Volume 2D: Turbomachinery 2020
DOI: 10.1115/gt2020-16321
|View full text |Cite
|
Sign up to set email alerts
|

Transfer Optimization in Accelerating the Design of Turbomachinery Cascades

Abstract: This paper draws motivation from the fact that engineering optimizations were mostly carried out from scratch. In contrast, however, humans routinely take advantage of the knowledge from past experiences whenever a new task is met. Such a transfer learning process by leveraging knowledge from already completed tasks can be promising to significantly improve the performance of current state-of-the-art algorithms, particularly in solving expensive black-box problems. In light of the above, we propose a Cokriging… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(3 citation statements)
references
References 0 publications
0
3
0
Order By: Relevance
“…Of these methods, co-kriging has proved to be particularly popular due to the natural way in which the heterogeneous uncertainties may be handled. An additional advantage is that the predictive uncertainty may be expressed through the kriging variance (see, e.g., [104][105][106][107] for examples in the aeronautics and turbomachinery spaces). In recent years, there has also been emphasis placed on developing ML methods for multi-scale [108][109][110] or multi-level [111,112] uncertainty propagation.…”
Section: Multi-fidelity Methodsmentioning
confidence: 99%
“…Of these methods, co-kriging has proved to be particularly popular due to the natural way in which the heterogeneous uncertainties may be handled. An additional advantage is that the predictive uncertainty may be expressed through the kriging variance (see, e.g., [104][105][106][107] for examples in the aeronautics and turbomachinery spaces). In recent years, there has also been emphasis placed on developing ML methods for multi-scale [108][109][110] or multi-level [111,112] uncertainty propagation.…”
Section: Multi-fidelity Methodsmentioning
confidence: 99%
“…36 They can be applied to optimization problems to reduce computational costs. Artificial Neural Networks (ANN), 37 Polynomial Response Surface Method (PRSM) 38 and the Kriging method 39 are three surrogate models frequently used for turbomachinery optimization. 40 Gradient-based approaches depend upon derivative information to locally detect an optimization search direction for all objectives and constraints.…”
Section: Introductionmentioning
confidence: 99%
“…36 They can be applied to optimization problems to reduce computational costs. Artificial Neural Networks (ANN), 37 Polynomial Response Surface Method (PRSM) 38 and the Kriging method 39 are three surrogate models frequently used for turbomachinery optimization. 40…”
Section: Introductionmentioning
confidence: 99%