Efficient seismic fragility analysis method utilizing ground motion clustering and probabilistic machine learning

Engineering Structures, Journal Year: 2023, Volume and Issue: 294, P. 116739 - 116739

Published: Aug. 9, 2023

Language: Английский

---

Seismic risk and vulnerability models considering typical urban building portfolios

Bulletin of Earthquake Engineering, Journal Year: 2024, Volume and Issue: 22(6), P. 2867 - 2902

Published: March 22, 2024

Language: Английский

---

Prediction of non-uniform shrinkage of steel-concrete composite slabs based on explainable ensemble machine learning model

Journal of Building Engineering, Journal Year: 2024, Volume and Issue: 88, P. 109002 - 109002

Published: March 12, 2024

Language: Английский

---

Multiscale damage analysis of engineering structures from material level to structural level: a systematic review

International Journal of Structural Integrity, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 27, 2025

Purpose Damage of engineering structures is a nonlinear evolutionary process that spans across both material and structural levels, from mesoscale to macroscale. This paper aims provide comprehensive review damage analysis methods at the levels. Design/methodology/approach study provides an overview multiscale structures, including its definition significance. Current status levels investigated, by reviewing models prediction single-scale perspectives. The discussion includes model-based simulation approaches data-driven techniques, emphasizing their roles applications. Finally, summarize main findings discuss potential future research directions in this field. Findings In level, primarily focuses on degradation properties macroscale using continuum mechanics (CDM). contrast, mesoscale, involves analyzing behavior meso-structural domain, focusing defects like microcracks void growth. structural-level analysis, typically divided into component scales. scale examines progression individual elements, such as beams columns, often detailed finite element or models. evaluates global entire structure, simplified beam shell elements. Originality/value To achieve realistic simulations, it essential include many details possible. However, results significant computational demands. balance accuracy efficiency, are employed. These categorized hierarchical approaches, where different scales processed sequentially, concurrent multiple solved simultaneously capture complex interactions

Language: Английский

---

Machine learning-based rapid damage states assessment and seismic response prediction of highway bridges supported by unbonded laminated rubber bearing

Structures, Journal Year: 2025, Volume and Issue: 75, P. 108826 - 108826

Published: April 8, 2025

Language: Английский

---

Generalized stacked LSTM for the seismic damage evaluation of ductile reinforced concrete buildings

Earthquake Engineering & Structural Dynamics, Journal Year: 2023, Volume and Issue: 52(11), P. 3477 - 3503

Published: March 20, 2023

Abstract To organize accurate and effective emergency responses after an earthquake, it is vital to conduct early precise assessment of damage structures. The use fragility/vulnerability curves advanced evaluation approach for structural assessments. However, the analysis based on fragility significantly varies depending soil conditions, ground motion, characteristics. overcome this issue, a stacked long short‐term memory network was proposed in research. Unlike previous studies, two input features (acceleration time history form vector number stories scalar) are utilized generalize results same plan building frames with different stories. Three approaches presented work link motion (2, 4, 8, 12, 20 stories) reinforced concrete frame, networks were tested unknown motions. Of three approaches, those providing good selected further analysis. For chosen, architectures changed diamond shape autoencoder‐like more hidden units (to obtain higher accuracy), which layout frames. accuracy obtained using these high (80%–90%) low training time. model compared other techniques shows significant accuracy. suggested exhibited scenarios estimating state motions, as well various Moreover, capability handle scalar examined by adding them probabilistically; additional variables, predicted

Language: Английский

---

Seismic vulnerability estimation of RC structures considering empirical and numerical simulation methods

Archives of Civil and Mechanical Engineering, Journal Year: 2024, Volume and Issue: 24(2)

Published: March 5, 2024

Language: Английский

---

Active learning methods for strength assessment of circular CFST under coupled long-term axial loading and random localized corrosion

Thin-Walled Structures, Journal Year: 2023, Volume and Issue: 193, P. 111254 - 111254

Published: Oct. 13, 2023

Language: Английский

---

Quantum‐enhanced machine learning technique for rapid post‐earthquake assessment of building safety

Computer-Aided Civil and Infrastructure Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: June 10, 2024

Abstract Fast, accurate damage assessment of numerous buildings for large areas is vital saving lives, enhancing decision‐making, and expediting recovery, thereby increasing urban resilience. The traditional methods, relying on expert mobilization, are slow unsafe. Recent advances in machine learning (ML) have improved assessments; however, quantum‐enhanced ML (QML), a rapidly advancing field, offers greater advantages over classical (CML) large‐scale data, the speed accuracy assessments. This study explores viability leveraging QML to evaluate safety reinforced concrete after earthquakes, focusing classification only. A algorithm trained using simulation datasets tested real‐world damaged datasets, with its performance compared various CML algorithms. results demonstrate potential revolutionize seismic assessments, offering promising direction future research practical applications.

Language: Английский

---

A numerical model database for rapid seismic damage assessment of typical regular reinforced concrete frame structures in urban building clusters

Journal of Building Engineering, Journal Year: 2024, Volume and Issue: 90, P. 109392 - 109392

Published: April 17, 2024

Language: Английский

---