Multi-fidelity robust design optimisation for composite structures based on low-fidelity models using successive high-fidelity corrections
نویسندگان
چکیده
In this paper, a novel multi-fidelity modelling-based optimisation framework is developed for the robust design of composite structures. The proposed provides significant savings on computation time compared to both conventional and high-fidelity modelling methods while maintaining an acceptable level accuracy. Artificial neural networks (ANNs) multi-level approach are incorporated into formulation. utilises varied High-Fidelity Model (HFM) Low-Fidelity (LFM) covering different spaces. This means that HFM has only few variables, whereas LFM explores entire spaces during process. formulation demonstrated by (RDO) mono-stringer stiffened panel considering uncertainty under non-linear post-buckling regime.
منابع مشابه
Multi-fidelity Bandit Optimisation∗
In many scientific and engineering applications, we are tasked with the optimisation of an expensive to evaluate black box function. Traditional methods for this problem assume just the availability of this single function. However, in many cases, cheap approximations may be available. For example, in optimal policy search in robotics, the expensive real world behaviour of a robot can be approx...
متن کاملMulti-fidelity Gaussian Process Bandit Optimisation
In many scientific and engineering applications, we are tasked with the optimisation of an expensive to evaluate black box function f . Traditional settings for this problem assume just the availability of this single function. However, in many cases, cheap approximations to f may be obtainable. For example, the expensive real world behaviour of a robot can be approximated by a cheap computer s...
متن کاملMulti-fidelity Bayesian Optimisation with Continuous Approximations
Bandit methods for black-box optimisation, such as Bayesian optimisation, are used in a variety of applications including hyper-parameter tuning and experiment design. Recently, multifidelity methods have garnered considerable attention since function evaluations have become increasingly expensive in such applications. Multifidelity methods use cheap approximations to the function of interest t...
متن کاملGaussian Process Optimisation with Multi-fidelity Evaluations
In many scientific and engineering applications, we are tasked with the optimisation of an expensive to evaluate black box function f . Traditional methods for this problem assume just the availability of this single function. However, in many cases, cheap approximations to f may be obtainable. For example, the expensive real world behaviour of a robot can be approximated by a cheap computer si...
متن کاملFlexible Process Enactment Using Low-Fidelity Models
Attempts to extend process enactment to support dynamic, knowledge intensive activities have not been as successful as workflow for routine business processes. In part this is due to the dynamic nature of knowledge-intensive work: the tasks performed change continually in response to the knowledge developed by those tasks. Also, knowledge work involves significant informal communications, which...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Composite Structures
سال: 2021
ISSN: ['0263-8223', '1879-1085']
DOI: https://doi.org/10.1016/j.compstruct.2020.113477