Modelling Vortex-Induced Loads Using Recurrent Neural Networks

Joshua A. Foster; Jan Rik Decuyper; Mark Runacres; Tim De Troyer

doi:10.1016/j.ifacol.2021.11.149

Modelling Vortex-Induced Loads Using Recurrent Neural Networks

Joshua A. Foster, Jan Rik Decuyper, Mark Runacres, Tim De Troyer

Research output: Chapter in Book/Report/Conference proceeding › Conference paper

3 Citations (Scopus)

147 Downloads (Pure)

Abstract

In this work recurrent neural networks of the LSTM type are used to describe unsteady fluid loading. Indirect load measurements are especially useful for structural health monitoring applications. Relying on discrete spatiotemporal measurements of the velocity field, both the forces and the corresponding displacement of a cylinder subjected to vortex shedding are modelled.

Original language	English
Title of host publication	Modeling, Estimation and Control Conference MECC 2021
Editors	Junmin Wang, Hosam Fathy, Qian Wang, Beibei Ren
Place of Publication	Austin, Texas, USA
Publisher	IFAC - PapersOnLine
Pages	32-37
Number of pages	6
Volume	54
Edition	20
DOIs	https://doi.org/10.1016/j.ifacol.2021.11.149
Publication status	Published - 25 Oct 2021
Event	2021 Modeling, Estimation and Control Conference - Online, Austin, United States Duration: 24 Oct 2021 → 27 Oct 2021 https://mecc2021.a2c2.org

Publication series

Name	IFAC Proceedings Volumes
Publisher	International Federation of Automatic Control (IFAC)
Number	20
Volume	54
ISSN (Electronic)	2405-8963

Conference

Conference	2021 Modeling, Estimation and Control Conference
Abbreviated title	MECC 2021
Country/Territory	United States
City	Austin
Period	24/10/21 → 27/10/21
Internet address	https://mecc2021.a2c2.org

Keywords

Machine learning
vortex-induced vibrations
unsteady fluid dynamics
Long Short-Term Memory Recurrent Neural Networks

Access to Document

10.1016/j.ifacol.2021.11.149

Modelling-vortex-induced-loads-using-Recurrent-Neural-Networks--_2021_IFAC-PFinal published version, 1.14 MB

Handle.net

Persistent link

Cite this

Foster, J. A., Decuyper, J. R., Runacres, M., & De Troyer, T. (2021). Modelling Vortex-Induced Loads Using Recurrent Neural Networks. In J. Wang, H. Fathy, Q. Wang, & B. Ren (Eds.), Modeling, Estimation and Control Conference MECC 2021 (20 ed., Vol. 54, pp. 32-37). (IFAC Proceedings Volumes; Vol. 54, No. 20). IFAC - PapersOnLine. https://doi.org/10.1016/j.ifacol.2021.11.149

@inproceedings{5b5ee9238b084bd0b61d659e367a1c39,

title = "Modelling Vortex-Induced Loads Using Recurrent Neural Networks",

abstract = "In this work recurrent neural networks of the LSTM type are used to describe unsteady fluid loading. Indirect load measurements are especially useful for structural health monitoring applications. Relying on discrete spatiotemporal measurements of the velocity field, both the forces and the corresponding displacement of a cylinder subjected to vortex shedding are modelled.",

keywords = "Machine learning, vortex-induced vibrations, unsteady fluid dynamics, Long Short-Term Memory Recurrent Neural Networks",

author = "Foster, {Joshua A.} and Decuyper, {Jan Rik} and Mark Runacres and {De Troyer}, Tim",

year = "2021",

month = oct,

day = "25",

doi = "10.1016/j.ifacol.2021.11.149",

language = "English",

volume = "54",

series = "IFAC Proceedings Volumes",

publisher = "IFAC - PapersOnLine",

number = "20",

pages = "32--37",

editor = "Junmin Wang and Hosam Fathy and Qian Wang and Beibei Ren",

booktitle = "Modeling, Estimation and Control Conference MECC 2021",

edition = "20",

note = "2021 Modeling, Estimation and Control Conference, MECC 2021 ; Conference date: 24-10-2021 Through 27-10-2021",

url = "https://mecc2021.a2c2.org",

}

Foster, JA, Decuyper, JR , Runacres, M & De Troyer, T 2021, Modelling Vortex-Induced Loads Using Recurrent Neural Networks. in J Wang, H Fathy, Q Wang & B Ren (eds), Modeling, Estimation and Control Conference MECC 2021. 20 edn, vol. 54, IFAC Proceedings Volumes, no. 20, vol. 54, IFAC - PapersOnLine, Austin, Texas, USA, pp. 32-37, 2021 Modeling, Estimation and Control Conference, Austin, Texas, United States, 24/10/21. https://doi.org/10.1016/j.ifacol.2021.11.149

Modelling Vortex-Induced Loads Using Recurrent Neural Networks. / Foster, Joshua A.; Decuyper, Jan Rik ; Runacres, Mark et al.
Modeling, Estimation and Control Conference MECC 2021. ed. / Junmin Wang; Hosam Fathy; Qian Wang; Beibei Ren. Vol. 54 20. ed. Austin, Texas, USA: IFAC - PapersOnLine, 2021. p. 32-37 (IFAC Proceedings Volumes; Vol. 54, No. 20).

Research output: Chapter in Book/Report/Conference proceeding › Conference paper

TY - GEN

T1 - Modelling Vortex-Induced Loads Using Recurrent Neural Networks

AU - Foster, Joshua A.

AU - Decuyper, Jan Rik

AU - Runacres, Mark

AU - De Troyer, Tim

PY - 2021/10/25

Y1 - 2021/10/25

N2 - In this work recurrent neural networks of the LSTM type are used to describe unsteady fluid loading. Indirect load measurements are especially useful for structural health monitoring applications. Relying on discrete spatiotemporal measurements of the velocity field, both the forces and the corresponding displacement of a cylinder subjected to vortex shedding are modelled.

AB - In this work recurrent neural networks of the LSTM type are used to describe unsteady fluid loading. Indirect load measurements are especially useful for structural health monitoring applications. Relying on discrete spatiotemporal measurements of the velocity field, both the forces and the corresponding displacement of a cylinder subjected to vortex shedding are modelled.

KW - Machine learning

KW - vortex-induced vibrations

KW - unsteady fluid dynamics

KW - Long Short-Term Memory Recurrent Neural Networks

UR - http://www.scopus.com/inward/record.url?scp=85124618521&partnerID=8YFLogxK

U2 - 10.1016/j.ifacol.2021.11.149

DO - 10.1016/j.ifacol.2021.11.149

M3 - Conference paper

VL - 54

T3 - IFAC Proceedings Volumes

SP - 32

EP - 37

BT - Modeling, Estimation and Control Conference MECC 2021

A2 - Wang, Junmin

A2 - Fathy, Hosam

A2 - Wang, Qian

A2 - Ren, Beibei

PB - IFAC - PapersOnLine

CY - Austin, Texas, USA

T2 - 2021 Modeling, Estimation and Control Conference

Y2 - 24 October 2021 through 27 October 2021

ER -

Modelling Vortex-Induced Loads Using Recurrent Neural Networks

Abstract

Publication series

Conference

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

SRP60: SRP-Groeifinanciering: A system identification framework for multi-fidelity modelling

Estimating a sparse nonlinear dynamical model of the flow around an oscillating cylinder in a fluid flow using SINDy

A nonlinear model of vortex-induced forces on an oscillating cylinder in a fluid flow

Modelling vortex-induced loads using machine learning

Data-driven modelling of unsteady fluid dynamics

Cite this

Modelling Vortex-Induced Loads Using Recurrent Neural Networks

Abstract

Publication series

Conference

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

Projects

SRP60: SRP-Groeifinanciering: A system identification framework for multi-fidelity modelling

Research output

Estimating a sparse nonlinear dynamical model of the flow around an oscillating cylinder in a fluid flow using SINDy

A nonlinear model of vortex-induced forces on an oscillating cylinder in a fluid flow

Modelling vortex-induced loads using machine learning

Activities

Data-driven modelling of unsteady fluid dynamics

Cite this