Recurrent neural networks for nonparametric modeling of ship maneuvering motion
2
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
A Recurrent Neural Network (RNN) model is presented in this paper to predict the ship maneuvering motion. Inputs to the model are the orders of rudder angle and its variation as well as the propeller speed (ship speed) and also the recursive outputs velocities of surge, sway and yaw. The past values for the velocities are retained in the inputs to indicate the influence of historical state of motion on the maneuvering prediction. The KRISO Container Ship (KCS) is taken as the study object. The data obtained from a manoeuvring mathematical model and free-running model test are respectively used to train the neural network. Tactical circles and zigzags are simulated by the RNN, the prediction for maneuvers not involved in the training set shows that the RNN in this paper has good generalization performance. The concept of uncertainty is proposed to be considered in the further work through the analysis.
Abstract
A Recurrent Neural Network (RNN) model is presented in this paper to predict the ship maneuvering motion. Inputs to the model are the orders of rudder angle and its variation as well as the propeller speed (ship speed) and also the recursive outputs velocities of surge, sway and yaw. The past values for the velocities are retained in the inputs to indicate the influence of historical state of motion on the maneuvering prediction. The KRISO Container Ship (KCS) is taken as the study object. The data obtained from a manoeuvring mathematical model and free-running model test are respectively used to train the neural network. Tactical circles and zigzags are simulated by the RNN, the prediction for maneuvers not involved in the training set shows that the RNN in this paper has good generalization performance. The concept of uncertainty is proposed to be considered in the further work through the analysis.
참고문헌 (26)
- Lectures on ship hydrodynamics, steering and maneuverability, "Abkowitz, M. A.", ~, pp.Report No. Hy- 5 (1964)
- Abkowitz, M. A., "Measurement of hydrodynamic characteristic from ship maneuvering trials by system identification", Trans. - Soc. Nav. Archit. Mar. Eng, 88, pp.283~318 (1980)
- Bhattacharyya, S. K., "Parametric identification for nonlinear ship manoeuvring", J. Ship Res, 50(3), pp.197~207 (2006)
- Chen, Y., "Parameters identification for ship motion model based on particle swarm optimization", Kybernetes, 39(6), pp.871~880 (2010)
- Planner Motion Mechanism Test and Full Scales Streering and Maneuvering Predictions for a Mariner Class Vessel, "Chislett, M. S.", ISP, ~ (1965)
- Turning and Course Keeping Qualities of Ships, "Davidson, K. S. M.", SNAME, ~ (1946)
- Goodman, A., "Plannar Motion Mechanism and System", 3052120~ (1962)
- Haddara, M. R., "Parametric identification of maneuvering models for ships", Int. Shipbuild. Prog, 46(445), pp.5~27 (1999)
- Herrero, E. R., "Two-step identification of non-linear manoeuvring models of marine vessels", Ocean Eng, 53, pp.72~82 (2012)
- Hess, D., "Simulation of Ship Maneuvers Using Recursive Neural Networks", Twenty-Third Symposium on Naval Hydrodynamics (2001)
- Hess, D., "Ship maneuvering simulation in wind and waves: a nonlinear timedomain approach using recursive neural networks", 26th Symposium on Naval Hydrodynamics (2006)
- Holzhuter, T., "Robust identification scheme in an adaptive track controller for ships", 3rd IFAC Symposium on Adaptive Systems in Control and Signal Processing, pp.118~123 (1989)
- K€allstrom, C. G., "Experiences of system identification applied to ship steering", Automatica, 17(1), pp.187~198 (1981)
- Luo, W. L., "Manoeuvring simulation of catamaran by using implicit models based on support vector machines", Ocean Eng, 82, pp.150~159 (2014)
- Moreira, L., "Dynamic model of maneuverability using recursive neural networks", Ocean Eng, 30, pp.1669~1697 (2003)
- Moreira, L., "Training recurrent neural networks with noisy data for manoeuvring simulation", 2nd International Conference on Computer Application & Information Technology in the Maritime Industries (COMPIT’03), Hamburg, GermanyPIT’03), pp.183~195 (2003)
- Moreira, L., "Comparison between manoeuvring trials and simulations with recursive neural networks", Ship Technol. Res, 50(2), pp.77~84 (2003)
- Moreira, L., "Recursive neural network model of catamaran manoeuvring", Transactions of the Royal Institution of Naval Architects, pp.154~ (2012)
- On the Streering Qualities of Ships, "Nomoto, K.", ISP, 35~ (1957)
- Rumelhart, D. E., "Parallel Distributed Processing: Explorations in the Microstructure of Cognition I&II" (1986), MIT Press
- Model experiments about the maneuverability and turning of ships, "Shiba, H.", DTMB, ~, pp.DTMB Report 1461 (1960)
- Van Amerongen, J., "Adaptive steering of ships-a model reference approach", Automatica, 20(1), pp.3~14 (1984)
- Wang, X. G., "System identification modeling of ship manoeuvring motion in 4 degrees of freedom based on support vector machines", China Ocean Eng, 29, pp.519~534 (2015)
- Wang, Z. H., "Kernel-based support vector regression for nonparametric modeling of ship maneuvering motion", Ocean Eng, 216, pp.107994~ (2020)
- Yoon, H. K., "Identification of hydrodynamic derivatives in ship maneuvering equations of motion by estimation-before-modeling technique", Ocean Eng, 30, pp.2379~2404 (2003)
- Zhou, W. W., "Identification of a class of nonlinear state-space models using RPE techniques", IEEE Trans. Automat. Control, 34(3), pp.312~316 (1989)