Article
Computer Science, Interdisciplinary Applications
Long Wang, Theodore T. Allen, Michael A. Groeber
Summary: Methods based on Gaussian stochastic process models and expected improvement functions are promising for solving box-constrained expensive optimization problems. The proposed tabu EGO algorithm maintains a tabu list to avoid repeating past experimental points, resulting in improved computational performance. Comparative results show that tabu EGO offers promising convergence speed and solution quality for all types of black-box optimization.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2021)
Article
Engineering, Civil
Leandro F. Fadel Miguel, Rafael Holdorf Lopez, Andre Jacomel Torii, Andre T. Beck
Summary: Pendulum-tuned mass dampers (PTMDs) are attractive for controlling horizontal vibrations in buildings. The Folded Pendulum Tuned Mass Dampers (FPTMDs) provide a solution to reduce the required space while retaining advantages. This article performs a reliability-based design optimization (RBDO) study of multiple FPTMDs installed in a tall building, showing that multiple FPTMDs are more reliable.
ENGINEERING STRUCTURES
(2022)
Article
Engineering, Aerospace
Mehti Koklu, John C. Lin, Judith A. Hannon, Latunia P. Melton, Marlyn Y. Andino, Keith B. Paschal, Veer N. Vatsa
Summary: A 10%-scale high-lift version of the Common Research Model (CRM-HL) was tested in NASA Langley Research Center's wind tunnel to investigate the vortices generated at the nacelle/pylon region. Wind tunnel tests revealed a lift degradation of the traditional CRM-HL model at high angles of attack, which was successfully mitigated by installing a nacelle chine on the inboard side of the engine nacelle.
Article
Engineering, Mechanical
Rafael Holdorf Lopez, Elizabeth Bismut, Daniel Straub
Summary: Engineering design and optimization often involve minimizing expected value functions with high noise variance and mixed/discrete design variables. This study extends the stochastic efficient global optimization (SEGO) method proposed by Carraro et al. (Struct Multidiscipl Optim 60(1):245-268, 2019) to address such problems. The study introduces two additional stopping criteria for Monte Carlo integration to approximate the objective function and adapts the active learning algorithm within SEGO to handle discrete design variables. The method is evaluated on two numerical examples and demonstrates its efficiency, particularly for cases with limited computational budget.
JOURNAL OF THE BRAZILIAN SOCIETY OF MECHANICAL SCIENCES AND ENGINEERING
(2023)
Article
Computer Science, Information Systems
Yong Zeng, Yuansheng Cheng, Jun Liu
Summary: This study proposes a novel three-stage infilling framework called CEGO-DI for solving expensive single-objective problems with constraints. Experimental results show that CEGO-DI has better or competitive performance on most problems.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Interdisciplinary Applications
Zhendong Guo, Qineng Wang, Liming Song, Jun Li
Summary: The study introduces a new infill criterion called Filter-GEI for addressing sample assignment issue in multi-fidelity optimization. By considering correlations between HF and LF models and adding an adaptive filter function on top of the GEI acquisition function, Filter-GEI efficiently allocates HF and LF samples to achieve a good balance between local and global search, with further improvement in efficiency through infilling multiple HF and LF samples in each iteration along with parallel computing. Tests on mathematical toy problems and an engineering problem demonstrate the effectiveness of the proposed algorithm.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2021)
Article
Computer Science, Interdisciplinary Applications
Youwei He, Jinju Sun, Peng Song, Xuesong Wang
Summary: The paper proposes a novel strategy to prevent the premature halt of the multi-objective efficient global optimization method by introducing an additional Kriging model to predict the success possibility of simulations. Experimental results suggest that this method consistently performs well on analytic and practical problems.
ENGINEERING WITH COMPUTERS
(2022)
Article
Engineering, Aerospace
Baohong Bai, Xiaodong Li
Summary: This study investigated the noise characteristics of leading-edge slats in realistic aircraft configurations using phased microphone arrays. The results showed that the angle of attack has different effects on the slat and nacelle/pylon/slat juncture noises, and the revealed noise characteristics are helpful for establishing a physics-based noise prediction model and developing noise reduction technologies.
AEROSPACE SCIENCE AND TECHNOLOGY
(2022)
Article
Engineering, Multidisciplinary
Mingyang Li, Bing Yi, Yue Yang
Summary: This article proposes an efficient global optimization method (MISK) based on kriging, which can obtain good optimization solutions in a shorter amount of time and requires fewer computing resources.
ENGINEERING OPTIMIZATION
(2022)
Article
Engineering, Mechanical
Andre Gustavo Carlon, Cibelle Dias de Carvalho Dantas Maia, Rafael Holdorf Lopez, Andre Jacomel Torii, Leandro Fleck Fadel Miguel
Summary: This paper proposes a global optimization framework to address the computational cost and non-convexity of Optimal Experimental Design (OED) problems. The framework combines Laplace approximation and polynomial chaos expansions (PCE) to reduce computational burden and noise in the evaluation of Shannon expected information gain (SEIG). The proposed approach outperforms state-of-the-art stochastic gradient descent algorithms in four numerical examples, demonstrating its efficiency and robustness in solving OED problems.
PROBABILISTIC ENGINEERING MECHANICS
(2023)
Article
Engineering, Multidisciplinary
Hu Wang, Wei Hu, Enying Li
Summary: This study proposes an improved multi-constraint global optimization method, including using LSSVR instead of kriging model, suggesting MPF strategy and MCP criterion to handle infeasible initial samples and multiple constraints. Experimental results indicate that the method demonstrates superior performance in deterministic benchmark tests.
INTERNATIONAL JOURNAL OF COMPUTATIONAL METHODS
(2021)
Article
Computer Science, Interdisciplinary Applications
Qingyu Wang, Takuji Nakashima, Chenguang Lai, Xinru Du, Taiga Kanehira, Yasufumi Konishi, Hiroyuki Okuizumi, Hidemi Mutsuda
Summary: This study proposes an improved system, called RKri-EGO-PEI, which filters out noise and maintains smooth trend in CFD simulations, as well as conducts parallel point infills. Through a comprehensive investigation of optimizers, the best one is chosen for this system. The results show that the proposed system improves the convergence of the EGO-PEI algorithm with fewer iterations and achieves faster search speed in optimization problems with noisy computations.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2022)
Article
Computer Science, Artificial Intelligence
Jiawei Wu, Zhenliang Jiang, Huaming Song, Liangqi Wan, Fu Huang
Summary: This study proposed a parallel efficient global optimization method integrated with the adaptive Kriging-Monte Carlo simulation for time-dependent reliability analysis (TRA) problems, which showed superior computing efficiency and high accuracy in solving high-dimensional TRA problems.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Interdisciplinary Applications
Marcela A. Juliani, Wellison J. S. Gomes
Summary: This study proposes a global optimization framework based on the Kriging surrogate model to tackle structural problems with expensive constraints. By improving the metamodel only in regions of the design space that are likely to contain the optimal design, unnecessary constraint evaluations in unimportant areas are avoided. The approach yields results close to the best found in the literature and requires significantly shorter computational times compared to other methods.
STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION
(2022)
Article
Engineering, Civil
Guangyong Sun, Xuesong Wang, Jianguang Fang, Tong Pang, Qing Li
Summary: The study focuses on developing a multiobjective optimization approach for bumper systems to consider multiple impact loading scenarios, resulting in improved intrusion reduction and increased energy absorption.
THIN-WALLED STRUCTURES
(2021)
