Assessment of High-Temperature Effects on Hypersonic Aerothermoelastic Analysis using Multi-Fidelity Multi-Variate Surrogates

Sadagopan, Aravinth; Huang, Daning; Düzel, Ümran; Martin, Liza E.; Hanquist, Kyle M.

doi:10.2514/6.2021-1610

Cited by 6 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the context of dynamical systems, the original MVGPR is defined over a single input [22], time; for the general case of multi-dimensional inputs, see Refs. [20,21].…”

Section: B Multivariate Gaussian Process Regressionmentioning

confidence: 99%

“…Similar to the univariate case, the prediction at a new input 𝑡 * is represented using a multivariate Gaussian distribution; see Refs. [20,21,28] for details.…”

Section: Multivariate Gprmentioning

confidence: 99%

“…Building on the general-purpose MVGPR framework developed previously by the authors [20][21][22], this study aims to demonstrate the feasibility of GPR-based modal analysis of spatiotemporal data, as an alternative to DMD and SPOD methods. Specifically, the goals of this paper are to 1) Present the theoretical formulation of MVGPR for modal analysis of spatiotemporal data.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Modal Analysis of Spatiotemporal Data via Multi-fidelity Multi-variate Gaussian Processes

Song

Huang

2023

AIAA AVIATION 2023 Forum

View full text Add to dashboard Cite

Modal analysis has become an essential tool to understand the coherent structure of complex flows. The classical modal analysis methods, such as dynamic mode decomposition (DMD) and spectral proper orthogonal decomposition (SPOD), rely on a sufficient amount of data that is regularly sampled in time. However, often one needs to deal with sparse temporally irregular data, e.g., due to experimental measurements and simulation algorithm. To overcome the limitations of data scarcity and irregular sampling, we propose a novel modal analysis technique using multi-variate Gaussian process regression (MVGPR). We first establish the connection between MVGPR and the existing modal analysis techniques, DMD and SPOD, from a linear system identification perspective. Next, leveraging this connection, we develop a MVGPR-based modal analysis technique that addresses the aforementioned limitations. The capability of MVGPR is endowed by its judiciously designed kernel structure for correlation function, that is derived from the assumed linear dynamics. Subsequently, the proposed MVGPR

show abstract

“…In the context of dynamical systems, the original MVGPR is defined over a single input [22], time; for the general case of multi-dimensional inputs, see Refs. [20,21].…”

Section: B Multivariate Gaussian Process Regressionmentioning

confidence: 99%

“…Similar to the univariate case, the prediction at a new input 𝑡 * is represented using a multivariate Gaussian distribution; see Refs. [20,21,28] for details.…”

Section: Multivariate Gprmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Modal Analysis of Spatiotemporal Data via Multi-fidelity Multi-variate Gaussian Processes

Song

Huang

2023

AIAA AVIATION 2023 Forum

View full text Add to dashboard Cite

show abstract

“…This challenge is acute for the nuclear industry, which must prioritize public safety through rigorous quality control measures in all aspects of power plant design and operation. We understand this challenge to resonate in other industries for which modeling and simulation involving ML can inform high consequence decisions, such as the medical device industry that uses the idea of Software as a Medical Device [2], or aerospace where assessments of hypersonic aerothermoelasticity use multifidelity multivariate surrogate models (i.e., one variant of an advanced physics-informed machine learning method) [3].…”

Section: Introductionmentioning

confidence: 99%

Credibility Assessment of Machine Learning in a Manufacturing Process Application

Banyay

Worrell

Sidener

et al. 2021

Journal of Verification, Validation and Uncertainty Quantification

View full text Add to dashboard Cite

We present a framework for establishing credibility of a machine learning model used to predict a key process control variable setting to maximize product quality in a nuclear component manufacturing application. Our model coupled a purely data-based machine learning model with a physics-based adjustment that encoded subject matter expertise of the physical process. Establishing credibility of the resulting model provided the basis for eliminating a costly intermediate testing process that was previously used to determine the control variable setting.

show abstract

Study of fluid–thermal–structural interaction in high-temperature high-speed flow using multi-fidelity multi-variate surrogates

Huang

Sadagopan

Düzel

et al. 2022

Journal of Fluids and Structures

View full text Add to dashboard Cite

Assessment of High-Temperature Effects on Hypersonic Aerothermoelastic Analysis using Multi-Fidelity Multi-Variate Surrogates

Cited by 6 publications

References 30 publications

Modal Analysis of Spatiotemporal Data via Multi-fidelity Multi-variate Gaussian Processes

Modal Analysis of Spatiotemporal Data via Multi-fidelity Multi-variate Gaussian Processes

Credibility Assessment of Machine Learning in a Manufacturing Process Application

Study of fluid–thermal–structural interaction in high-temperature high-speed flow using multi-fidelity multi-variate surrogates

Contact Info

Product

Resources

About