Attention-Based Sequence-to-Sequence Learning for Online Structural Response Forecasting Under Seismic Excitation

2021 ◽  
pp. 1-17
Author(s):  
Teng Li ◽  
Yuxin Pan ◽  
Kaitai Tong ◽  
Carlos E. Ventura ◽  
Clarence W. de Silva
Keyword(s):  
Sequence Learning ◽  
Structural Response ◽  
Seismic Excitation

scholarly journals Seismic Performance of Curved Bridges with Longitudinal Slope

2019 ◽  
Vol 9 (4) ◽  
pp. 771
Author(s):  
Peng Su ◽  
Yanjiang Chen ◽  
Zhongwei Zhao ◽  
Weiming Yan
Keyword(s):  
Ground Motion ◽  
Structural Response ◽  
Seismic Excitation ◽  
Tangential Displacement ◽  
Site Conditions ◽  
Rotation Effect ◽  
Curved Bridges ◽  
Curved Bridge ◽  
Displacement Response ◽  
Main Girder

A curved bridge test model with a scale ratio of 1:10 was constructed to investigate the influence of site conditions on curved bridges with longitudinal slopes based on a similar theory. The natural ground motions of five different groups, namely, Sites A–E, were selected from the Pacific Earthquake Engineering Center (PEER) seismic database, and the shaking table model test was conducted under horizontal unidirectional and bidirectional excitations. Results showed that the structural response of the curved bridge is sensitive to the ground motion of different site conditions. Spatial characteristics are observed in the main girder structural response of the curved bridge. When the curved bridge is parallel to the direction of the principal ground motion, the rotation effect of the main girder is greater than that perpendicular to the direction of the principal ground motion. The rotation effect of the main girder leads to evident beam end and bearing displacements at the low pier. The seismic excitation direction and pier height notably affect the displacement response of the pier, and the tangential displacement response of the fixed pier is sensitive to seismic excitation.

The Model of Bounds on Seismic Responses

2012 ◽  
Vol 166-169 ◽  
pp. 2120-2123
Author(s):  
Ju Lin Wang
Keyword(s):  
Power Spectrum ◽  
Structural Response ◽  
Seismic Excitation ◽  
Convex Model ◽  
Elastic Structures ◽  
Forcing Function ◽  
Target Spectrum ◽  
Under Construction ◽  
Random Fluctuations ◽  
Global Parameters

Seismic excitation of linearly elastic structures is dealt with in the paper. It is well known that dynamical structural response is very sensitive to random fluctuations of the excitation; the consequence is that the identification of the forcing function on the basis of a few global parameters does not allow to predict exhaustively stresses in seismically excited structures. In the paper, a convex model is established to treat uncertainty associated with the details of the excitation. In order to set bounds on the response parameters of a SDOF system, assuming that only rough information is available for expected earthquakes at a given site. In particular, we assume that the maximum expected energy of the acclerogram, and the maximum distance of its power spectrum from the target spectrum, typical for the site under construction, are specified.

Aeolic and Seismic Structural Vibrations Mitigation on Long-Span Cable-Supported Bridges

2013 ◽  
Vol 690-693 ◽  
pp. 1168-1171 ◽  
Author(s):  
Marco Domaneschi ◽  
Luca Martinelli ◽  
Chun Xia Shi
Keyword(s):  
Structural Response ◽  
Suspension Bridge ◽  
Original Data ◽  
Seismic Excitation ◽  
Seismic Action ◽  
Bridge Structure ◽  
Structural Vibrations ◽  
Long Span Bridges ◽  
Wind Action ◽  
Long Span

Herein, two models of long-span bridges, namely a suspension and a cable-stayed one, are developed at the numerical level in a commercial finite elements code, starting from original data, and they are used to simulate the structural response under wind excitation and seismic excitation. The main goal of this study consists in the evaluation of a control strategy, designed and proven effective for the wind action, considering the suspension bridge, or for the seismic action, for the cable-stayed one, when the bridge structure is subjected to the seismic and the wind action respectively.

A Practical Response Spectrum Method in Considering the Input Angle of Seismic Excitation

2013 ◽  
Vol 438-439 ◽  
pp. 1506-1509
Author(s):  
Shi Mei Liu ◽  
Ling Tao Xia
Keyword(s):  
Random Vibration ◽  
Response Spectrum ◽  
Power Spectra ◽  
Structural Response ◽  
Seismic Excitation ◽  
Response Spectrum Method ◽  
Displacement Response ◽  
Spectrum Method

To the asymmetric-plan structures, the torsion model is obvious, and the influence of input angle of excitation on structural response is sensitive, so a practical response spectrum method for analyzing the behaviors of this kind of structure is studied. Based on the achievements about the multi-components accelerations power spectra matrix, a rational formula, considering the input angle of excitation, is deduced by using stationary random vibration principle. A practical formula is proposed by introducing displacement response spectrum as equally as to considering the non-stationarity of excitation.

Detecting structural damage under unknown seismic excitation by deep convolutional neural network with wavelet-based transmissibility data

2020 ◽  
pp. 147592172092308
Author(s):  
Ying Lei ◽  
Yixiao Zhang ◽  
Jianan Mi ◽  
Weifeng Liu ◽  
Lijun Liu
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Structural Damage ◽  
Structural Response ◽  
Deep Convolutional Neural Network ◽  
Seismic Excitation ◽  
Seismic Excitations ◽  
Deep Convolutional Neural Networks ◽  
Response Data ◽  
Structural Responses

Many research groups in the structural health monitoring community have made efforts to utilize deep learning-based approaches for damage detection on a variety of structures. Among these approaches, structural damage detection through deep convolutional neural networks using raw structural response data has received great attention. However, structural responses are affected not only by structural properties but also by excitation characteristics. For detecting of structures’ damage under seismic excitations, different seismic excitations definitely cause varied structural responses data. In practice, it is impossible to accurately predict the characteristics of future seismic excitation for pre-training the deep convolutional neural network. Therefore, it is essential to investigate the autonomous detection of structural element damage subject to unknown seismic excitation. In this article, a new approach is proposed for detecting structural damage subject to unknown seismic excitation based on a convolutional neural network with wavelet-based transmissibility of structural response data. The transmissibility functions of structural response data are used to eliminate the influence of different seismic excitations. Moreover, contrary to the traditional Fourier transform in the conventional transmissibility function, wavelet-based transmissibility function is presented using the ability in subtle information acquisition of wavelet transform. The wavelet-based transmissibility data of structural responses are used as the inputs to constructed deep convolutional neural networks. Both a numerical simulation example and an experimental test are used to validate the performance of the proposed approach based on deep convolutional neural network.

Nonhuman sequence learning findings argue against Hoerl and McCormack's two systems of temporal cognition

2019 ◽  
Vol 42 ◽  
Author(s):  
Benjamin J. De Corte ◽  
Edward A. Wasserman
Keyword(s):  
Sequence Learning ◽  
Past Research ◽  
Ordinal Position ◽  
Temporal Cognition ◽  
Two Systems

Abstract Hoerl & McCormack propose that animals learn sequences through an entrainment-like process, rather than tracking the temporal addresses of each event in a given sequence. However, past research suggests that animals form “temporal maps” of sequential events and also comprehend the concept of ordinal position. These findings suggest that a clarification or qualification of the authors’ hypothesis is needed.

fMRI of Implicit and Explicit Sequence Learning: Evidence for Parallel Systems

2000 ◽  
Author(s):  
Joanna Salidas ◽  
Daniel B. Willingham ◽  
John D. E. Gabrieli
Keyword(s):  
Sequence Learning ◽  
Parallel Systems ◽  
Implicit And Explicit

Implementing Flexibility in Automaticity: Evidence From Context-Specific Implicit Sequence Learning

2012 ◽  
Author(s):  
Maria C. D'Angelo ◽  
Luis Jimenez ◽  
Juan Lupianez ◽  
Bruce Milliken
Keyword(s):  
Sequence Learning ◽  
Implicit Sequence Learning ◽  
Context Specific
Sign in / Sign up

Export Citation Format

Share Document