: A deep learning approach based on the gated recurrent neural network (GRU) is proposed to predict the seismic responses of underground structures in single-layered soil and multi-layered soil. The GRU network achieved satisfactory prediction performances on the acceleration responses of underground structures in various soil conditions. It showed better prediction performance in a tunnel located in a homogeneous sand layer than in a clay layer.

SOIL DYNAMICS AND EARTHQUAKE ENGINEERING (2023)

Article Construction & Building Technology

Seismic performance and fragility of two-story and three-span underground structures using a random forest model and a new damage description method

Jing Yang et al.

Summary: This paper proposes a new method for evaluating the seismic performance and fragility of large underground structures. A finite element model of a nonlinear dynamic soil-underground structure interaction system is developed considering site variation and input ground motion uncertainty. The seismic responses of a subway station structure are calculated using the incremental dynamic analysis method for 900 cases, accelerated by Python software. A new concept of average seismic damage value is proposed to overcome limitations of expert judgment, and a random forest prediction model is used to estimate seismic performance levels (SPLs). The correlation between seismic damage and inter-story drift ratios (IDR) is verified, and a quantification system for SPL is advanced. The seismic fragility curves of the subway station structure are constructed and analyzed. Rating: 8/10.

TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY (2023)

Article Construction & Building Technology

Effect of parameters associated with soil-to-structure relative stiffness on seismic fragility curves of subway station

Jiawei Jiang et al.

Summary: This paper investigates the influence of relative stiffness parameters on the seismic fragility curves of subway station structures. The results show that the failure probability of the structure decreases significantly as soil shear wave velocity increases, and there is a significant difference in the failure probability between structures in heterogeneous and homogeneous soil. The cross-section type of the structure has less influence on its seismic vulnerability.

TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY (2023)

Article Engineering, Civil

Physical and numerical modeling of seismic soil-structure interaction of prefabricated subway station structure

Jinnan Chen et al.

Summary: Physical and numerical studies were conducted to investigate the behavior of multi-story and multi-span prefabricated subway station structures during earthquakes. A scaled model was subjected to a static pushover test to determine its horizontal resistance and interstory displacement ratio values. The experimental results showed that the upper layer of the structure suffered more severe damage than the lower layer, and the column ends were the weakest parts in terms of seismic resistance. Reliable splicing joints were observed, but visible cracks appeared at the side wall-middle span joint. Finite element analysis indicated that vertical load significantly affects the horizontal bearing capacity of the subway station.

ENGINEERING STRUCTURES (2023)

Article Engineering, Geological

Shaking table test for near-valley subway station-Part II: Seismic response of the station

Haitao Yu et al.

Summary: With the growth of metro lines in cities, the number of subway stations near urban valleys is increasing. However, the impact of valleys on nearby subway stations during earthquakes is not well understood. This study conducted shaking table tests to investigate the seismic performance of a two-story, three-span subway station near a valley. The results showed that the acceleration response of the near-valley structure was significantly larger compared to the case without a valley. The structure also exhibited strong lateral racking and increased dynamic earth pressure near the valley.

SOIL DYNAMICS AND EARTHQUAKE ENGINEERING (2023)

Article Engineering, Civil

Nonparametric probabilistic seismic demand model and fragility analysis of subway stations using deep learning techniques

Pengfei Huang et al.

Summary: This article proposes a novel and computationally efficient method for developing a nonparametric probabilistic seismic demand model (PSDM) to accurately and efficiently conduct fragility analysis of subway stations. The probability density evolution method (PDEM) is used to calculate the evolutionary probability density function of demand measure (DM) without assuming the distribution pattern of DM. To reduce computational cost, a one-dimensional convolutional neural network (1D-CNN) is used as a surrogate model to predict seismic responses. The results show that the PDEM-based PSDM has the best performance and the time-dependent fragility surface provides important indexes for resilience-based seismic evaluation such as estimating escape time and casualties in an earthquake.

UNDERGROUND SPACE (2023)

Article Engineering, Civil

Seismic vulnerability modelling of building portfolios using artificial neural networks

Petros Kalakonas et al.

Summary: The study investigates the advantages of incorporating machine learning algorithms such as artificial neural networks in earthquake engineering, demonstrating their potential superiority in addressing seismic risk assessment for buildings.

EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS (2022)

Article Engineering, Civil

Machine Learning-Based Fast Seismic Risk Assessment of Building Structures

Qi Tang et al.

Summary: A machine learning-based fast seismic risk assessment framework is proposed to efficiently estimate potential earthquake-induced loss of buildings, with hazard and structural parameters as inputs and risk values as outputs. A proof-of-concept study demonstrated the feasibility of the approach, with artificial neural networks achieving high accuracy for both regression and classification tasks.

JOURNAL OF EARTHQUAKE ENGINEERING (2022)

Article Engineering, Civil

Amplitude scaling of ground motions as a potential source of bias: Large-scale investigations on structural drifts

Konstantinos Theodoros Tsalouchidis et al.

Summary: This study investigates the bias introduced by amplitude scaling of ground motion records in earthquake engineering. The results show that scaled records can be safely used to assess seismic structural behavior, under certain conditions.

EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS (2022)

Article Construction & Building Technology

Stochastic ground motion simulation and seismic damage performance assessment of a 3-D subway station structure based on stochastic dynamic and probabilistic analysis

Rui Pang et al.

Summary: This paper analyzes the dynamic response and reliability level of a subway station from the perspective of random vibration. A model for generating nonstationary ground motions is proposed and combined with the probability density evolution method (PDEM) to analyze the seismic response of the station. The results show that the characteristics of earthquakes significantly influence the seismic response of subway stations, and the proposed method accurately evaluates the seismic performance and reliability level of subway stations.

TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY (2022)

Article Construction & Building Technology

Shaking table test of the effect of an enclosure structure on the seismic performance of a prefabricated subway station

Lianjin Tao et al.

Summary: The enclosure structure plays a crucial role in the seismic response of the prefabricated subway station structure, improving its performance and reducing damage.

TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY (2022)

Article Engineering, Civil

Static pushover test of spring-underground structure system for seismic performance analysis of underground structure

Runbo Han et al.

Summary: The static test can be used to study the seismic performance of underground structures. By simulating the initial stress state and soil-structure interactions, valuable information about interstory drift, concrete strain changes, failure phenomena, and seismic performance can be obtained.

ENGINEERING STRUCTURES (2022)

Article Engineering, Civil

Novel hybrid MFO-XGBoost model for predicting the racking ratio of the rectangular tunnels subjected to seismic loading

Van-Quang Nguyen et al.

Summary: This study introduces a novel hybrid MFO-XGBoost model for predicting the racking ratio of rectangular tunnels under seismic loading, which outperforms existing models. By analyzing dynamic simulations and constructing a database, the model effectively captures the relationship between different parameters and the racking ratio of the tunnel.

TRANSPORTATION GEOTECHNICS (2022)

Article Computer Science, Interdisciplinary Applications

Real-time regional seismic damage assessment framework based on long short-term memory neural network

Yongjia Xu et al.

Summary: This study proposes a framework for real-time regional seismic damage assessment based on the LSTM neural network architecture, which can rapidly and accurately assess earthquake-induced damage. By establishing a workflow and optimizing model utilization, damage prediction can be performed at a regional scale.

COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING (2021)

Article Engineering, Civil

Deep learning for nonlinear seismic responses prediction of subway station

Pengfei Huang et al.

Summary: A novel method for predicting the nonlinear seismic response of subway stations using deep learning approaches has been developed, with 1D-CNN and LSTM networks showing better prediction performance compared to baseline MLP model. The study demonstrates the potential of applying deep learning methods for reducing computational cost in seismic responses analysis.

ENGINEERING STRUCTURES (2021)

Article Engineering, Civil

Numerical simulation of damage evolution of Daikai station during the 1995 Kobe earthquake

Van-Quang Nguyen et al.

ENGINEERING STRUCTURES (2020)

Article Engineering, Geological

Seismic fragility assessment of the Daikai subway station in layered soil

Zilan Zhong et al.

SOIL DYNAMICS AND EARTHQUAKE ENGINEERING (2020)

Article Engineering, Civil

Seismic response analysis of assembled monolithic subway station in the transverse direction

Hongtao Liu et al.

ENGINEERING STRUCTURES (2020)

Article Construction & Building Technology

Seismic response of subway station in soft soil: Shaking table testing versus numerical analysis

Weifeng Wu et al.

TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY (2020)

Article Computer Science, Interdisciplinary Applications

Deep long short-term memory networks for nonlinear structural seismic response prediction

Ruiyang Zhang et al.

COMPUTERS & STRUCTURES (2019)

Article Engineering, Civil

Does amplitude scaling of ground motion records result in biased nonlinear structural drift responses?

Nicolas Luco et al.

EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS (2007)

Article Engineering, Geological

Selection of ground motion time series and limits on scaling

J Watson-Lamprey et al.

SOIL DYNAMICS AND EARTHQUAKE ENGINEERING (2006)

Article Engineering, Civil

Incremental dynamic analysis

D Vamvatsikos et al.

EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS (2002)