Enter your email address
Submit
Write your message
1- Sharif University of Technology
Abstract: (55 Views)
Today, Unmanned Surface Vehicles (USVs) are used in a wide range of maritime operations. Designing the control system and simulating the maneuvering behavior of such vessels prior to actual deployment is of great importance. Therefore, it is essential to extract an accurate dynamic model for each vessel. There are various methods available to derive a vessel’s maneuvering dynamics. However, due to the complexity and nonlinear effects present in vessel dynamics, deriving the model using equations of motion and hydrodynamics is relatively challenging.
In recent years, the use of artificial neural networks for modeling vessel dynamics has become a suitable alternative to traditional methods, reducing the need for detailed understanding and application of hydrodynamic equations. In this study, the dynamic relationship between the rudder angle and the yaw rate is modeled using a trained artificial neural network. Since real-world testing conditions were not available, a computer simulation model of the vessel in the Simulink environment was utilized. The network was trained using data from zigzag maneuver tests, and then evaluated using input types different from the training data, such as sinusoidal and sawtooth signals.
In recent years, the use of artificial neural networks for modeling vessel dynamics has become a suitable alternative to traditional methods, reducing the need for detailed understanding and application of hydrodynamic equations. In this study, the dynamic relationship between the rudder angle and the yaw rate is modeled using a trained artificial neural network. Since real-world testing conditions were not available, a computer simulation model of the vessel in the Simulink environment was utilized. The network was trained using data from zigzag maneuver tests, and then evaluated using input types different from the training data, such as sinusoidal and sawtooth signals.
Keywords: system identification, recurrent neural network, Simultaneous Simulation and Identification
Type of Study: Research Paper |
Subject:
Ship Hydrodynamic
Received: 2025/05/22 | Accepted: 2025/07/27
Received: 2025/05/22 | Accepted: 2025/07/27
فایل صوتی چکیده مقاله [MP3 2012 KB] (2 Download)
References
1. Liu, Z., Zhang, Y., Yu, X., & Yuan, C. (2016). Unmanned surface vehicles: An overview of developments and challenges. Annual Reviews in Control, 41, 71-93. [DOI:10.1016/j.arcontrol.2016.04.018]
2. Roberts, G. N., & Sutton, R. (Eds.). (2006). Advances in unmanned marine vehicles (Vol. 69). Iet. [DOI:10.1049/PBCE069E]
3. Manley, J. E. (2008, September). Unmanned surface vehicles, 15 years of development. In OCEANS 2008 (pp. 1-4). Ieee. [DOI:10.1109/OCEANS.2008.5289429]
4. Fossen, T. I. (2011). Handbook of marine craft hydrodynamics and motion control. John Wiley & Sons. [DOI:10.1002/9781119994138]
5. Zhang, Z. R., Hui, L., & Feng, Z. H. A. O. (2006). Application of CFD in ship engineering design practice and ship hydrodynamics. Journal of Hydrodynamics, Ser. B, 18(3), 315-322. [DOI:10.1016/S1001-6058(06)60072-3]
6. Luo, W. and Z. Zhang, Modeling of ship maneuvering motion using neural networks. Journal of Marine Science and Application, 2016. 15(4): p. 426-432. [DOI:10.1007/s11804-016-1380-8]
7. Xing, Z. and L. McCue, Modeling ship equations of roll motion using neural networks. Naval Engineers Journal, 2010. 122(3): p. 49-60. [DOI:10.1111/j.1559-3584.2010.00241.x]
8. Zăgan, R., M.G. Chiţu, and E. Manea, Ship Manoeuvrability Prediction Using Neural Networks Analysis. Advanced Materials Research, 2014. 1036: p. 946-951. [DOI:10.4028/www.scientific.net/AMR.1036.946]
9. Skjetne, R., T.I. Fossen, and P.V. Kokotović, Adaptive maneuvering, with experiments, for a model ship in a marine control laboratory. Automatica, 2005. 41(2): p. 289-298. [DOI:10.1016/j.automatica.2004.10.006]
10. Faramin, M., R. Goudarzi, and A. Maleki, Track-keeping observer-based robust adaptive control of an unmanned surface vessel by applying a 4-DOF maneuvering model. Ocean Engineering, 2019. 183: p. 11-23. [DOI:10.1016/j.oceaneng.2019.04.051]
11. Juang, J.Y. and B. Chang. Robust control theory applied to ship maneuvering. in Proceedings of the 38th IEEE Conference on Decision and Control (Cat. No. 99CH36304). 1999. IEEE.
12. Luque, J.C.C. and D.C. Donha, Auv identification and robust control. IFAC Proceedings Volumes, 2011. 44(1): p. 14735-14741. [DOI:10.3182/20110828-6-IT-1002.03554]
13. Haseltalab, A. and R.R. Negenborn, Adaptive control for autonomous ships with uncertain model and unknown propeller dynamics. Control Engineering Practice, 2019. 91: p. 104116. [DOI:10.1016/j.conengprac.2019.104116]
14. Kahveci, N.E. and P.A. Ioannou, Adaptive steering control for uncertain ship dynamics and stability analysis. Automatica, 2013. 49(3): p. 685-697. [DOI:10.1016/j.automatica.2012.11.026]
15. Perera, L.P. and C.G. Soares, Lyapunov and Hurwitz based controls for input-output linearisation applied to nonlinear vessel steering. Ocean Engineering, 2013. 66: p. 58-68. [DOI:10.1016/j.oceaneng.2013.04.002]
16. Zheng, J., Y. Li, and F. Meng. Online Identification Method of Nonlinear Ship Motion Mathematical Models from Free-Running Tests. in 2019 IEEE 28th International Symposium on Industrial Electronics (ISIE). 2019. IEEE. [DOI:10.1109/ISIE.2019.8781124]
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
International Journal of Maritime Technology is licensed under a
Creative Commons Attribution-NonCommercial 4.0 International License.