Predicting Bolt Stress Under Uncertainty in Offshore Wind Turbine Structural Connections Using a Gaussian Process Surrogate Model

Jack Jorgensen; Melinda Hodkiewicz; Edward Cripps; Ghulam Mubashar Hassan

Predicting Bolt Stress Under Uncertainty in Offshore Wind Turbine Structural Connections Using a Gaussian Process Surrogate Model

Jack Jorgensen, Melinda Hodkiewicz, Edward Cripps, Ghulam Mubashar Hassan

Research output: Chapter in Book/Conference paper › Conference paper › peer-review

Abstract

Fatigue assessment of bolted ring-flanges in offshore wind turbine structures is a critical step in the overall structural design process. Analytical and numerical methods are employed to predict bolt stress, offering the convenience of speed (analytical) or accuracy (numerical). In this paper, we investigate the application of a Gaussian Process (GP) surrogate model, leveraging the accuracy of numerical techniques with significant gains in computation times. We present the notion of predictive uncertainty available from the GP surrogate model. Finally, we demonstrate the capacity of the GP surrogate model to propagate input space uncertainty in a computationally efficient manner.

Original language	English
Title of host publication	Proceedings of the Thirty-First International Ocean and Polar Engineering Conference
Publisher	International Society of Offshore and Polar Engineers
Pages	477-484
Number of pages	8
ISBN (Print)	978-1-880653-82-1
Publication status	Published - 20 Jun 2021
Event	31st International Ocean and Polar Engineering Conference - Rhodes, Greece Duration: 20 Jun 2021 → 25 Jun 2021 Conference number: 31

Conference

Conference	31st International Ocean and Polar Engineering Conference
Country/Territory	Greece
City	Rhodes
Period	20/06/21 → 25/06/21

Access to Document

https://onepetro.org/ISOPEIOPEC/proceedings/ISOPE21/All-ISOPE21/ISOPE-I-21-1201/464518

Cite this

Jorgensen, J., Hodkiewicz, M., Cripps, E., & Hassan, G. M. (2021). Predicting Bolt Stress Under Uncertainty in Offshore Wind Turbine Structural Connections Using a Gaussian Process Surrogate Model. In Proceedings of the Thirty-First International Ocean and Polar Engineering Conference (pp. 477-484). International Society of Offshore and Polar Engineers. https://onepetro.org/ISOPEIOPEC/proceedings/ISOPE21/All-ISOPE21/ISOPE-I-21-1201/464518

@inproceedings{52b3a98f97fb4e729ea995f01f925feb,

title = "Predicting Bolt Stress Under Uncertainty in Offshore Wind Turbine Structural Connections Using a Gaussian Process Surrogate Model",

abstract = "Fatigue assessment of bolted ring-flanges in offshore wind turbine structures is a critical step in the overall structural design process. Analytical and numerical methods are employed to predict bolt stress, offering the convenience of speed (analytical) or accuracy (numerical). In this paper, we investigate the application of a Gaussian Process (GP) surrogate model, leveraging the accuracy of numerical techniques with significant gains in computation times. We present the notion of predictive uncertainty available from the GP surrogate model. Finally, we demonstrate the capacity of the GP surrogate model to propagate input space uncertainty in a computationally efficient manner.",

author = "Jack Jorgensen and Melinda Hodkiewicz and Edward Cripps and Hassan, {Ghulam Mubashar}",

year = "2021",

month = jun,

day = "20",

language = "English",

isbn = "978-1-880653-82-1",

pages = "477--484",

booktitle = "Proceedings of the Thirty-First International Ocean and Polar Engineering Conference",

publisher = "International Society of Offshore and Polar Engineers",

address = "United States",

note = "31st International Ocean and Polar Engineering Conference ; Conference date: 20-06-2021 Through 25-06-2021",

}

Jorgensen, J , Hodkiewicz, M , Cripps, E & Hassan, GM 2021, Predicting Bolt Stress Under Uncertainty in Offshore Wind Turbine Structural Connections Using a Gaussian Process Surrogate Model. in Proceedings of the Thirty-First International Ocean and Polar Engineering Conference. International Society of Offshore and Polar Engineers, pp. 477-484, 31st International Ocean and Polar Engineering Conference, Rhodes, Greece, 20/06/21. <https://onepetro.org/ISOPEIOPEC/proceedings/ISOPE21/All-ISOPE21/ISOPE-I-21-1201/464518>

Predicting Bolt Stress Under Uncertainty in Offshore Wind Turbine Structural Connections Using a Gaussian Process Surrogate Model. / Jorgensen, Jack ; Hodkiewicz, Melinda ; Cripps, Edward et al.

Proceedings of the Thirty-First International Ocean and Polar Engineering Conference. International Society of Offshore and Polar Engineers, 2021. p. 477-484.

Research output: Chapter in Book/Conference paper › Conference paper › peer-review

TY - GEN

T1 - Predicting Bolt Stress Under Uncertainty in Offshore Wind Turbine Structural Connections Using a Gaussian Process Surrogate Model

AU - Jorgensen, Jack

AU - Hodkiewicz, Melinda

AU - Cripps, Edward

AU - Hassan, Ghulam Mubashar

N1 - Conference code: 31

PY - 2021/6/20

Y1 - 2021/6/20

N2 - Fatigue assessment of bolted ring-flanges in offshore wind turbine structures is a critical step in the overall structural design process. Analytical and numerical methods are employed to predict bolt stress, offering the convenience of speed (analytical) or accuracy (numerical). In this paper, we investigate the application of a Gaussian Process (GP) surrogate model, leveraging the accuracy of numerical techniques with significant gains in computation times. We present the notion of predictive uncertainty available from the GP surrogate model. Finally, we demonstrate the capacity of the GP surrogate model to propagate input space uncertainty in a computationally efficient manner.

AB - Fatigue assessment of bolted ring-flanges in offshore wind turbine structures is a critical step in the overall structural design process. Analytical and numerical methods are employed to predict bolt stress, offering the convenience of speed (analytical) or accuracy (numerical). In this paper, we investigate the application of a Gaussian Process (GP) surrogate model, leveraging the accuracy of numerical techniques with significant gains in computation times. We present the notion of predictive uncertainty available from the GP surrogate model. Finally, we demonstrate the capacity of the GP surrogate model to propagate input space uncertainty in a computationally efficient manner.

UR - https://www.isope.org/wp-content/uploads/2020/11/CALL-2021-Rhodes-DL1210jc.pdf

UR - https://www.isope.org/

M3 - Conference paper

SN - 978-1-880653-82-1

SP - 477

EP - 484

BT - Proceedings of the Thirty-First International Ocean and Polar Engineering Conference

PB - International Society of Offshore and Polar Engineers

T2 - 31st International Ocean and Polar Engineering Conference

Y2 - 20 June 2021 through 25 June 2021

ER -

Predicting Bolt Stress Under Uncertainty in Offshore Wind Turbine Structural Connections Using a Gaussian Process Surrogate Model

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Finite Element Method Numerical Simulation results for analysis of Segment Model of Bolted Ring Flange

ARC ITRH for Offshore Floating Facilities

Cite this

Predicting Bolt Stress Under Uncertainty in Offshore Wind Turbine Structural Connections Using a Gaussian Process Surrogate Model

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Datasets

Finite Element Method Numerical Simulation results for analysis of Segment Model of Bolted Ring Flange

Projects

ARC ITRH for Offshore Floating Facilities

Cite this