Simulation of spectrum-correspondent accelerogram by using artificial neural networks

Izadi, Mohammad Mehdi; Mohammadi, Majid

doi:10.21595/jve.2016.16623

Cited by 3 publications

(2 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mohammadi and Amjadipoor examined only prime natural frequencies of (8-0) and (10-0) zigzag nanotubes. 35 Similar conclusions with the position of a monovacancy are presented for a smaller subset, which validates the results presented in this work. In addition to the above mentioned studies, research about structures in the form of CNT is available in literature involving continuum approximations, 36 nonlinear modeling 37 38 and finite element models.…”

Section: Introductionsupporting

confidence: 88%

Structural Vibration Analysis of Single Walled Carbon Nanotubes with Atom Vacancies

Dogan¹,

Yazıcıoğlu²

2014

Jnl of Comp & Theo Nano

View full text Add to dashboard Cite

Recent investigations in nanotechnology show that carbon nanotubes have significant mechanical, electrical and optical properties. Interactions between those are also promising in both research and industrial fields. Those unique characteristics are mainly due to the atomistic structure of carbon nanotubes. In this paper, the structural effects of vacant atoms on single walled carbon nanotubes are investigated using matrix stiffness method. In order to use this technique, a linkage between structural mechanics and molecular mechanics is established. A code has been developed to construct the single walled carbon nanotubes with the desired chirality, extracting the vacant atoms with the corresponding atomic bonds between the neighbor nodes and calculating the effect of these vacancies on their vibrational properties. In order to investigate the effect of those vacant nodes, large number of simulations has been carried out with randomly positioned vacant atoms. Also, consecutive vacant nodes have been positioned in order to investigate their effect on the structural properties through the length of a single walled carbon nanotubes. Effects of vacancies on Young's modulus have also been investigated. It is concluded that any amount of vacant atoms have substantial effect on modal frequencies and modulus of elasticity. Chirality and the amount/position of the vacancies are the main parameters determining the structural properties.

show abstract

Section: Introductionsupporting

confidence: 88%

Structural Vibration Analysis of Single Walled Carbon Nanotubes with Atom Vacancies

Dogan¹,

Yazıcıoğlu²

2014

Jnl of Comp & Theo Nano

View full text Add to dashboard Cite

show abstract

“…(2022) and Rajabi and Ghodrati Amiri (2020) dealt with mainshock‐aftershock sequences—and the dearth of qualified GMs in previous databases (Ghaboussi & Lin, 1998; Lee & Han, 2002). Besides, most of the trained ANNs can only generate one artificial GM at a time (Amiri et al., 2009,2012), and its effectiveness has been merely examined through a visual comparison between input and output response spectra (Izadi & Mohammadi, 2016; Vahedian et al., 2022). Therefore, it remains unknown whether these artificial GMs can be used confidently in tasks such as seismic risk assessment and PBSD.…”

Section: Introductionmentioning

confidence: 99%

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

Ning

Xie

2023

Computer aided Civil Eng

View full text Add to dashboard Cite

This study develops an end‐to‐end deep learning framework to learn and analyze ground motions (GMs) through their latent features, and achieve reliable GM classification, selection, and generation of simulated motions. The framework is composed of an analysis workflow that transforms and reconstructs GMs through short‐time Fourier transform (STFT), encodes and decodes their latent features through convolutional variational autoencoder (CVAE), and classifies and generates GMs by grouping and interpolating latent variables. A benchmark study is established to confirm the minor difference between original GMs and the corresponding reconstructed accelerograms. The encoded latent space reveals that certain latent variables are directly linked to the dominant physical features of GMs. Resultantly, clustering latent variables using the k‐means algorithm successfully classifies GMs into different groups that vary in earthquake magnitude, soil type, field distance, and fault mechanism. By linearly interpolating two parent latent variables, simulated GMs are generated with consistent class information and matching response spectra. Furthermore, seismic fragility models are developed for a steel frame building and a concrete bridge using different sets of GMs. Using five classified, top‐ranked motions, regardless of recorded or simulated accelerograms, can achieve reasonable and efficient fragility estimates compared to the case that adopts 230 GMs. The proposed deep learning framework addresses two compelling questions regarding seismic fragility assessment: How many GMs are sufficient and what types of motions should be selected.

show abstract

Ground Motion Time History Simulation for Seismic Response History Analysis

Yang

Wang

2022

Front. Earth Sci.

View full text Add to dashboard Cite

In the seismic design and analysis of important structures, ground motion time histories are generally required as the input for the conduction of seismic response history analysis. Taking a selected spectrum as the target, the approaches for generating spectral compatible time histories based on artificial or synthetic ground motion and real recorded earthquake ground motion, respectively, are commonly used and discussed in this review. The pure artificial approaches have relative higher effectiveness and computational efficiency, while the approaches by adjusting the real records could simulate the nonstationary in both time domain and frequency domain.

show abstract

Simulation of spectrum-correspondent accelerogram by using artificial neural networks

Cited by 3 publications

References 30 publications

Structural Vibration Analysis of Single Walled Carbon Nanotubes with Atom Vacancies

Structural Vibration Analysis of Single Walled Carbon Nanotubes with Atom Vacancies

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

Ground Motion Time History Simulation for Seismic Response History Analysis

Contact Info

Product

Resources

About