Standardization in building an ANN-based mooring line top tension prediction system
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
ANN-based mooring line top tension prediction systems are trained on ship motion and mooring line top tension time histories from multiple wave states with a certain simulation length. In the previous studies, selection of the wave states and the simulation length differs between the studies and they are not standardized. Also, a plain neural network is mostly used. In this paper, tension prediction performances with respect to a distribution shape of the wave states, a number of the wave states, and the simulation length are first studied. Then, the prediction performances with respect to Batch Normalization (BN) and Learning Rate Decay (LRD) are studied, in which BN and LRD are very common components in modern neural network models. Lastly, a guideline for selecting the wave states and the simulation length is proposed, and BN and LRD are proven to be advisable to use to improve the prediction performance.
Abstract
ANN-based mooring line top tension prediction systems are trained on ship motion and mooring line top tension time histories from multiple wave states with a certain simulation length. In the previous studies, selection of the wave states and the simulation length differs between the studies and they are not standardized. Also, a plain neural network is mostly used. In this paper, tension prediction performances with respect to a distribution shape of the wave states, a number of the wave states, and the simulation length are first studied. Then, the prediction performances with respect to Batch Normalization (BN) and Learning Rate Decay (LRD) are studied, in which BN and LRD are very common components in modern neural network models. Lastly, a guideline for selecting the wave states and the simulation length is proposed, and BN and LRD are proven to be advisable to use to improve the prediction performance.
참고문헌 (14)
- Christiansen, N. H., "Efficient mooring line fatigue analysis using a hybrid method time domain simulation scheme", Proceedings of the AMSE 2013 32nd International Conference on Ocean, Offshore and Arctic Engineering (2013)
- Diaconescu, E., "The use of NARX neural networks to predict chaotic time series", WSEAS Trans. Comput. Res, 3, pp.182~191 (2008)
- DNV-GL, "Class Guideline (DNVGL-CG-0130): Wave Loads", ~ (2018)
- Guarize, R., "Neural networks in the dynamic response analysis of slender marine structures", Appl. Ocean Res, 29, pp.191~198 (2007)[DOI]
- Ioffe, S., "Batch normalization: accelerating deep network training by reducing internal covariate shift", 32nd International Conference on Machine Learning, ICML 2015. International Machine Learning Society (IMLS), pp.448~456 (2015)
- Kang, H. H., "A study on the effectiveness of the heading control on the mooring line tension and position offset for an arctic floating structure under complex environmental loads", J. Mar. Sci. Eng, 9, pp.1~17 (2021)[DOI]
- Macqueen, J., "Some methods for classification and analysis of multivariate observations", Proceedings of 5th Berkeley Symposium on Mathematical Statistics and Probability (1967)
- Sidarta, D. E., "Prediction of offshore platform mooring line tensions using artificial neural network", Proceedings of the 27th International Ocean and Polar Engineering Conference, pp.1~11 (2017)
- Sim~oes, M. G., "Neural-Network-based prediction of mooring forces in floating production storage and offloading systems", IEEE Trans. Ind. Appl, 38, pp.457~466 (2002)[DOI]
- Wheelan, C., "Naked Statistics: Stripping the Dread from Data" (2013), W. W. Norton & Company
- Xie, H., "Time series prediction based on NARX neural networks: an advanced approach", Proc. 2009 Int. Conf. Mach. Learn. Cybern, 3, pp.1275~1279 (2009)
- Yetkin, M., "Mooring line top-tension prediction using NARX", Proceedings of the AMSE 2017 36th International Conference on Ocean, Offshore and Arctic Engineering, pp.196~202 (2017)
- Yetkin, M., "Time series prediction of mooring line top tension by the NARX and Volterra model", Appl. Ocean Res, 88, pp.170~186 (2019)[DOI]
- You, K., "How Does Learning Rate Decay Help Modern Neural Networks?", ~ (2019)