Jaehoon Bae

Generative design based on deep learning has enormous potential for developing innovative structural components, such as steel dampers for seismic design. Nevertheless, an important challenge to real-world implementation is that current models frequently produce disconnected structures and physically infeasible designs that cannot be manufactured. This study overcomes this fundamental challenge by introducing a deep generative framework that integrates a connectivity constraint. The manufacturability of generated lattice structures is directly implemented through a hybrid Variational Autoencoder–Generative Adversarial Network (VAE–GAN) model that includes a connectivity loss function. Multi-objective optimization produced a physically meaningful Pareto dataset that was used to train the model. The seismic performance of the generated designs is then rapidly predicted by a convolutional neural network, significantly reducing evaluation costs and providing a suitable alternative by comparing the performance of generated shapes. This framework is used to design high-performance steel dampers for seismic design. The optimal design is fabricated via metal additive manufacturing (AM) and tested in real experiments and via nonlinear finite element analysis, demonstrating close agreement with predictions and a robust efficiency gain over conventional dampers, with parity with honeycomb dampers on a per-volume basis. The experimental campaign further demonstrated a progressive, multi-path energy-dissipation mode enabled by the lattice’s structural redundancy, which is generally challenging to achieve with conventional standardized dampers. This method extends the realistic design space beyond parametric designs created individually, reduces assessment costs, and incorporates manufacturing feasibility into the generation process. By ensuring that manufacturing feasibility is a crucial component of the generative process, this research offers a comprehensive, validated workflow that closes the gap between generative design and practical engineering.

Data scarcity remains a fundamental challenge in data-driven seismic response modeling, especially for complex structural systems subjected to stochastic earthquake excitations. To address this limitation, we introduce a novel physics-informed few-shot learning (FSL) framework for the system identification of seismic structural coupling systems. A formalized typology of sequence-to-sequence mapping relationships is established to characterize structural behavior under stochastic ground motions. We propose a stacked Long Short-Term Memory network architecture, enhanced with a sliding-window data augmentation strategy to expand the limited training sequences. Furthermore, a vibration equilibrium correction module is incorporated to align predictions with the underlying physical dynamics, thereby improving interpretability and accuracy. Validated on a reproducible benchmark comprising both regular and irregular building models, our framework demonstrates robust prediction of inter-story displacements under unseen earthquake records, with correlation coefficients consistently exceeding 0.94. This work presents the first open benchmark and a generalizable FSL framework for structural system identification, bridging data-driven modeling with physical principles to advance intelligent seismic response simulation and structural health monitoring.

In this study, bentonite clay was modified through silane treatment and calcination to enhance its compatibility with basalt fiber (BF) and epoxy in multiscale composites. The as-received bentonite (ARB) was subjected to silane treatment using APTES, producing silane-modified bentonite (STB), while calcination yielded calcined bentonite (CB). The modified clays were incorporated into basalt fiber-reinforced epoxy (BFRP) composites, which were fabricated using the vacuum-assisted resin transfer method (VARTM). Analytical techniques, including X-ray diffraction (XRD) and Fourier-transform infrared (FTIR) spectroscopy, confirmed the structural changes in the clays. BET surface area analysis revealed a 314% increase in the surface area of STB and a 176% increase for CB. The modified clays also demonstrated reduced hydrophilicity and swelling behavior. Thermogravimetric analysis (TGA) indicated a minimal improvement in thermal stability, with the degradation onset temperatures increasing by less than 3 °C. However, tensile tests showed significant gains, with CB- and STB-reinforced composites achieving 48% and 21% higher tensile strength than ARB-reinforced composites. Tribological tests revealed substantial reductions in wear, with CB- and STB-reinforced composites showing 90% and 84% decreases in the wear volume, respectively. These findings highlight the potential of modified bentonite clays to improve the mechanical and wear properties of basalt fiber–epoxy composites.

1. 서 론 신기후체제 이후, 유엔기후변화협약을 통해 각국은 탄소중 립 목표를 설정하였으며

The increasing adoption of metaverse exhibitions aims to overcome the limitations of traditional offline exhibitions by enhancing accessibility and creating imaginative spaces without temporal and spatial constraints. This study explores how incorporating gamification into metaverse exhibitions can leverage the strengths of online and offline experiences. By integrating metaverse elements and gamification, we designed an interactive metaverse space and evaluated its effectiveness through user feedback. Our findings indicate that guiding visitors to complete missions within the metaverse enhances their understanding of the offline exhibition narratives, thereby increasing their engagement with the exhibition themes. Furthermore, online experiences in the metaverse can stimulate interest in offline exhibitions, promoting visitor attendance. The metaverse space also encourages users to contribute personal stories to the exhibition content, fostering continuous content expansion. This approach strengthens the connection between online and offline exhibitions, increases visitor engagement, and promotes repeat visits, thereby addressing the limitations of traditional exhibitions. Additionally, metaverse exhibitions enhance the preservation and accessibility of cultural heritage through digital archiving, offering inclusive participation opportunities and promoting social sustainability. This study underscores the potential of metaverse exhibitions to evolve beyond technological innovation toward contributing to social sustainability.