Conditional Generative Adversarial Network-Based Framework for Predicting Blast-Induced Damage Distribution in RC Columns

Q: What does this research mean for the field?

A conditional generative adversarial network (cGAN)-based framework can be utilized to predict the distribution of blast-induced damage in reinforced concrete (RC) columns. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

Haewon Kang; Yeeun Kim; Jiuk Shin

doi:10.7734/coseik.2026.39.4.235

August 31, 2026Journal of the Computational Structural Engineering Institute of KoreaOpen Access

Conditional Generative Adversarial Network-Based Framework for Predicting Blast-Induced Damage Distribution in RC Columns

View Full Paper

Ask AI

Bookmark

Share

Key Points

Develop a conditional generative adversarial network-based computational framework to predict blast-induced local damage distribution and complex failure modes in reinforced concrete columns.
Characterized high strain-rate blast loading dynamics, evaluating incident overpressure, reflected overpressure, charge weight, and standoff distance.
Formulated a conditional generative adversarial network (cGAN) architecture designed to learn mappings between blast load parameters and localized concrete structural damage states.
Identified that localized failure mechanisms—specifically spalling, back-face scabbing, crushing, and rebar buckling—dominate the structural response over global deformation under high-rate blast loading.
Established the dependency of severe localized damage patterns on shock reflection conditions and scaled distance rather than gross structural displacement alone.

Implication

Computational modeling study demonstrates blast-induced localized damage patterns in reinforced concrete columns, highlighting complex failure mechanisms under high strain rates.

Abstract

No abstract yet. The journal hasn't published one we can show.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Kang et al. (2026) studied this question.

synapsesocial.com/papers/6a9935a0636c6408cfa7e08a https://doi.org/10.7734/coseik.2026.39.4.235

View Full Paper

Ask AI

Bookmark

Share

Conditional Generative Adversarial Network-Based Framework for Predicting Blast-Induced Damage Distribution in RC Columns

Key Points

Implication

Abstract

Discussion

Cite This Study

Conditional Generative Adversarial Network-Based Framework for Predicting Blast-Induced Damage Distribution in RC Columns

Key Points

Implication

Abstract

Discussion

Cite This Study

Keep reading

More related papers

More from Journal of the Computational Structural Engineering Institute of Korea

Keep reading

More related papers

More from Journal of the Computational Structural Engineering Institute of Korea