2020
DOI: 10.1177/8755293020919414
|View full text |Cite
|
Sign up to set email alerts
|

Efficient intensity measures and machine learning algorithms for collapse prediction of tall buildings informed by SCEC CyberShake ground motion simulations

Abstract: In contrast to approaches based on scaling of recorded seismograms, using extensive inventories of numerically simulated earthquakes avoids the need for any selection and scaling of motions which implicitly requires assumptions on intensity measures (IMs) that correlate with structural response. This study has the objectives to examine seismogram features that control the collapse response of tall buildings and to develop efficient and reliable collapse classification algorithms. To that end, machine learning … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

0
13
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6

Relationship

1
5

Authors

Journals

citations
Cited by 16 publications
(13 citation statements)
references
References 35 publications
0
13
0
Order By: Relevance
“…They are represented by the vertical lines at 30 s and 55 s in Figure 2A, similar to the calculation of the significant duration. [43,44] In the time interval between these time instants, the desired percentiles of the absolute values of the acceleration response are determined. For example, in Figure 2A, the horizontal dash-dotted lines correspond to the 80th percentile, that is, the areas labeled A1 and A2 contain 20% of the accelerations, while area B contains the remaining 80% in the time frame between 30 and 55 s. The peak acceleration indicated by the marker corresponds to the common definition of spectral acceleration.…”
Section: Percentile Spectramentioning
confidence: 99%
See 1 more Smart Citation
“…They are represented by the vertical lines at 30 s and 55 s in Figure 2A, similar to the calculation of the significant duration. [43,44] In the time interval between these time instants, the desired percentiles of the absolute values of the acceleration response are determined. For example, in Figure 2A, the horizontal dash-dotted lines correspond to the 80th percentile, that is, the areas labeled A1 and A2 contain 20% of the accelerations, while area B contains the remaining 80% in the time frame between 30 and 55 s. The peak acceleration indicated by the marker corresponds to the common definition of spectral acceleration.…”
Section: Percentile Spectramentioning
confidence: 99%
“…In this way, the aim is to capture the sustained amplitude of GM that has been shown to affect structural collapse in certain cases. [44,45] One advantage of the proposed percentile spectra is their straightforward computation. That is, the procedure for their calculation is the same as for the calculation of the response spectra, the only modification being that a percentile response is of interest rather than the peak response.…”
Section: Percentile Spectramentioning
confidence: 99%
“…5,6 Previous research on application of ML tools for seismic fragility assessment revolved around development of probabilistic seismic demand models and parameterized fragility functions with application to highway bridges e.g. 7-18, single-degree-of-freedom structures on liquefiable sand deposit, 19 reinforced concrete (RC) shear walls, 20 risk modeling of regional portfolios of structures, 14,15,18,[21][22][23][24] and estimation of collapse vulnerability of buildings. [25][26][27][28] However, similar to the general trends in the ML community, 29 the majority of the past research efforts focused on algorithmic developments or contrasting of the performance of different ML tools, while putting less emphasis on the most effective use of data.…”
Section: Introductionmentioning
confidence: 99%
“…7-18, single-degree-of-freedom structures on liquefiable sand deposit, 19 reinforced concrete (RC) shear walls, 20 risk modeling of regional portfolios of structures, 14,15,18,[21][22][23][24] and estimation of collapse vulnerability of buildings. [25][26][27][28] However, similar to the general trends in the ML community, 29 the majority of the past research efforts focused on algorithmic developments or contrasting of the performance of different ML tools, while putting less emphasis on the most effective use of data. As an example of the latter, studies [30][31][32] focused on the use of stochastic surrogate models to better utilize results of linear and nonlinear response history analyses for risk assessments.…”
Section: Introductionmentioning
confidence: 99%
“…CyberShake was developed to simulate many events using a single simulation routine (Graves and Pitarka, 2010) to facilitate simulation-based seismic hazard analyses (Graves et al, 2011b;Milner et al, 2021). CyberShake also produces time series for each of the events that can be used for response history structural analyses (Bijelic´et al, 2019(Bijelic´et al, , 2020.…”
Section: Introductionmentioning
confidence: 99%