Aarhus University Seal

Dansk

You are here: » Training of a Classifier for Structural Component Failure...

About Aarhus University

Training of a Classifier for Structural Component Failure Based on Hybrid Simulation and Kriging

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaper › Journal article › Research › peer-review

Standard

Training of a Classifier for Structural Component Failure Based on Hybrid Simulation and Kriging. / Abbiati, Giuseppe; Marelli, Stefano; Ligeikis, Connor et al.
In: Journal of Engineering Mechanics, Vol. 148, No. 1, 04021137, 01.2022.

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaper › Journal article › Research › peer-review

Harvard

Abbiati, G, Marelli, S, Ligeikis, C, Christenson, R & Stojadinović, B 2022, 'Training of a Classifier for Structural Component Failure Based on Hybrid Simulation and Kriging', Journal of Engineering Mechanics, vol. 148, no. 1, 04021137. https://doi.org/10.1061/(ASCE)EM.1943-7889.0002048

APA

Abbiati, G., Marelli, S., Ligeikis, C., Christenson, R., & Stojadinović, B. (2022). Training of a Classifier for Structural Component Failure Based on Hybrid Simulation and Kriging. Journal of Engineering Mechanics, 148(1), Article 04021137. https://doi.org/10.1061/(ASCE)EM.1943-7889.0002048

CBE

Abbiati G, Marelli S, Ligeikis C, Christenson R, Stojadinović B. 2022. Training of a Classifier for Structural Component Failure Based on Hybrid Simulation and Kriging. Journal of Engineering Mechanics. 148(1):Article 04021137. https://doi.org/10.1061/(ASCE)EM.1943-7889.0002048

MLA

Abbiati, Giuseppe et al. "Training of a Classifier for Structural Component Failure Based on Hybrid Simulation and Kriging". Journal of Engineering Mechanics. 2022. 148(1). https://doi.org/10.1061/(ASCE)EM.1943-7889.0002048

Vancouver

Abbiati G, Marelli S, Ligeikis C, Christenson R, Stojadinović B. Training of a Classifier for Structural Component Failure Based on Hybrid Simulation and Kriging. Journal of Engineering Mechanics. 2022 Jan;148(1):04021137. doi: 10.1061/(ASCE)EM.1943-7889.0002048

Author

Abbiati, Giuseppe ; Marelli, Stefano ; Ligeikis, Connor et al. / Training of a Classifier for Structural Component Failure Based on Hybrid Simulation and Kriging. In: Journal of Engineering Mechanics. 2022 ; Vol. 148, No. 1.

Bibtex

@article{7a53ed37eb2845ccbb879f326022b4f0,
title = "Training of a Classifier for Structural Component Failure Based on Hybrid Simulation and Kriging",
abstract = "Hybrid simulation is a tool for investigating the dynamic response of a structural prototype subjected to realistic loading. Hybrid simulation is conducted using a hybrid model that combines physical and numerical substructures interacting with each other in a feedback loop. As a result, the tested substructure interacts with a realistic assembly subjected to a credible loading scenario. In the current practice, experimental results obtained via hybrid simulation support conceptualization and calibration of computational models for structural analysis. Instead, this paper extends the scope of hybrid simulation in constructing a safe/failure state classifier for the tested substructure by adaptively designing a sequence of parametrized hybrid simulations. Such a classifier is intended to compute the state of any physical-substructure-like component within system-level numerical simulations. It follows that the main contribution of this paper lies in the way experimental results are aggregated and integrated with structural analysis. The proposed procedure is experimentally validated for a three-degrees-of-freedom hybrid model subjected to Euler buckling.",
keywords = "Active learning, Buckling, Classifier, FRAME, Hybrid simulation, Kriging, Metamodeling",
author = "Giuseppe Abbiati and Stefano Marelli and Connor Ligeikis and Richard Christenson and Bozidar Stojadinovi{\'c}",
note = "Publisher Copyright: {\textcopyright} 2021 American Society of Civil Engineers.",
year = "2022",
month = jan,
doi = "10.1061/(ASCE)EM.1943-7889.0002048",
language = "English",
volume = "148",
journal = "Journal of Engineering Mechanics",
issn = "0733-9399",
publisher = "American Society of Civil Engineers",
number = "1",

}

RIS

TY - JOUR

T1 - Training of a Classifier for Structural Component Failure Based on Hybrid Simulation and Kriging

AU - Abbiati, Giuseppe

AU - Marelli, Stefano

AU - Ligeikis, Connor

AU - Christenson, Richard

AU - Stojadinović, Bozidar

N1 - Publisher Copyright: © 2021 American Society of Civil Engineers.

PY - 2022/1

Y1 - 2022/1

N2 - Hybrid simulation is a tool for investigating the dynamic response of a structural prototype subjected to realistic loading. Hybrid simulation is conducted using a hybrid model that combines physical and numerical substructures interacting with each other in a feedback loop. As a result, the tested substructure interacts with a realistic assembly subjected to a credible loading scenario. In the current practice, experimental results obtained via hybrid simulation support conceptualization and calibration of computational models for structural analysis. Instead, this paper extends the scope of hybrid simulation in constructing a safe/failure state classifier for the tested substructure by adaptively designing a sequence of parametrized hybrid simulations. Such a classifier is intended to compute the state of any physical-substructure-like component within system-level numerical simulations. It follows that the main contribution of this paper lies in the way experimental results are aggregated and integrated with structural analysis. The proposed procedure is experimentally validated for a three-degrees-of-freedom hybrid model subjected to Euler buckling.

AB - Hybrid simulation is a tool for investigating the dynamic response of a structural prototype subjected to realistic loading. Hybrid simulation is conducted using a hybrid model that combines physical and numerical substructures interacting with each other in a feedback loop. As a result, the tested substructure interacts with a realistic assembly subjected to a credible loading scenario. In the current practice, experimental results obtained via hybrid simulation support conceptualization and calibration of computational models for structural analysis. Instead, this paper extends the scope of hybrid simulation in constructing a safe/failure state classifier for the tested substructure by adaptively designing a sequence of parametrized hybrid simulations. Such a classifier is intended to compute the state of any physical-substructure-like component within system-level numerical simulations. It follows that the main contribution of this paper lies in the way experimental results are aggregated and integrated with structural analysis. The proposed procedure is experimentally validated for a three-degrees-of-freedom hybrid model subjected to Euler buckling.

KW - Active learning

KW - Buckling

KW - Classifier

KW - FRAME

KW - Hybrid simulation

KW - Kriging

KW - Metamodeling

U2 - 10.1061/(ASCE)EM.1943-7889.0002048

DO - 10.1061/(ASCE)EM.1943-7889.0002048

M3 - Journal article

AN - SCOPUS:85119220019

VL - 148

JO - Journal of Engineering Mechanics

JF - Journal of Engineering Mechanics

SN - 0733-9399

IS - 1

M1 - 04021137

ER -