Optimized Mooring Line Simulation Using a Hybrid Method Time Domain Scheme

Niels Hørbye Christiansen; Per Erlend Torbergsen Voie; Jan Høgsberg; Nils Sodahl

doi:10.1115/omae2014-23939

Optimized Mooring Line Simulation Using a Hybrid Method Time Domain Scheme

Niels Hørbye Christiansen, Per Erlend Torbergsen Voie, Jan Høgsberg, Nils Sodahl

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

Dynamic analyses of slender marine structures are computationally expensive. Recently it has been shown how a hybrid method which combines FEM models and artificial neural networks (ANN) can be used to reduce the computation time spend on the time domain simulations associated with fatigue analysis of mooring lines by two orders of magnitude. The present study shows how an ANN trained to perform nonlinear dynamic response simulation can be optimized using a method known as optimal brain damage (OBD) and thereby be used to rank the importance of all analysis input. Both the training and the optimization of the ANN are based on one short time domain simulation sequence generated by a FEM model of the structure. This means that it is possible to evaluate the importance of input parameters based on this single simulation only. The method is tested on a numerical model of mooring lines on a floating offshore installation. It is shown that it is possible to estimate the cost of ignoring one or more input variables in an analysis.

Original language	English
Title of host publication	Proceedings of the 33rd International Conference on Ocean, Offshore and Arctic Engineering : Offshore Technology
Number of pages	10
Volume	1B
Publisher	The American Society of Mechanical Engineers (ASME)
Publication date	2014
Article number	OMAE2014-23939
ISBN (Print)	978-0-7918-4538-7
DOIs	https://doi.org/10.1115/omae2014-23939
Publication status	Published - 2014
Event	33rd International Conference on Ocean, Offshore and Arctic Engineering - San Francisco, CA, United States Duration: 8 Jun 2014 → 13 Jun 2014 http://www.asmeconferences.org/OMAE2014/

Conference

Conference	33rd International Conference on Ocean, Offshore and Arctic Engineering
Country/Territory	United States
City	San Francisco, CA
Period	08/06/2014 → 13/06/2014
Internet address	http://www.asmeconferences.org/OMAE2014/

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1115/omae2014-23939

OpenUrl availability

Full text

Cite this

Christiansen, N. H., Voie, P. E. T., Høgsberg, J., & Sodahl, N. (2014). Optimized Mooring Line Simulation Using a Hybrid Method Time Domain Scheme. In Proceedings of the 33rd International Conference on Ocean, Offshore and Arctic Engineering: Offshore Technology (Vol. 1B). Article OMAE2014-23939 The American Society of Mechanical Engineers (ASME). https://doi.org/10.1115/omae2014-23939

@inproceedings{1f6611ec93e54f94b429ae6d6c6b02ff,

title = "Optimized Mooring Line Simulation Using a Hybrid Method Time Domain Scheme",

abstract = "Dynamic analyses of slender marine structures are computationally expensive. Recently it has been shown how a hybrid method which combines FEM models and artificial neural networks (ANN) can be used to reduce the computation time spend on the time domain simulations associated with fatigue analysis of mooring lines by two orders of magnitude. The present study shows how an ANN trained to perform nonlinear dynamic response simulation can be optimized using a method known as optimal brain damage (OBD) and thereby be used to rank the importance of all analysis input. Both the training and the optimization of the ANN are based on one short time domain simulation sequence generated by a FEM model of the structure. This means that it is possible to evaluate the importance of input parameters based on this single simulation only. The method is tested on a numerical model of mooring lines on a floating offshore installation. It is shown that it is possible to estimate the cost of ignoring one or more input variables in an analysis.",

author = "Christiansen, \{Niels H{\o}rbye\} and Voie, \{Per Erlend Torbergsen\} and Jan H{\o}gsberg and Nils Sodahl",

year = "2014",

doi = "10.1115/omae2014-23939",

language = "English",

isbn = "978-0-7918-4538-7",

volume = "1B",

booktitle = "Proceedings of the 33rd International Conference on Ocean, Offshore and Arctic Engineering",

publisher = "The American Society of Mechanical Engineers (ASME)",

address = "United States",

note = "33rd International Conference on Ocean, Offshore and Arctic Engineering ; Conference date: 08-06-2014 Through 13-06-2014",

url = "http://www.asmeconferences.org/OMAE2014/",

}

Christiansen, NH, Voie, PET, Høgsberg, J & Sodahl, N 2014, Optimized Mooring Line Simulation Using a Hybrid Method Time Domain Scheme. in Proceedings of the 33rd International Conference on Ocean, Offshore and Arctic Engineering: Offshore Technology. vol. 1B, OMAE2014-23939, The American Society of Mechanical Engineers (ASME), 33rd International Conference on Ocean, Offshore and Arctic Engineering, San Francisco, CA, United States, 08/06/2014. https://doi.org/10.1115/omae2014-23939

Optimized Mooring Line Simulation Using a Hybrid Method Time Domain Scheme. / Christiansen, Niels Hørbye; Voie, Per Erlend Torbergsen; Høgsberg, Jan et al.
Proceedings of the 33rd International Conference on Ocean, Offshore and Arctic Engineering: Offshore Technology. Vol. 1B The American Society of Mechanical Engineers (ASME), 2014. OMAE2014-23939.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Optimized Mooring Line Simulation Using a Hybrid Method Time Domain Scheme

AU - Christiansen, Niels Hørbye

AU - Voie, Per Erlend Torbergsen

AU - Høgsberg, Jan

AU - Sodahl, Nils

PY - 2014

Y1 - 2014

N2 - Dynamic analyses of slender marine structures are computationally expensive. Recently it has been shown how a hybrid method which combines FEM models and artificial neural networks (ANN) can be used to reduce the computation time spend on the time domain simulations associated with fatigue analysis of mooring lines by two orders of magnitude. The present study shows how an ANN trained to perform nonlinear dynamic response simulation can be optimized using a method known as optimal brain damage (OBD) and thereby be used to rank the importance of all analysis input. Both the training and the optimization of the ANN are based on one short time domain simulation sequence generated by a FEM model of the structure. This means that it is possible to evaluate the importance of input parameters based on this single simulation only. The method is tested on a numerical model of mooring lines on a floating offshore installation. It is shown that it is possible to estimate the cost of ignoring one or more input variables in an analysis.

AB - Dynamic analyses of slender marine structures are computationally expensive. Recently it has been shown how a hybrid method which combines FEM models and artificial neural networks (ANN) can be used to reduce the computation time spend on the time domain simulations associated with fatigue analysis of mooring lines by two orders of magnitude. The present study shows how an ANN trained to perform nonlinear dynamic response simulation can be optimized using a method known as optimal brain damage (OBD) and thereby be used to rank the importance of all analysis input. Both the training and the optimization of the ANN are based on one short time domain simulation sequence generated by a FEM model of the structure. This means that it is possible to evaluate the importance of input parameters based on this single simulation only. The method is tested on a numerical model of mooring lines on a floating offshore installation. It is shown that it is possible to estimate the cost of ignoring one or more input variables in an analysis.

U2 - 10.1115/omae2014-23939

DO - 10.1115/omae2014-23939

M3 - Article in proceedings

SN - 978-0-7918-4538-7

VL - 1B

BT - Proceedings of the 33rd International Conference on Ocean, Offshore and Arctic Engineering

PB - The American Society of Mechanical Engineers (ASME)

T2 - 33rd International Conference on Ocean, Offshore and Arctic Engineering

Y2 - 8 June 2014 through 13 June 2014

ER -

Optimized Mooring Line Simulation Using a Hybrid Method Time Domain Scheme

Abstract

Conference

UN SDGs

Access to Document

OpenUrl availability

Fingerprint

Cite this