Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225708682> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4225708682 abstract "A multi-fidelity (MF) active learning method is presented for design optimization problems characterized by noisy evaluations of the performance metrics. Namely, a generalized MF surrogate model is used for design-space exploration, exploiting an arbitrary number of hierarchical fidelity levels, i.e., performance evaluations coming from different models, solvers, or discretizations, characterized by different accuracy. The method is intended to accurately predict the design performance while reducing the computational effort required by simulation-driven design (SDD) to achieve the global optimum. The overall MF prediction is evaluated as a low-fidelity trained surrogate corrected with the surrogates of the errors between consecutive fidelity levels. Surrogates are based on stochastic radial basis functions (SRBF) with least squares regression and in-the-loop optimization of hyperparameters to deal with noisy training data. The method adaptively queries new training data, selecting both the design points and the required fidelity level via an active learning approach. This is based on the lower confidence bounding method, which combines performance prediction and associated uncertainty to select the most promising design regions. The fidelity levels are selected considering the benefit-cost ratio associated with their use in the training. The method's performance is assessed and discussed using four analytical tests and three SDD problems based on computational fluid dynamics simulations, namely the shape optimization of a NACA hydrofoil, the DTMB 5415 destroyer, and a roll-on/roll-off passenger ferry. Fidelity levels are provided by both adaptive grid refinement and multi-grid resolution approaches. Under the assumption of a limited budget of function evaluations, the proposed MF method shows better performance in comparison with the model trained by high-fidelity evaluations only." @default.
- W4225708682 created "2022-05-05" @default.
- W4225708682 creator A5005601025 @default.
- W4225708682 creator A5047085967 @default.
- W4225708682 creator A5058949283 @default.
- W4225708682 creator A5073878030 @default.
- W4225708682 creator A5074571660 @default.
- W4225708682 creator A5079572890 @default.
- W4225708682 date "2022-02-14" @default.
- W4225708682 modified "2023-10-16" @default.
- W4225708682 title "A Multi-Fidelity Active Learning Method for Global Design Optimization Problems with Noisy Evaluations" @default.
- W4225708682 doi "https://doi.org/10.48550/arxiv.2202.06902" @default.
- W4225708682 hasPublicationYear "2022" @default.
- W4225708682 type Work @default.
- W4225708682 citedByCount "0" @default.
- W4225708682 crossrefType "posted-content" @default.
- W4225708682 hasAuthorship W4225708682A5005601025 @default.
- W4225708682 hasAuthorship W4225708682A5047085967 @default.
- W4225708682 hasAuthorship W4225708682A5058949283 @default.
- W4225708682 hasAuthorship W4225708682A5073878030 @default.
- W4225708682 hasAuthorship W4225708682A5074571660 @default.
- W4225708682 hasAuthorship W4225708682A5079572890 @default.
- W4225708682 hasBestOaLocation W42257086821 @default.
- W4225708682 hasConcept C10485038 @default.
- W4225708682 hasConcept C119857082 @default.
- W4225708682 hasConcept C12267149 @default.
- W4225708682 hasConcept C126255220 @default.
- W4225708682 hasConcept C131675550 @default.
- W4225708682 hasConcept C154945302 @default.
- W4225708682 hasConcept C187691185 @default.
- W4225708682 hasConcept C2524010 @default.
- W4225708682 hasConcept C2776459999 @default.
- W4225708682 hasConcept C2778049539 @default.
- W4225708682 hasConcept C33923547 @default.
- W4225708682 hasConcept C41008148 @default.
- W4225708682 hasConcept C63584917 @default.
- W4225708682 hasConcept C76155785 @default.
- W4225708682 hasConcept C8642999 @default.
- W4225708682 hasConceptScore W4225708682C10485038 @default.
- W4225708682 hasConceptScore W4225708682C119857082 @default.
- W4225708682 hasConceptScore W4225708682C12267149 @default.
- W4225708682 hasConceptScore W4225708682C126255220 @default.
- W4225708682 hasConceptScore W4225708682C131675550 @default.
- W4225708682 hasConceptScore W4225708682C154945302 @default.
- W4225708682 hasConceptScore W4225708682C187691185 @default.
- W4225708682 hasConceptScore W4225708682C2524010 @default.
- W4225708682 hasConceptScore W4225708682C2776459999 @default.
- W4225708682 hasConceptScore W4225708682C2778049539 @default.
- W4225708682 hasConceptScore W4225708682C33923547 @default.
- W4225708682 hasConceptScore W4225708682C41008148 @default.
- W4225708682 hasConceptScore W4225708682C63584917 @default.
- W4225708682 hasConceptScore W4225708682C76155785 @default.
- W4225708682 hasConceptScore W4225708682C8642999 @default.
- W4225708682 hasLocation W42257086821 @default.
- W4225708682 hasLocation W42257086822 @default.
- W4225708682 hasLocation W42257086823 @default.
- W4225708682 hasOpenAccess W4225708682 @default.
- W4225708682 hasPrimaryLocation W42257086821 @default.
- W4225708682 hasRelatedWork W2921683824 @default.
- W4225708682 hasRelatedWork W2954882791 @default.
- W4225708682 hasRelatedWork W2966473332 @default.
- W4225708682 hasRelatedWork W3128150010 @default.
- W4225708682 hasRelatedWork W3195699808 @default.
- W4225708682 hasRelatedWork W3199608561 @default.
- W4225708682 hasRelatedWork W4225708682 @default.
- W4225708682 hasRelatedWork W4287374055 @default.
- W4225708682 hasRelatedWork W4296483387 @default.
- W4225708682 hasRelatedWork W76331760 @default.
- W4225708682 isParatext "false" @default.
- W4225708682 isRetracted "false" @default.
- W4225708682 workType "article" @default.