Kyoto University · 공학
Bach Do 교수의 연구실은 고비용이고 복잡한 공학 설계 최적화 문제를 해결하기 위해 다중 정밀도 최적화(Multifidelity Optimization)와 베이지안 최적화(Bayesian Optimization)를 융합한 혁신적인 기법을 주요 연구 분야로 다룹니다. 특히 유한요소 해석, 유전적 프로그래밍, 가우시안 프로세스 기반의 서rogate 모델을 활용해 구조물의 피로 균열 복구, 지진 하중에 대한 내진 설계 최적화 등 실용적인 공학 문제를 해결합니다. 연구는 정확도와 자원 효율성을 동시에 확보하는 데 초점을 맞추며, 복잡한 설계 공간에서의 탐색과 확장성 있는 최적화를 실현합니다.
표시된 성과는 수집된 데이터 기준으로 산출되며, 일부 차이가 있을 수 있습니다.
A practical design optimization of fiber-reinforced polymer (FRP) patches for repairing fatigue cracks in metallic structures is presented. The design procedure combines finite-element (FE), genetic programming (GP), and genetic algorithm (GA) approaches. An optimum patch design is defined as the combination of design parameters that simultaneously minimizes the patch volume and reduces the stress intensity factor (SIF) range below the fatigue threshold range. A patching correction factor, which
Abstract Bayesian optimization (BO) has become a powerful tool for solving simulation-based engineering optimization problems thanks to its ability to integrate physical and mathematical understandings, consider uncertainty, and address the exploitation–exploration dilemma. Thompson sampling (TS) is a preferred solution for BO to handle the exploitation–exploration tradeoff. While it prioritizes exploration by generating and minimizing random sample paths from probabilistic models—a fundamental
Abstract This work presents a novel sequential sampling approach to the multi‐objective reliability‐based design optimization of moment‐resisting steel frames subjected to earthquake excitation. The optimization problem is formulated with two objective functions, namely, the total mass and the energy dissipated by beam members of the frame, and subject to uncorrelated probabilistic constraints on dynamic responses under the effects of correlated random parameters of floor masses, external loads,
Resided at the intersection of multifidelity optimization (MFO) and Bayesian optimization (BO), MF BO has found a niche in solving expensive engineering design optimization problems, thanks to its advantages in incorporating physical and mathematical understandings of the problems, saving resources, addressing exploitation–exploration trade-off, considering uncertainty, and processing parallel computing. The increasing number of works dedicated to MF BO suggests the need for a comprehensive revi
This paper presents an approach that combines the finite element (FE) modeling and genetic programming (GP) to provide accurate empirical stress intensity factor (SIF) equations for center-cracked steel plates repaired with adhesive-bonded double-sided fiber-reinforced polymer (FRP) patches. Several past studies in recent years independently showed that the reduction on the SIF of cracked structures after the patch repair is dependent on many factors such as bonding techniques, material paramete
Resided at the intersection of multi-fidelity optimization (MFO) and Bayesian optimization (BO), MF BO has found a niche in solving expensive engineering design optimization problems, thanks to its advantages in incorporating physical and mathematical understandings of the problems, saving resources, addressing exploitation-exploration trade-off, considering uncertainty, and processing parallel computing. The increasing number of works dedicated to MF BO suggests the need for a comprehensive rev
