Motion predictive control for DPS using predicted drifted ship position based on deep learning and replay buffer
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Typically, a Dynamic Positioning System (DPS) uses a PID feed-back system, and it often adopts a wind feed-forward system because of its easier implementation than a feed-forward system based on current or wave. But, because a ship’s drifting motion is caused by wind, current, and wave drift loads, all three environmental loads should be considered. In this study, a motion predictive control for the PID feedback system of the DPS is proposed, which considers the three environmental loads by utilizing predicted drifted ship positions in the future since it contains information about the three environmental loads from the moment to the future. The prediction accuracy for the future drifted ship position is ensured by adopting deep learning algorithms and a replay buffer. Finally, it is shown that the proposed motion predictive system results in better station-keeping performance than the wind feed-forward system.
Abstract
Typically, a Dynamic Positioning System (DPS) uses a PID feed-back system, and it often adopts a wind feed-forward system because of its easier implementation than a feed-forward system based on current or wave. But, because a ship’s drifting motion is caused by wind, current, and wave drift loads, all three environmental loads should be considered. In this study, a motion predictive control for the PID feedback system of the DPS is proposed, which considers the three environmental loads by utilizing predicted drifted ship positions in the future since it contains information about the three environmental loads from the moment to the future. The prediction accuracy for the future drifted ship position is ensured by adopting deep learning algorithms and a replay buffer. Finally, it is shown that the proposed motion predictive system results in better station-keeping performance than the wind feed-forward system.
참고문헌 (23)
- Aalbers, A., "Wave feed forward DP and the effect on shuttle tanker operation", Dynamic Positioning Conference (2004)
- Cho, K., "Learning phrase representations using RNN encoder-decoder for statistical machine translation", ArXiv Preprint ArXiv:1406.1078, 1724~1734 (2014)
- De Wit, C., "Optimal Thrust Allocation Methods for Dynamic Positioning of Ships", pp.2009
- Du, Jialu, "Robust dynamic positioning of ships with disturbances under input saturation", Automatica (2016)
- Fossen, T. I., "Nonlinear output feedback control of dynamically positioned ships using vectorial observer backstepping", IEEE Trans. Contr. Syst. Technol (1998)
- Fossen, T. I., "Kalman filtering for positioning and heading control of ships and offshore rigs: estimating the effects of waves, wind, and current", IEEE Contr. Syst. Mag, 29, pp.32~46 (2009)[DOI]
- Gao, Xiaoyang, "Online optimal control for dynamic positioning of vessels via time-based adaptive dynamic programming", Int. J. Ambient Intell. Humanized Comput (2019)
- Glorot, X., "Understanding the difficulty of training deep feedforward neural networks", J. Mach. Learn. Res, 249(256) (2010)
- Hochreiter, S., "Long short-term memory", Neural Comput, 9, pp.1735~1780 (1997)[DOI]
- IMCA, "Specification for DP Capability Plots", ~ (2000)
- Kingma, D. P., "Adam: a method for stochastic optimization", 3rd International Conference on Learning Representations. International Conference on Learning Representations (2015), ICLR
- Lee, D., "Application of recent developments in deep learning to ANN-based automatic berthing systems", Int. J. Eng. Technol. Innov, 10, pp.75~90 (2020)
- Lee, S. J., "The Effects of LNG-Sloshing on the Global Responses of LNG-Carriers", pp.2008
- Li, Mingyang, "Anti-windup reconfigurable control for dynamic positioning vessel with thruster faults", Trans. Inst. Meas. Contr (2020)
- Mnih, V., "Playing atari with deep reinforcement learning", ArXiv Preprint ArXiv:1312.5602, ~ (2013)
- (2019)[URL]
- 송순석, "선체운동 예측을 이용한 Dynamic Positioning System의 피드포워드 제어 알고리즘에 관한 연구", 해양환경안전학회지, 22(1), pp.129~137 (2016), 해양환경안전학회[DOI]
- Srivastava, N., "Dropout : a simple way to prevent neural networks from overfitting", J. Mach. Learn. Res, 15, pp.1929~1958 (2014)
- Tannuri, E. A., "Dynamic positioning systems : An experimental analysis of sliding mode control", Contr. Eng. Pract (2010)
- Wang, Yu-Long, "Network-Based TeS Fuzzy Dynamic Positioning Controller Design for Unmanned Marine Vehicles", IEEE Trans. cybern (2018)
- Watkins, C. J. C. H., "Q-learning", Mach. Learn, 8, pp.279~292 (1992)[DOI]
- Yeung, R. W., , International Workshop on Ship and Platform Motions (1983)
- Ziegler, J. G., "Optimum Settings for Automatic Controllers", ASME, ~ (1942)