간행물
한국대공간건축 논문집(구 한국공간구조학회지) KCI 등재 Korean Journal of Spatial Architecture
- 발행기관 한국공간구조학회
- 자료유형 학술지
- 간기 계간
- ISSN 3092-4251 (Print)3092-4413 (Online)
- 수록기간 2001 ~ 2026
- 주제분류 공학 > 건축공학 공학 분류의 다른 간행물
- 십진분류KDC 540DDC 690
권호리스트/논문검색
제25권 제3호 통권101호 (2025년 9월) 7건
1.
2025.09
구독 인증기관 무료, 개인회원 유료
4,000원
2.
2025.09
구독 인증기관 무료, 개인회원 유료
With the increasing number of aging buildings, the importance of structural safety inspections has grown significantly. Traditional methods for inspecting welding defects, such as visual inspection and magnetic testing, rely heavily on human expertise, making them time-consuming, costly, and subjective. To address these limitations, thermographic technology has been introduced as a non-contact alternative, significantly reducing both time and cost. Furthermore, by incorporating AI, an objective and automated evaluation of welding defects can be achieved. In this study, we propose an AI-based thermographic approach for detecting welding defects. To validate the applicability of this method, a Mock-up Test was conducted. Specifically, 12 types of welding specimens with 4 welding part were prepared, generating a dataset of 6,500 thermographic images. Among 7 regression algorithms tested, RF and EXT were selected due to their superior performance. By ensemble learning these two models, we developed a robust welding defect measurement algorithm. To further verify its effectiveness, we applied the developed algorithm to 2 real projects, evaluating its applicability using 450 thermographic images. The results of this study demonstrate the feasibility of AI and thermographic technology in welding defect detection, highlighting its potential to enhance the efficiency and reliability of structural safety inspections in aging infrastructures.
4,000원
3.
2025.09
구독 인증기관 무료, 개인회원 유료
Machine learning (ML) techniques have been increasingly applied to the field of structural engineering for the prediction of complex dynamic responses of safety-critical infrastructures such as nuclear power plant (NPP) structures. However, the development of ML-based prediction models requires a large amount of training data, which is computationally expensive to generate using traditional finite element method (FEM) time history analysis, especially for aging NPP structures. To address this issue, this study investigates the effectiveness of synthetic data generated using Conditional Tabular GAN (CTGAN) in training ML models for seismic response prediction of an NPP auxiliary building. To overcome the high computational cost of data generation, synthetic tabular data was generated using CTGAN and its quality was evaluated in terms of distribution similarity (Shape) and feature relationship consistency (Pair Trends) with the original FEM data. Four training datasets with varying proportions of synthetic data were constructed and used to train neural network models. The predictive accuracy of the models was assessed using a separate test set composed only of original FEM data. The results showed that models trained with up to 50% synthetic data maintained high prediction accuracy, comparable to those trained with only original data. These findings indicate that CTGAN-generated data can effectively supplement training datasets and reduce the computational burden in ML model development for seismic response prediction of NPP structures.
4,000원
4.
2025.09
구독 인증기관 무료, 개인회원 유료
This study proposes empirical formulas for predicting the nonlinear behavior of GIR beam-to-column connections in timber structures to evaluate their structural performance. A database comprising 59 experimental results of GIR connections was collected, and the normality of data distribution was verified. Statistical analysis were conducted to investigate the correlations between input and output parameters. Based on input parameters with high correlation, derived variables were formulated and utilized in a multiple regression analysis to develop empirical formulas for moment capacity and rotation. The R-squared values of the proposed formulas exceeded 0.9, and the predicted initial stiffness and strength closely matched those of experimental results not used in the regression analysis. So the suggested empirical formulas exhibit excellent predictive performance for the nonlinear behavior of GIR beam-to-column connections in timber structures.
4,000원
5.
2025.09
구독 인증기관 무료, 개인회원 유료
This study was intended to compare with seismic fragility assessments for a low-rise RC piloti structure using the Capacity Spectrum Method (CSM) and the Incremental Dynamic Analysis (IDA). Distribution-parameters were estimated using the Method of Moments (MoM) and the Maximum Likelihood Estimation (MLE). For given limit states defined by FEMA 356, two seismic fragility assessments yielded different medians and dispersions: the CSM produced steeper in the slopes of fragility curves with smaller dispersions, whereas the IDA captured wider response scatters and broader dispersions. When fitting the fragility curves, the MLE scheme provided to well match with the empirical cumulative distribution function(CDF) than the MoM scheme, which understated dispersions.
4,000원
6.
2025.09
구독 인증기관 무료, 개인회원 유료
Existing reinforced concrete building structures have seismically-deficient details on columns and beam–column joints; therefore, accurate modeling of structural behavior is required for reliable seismic performance assessment. This study aims to investigate the differences in dynamic responses resulting from modeling variations through developing four distinct numerical models. Separate models were established to simulate flexural and shear failures of columns and beam–column joints. Using these component-level models, a structural analysis model of the target building was constructed, and nonlinear time-history analyses were performed to evaluate seismic performance. Based on the simulated dynamic behavior of the target building, soft-story mechanisms were identified, and it was identified and confirmed that column behavior plays a dominant role in governing the overall structural response.
4,300원
7.
2025.09
구독 인증기관 무료, 개인회원 유료
This study analyzed the structural performance of a microalgae-based lightweight ecological integration system for large-span structures to achieve carbon neutrality. To address the load problems of existing soil-based ecological systems, a lightweight system utilizing microalgae bioreactors was proposed, and structural performance was evaluated for four types of large-span structures: truss, arch, dome, and cable structures. Structural analysis results through finite element analysis showed that the proposed system achieved a 70% load reduction effect compared to existing systems, with structural performance improvements including 35-40% reduction in maximum deflection, 30-35% reduction in maximum stress, and 25-30% increase in natural frequency. Environmental performance analysis confirmed CO₂absorption capacity of 12-18 kg per m² annually and PM2.5 reduction effects of 15-25%. Economic analysis results indicated that benefits of 3.95-6.7 million KRW per year are generated for a 1,000 m²reference area, creating cumulative benefits of 179.75-227.5 million KRW over 25 years. Verification through the German BIQ House case confirmed CO₂reduction performance of 6 tons per year for 200 m², demonstrating the practical applicability of the system. This study presented the potential of an innovative ecological integration system that can ensure structural safety of large-span structures while simultaneously contributing to carbon neutrality.
4,300원
