Optimization of neural networks for time-domain simulation of mooring lines

Abstract

When using artificial neural networks in methods for dynamic analysis of slender structures, the computational effort associated with time-domain response simulation may be reduced drastically compared to classic solution strategies. This article demonstrates that the network structure of an artificial neural network, which has been trained to simulate forces in a mooring line of a floating offshore platform, can be optimized and reduced by different optimization procedures. The procedures both detect and prune the least salient network weights successively, and besides trimming the network, they also can be used to rank the importance of the various network inputs. The dynamic response of slender marine structures often depends on several external load components, and by applying the optimization procedures to a trained artificial neural network, it is possible to classify the external force components with respect to importance and subsequently determine which of them may be ignored in the analysis. The performance of the optimization procedures is illustrated by a numerical example, which shows that, in particular, the most simple procedures are able to remove more than half of the network weights in an artificial neural network without significant loss of simulation accuracy.

Keywords

Nonlinear dynamics slender marine structures neural networks optimal brain damage optimal brain surgeon

Get full access to this article

View all access options for this article.

References

Adeli

. Neural networks in civil engineering: 1989–2000. Comput-Aided Civ Inf 2001; 16: 126–142.

Bakhary

Hao

Deeks

. Damage detection using artificial neural network with consideration of uncertainties. Eng Struct 2007; 29: 2806–2815.

Guarize

Matos

NAF

Sagrilo

LVS

. Neural networks in dynamic response analysis of slender marine structures. Appl Ocean Res 2008; 29: 191–198.

Christiansen

Voie

PET

Sødahl

. Efficient mooring line fatigue analysis using a hybrid method time domain simulation scheme. In: Proceedings of the OMAE2013 international conference on ocean, offshore and arctic engineering, Nantes, 9–14 June 2013, vol. 32, paper no. 10682. New York: ASME.

Christiansen

Voie

PET

Winther

. Comparison of error measures for neural networks for simulation of slender marine structures. J Appl Math 2014; 2014: 759834.

Reed

. Pruning algorithms—a survey. IEEE T Neural Networ 1993; 4: 740–747.

Le Cun

Denker

Solla

. Optimal brain damage. In: Touretzky

(ed.) Advances in neural information processing systems, vol. 2. San Mateo, CA: Morgan Kaufmann, 1990, pp.598–605.

Hassibi

Stork

Wolff

. Optimal brain surgeon and general network pruning. IEEE IJCNN 1993; 1–3: 293–299.

Warner

Misra

. Understanding neural networks as statistical tools. Am Stat 1996; 50(4): 284–293.

10.

Bishop

. Pattern recognition and machine learning. New York: Springer, 2006.

11.

Bishop

. Neural networks for pattern recognition. Oxford: Clarendon Press, 1995.

12.

Hanson

Burr

. Minkowski-r back-propagation: learning in connectionist models with non-Euclidean error signals. In: Proceedings of IEEE Conference on Neural information processing systems – Natural and Synthetic (ed Anderson

), Denver, CO, 8–12 November 1987, pp. 348–357. New York: American Institute of Physics.

13.

Fletcher

. Practical methods of optimization. Hoboken, NJ: Wiley, 1987.

14.

MARINTEK. SIMO theory manual. Trondheim: Sintef, 2009.

15.

MARINTEK. RIFLEX theory manual. Trondheim: Sintef, 2008.

16.

Dowling

Socie

. Simple rainflow counting algorithms. Int J Fatigue 1982; 4: 31–40.

17.

McClelland

. Explorations in parallel distributed processing: a handbook models, programs, and exercises, February 2013. California, USA: Stanford University.

18.

Thrun

Bala

Bloedorn

. The monk’s problems—a performance comparison of different learning algorithms. Technical report, CMU-CS-91-197, 1991. Pittsburgh, PA: Carnegie Mellon University.