Convolutional variational autoencoder for ground motion classification and generation toward efficient seismic fragility assessment

Ning, Chunxiao; Xie, Yazhou

doi:10.1111/mice.13061

Cited by 8 publications

(1 citation statement)

References 111 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The rapid increase in earthquake ground motions in recent years has also prompted researchers to use cluster analysis, an unsupervised big data approach, for categorization [20][21][22][23]. Alimoradi et al introduced a fuzzy C-means clustering method for strong earthquake ground motion records, classifying 1470 horizontal ground motion records into six categories based on peak ground acceleration, duration, effective peak acceleration, effective peak velocity, maximum incremental velocity, and maximum incremental displacement [24].…”

Section: Introductionmentioning

confidence: 99%

A Classification Method of Earthquake Ground Motion Records Based on the Results of K-Means Clustering Analysis

Ding,

Nie,

et al. 2024

Buildings

View full text Add to dashboard Cite

This paper presents a classification method for earthquake ground motion records utilizing the results of K-means cluster analysis. The moment magnitude and Joyner–Boore distance are utilized as the primary parameters for clustering the earthquake ground motion records. The classification boundaries are established through an examination of moment magnitude ranges, Joyner–Boore distance ranges, and spectral characteristics within each cluster. In this study, a comprehensive dataset comprising 7627 horizontal earthquake acceleration records was meticulously curated for analysis. The data were subjected to separate clustering and grouping procedures, allowing for insightful comparisons between the resultant clusters. Significant disparities in spectral characteristics across the classification groups were demonstrated. These differences become particularly pronounced when a moment magnitude threshold of 6 and a Joyner–Boore distance threshold of 140 km are employed to categorize the ground motion records. The approach underscores the substantial impact of classification based on earthquake ground motion spectral characteristics, while also mitigating the potential instabilities inherent in cluster analysis results. A refined and quantitatively robust framework for understanding and categorizing earthquake ground motions is provided, offering valuable insights for seismic data analysis and contributing to more accurate and reliable assessments of seismic activity.

show abstract

Section: Introductionmentioning

confidence: 99%

A Classification Method of Earthquake Ground Motion Records Based on the Results of K-Means Clustering Analysis

Ding,

Nie,

et al. 2024

Buildings

View full text Add to dashboard Cite

show abstract

Enabling efficient regional seismic fragility assessment of multi‐component bridge portfolios through Gaussian process regression and active learning

Ning,

Xie,

Burton

et al. 2024

Earthq Engng Struct Dyn

Self Cite

View full text Add to dashboard Cite

Regional seismic fragility assessment of bridge portfolios must address the embedded uncertainties and variations stemming from both the earthquake hazard and bridge attributes (e.g., geometry, material, design detail). To achieve bridge‐specific fragility assessment, multivariate probabilistic seismic demand models (PSDM) have recently been developed that use both the ground motion intensity measure and bridge parameters as inputs. However, explicitly utilizing bridge parameters as inputs requires numerous nonlinear response history analyses (NRHAs). In this situation, the associated computational cost increases exponentially for high‐fidelity bridge models with complex component connectivity and sophisticated material constitutive laws. Moreover, it remains unclear how many analyses are sufficient for the response data and the resulting demand model to cover the entire solution space without overfitting. To deal with these issues, this study integrates Gaussian process regression (GPR) and active learning (AL) into a multistep workflow to achieve efficient regional seismic fragility assessment of bridge portfolios. The GPR relaxes the probability distribution assumptions made in typical cloud analysis‐based PSDMs to enable heteroskedastic nonparametric seismic demand modeling. The AL leverages the varying standard deviation to select the least but most representative bridge‐model‐ground‐motion sample pairs to conduct NRHA with much‐improved efficiency. Both independent and correlated multi‐output GPRs are proposed to deal with bridge portfolios with seismic demand correlations among multiple components (column, bearing, shear key, abutment, unseating, and joint seal). Considering a single benchmark highway bridge class in California as the case study, the AL‐GPR framework and the associated component‐level fragility results are investigated in terms of their efficiency, accuracy, and robustness. The fragility results show that 70 AL‐selected samples would enable the GPR to derive bridge‐specific fragility models comparable to the ones using the multiple stripes analysis approach with 1950 ground motions considered for each individual bridge. The AL‐GPR model also successfully captures the physics of how bridge span length, deck area, column slenderness, and steel reinforcement ratio would change the damage state exceedance probabilities of different bridge components. The efficiency of AL stems from the fact that, with the multi‐output independent GPR, a stable and reliable fragility model can be achieved using 50 AL‐selected samples compared to at least 270 randomly chosen samples. The proposed methodology advances the state of the art in enabling more efficient and reliable regional seismic fragility assessment of multi‐component bridge portfolios.

show abstract

A Clustering‐Based Loading History Selection Method for the Calibration of Buckling‐Restrained Braces in Seismic Analysis

Zhang,

Kwon,

Christopoulos

2024

Earthq Engng Struct Dyn

View full text Add to dashboard Cite

The accuracy of engineering demand parameters obtained from nonlinear time‐history analysis (NTHA) is crucial in a performance‐based earthquake engineering framework. Hysteretic models are commonly used for predicting the nonlinear response of critical structural components and are essential for ensuring the accuracy of NTHA results. Hysteretic models are typically calibrated based on the experimental data from a quasi‐static test utilizing a standardized reversed‐cyclic loading protocol. Recent studies, however, have shown that this conventional model calibration method may lead to inaccurate dynamic response of a structural system because the standardized reversed‐cyclic loading history (LH) is unrealistic compared to what the component would experience in a structural system subjected to earthquake ground motions. These studies have demonstrated the benefits of using more realistic LHs for hysteretic model calibration by evaluating the calibration relevance (CR) of different calibration methods. The objective of this study is to extend the framework of evaluating calibration methods and to provide additional insights and recommendations to enhance the robustness of model calibrations. This is achieved by analyses conducted on a suite of buckling‐restrained braced frames (BRBFs). First, a comprehensive global sensitivity analysis (GSA) of parameters for a commonly used hysteretic model is conducted based on a probabilistic input model that was derived previously from multiple hybrid simulations. The GSA is conducted by evaluating Sobol’ indices using a metamodel‐based approach with polynomial chaos expansions (PCEs). Next, 20 features are extracted from each realistic LH considering the characteristics in the transitional and plastic ranges of the corresponding hysteresis curve. A clustering‐based LH selection criterion based on these features is then proposed to identify an optimal cluster of LHs exhibiting greater CR values, which are desirable in achieving higher accuracy in the global model of the structural system.

show abstract

Convolutional variational autoencoder for ground motion classification and generation toward efficient seismic fragility assessment

Cited by 8 publications

References 111 publications

A Classification Method of Earthquake Ground Motion Records Based on the Results of K-Means Clustering Analysis

A Classification Method of Earthquake Ground Motion Records Based on the Results of K-Means Clustering Analysis

Enabling efficient regional seismic fragility assessment of multi‐component bridge portfolios through Gaussian process regression and active learning

A Clustering‐Based Loading History Selection Method for the Calibration of Buckling‐Restrained Braces in Seismic Analysis

Contact Info

Product

Resources

About