A multi-scale attention neural network for sensor location selection and nonlinear structural seismic response prediction

Li, Teng; Pan, Yuxin; Tong, Kaitai; Ventura, Carlos E.; Silva, Clarence W. de

doi:10.1016/j.compstruc.2021.106507

Cited by 33 publications

(24 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to maximize measurement convenience and accuracy, the measuring points shall be located as close to the building's end as possible [21]. Accordingly, the measurement locations for this test are located at the north floor intersections of axis 1 and 7 .…”

Section: Sensors Arrangementmentioning

confidence: 99%

Field Test for a Base Isolation Structure on Condition of Horizontal and Initial Displacement

Dong

Lin

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

There are a few isolated structures that have been subjected to seismic testing. An isolated structure is incapable of tracking, adjusting, and controlling its dynamic characteristics. As a result, field evaluations of solitary structures’ dynamic characteristics are important. The horizontal initial displacement of a base isolation kindergarten made of 46 isolation bearings is 75 mm. The method for creating the horizontal initial displacement condition is illustrated, as are the primary test findings. Horizontal initial displacement is accomplished with the assistance of a reaction wall, rods, and hydraulic pump system. To begin, we removed the building using hydraulic jacks to produce horizontal displacement of the isolation layer and then attached rods to support the building. The rods were then shot and unloaded, causing the building to shake freely, and its dynamic response and other parameters were tested. The results indicate that the natural vibration period of an isolated structure is much greater than the natural vibration period of a seismic structure. The isolation layer’s hysteretic curve as completely filled; upon unloading, the isolation layer as promptly reset; the dynamic response control effect of each was visible, but the top floor’s acceleration was magnified by approximately 1.27 times.

show abstract

Section: Sensors Arrangementmentioning

confidence: 99%

Field Test for a Base Isolation Structure on Condition of Horizontal and Initial Displacement

Dong

Lin

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Predicting the future performance of structures is exceptionally challenging due to the complexity of earthquake signals and highly nonlinear structural behaviour. These issues and complexity are significantly intensified when considering structural damage accumulated over multiple seismic events 19,20 . Methods using finite element modelling (FEM) are the most common predictive approaches to simulate/predict seismic responses by nonlinear time history analysis 21,22 .…”

Section: Introductionmentioning

confidence: 99%

“…Methods using finite element modelling (FEM) are the most common predictive approaches to simulate/predict seismic responses by nonlinear time history analysis 21,22 . However, FEM and similar methods are computationally demanding, and their accuracy depends highly on the model defined for prediction purposes 19,20,23 . Furthermore, their accuracy significantly decreases as structural damage and nonlinearity increase 20,23 …”

Section: Introductionmentioning

confidence: 99%

“…Over the past years, artificial intelligence (AI) 23–33 and support vector machines (SVM) 3,20,34 have been applied to seismic response prediction 19,23 . However, the training process for these methods requires a lot of real‐world seismic data over a wide range of earthquake scenarios, which is not necessarily available in practice.…”

Section: Introductionmentioning

confidence: 99%

“…However, the training process for these methods requires a lot of real‐world seismic data over a wide range of earthquake scenarios, which is not necessarily available in practice. Alternative data obtained by computer simulation or shake‐table tests is costly and may not lead to realistic and reliable training data 19 . Further, the typical black‐box design of current data‐driven methods can restrict their real‐world application, where coherent approaches are more explicable to building owners and insurance firms as the primary stakeholders in the aftermath of earthquakes 19 …”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Experimental verification for a mechanics‐based digital cloning method predicting structural performance and damage

Rabiepour

Zhou

Chase

2023

Earthq Engng Struct Dyn

View full text Add to dashboard Cite

This paper introduces a novel digital twin modelling framework combining accurate structural health monitoring (SHM) results delivered by hysteresis loop analysis (HLA) with the basis function modelling to predict structural damage and responses of earthquake-affected structures under future seismic events. The measured data sets of a 12-storey 1/10 scale reinforced concrete (RC) structure shaken by three damaging base excitations (Events 1, 2 and 3) using a shake table has been employed to validate the performance of the introduced predictive framework. The results show that the digital twin created under the first base excitation (Event 1) predicts the inter-storey displacement responses of the test structure due to the second and third excitations (Events 2 and 3) with an average correlation coefficient of ∼0.88 and ∼0.94, respectively. The inter-storey drift ratio (IDR) values predicted by the digital twin also result in the same seismic performance delivered by the measured values, making the introduced framework a promising tool for assessing structural collapse and subsequent financial risk using incremental dynamic analysis (IDA). Moreover, the maximum difference of 5% between the identified and predicted stiffness values illustrates the robust and accurate performance of the proposed framework in diagnosing structural damage in highly nonlinear and damaged structures.

show abstract

Optimal sensor placement for joint reconstruction of multiscale responses and unknown inputs using modal Kalman filter

He,

Tong,

Zhang

et al. 2024

Structural Design Tall Build

View full text Add to dashboard Cite

SummaryMany optimal sensor placement (OSP) techniques have been developed basing on known external loads. However, it is often difficult to obtain excitation measurements. Therefore, the development of OSP under unknown inputs (OSP‐UI) is desirable. In this paper, based on modal Kalman filter (MKF), an OSP‐UI approach (MKF‐OSP‐UI) is proposed for optimally determining the number and locations of multitype sensors with the aim of minimizing the reconstructed responses errors. An MKF‐based approach previously developed by the authors is first employed for estimating multiscale structural responses and unknown loads. Then, an error covariance matrix is defined as a measure of the differences between the reconstructed responses and the corresponding actual ones. By using the covariance matrix of measurement noise for normalization, the ill‐conditioning problem caused by data fusion of multiscale responses is avoided. The sensors that have few contributions to the reconstructed responses are removed from the candidate set during iteration procedure. The sensor placement is finally determined when the estimation errors are below the preset level. Numerical results show that the sensor configuration determined by the proposed approach has a better performance on the joint estimation of multiscale responses and unknown inputs, as compared with that determined by experience.

show abstract

A multi-scale attention neural network for sensor location selection and nonlinear structural seismic response prediction

Cited by 33 publications

References 33 publications

Field Test for a Base Isolation Structure on Condition of Horizontal and Initial Displacement

Field Test for a Base Isolation Structure on Condition of Horizontal and Initial Displacement

Experimental verification for a mechanics‐based digital cloning method predicting structural performance and damage

Optimal sensor placement for joint reconstruction of multiscale responses and unknown inputs using modal Kalman filter

Contact Info

Product

Resources

About