Integrated framework for seismic fragility assessment of cable-stayed bridges using deep learning neural networks

Pang, Yutao; Yin, Pengcheng; Wang, Jianguo; Wu, Li

doi:10.1007/s11431-022-2245-1

Cited by 17 publications

(1 citation statement)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this case study, the peak ground velocity (PGV) was adopted as the optimal IM for seismic fragility assessment of cable-stayed bridge. [48][49][50] The same record suite as the above example was adopted, namely the 80 unscaled ground motions from Baker et al 43 All these ground motions were scaled by a factor of 2.0 to obtain additional 80 records in Cloud. For the IDA method, these 80 records were scaled at 16 intensity levels from 0.1 to 3.0 m/s, leading to a total of 1280 nonlinear time-history analyses.…”

Section: Resultsmentioning

confidence: 99%

An efficient and accurate fragility approach for seismic performance assessment of structures

Pang,

Wei,

Wang

et al. 2023

Earthquake Engineering and Resilience

Self Cite

View full text Add to dashboard Cite

In seismic risk assessment of bridges, developing fragility function is a fundamental step to characterize the structural vulnerability, which is usually derived based on the relationship between the engineering demand parameter (EDP) and intensity measure (IM). The EDP‐IM relationships are generally developed through three approaches, namely Cloud analysis (Cloud), incremental dynamic analysis (IDA), and multiple strip analysis (MSA). It is known that the Cloud method is computationally efficient while the IDA and MSA can provide the accurate fragility estimates. Thus, the present paper proposes an efficient and accurate fragility (EAF) approach which has similar computational demand as Cloud but keeps the same level of accuracy as IDA or MSA. In this proposed EAF procedure, the nonlinear time‐history responses at the intensifying duration of ground motions were used to develop the EDP‐IM curves. And these EDP‐IM curves are accurate enough to replace the IDA curves in developing fragility curves. To illustrate the efficiency and accuracy of the proposed EAF method, two typical bridges (a two‐span single‐frame bridge and a single‐pylon cable‐stayed bridge) were selected and modeled in OpenSees and employed as case studies. By comparing the fragility estimates of these bridges to IDA and MSA, it is demonstrated that the proposed EAF approach leads to reliable fragility results, while has similar computational time as Cloud.

show abstract

Section: Resultsmentioning

confidence: 99%

An efficient and accurate fragility approach for seismic performance assessment of structures

Pang,

Wei,

Wang

et al. 2023

Earthquake Engineering and Resilience

Self Cite

View full text Add to dashboard Cite

show abstract

An efficient and accurate method of added mass for evaluating the seismic hydrodynamic effect of deep‐water piers

Yang,

Huai,

Pang

et al. 2024

Earthquake Engineering and Resilience

View full text Add to dashboard Cite

Due to the effects of complex fluid‐structure interaction, deep‐water bridges are more prone to damage under strong earthquakes. Quantification of seismic fluid‐structure interaction can be crucial for evaluating the seismic performance of deep‐water bridges. Currently, there is a lack of suitable methods for rapidly calculating hydrodynamic added mass for deep‐water piers with complex cross‐sectional shapes in the seismic performance assessment of deep‐water bridges. In light of this, the present paper proposed an efficient and accurate method for calculating the hydrodynamic added mass of piers with different cross‐sectional shapes. Taking circular, rectangular, and dumbbell‐shaped piers as examples, the proposed method was employed to calculate the hydrodynamic added mass for deep‐water bridge piers. Comparison of the seismic responses obtained from the analytical formula, fluid‐structure coupling refined numerical model and the proposed method in this paper validated the accuracy of the proposed method. Finally, the hydrodynamic coupling effects of deep‐water bridge piers were also investigated. It was concluded that the proposed method can be efficient and accurate for obtaining the added mass of deep‐water piers.

show abstract

Data‐Physical Fusion Deep Learning for Site Seismic Response Using KiK‐Net Records

Chen,

Hu,

Jiang

et al. 2024

Earthq Engng Struct Dyn

View full text Add to dashboard Cite

In the realm of earthquake engineering, response spectra play a crucial role in characterizing the effects of site dynamic characteristics under seismic activity. Consequently, accurately predicting seismic response spectra is of paramount importance. We have developed a physics‐guided bidirectional long short‐term memory neural network model (Phy‐BiLSTM) that is proficient in predicting site seismic response based on bedrock records. The core principle of the Phy‐BiLSTM is to improve the alignment between the solution space and the ground truth by integrating physics knowledge obtained from the physical model. The model introduced in this study utilized the 5%‐damped response spectra, which were derived from strong ground motion records collected at the KiK‐net downhole array. The results substantiate the performance enhancement of Phy‐BiLSTM in comparison to the data‐driven BiLSTM model. Furthermore, we conduct a comparative analysis of the Phy‐BiLSTM model against traditional methods (EQ, SBSR) as well as other neural network architectures (CNN and LSTM). The result highlights the advantages of Phy‐BiLSTM in accurately predicting the site seismic response.

show abstract

Integrated framework for seismic fragility assessment of cable-stayed bridges using deep learning neural networks

Cited by 17 publications

References 54 publications

An efficient and accurate fragility approach for seismic performance assessment of structures

An efficient and accurate fragility approach for seismic performance assessment of structures

An efficient and accurate method of added mass for evaluating the seismic hydrodynamic effect of deep‐water piers

Data‐Physical Fusion Deep Learning for Site Seismic Response Using KiK‐Net Records

Contact Info

Product

Resources

About