Variable-fidelity hypervolume-based expected improvement criteria for multi-objective efficient global optimization of expensive functions

He, Youwei; Sun, Jinju; Song, Peng; Wang, Xuesong

doi:10.1007/s00366-021-01404-9

Cited by 19 publications

(5 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This requires us to scientifically analyze its internal and external environmental factors. The most basic and effective way for a system is to use economic means to realize the rational allocation and full development of resources, so as to improve the level of total social output and the growth rate of national income, and reduce unnecessary expenditure [9][10]. When optimizing the resource balance of mechanical engineering projects, it is necessary to first determine the resource requirements, that is, the requirements for the quantity and quality of various materials required by the project.…”

Section: Resource Balance Of Mechanical Engineering Projectsmentioning

confidence: 99%

Resource Balance Optimization Method of Mechanical Engineering Project Considering Multi-objective Optimization

2023

KME

View full text Add to dashboard Cite

In the current project construction in China, it is an important work to coordinate and cooperate among various project departments. In consideration of the resource balance, full attention should be paid to the connection, cooperation and information sharing among various departments. Taking the field of mechanical engineering planning and design as an example, this paper establishes a scheme and strategy system for scientific and reasonable resource allocation from the perspective of external environment to achieve the overall goal. After optimization, human resource allocation and personnel structure arrangement can be used to improve the efficiency of staff in the shortest time. Then, based on the multi-objective optimization algorithm, the resource balance model of mechanical engineering project is designed and the model is tested. The test results show that the model has small variance and low range, which shows that the model has excellent optimization effect.

show abstract

Section: Resource Balance Of Mechanical Engineering Projectsmentioning

confidence: 99%

Resource Balance Optimization Method of Mechanical Engineering Project Considering Multi-objective Optimization

2023

KME

View full text Add to dashboard Cite

show abstract

“…In this work, the variable fidelity expected improvement matrix (VFEIM) [43] approach is used to simultaneously find the next infill design point and the solver's fidelity during the infill phase. Moreover, the acquisition function is expanded to account for failed simulations in the different levels of fidelity and to also provide multiple designs per infill iteration.…”

Section: Multi-fidelity Multi-objective Acquisition Functionmentioning

confidence: 99%

“…These two methods, Variable Fidelity Expected Improvement [44], and Expected Improvement Matrix [46] can be easily merged to tackle multi-fidelity multi-objective optimization problems as it was proposed by He Y. et al [43]. In this approach, the expected improvement matrix of Eq.…”

Section: Multi-objective Multi-fidelitymentioning

confidence: 99%

Multi-fidelity Multi-Objective Optimization of a High-Altitude Propeller

Mourousias

Malim

Marinus

et al. 2023

AIAA AVIATION 2023 Forum

View full text Add to dashboard Cite

show abstract

“…In this framework, surrogate-based optimization is a popular approach [8]: the idea is to approximate the desired design objective using a data-driven surrogate model. Several models are commonly used, including but not limited to Gaussian processes [9][10][11], Neural networks [12,13], Polynomial chaos expansion [14,15], and Tree-structured Parzen estimator [16] . Such model is built based on a limited number of (expensive) simulations and is cheap-to-evaluate.…”

Section: Introductionmentioning

confidence: 99%

Bi-objective Bayesian optimization of engineering problems with cheap and expensive cost functions

Loka

Couckuyt

Garbuglia

et al. 2022

Engineering with Computers

View full text Add to dashboard Cite

Multi-objective optimization of complex engineering systems is a challenging problem. The design goals can exhibit dynamic and nonlinear behaviour with respect to the system's parameters. Additionally, modern engineering is driven by simulationbased design which can be computationally expensive due to the complexity of the system under study. Bayesian optimization (BO) is a popular technique to tackle this kind of problem. In multi-objective BO, a data-driven surrogate model is created for each design objective. However, not all of the objectives may be expensive to compute. We develop an approach that can deal with a mix of expensive and cheap-to-evaluate objective functions. As a result, the proposed technique offers lower complexity than standard multi-objective BO methods and performs significantly better when the cheap objective function is difficult to approximate. In particular, we extend the popular hypervolume-based Expected Improvement (EI) and Probability of Improvement (POI) in bi-objective settings. The proposed methods are validated on multiple benchmark functions and two real-world engineering design optimization problems, showing that it performs better than its non-cheap counterparts. Furthermore, it performs competitively or better compared to other optimization methods.

show abstract

Variable-fidelity hypervolume-based expected improvement criteria for multi-objective efficient global optimization of expensive functions

Cited by 19 publications

References 62 publications

Resource Balance Optimization Method of Mechanical Engineering Project Considering Multi-objective Optimization

Resource Balance Optimization Method of Mechanical Engineering Project Considering Multi-objective Optimization

Multi-fidelity Multi-Objective Optimization of a High-Altitude Propeller

Bi-objective Bayesian optimization of engineering problems with cheap and expensive cost functions

Contact Info

Product

Resources

About