Attention mechanism based neural networks for structural post-earthquake damage state prediction and rapid fragility analysis

Chen, Youjun; Sun, Zeyang; Zhang, Ruiyang; Yao, Liuzhen; Wu, Gang

doi:10.1016/j.compstruc.2023.107038

Cited by 14 publications

(1 citation statement)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the CNCSI of the models using coarse-grained multiscale neural networks as the discriminator (MWGAN-TF and MWGAN-T) is much lower than the that of the other two models (WGAN-TF and WGAN-T), which further indicates that the discriminator based on the coarse-grained multiscale CNN proposed in this study can improve the ability of the negative peaks, it can be observed that the reconstruction response of MWGAN-TF still provides more accurate detailed features. Obtaining an accurate structural peak response has important implications for assessing the health status of a structure [65].…”

Section: Results Of the Rc Framework Structural Modelsmentioning

confidence: 99%

Structural seismic response reconstruction method based on multidomain feature-guided generative adversarial neural networks

Liu,

Xu,

Chen

et al. 2024

Smart Mater. Struct.

View full text Add to dashboard Cite

Structural seismic response reconstruction is important to assess the safety of structures. This study presents a novel multidomain feature-guided generative adversarial neural network model (MWGAN-TF) for reconstructing the seismic responses of structures, which takes into account the joint non-stationarity of the seismic response in the time-frequency statistical domain. It innovatively incorporates time, frequency, and statistical-domain feature constraints into the multiscale generative adversarial neural network, which guides the model to learn the multidomain feature information of the seismic response at different time scales. A statistical indicator (CNCSI) was proposed to evaluate the performance of the model in capturing nonstationary characteristics. The effectiveness of the MWGAN-TF was verified using response data from numerical models of a reinforced concrete (RC) frame structure and the field measurement data of an actual building. Thereafter, the effects of different domain feature-guided models on the reconstruction response accuracy are discussed. The results show that embedding multidomain feature constraints can provide a more reliable response reconstruction by improving the ability of the model to capture nonstationary characteristics. Thus, the deep learning paradigm based on multidomain feature guidance outperforms the classical neural network guided only by time-domain features.

show abstract

Section: Results Of the Rc Framework Structural Modelsmentioning

confidence: 99%